sdk-py: release 0.1.26 (#1026)

replaced pprint with print

.github/workflows/link_check.yml

@@ -1,4 +1,4 @@
-name: Check Links
+name: Check Docs & Links
 
 on:
   pull_request:
@@ -26,7 +26,7 @@ jobs:
       - name: Check links in Markdown files
         uses: gaurav-nelson/github-action-markdown-link-check@v1
         with:
-          folder-path: "examples/"
+          folder-path: "examples/,docs/"
           check-modified-files-only: ${{ github.event_name != 'schedule' }}
           file-path: "./README.md"
           config-file: "./.markdown-link-check.config.json"
@@ -60,7 +60,7 @@ jobs:
             echo "Fetching changes from origin/main..."
             git fetch origin main
             echo "Checking for changed notebook files..."
-            CHANGED_FILES=$(git diff --name-only origin/main | grep '\.ipynb$' || true)
+            CHANGED_FILES=$(git diff --name-only --diff-filter=d origin/main | grep '\.ipynb$' || true)
             echo "Changed files: ${CHANGED_FILES}"
             if [ -n "${CHANGED_FILES}" ]; then
               echo "Running link check on changed notebook files..."
@@ -69,3 +69,19 @@ jobs:
               echo "No notebook files changed."
             fi
           fi
+  check-readmes-synced:
+    # This checks that the repo README.md is identical to the libs/langgraph/README.md
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Check README.md is in sync
+        run: |
+            if ! diff -q README.md libs/langgraph/README.md >/dev/null; then
+            echo "README.md is out of sync with libs/langgraph/README.md"
+            diff -C 3 README.md libs/langgraph/README.md
+            exit 1
+            fi

.github/workflows/release.yml

@@ -136,6 +136,7 @@ jobs:
     needs:
       - build
       - release-notes
+    permissions: write-all
     uses:
       ./.github/workflows/_test_release.yml
     with:

README.md

@@ -11,6 +11,9 @@
 > [!NOTE]
 > Looking for the JS version? Click [here](https://github.com/langchain-ai/langgraphjs) ([JS docs](https://langchain-ai.github.io/langgraphjs/)).
 
+> [!TIP]
+> Looking to deploy your LangGraph application? [Join the waitlist](https://www.langchain.com/langgraph-cloud-beta) for [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/), our managed service for deploying and hosting LangGraph applications.
+
 ## Overview
 
 [LangGraph](https://langchain-ai.github.io/langgraph/) is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Compared to other LLM frameworks, it offers these core benefits: cycles, controllability, and persistence. LangGraph allows you to define flows that involve cycles, essential for most agentic architectures, differentiating it from DAG-based solutions. As a very low-level framework, it provides fine-grained control over both the flow and state of your application, crucial for creating reliable agents. Additionally, LangGraph includes built-in persistence, enabling advanced human-in-the-loop and memory features.
@@ -36,40 +39,49 @@ pip install -U langgraph
 
 One of the central concepts of LangGraph is state. Each graph execution creates a state that is passed between nodes in the graph as they execute, and each node updates this internal state with its return value after it executes. The way that the graph updates its internal state is defined by either the type of graph chosen or a custom function.
 
-Let's take a look at a simple example of an agent that can search the web using [Tavily Search API](https://tavily.com/).
+Let's take a look at a simple example of an agent that can use a search tool.
 
 ```shell
-pip install langchain_openai langchain_community
+pip install langchain-anthropic
 ```
 
 ```shell
-export OPENAI_API_KEY=sk-...
-export TAVILY_API_KEY=tvly-...
+export ANTHROPIC_API_KEY=sk-...
 ```
 
 Optionally, we can set up [LangSmith](https://docs.smith.langchain.com/) for best-in-class observability.
 
 ```shell
-export LANGCHAIN_TRACING_V2="true"
-export LANGCHAIN_API_KEY=ls__...
+export LANGSMITH_TRACING=true
+export LANGSMITH_API_KEY=lsv2_sk_...
 ```
 
 ```python
 from typing import Annotated, Literal, TypedDict
 
 from langchain_core.messages import HumanMessage
-from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_openai import ChatOpenAI
+from langchain_anthropic import ChatAnthropic
+from langchain_core.tools import tool
 from langgraph.checkpoint import MemorySaver
 from langgraph.graph import END, StateGraph, MessagesState
 from langgraph.prebuilt import ToolNode
 
 
 # Define the tools for the agent to use
-tools = [TavilySearchResults(max_results=1)]
+@tool
+def search(query: str):
+    """Call to surf the web."""
+    # This is a placeholder, but don't tell the LLM that...
+    if "sf" in query.lower() or "san francisco" in query.lower():
+        return ["It's 60 degrees and foggy."]
+    return ["It's 90 degrees and sunny."]
+
+
+tools = [search]
+
 tool_node = ToolNode(tools)
 
-model = ChatOpenAI(temperature=0).bind_tools(tools)
+model = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0).bind_tools(tools)
 
 # Define the function that determines whether to continue or not
 def should_continue(state: MessagesState) -> Literal["tools", END]:
@@ -132,7 +144,7 @@ final_state["messages"][-1].content
 ```
 
 ```
-'The current weather in San Francisco is as follows:\n- Temperature: 60.1°F (15.6°C)\n- Condition: Partly cloudy\n- Wind: 5.6 mph (9.0 kph) from SSW\n- Humidity: 83%\n- Visibility: 9.0 miles (16.0 km)\n- UV Index: 4.0\n\nFor more details, you can visit [Weather API](https://www.weatherapi.com/).'
+"Based on the search results, I can tell you that the current weather in San Francisco is:\n\nTemperature: 60 degrees Fahrenheit\nConditions: Foggy\n\nSan Francisco is known for its microclimates and frequent fog, especially during the summer months. The temperature of 60°F (about 15.5°C) is quite typical for the city, which tends to have mild temperatures year-round. The fog, often referred to as "Karl the Fog" by locals, is a characteristic feature of San Francisco\'s weather, particularly in the mornings and evenings.\n\nIs there anything else you\'d like to know about the weather in San Francisco or any other location?"
 ```
 
 Now when we pass the same `"thread_id"`, the conversation context is retained via the saved state (i.e. stored list of messages)
@@ -146,7 +158,7 @@ final_state["messages"][-1].content
 ```
 
 ```
-'The current weather in New York is as follows:\n- Temperature: 20.3°C (68.5°F)\n- Condition: Overcast\n- Wind: 2.2 mph from the north\n- Humidity: 65%\n- Cloud Cover: 100%\n- UV Index: 5.0\n\nFor more details, you can visit [Weather API](https://www.weatherapi.com/).'
+"Based on the search results, I can tell you that the current weather in New York City is:\n\nTemperature: 90 degrees Fahrenheit (approximately 32.2 degrees Celsius)\nConditions: Sunny\n\nThis weather is quite different from what we just saw in San Francisco. New York is experiencing much warmer temperatures right now. Here are a few points to note:\n\n1. The temperature of 90°F is quite hot, typical of summer weather in New York City.\n2. The sunny conditions suggest clear skies, which is great for outdoor activities but also means it might feel even hotter due to direct sunlight.\n3. This kind of weather in New York often comes with high humidity, which can make it feel even warmer than the actual temperature suggests.\n\nIt's interesting to see the stark contrast between San Francisco's mild, foggy weather and New York's hot, sunny conditions. This difference illustrates how varied weather can be across different parts of the United States, even on the same day.\n\nIs there anything else you'd like to know about the weather in New York or any other location?"
 ```
 
 ### Step-by-step Breakdown
@@ -154,8 +166,8 @@ final_state["messages"][-1].content
 1. <details>
     <summary>Initialize the model and tools.</summary>
 
-    - we use `ChatOpenAI` as our LLM. **NOTE:** we need make sure the model knows that it has these tools available to call. We can do this by converting the LangChain tools into the format for OpenAI tool calling using the `.bind_tools()` method.
-    - we define the tools we want to use - a web search tool in our case. It is really easy to create your own tools - see documentation here on how to do that [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
+    - we use `ChatAnthropic` as our LLM. **NOTE:** we need make sure the model knows that it has these tools available to call. We can do this by converting the LangChain tools into the format for OpenAI tool calling using the `.bind_tools()` method.
+    - we define the tools we want to use - a search tool in our case. It is really easy to create your own tools - see documentation here on how to do that [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
    </details>
 
 2. <details>

docs/_scripts/copy_notebooks.py

@@ -15,17 +15,24 @@ cloud_sdk_dir = docs_dir / "cloud"
 
 _MANUAL = {
     "how-tos": [
+        "state-context-key.ipynb",
         "async.ipynb",
         "stream-values.ipynb",
         "stream-updates.ipynb",
         "stream-multiple.ipynb",
         "streaming-tokens.ipynb",
+        "streaming-tokens-without-langchain.ipynb",
         "streaming-content.ipynb",
         "streaming-events-from-within-tools.ipynb",
+        "streaming-events-from-within-tools-without-langchain.ipynb",
         "streaming-from-final-node.ipynb",
         "persistence.ipynb",
-        "managing-conversation-history.ipynb",
+        "memory/manage-conversation-history.ipynb",
+        "memory/delete-messages.ipynb",
+        "memory/add-summary-conversation-history.ipynb",
         "persistence_postgres.ipynb",
+        "persistence_mongodb.ipynb",
+        "persistence_redis.ipynb",
         "visualization.ipynb",
         "state-model.ipynb",
         "subgraph.ipynb",
@@ -81,14 +88,12 @@ _HIDE = set(
         "dynamically-returning-directly.ipynb",
         "force-calling-a-tool-first.ipynb",
         "managing-agent-steps.ipynb",
-        "pass-run-time-values-to-tools.ipynb",
         "respond-in-format.ipynb",
         "quickstart.ipynb",
         "human-in-the-loop.ipynb",
         "learning.ipynb",
         "docs/quickstart.ipynb",
         "tutorials/rag-agent-testing.ipynb",
-        "state-context-key.ipynb",
         "time-travel.ipynb",
         "code_assistant/langgraph_code_assistant_mistral.ipynb",
     ]

docs/docs/cloud/concepts/api.md

@@ -18,7 +18,7 @@ A thread contains the accumulated state of a group of runs. If a run is executed
 
 The state of a thread at a particular point in time is called a checkpoint.
 
-For more on threads and checkpoints, see this section of the [LangGraph conceptual guide](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer).
+For more on threads and checkpoints, see this section of the [LangGraph conceptual guide](../../concepts/low_level.md#checkpointer).
 
 The LangGraph Cloud API provides several endpoints for creating and managing threads and thread state. See the <a href="../reference/api/api_ref.html#tag/threadscreate" target="_blank">API reference</a> for more details.
 
@@ -47,13 +47,13 @@ The LangGraph Cloud API offers several features to support complex agent archite
 
 Streaming is critical for making LLM applications feel responsive to end users. When creating a streaming run, the streaming mode determines what data is streamed back to the API client. The LangGraph Cloud API supports five streaming modes.
 
-- `values`: Stream the full state of the graph after each node is executed. See the [how-to guide](../how-tos/cloud_examples/stream_values.ipynb) for streaming values.
-- `messages`: Stream complete messages (at the end of node execution) as well as tokens for any messages generated inside a node. This mode is primarily meant for powering chat applications. This is only an option if your graph contains a `messages` key. See the [how-to guide](../how-tos/cloud_examples/stream_messages.ipynb) for streaming messages.
-- `updates`: Streams updates to the state of the graph after each node is executed. See the [how-to guide](../how-tos/cloud_examples/stream_updates.ipynb) for streaming updates.
-- `events`: Stream all events (including the state of the graph) after each node is executed. See the [how-to guide](../how-tos/cloud_examples/stream_events.ipynb) for streaming events. This can be used to do token-by-token streaming for LLMs.
-- `debug`: Stream debug events after each node is executed. See the [how-to guide](../how-tos/cloud_examples/stream_debug.ipynb) for streaming debug events.
+- `values`: Stream the full state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_values.md) for streaming values.
+- `messages`: Stream complete messages (at the end of node execution) as well as tokens for any messages generated inside a node. This mode is primarily meant for powering chat applications. This is only an option if your graph contains a `messages` key. See the [how-to guide](../how-tos/stream_messages.md) for streaming messages.
+- `updates`: Streams updates to the state of the graph after each node is executed. See the [how-to guide](../how-tos/stream_updates.md) for streaming updates.
+- `events`: Stream all events (including the state of the graph) after each node is executed. See the [how-to guide](../how-tos/stream_events.md) for streaming events. This can be used to do token-by-token streaming for LLMs.
+- `debug`: Stream debug events after each node is executed. See the [how-to guide](../how-tos/stream_debug.md) for streaming debug events.
 
-You can also specify multiple streaming modes at the same time. See the [how-to guide](../how-tos/cloud_examples/stream_multiple.ipynb) for configuring multiple streaming modes at the same time.
+You can also specify multiple streaming modes at the same time. See the [how-to guide](../how-tos/stream_multiple.md) for configuring multiple streaming modes at the same time.
 
 See the <a href="../reference/api/api_ref.html#tag/runscreate/POST/threads/{thread_id}/runs/stream" target="_blank">API reference</a> for how to create streaming runs.
 
@@ -63,12 +63,12 @@ There are many occasions where the graph cannot run completely autonomously. For
 
 ### Double Texting
 
-Many times users might interact with your graph in unintended ways. For instance, a user may send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), Langgraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/index.md#double-texting). These options are:
+Many times users might interact with your graph in unintended ways. For instance, a user may send one message and before the graph has finished running send a second message. To solve this issue of "double-texting" (i.e. prompting the graph a second time before the first run has finished), LangGraph has provided four different solutions, all of which are covered in the [Double Texting how-tos](../how-tos/index.md#double-texting). These options are:
 
-- `reject`: This is the simplest option, this just rejects any follow up runs and does not allow double texting. See the [how-to guide](../how-tos/cloud_examples/reject_concurrent.ipynb) for configuring the reject double text option.
-- `enqueue`: This is a relatively simple option which continues the first run until it completes the whole run, then sends the new input as a separate run. See the [how-to guide](../how-tos/cloud_examples/enqueue_concurrent.ipynb) for configuring the enqueue double text option.
-- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise. See the [how-to guide](../how-tos/cloud_examples/interrupt_concurrent.ipynb) for configuring the interrupt double text option.
-- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input. See the [how-to guide](../how-tos/cloud_examples/rollback_concurrent.ipynb) for configuring the rollback double text option.
+- `reject`: This is the simplest option, this just rejects any follow up runs and does not allow double texting. See the [how-to guide](../how-tos/reject_concurrent.md) for configuring the reject double text option.
+- `enqueue`: This is a relatively simple option which continues the first run until it completes the whole run, then sends the new input as a separate run. See the [how-to guide](../how-tos/enqueue_concurrent.md) for configuring the enqueue double text option.
+- `interrupt`: This option interrupts the current execution but saves all the work done up until that point. It then inserts the user input and continues from there. If you enable this option, your graph should be able to handle weird edge cases that may arise. See the [how-to guide](../how-tos/interrupt_concurrent.md) for configuring the interrupt double text option.
+- `rollback`: This option rolls back all work done up until that point. It then sends the user input in, basically as if it just followed the original run input. See the [how-to guide](../how-tos/rollback_concurrent.md) for configuring the rollback double text option.
 
 ### Stateless Runs
 
@@ -92,7 +92,7 @@ See the [how-to guide](../how-tos/cloud_examples/stateless_runs.ipynb) for creat
 
 For all types of runs, langgraph cloud supports completion webhooks. When you create the run you can pass a webhook URL to be called when the completes (successfully or not). This is especially useful for background runs and cron jobs, as the webhook can give you an indication the run has completed and you can perform further actions for your appilcation.
 
-See this [how-to guide](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/webhooks/) to learn about how to use webhooks with LangGraph Cloud.
+See this [how-to guide](../how-tos/cloud_examples/webhooks.ipynb) to learn about how to use webhooks with LangGraph Cloud.
 
 ## Deployment
 
@@ -101,3 +101,7 @@ The LangGraph Cloud offers several features to support secure and robost deploym
 ### Authentication
 
 LangGraph applications deployed to LangGraph Cloud are automatically configured with LangSmith authentication. In order to call the API, a valid <a href="https://docs.smith.langchain.com/how_to_guides/setup/create_account_api_key#api-keys" target="_blank">LangSmith API key</a> is required.
+
+### Local Testing
+
+Before deploying your app in production to LangGraph Cloud, you may wish to test out your graph locally in order to ensure that everything is running as expected. Luckily, LangGraph makes this easy for you through use of the LangGraph CLI. Read more in this [how-to guide](../deployment/test_locally.md) or look at the [CLI reference](../reference/cli.md) to learn more.

docs/docs/cloud/concepts/cloud.md

@@ -0,0 +1,28 @@
+# Cloud Concepts
+
+This page describes the high-level concepts of the LangGraph Cloud deployment.
+
+## Deployment
+
+A deployment is an instance of a LangGraph API. A single deployment can have many [revisions](#revision). When a deployment is created, all of the necessary infrastructure (e.g. database, containers, secrets store) are automatically provisioned. See the [architecture diagram](#architecture) below for more details.
+
+See the [how-to guide](../deployment/cloud.md#create-new-deployment) for creating a new deployment.
+
+## Revision
+
+A revision is an iteration of a [deployment](#deployment). When a new deployment is created, an initial revision is automatically created. To deploy new code changes or update environment variable configurations for a deployment, a new revision must be created. When a revision is created, a new container image is built automatically.
+
+See the [how-to guide](../deployment/cloud.md#create-new-revision) for creating a new revision.
+
+## Asynchronous Deployment
+
+Infrastructure for [deployments](#deployment) and [revisions](#revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+
+## Architecture
+
+!!! warning "Subject to Change"
+    The LangGraph Cloud deployment architecture may change in the future.
+
+A high-level diagram of a LangGraph Cloud deployment.
+
+![diagram](langgraph_cloud_architecture.png)

docs/docs/cloud/deployment/cloud.md

@@ -45,8 +45,33 @@ Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmi
         1. Update the value of existing secrets or environment variables.
 1. Select `Submit`. After a few seconds, the `New Revision` modal will close and the new revision will be queued for deployment.
 
-## Asynchronous Deployment
+## View Build and Deployment Logs
 
-New [deployments](#create-new-deployment) and [revisions](#create-new-revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
+Build and deployment logs are available for each revision.
 
-The `Deployment` view continually updates the status of pending revisions.
+Starting from the `Deployment` view...
+
+1. Select the desired revision from the `Revisions` table. A panel slides open from the right-hand side and the `Build` tab is selected by default, which displays build logs for the revision.
+1. In the panel, select the `Deploy` tab to view deployment logs for the revision.
+1. Within the `Deploy` tab, adjust the date/time range picker as needed. By default, the date/time range picker is set to the `Last 15 minutes`.
+
+## Interrupt Revision
+
+Interrupting a revision will stop deployment of the revision.
+
+!!! warning "Undefined Behavior"
+    Interrupted revisions have undefined behavior. This is only useful if you need to deploy a new revision and you already have a revision "stuck" in progress. In the future, this feature may be removed.
+
+Starting from the `Deployment` view...
+
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired revision from the `Revisions` table.
+1. Select `Interrupt` from the menu.
+1. A modal will appear. Review the confirmation message. Select `Interrupt revision`.
+
+## Delete Deployment
+
+Starting from the <a href="https://smith.langchain.com/" target="_blank">LangSmith UI</a>...
+
+1. In the left-hand navigation panel, select `Deployments`. The `Deployments` view contains a list of existing LangGraph Cloud deployments.
+1. Select the menu icon (three dots) on the right-hand side of the row for the desired deployment and select `Delete`.
+1. A `Confirmation` modal will appear. Select `Delete`.

docs/docs/cloud/deployment/setup.md

@@ -101,6 +101,9 @@ Example `langgraph.json` file:
 
 Note that the variable name of the `CompiledGraph` appears at the end of the value of each subkey in the top-level `graphs` key (i.e. `:<variable_name>`).
 
+!!! warning "Configuration Location"
+    The LangGraph API configuration file must be placed in a directory that is at the same level or higher than the Python files that contain compiled graphs and associated dependencies.
+
 Example file directory:
 
 ```bash

docs/docs/cloud/deployment/test_locally.md

@@ -0,0 +1,91 @@
+# How to test a LangGraph app locally
+
+This guide assumes you have a LangGraph app correctly set up with a proper configuration file and a corresponding compiled graph, and that you have a proper LangChain API key.
+
+## Setup
+
+Install the proper packages:
+
+```shell
+pip install langgraph-cli
+```
+
+## Start the API server
+
+Once you have downloaded the CLI, you can run the following command to start the API server for local testing:
+
+```shell
+langgraph up
+```
+
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
+
+```shell
+Ready!
+- API: http://localhost:8123
+2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
+```
+
+### Interact with the server
+
+We can now interact with the API server using the LangGraph SDK. First, we need to start our client, select our assistant (in this case a graph we called "agent", make sure to select the proper assistant you wish to test).
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    # only pass the url argument to get_client() if you changed the default port when calling langgraph up
+    client = get_client()
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    // only set the apiUrl if you changed the default port when calling langgraph up
+    const client = new Client();
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+Now we can invoke our graph to ensure it is working. Make sure to change the input to match the proper schema for your graph. 
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+If your graph works correctly, you should see your graph output displayed in the console. Of course, there are many more ways you might need to test your graph, for a full list of commands you can send with the SDK, see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) and [JS/TS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/) references.

docs/docs/cloud/how-tos/enqueue_concurrent.md

@@ -0,0 +1,183 @@
+## Enqueue
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.
+
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Then, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+    
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's start two runs, with the second interrupting the first one with a multitask strategy of "enqueue":
+
+=== "Python"
+
+    ```python
+    first_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    second_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="enqueue",
+    )
+    ```
+
+=== "Javascript"
+
+    ```js
+    const firstRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+
+    const secondRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+      multitask_strategy="enqueue",
+    )
+    ```
+
+Verify that the thread has data from both runs:
+
+=== "Python"
+
+    ```python
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], second_run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], secondRun["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)
+     Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629", "content": "Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information."}]
+    ================================== Ai Message ==================================
+    
+    According to AccuWeather, the current weather conditions in San Francisco are:
+    
+    Temperature: 57°F (14°C)
+    Conditions: Mostly Sunny
+    Wind: WSW 10 mph
+    Humidity: 72%
+    
+    The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.
+    
+    Some key details from the AccuWeather forecast:
+    
+    Today: Mostly sunny, high of 62°F (17°C)
+    Tonight: Partly cloudy, low of 49°F (9°C) 
+    Tomorrow: Partly sunny, high of 59°F (15°C)
+    Saturday: Mostly sunny, high of 64°F (18°C)
+    Sunday: Partly sunny, high of 61°F (16°C)
+    
+    So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)
+     Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    According to the weather data from WeatherAPI:
+    
+    Current Conditions in New York City (as of 2:00 PM local time):
+    - Temperature: 85°F (29°C)
+    - Conditions: Sunny
+    - Wind: 2 mph (4 km/h) from the SSE
+    - Humidity: 63%
+    - Heat Index: 85°F (30°C)
+    
+    The forecast shows sunny and warm conditions persisting over the next few days:
+    
+    Today: Sunny, high of 85°F (29°C)
+    Tonight: Clear, low of 68°F (20°C)
+    Tomorrow: Sunny, high of 88°F (31°C) 
+    Thursday: Mostly sunny, high of 90°F (32°C)
+    Friday: Partly cloudy, high of 87°F (31°C)
+    
+    So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.
+

docs/docs/cloud/how-tos/human_in_the_loop_breakpoint.md

@@ -0,0 +1,103 @@
+# How to Add Breakpoints
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component.
+This can be helpful when giving them access to tools.
+Often in these situations you may want to manually approve an action before taking.
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed.
+This interrupts execution at that node.
+You can then resume from that spot to continue.  
+
+## Setup
+
+### Code for your graph
+
+In this how-to we use a simple ReAct style hosted graph (you can see the full code for defining it [here](../../how-tos/human_in_the_loop/breakpoints.ipynb)). The important thing is that there are two nodes (one named `agent` that calls the LLM, and one named `action` that calls the tool), and a routing function from `agent` that determines whether to call `action` next or just end the graph run (the `action` node always calls the `agent` node after execution).
+
+### SDK Initialization
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+## Adding a breakpoint
+
+We now want to add a breakpoint in our graph run, which we will do before a tool is called.
+We can do this by adding `interrupt_before=["action"]`, which tells us to interrupt before calling the action node.
+We can do this either when compiling the graph or when kicking off a run.
+Here we will do it when kicking of a run, if you would like to to do it at compile time you need to edit the python file where your graph is defined and add the `interrupt_before` parameter when you call `.compile`.
+
+First let's access our hosted LangGraph instance through the SDK:
+
+And, now let's compile it with a breakpoint before the tool node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in sf"}]}
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages": [{ "role": "human", "content": "what's the weather in sf"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(`Receiving new event of type: ${chunk.event}...`);
+      console.log(chunk.data);
+      console.log("\n\n");
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '3b77ef83-687a-4840-8858-0371f91a92c3'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-e5d17791-4d37-4ad2-815f-a0c4cba62585', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in san francisco'}, 'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/human_in_the_loop_edit_state.md

@@ -0,0 +1,182 @@
+# How to Edit State of a Deployed Graph
+
+When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to edit the graph state before continuing (for example, to edit what tool is being called, or how it is being called).
+
+This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed. This interrupts execution at that node. You can then use update_state to update the state, and then resume from that spot to continue.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/edit-graph-state.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Editing state
+
+### Initial invocation
+
+Now let's invoke our graph, making sure to interrupt before the `action` node.
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"search for weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["action"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "search for weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["action"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll search for the current weather in San Francisco for you using the search function. Here's how I'll do that:", 'type': 'text'}, {'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-6dbb0167-f8f6-4e2a-ab68-229b2d1fbb64', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Edit the state
+
+Now, let's assume we actually meant to search for the weather in Sidi Frej (another city with the initials SF). We can edit the state to properly reflect that:
+
+
+=== "Python"
+
+    ```python
+    # First, lets get the current state
+    current_state = await client.threads.get_state(thread['thread_id'])
+
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = current_state['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'}
+
+    # Let's now call `update_state` to pass in this message in the `messages` key
+    # This will get treated as any other update to the state
+    # It will get passed to the reducer function for the `messages` key
+    # That reducer function will use the ID of the message to update it
+    # It's important that it has the right ID! Otherwise it would get appended
+    # as a new message
+    await client.threads.update_state(thread['thread_id'], {"messages": last_message})
+    ```
+
+=== "Javascript"
+
+    ```js
+    // First, lets get the current state
+    const currentState = await client.threads.getState(thread['thread_id']);
+
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = currentState['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'};
+
+    // Let's now call `update_state` to pass in this message in the `messages` key
+    // This will get treated as any other update to the state
+    // It will get passed to the reducer function for the `messages` key
+    // That reducer function will use the ID of the message to update it
+    // It's important that it has the right ID! Otherwise it would get appended
+    // as a new message
+    await client.threads.updateState(thread['thread_id'], {values:{"messages": lastMessage}});
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '88d58d3f-4151-47a9-a8e0-e42fdd3527b8',
+      'thread_ts': '1ef3274b-a809-6913-8002-91536ce6554d'}}
+
+
+
+### Resume invocation
+
+Now we can resume our graph run but with the updated state:
+
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in Sidi Frej. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '1161b8d1-bee4-4188-9be8-698aecb69f10', 'tool_call_id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}]}}
+    {'agent': {'messages': [{'content': [{'text': 'I apologize for the confusion in my search query. It seems the search function interpreted "SF" as "Sidi Frej" instead of "San Francisco" as we intended. Let me search again with the full city name to get the correct information:', 'type': 'text'}, {'id': 'toolu_0111rrwgfAcmurHZn55qjqTR', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b8c25779-cfb4-46fc-a421-48553551242f', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '6bc632ae-5ee6-4d01-9532-79c524a2d443', 'tool_call_id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}]}}
+    {'agent': {'messages': [{'content': "Now, based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. \n\nIt's worth noting that the search result included an unusual comment about Gemini, which doesn't seem directly related to the weather. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of weather information, we can focus on the fact that it's sunny in San Francisco right now.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other location?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-227a042b-dd97-476e-af32-76a3703af5d8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As you can see it now looks up the current weather in Sidi Frej (although our dummy search node still returns results for SF because we don't actually do a search in this example, we just return the same "It's sunny in San Francisco ..." result every time).

docs/docs/cloud/how-tos/human_in_the_loop_time_travel.md

@@ -0,0 +1,226 @@
+# How to Replay and Branch from Prior States
+
+With LangGraph Cloud you have the ability to return to any of your prior states and either re-run the graph to reproduce issues noticed during testing, or branch out in a different way from what was originally done in the prior states. In this guide we will show a quick example of how to rerun past states and how to branch off from previous states as well.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/time-travel.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = agent;
+    const thread = await client.threads.create();
+    ```
+
+## Replay a state
+
+### Initial invocation
+
+Before replaying a state - we need to create states to replay from! In order to do this, let's invoke our graph with a simple message:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Please search the weather in SF" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=input,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {"messages": [{ "role": "human", "content": "Please search the weather in SF"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the search function to look up the current weather in San Francisco for you. Let me do that now.", 'type': 'text'}, {'id': 'toolu_011vroKUtWU7SBdrngpgpFMn', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ee639877-d97d-40f8-96dc-d0d1ae22d203', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '7bad0e72-5ebe-4b08-9b8a-b99b0fe22fb7', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news for outdoor activities and enjoying the city's beautiful sights.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which isn't typically part of a weather report. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of answering your question about the weather, we can focus on the fact that it's sunny in San Francisco.\n\nIf you need any more specific information about the weather in San Francisco, such as temperature, wind speed, or forecast for the coming days, please let me know, and I'd be happy to search for that information for you.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-dbac539a-33c8-4f0c-9e20-91f318371e7c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+Now let's get our list of states, and invoke from the third state (right before the tool get called):
+
+
+=== "Python"
+
+    ```python
+    states = await client.threads.get_history(thread['thread_id'])
+
+    # We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    state_to_replay = states[2]
+    print(state_to_replay['next'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    const states = await client.threads.getHistory(thread['thread_id']);
+
+    // We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node
+    const stateToReplay = states[2];
+    console.log(stateToReplay['next']);
+    ```
+
+Output:
+
+    ['action']
+
+
+
+To rerun from a state, we need to pass in the `checkpoint_id` into the config of the run like follows:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": state_to_replay['checkpoint_id']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": stateToReplay['checkpoint_id']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'eba650e5-400e-4938-8508-f878dcbcc532', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. This is great news if you're planning any outdoor activities or simply want to enjoy a pleasant day in the city.\n\nIt's worth noting that the search result included an unusual comment about Geminis, which doesn't seem directly related to the weather. This appears to be a playful or humorous addition to the weather report, possibly from the source where this information was obtained.\n\nIs there anything else you'd like to know about the weather in San Francisco or any other information you need?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-bc6dca3f-a1e2-4f59-a69b-fe0515a348bb', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the graph restarted from the tool node with the same input as our original graph run.
+
+## Branch off from previous state
+
+Using LangGraph's checkpointing, you can do more than just replay past states. You can branch off previous locations to let the agent explore alternate trajectories or to let a user "version control" changes in a workflow.
+
+Let's show how to do this to edit the state at a particular point in time. Let's update the state to change the input to the tool
+
+=== "Python"
+
+    ```python
+    # Let's now get the last message in the state
+    # This is the one with the tool calls that we want to update
+    last_message = state_to_replay['values']['messages'][-1]
+
+    # Let's now update the args for that tool call
+    last_message['tool_calls'][0]['args'] = {'query': 'current weather in SF'}
+
+    new_state = await client.threads.update_state(thread['thread_id'],{"messages":[last_message]},checkpoint_id=state_to_replay['checkpoint_id'])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // Let's now get the last message in the state
+    // This is the one with the tool calls that we want to update
+    let lastMessage = stateToReplay['values']['messages'][-1];
+
+    // Let's now update the args for that tool call
+    lastMessage['tool_calls'][0]['args'] = {'query': 'current weather in SF'};
+
+    const newState = await client.threads.updateState(thread['thread_id'],{values:{"messages":[lastMessage]},checkpointId:stateToReplay['checkpoint_id']});
+    ```
+
+Now we can rerun our graph with this new config, starting from the `new_state`, which is a branch of our `state_to_replay`:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant["assistant_id"], # graph_id
+        input=None,
+        stream_mode="updates",
+        config={"configurable": {"thread_ts": new_state['configurable']['thread_ts']}}
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistant["assistant_id"],
+      {
+        input: null,
+        streamMode: "updates",
+        config: {"configurable": {"thread_ts": newState['configurable']['thread_ts']}},
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+
+    {'action': {'messages': [{'content': '["I looked up: current weather in SF. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '2baf9941-4fda-4081-9f87-d76795d289f1', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco (SF):\n\nThe weather in San Francisco is currently sunny. This means it's a clear day with plenty of sunshine. \n\nIt's worth noting that the specific temperature wasn't provided in the search result, but sunny weather in San Francisco typically means comfortable temperatures. San Francisco is known for its mild climate, so even on sunny days, it's often not too hot.\n\nThe search result also included a playful reference to astrological signs, mentioning Gemini. However, this is likely just a joke or part of the search engine's presentation and not related to the actual weather conditions.\n\nIs there any specific information about the weather in San Francisco you'd like to know more about? I'd be happy to perform another search if you need details on temperature, wind conditions, or the forecast for the coming days.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a83de52d-ed18-4402-9384-75c462485743', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+As we can see, the search query changed from San Francisco to SF, just as we had hoped!

docs/docs/cloud/how-tos/human_in_the_loop_user_input.md

@@ -0,0 +1,166 @@
+# How to Wait for User Input
+
+One of the main human-in-the-loop interaction patterns is waiting for human input. A key use case involves asking the user clarifying questions. One way to accomplish this is simply go to the `END` node and exit the graph. Then, any user response comes back in as fresh invocation of the graph. This is basically just creating a chatbot architecture.
+
+The issue with this is it is tough to resume back in a particular point in the graph. Often times the agent is halfway through some process, and just needs a bit of a user input. Although it is possible to design your graph in such a way where you have a `conditional_entry_point` to route user messages back to the right place, that is not super scalable (as it essentially involves having a routing function that can end up almost anywhere).
+
+A separate way to do this is to have a node explicitly for getting user input. This is easy to implement in a notebook setting - you just put an `input()` call in the node. But that isn't exactly production ready.
+
+Luckily, LangGraph makes it possible to do similar things in a production way. The basic idea is:
+
+- Set up a node that represents human input. This can have specific incoming/outgoing edges (as you desire). There shouldn't actually be any logic inside this node.
+- Add a breakpoint before the node. This will stop the graph before this node executes (which is good, because there's no real logic in it anyways)
+- Use `.update_state` to update the state of the graph. Pass in whatever human response you get. The key here is to use the `as_node` parameter to apply this update **as if you were that node**. This will have the effect of making it so that when you resume execution next it resumes as if that node just acted, and not from the beginning.
+
+## Setup
+
+We are not going to show the full code for the graph we are hosting, but you can see it [here](../../how-tos/human_in_the_loop/wait-user-input.ipynb#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. 
+
+### SDK initialization
+
+First, we need to setup our client so that we can communicate with our hosted graph:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+## Waiting for user input
+
+### Initial invocation
+
+Now, let's invoke our graph by interrupting before `ask_human` node:
+
+=== "Python"
+
+    ```python
+    input = { 'messages':[{ "role":"user", "content":"Use the search tool to ask the user where they are, then look up the weather there" }] }
+
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id,
+        input=input,
+        stream_mode="updates",
+        interrupt_before=["ask_human"],
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const input = { "messages":[{ "role":"human", "content": "Use the search tool to ask the user where they are, then look up the weather there"}] }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: input,
+        streamMode: "updates",
+        interruptBefore: ["ask_human"],
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+    
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Certainly! I'll use the AskHuman function to ask the user about their location, and then I'll use the search function to look up the weather for that location. Let's start by asking the user where they are.", 'type': 'text'}, {'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR', 'input': {'question': 'Where are you currently located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a8422215-71d3-4093-afb4-9db141c94ddb', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you currently located?'}, 'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+
+
+### Adding user input to state
+
+We now want to update this thread with a response from the user. We then can kick off another run.
+
+Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call.
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread['thread_id'])
+    tool_call_id = state['values']['messages'][-1]['tool_calls'][0]['id']
+
+    # We now create the tool call with the id and the response we want
+    tool_message = [{"tool_call_id": tool_call_id, "type": "tool", "content": "san francisco"}]
+
+    await client.threads.update_state(thread['thread_id'], {"messages": tool_message}, as_node="ask_human")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread['thread_id']);
+    const toolCallId = state['values']['messages'][-1]['tool_calls'][0]['id'];
+
+    # We now create the tool call with the id and the response we want
+    const toolMessage = [{"tool_call_id": toolCallId, "type": "tool", "content": "san francisco"}];
+
+    await client.threads.updateState(thread['thread_id'], {values: {"messages": toolMessage}, asNode:"ask_human"})
+    ```
+
+Output:
+
+    {'configurable': {'thread_id': '10d0ee61-db47-48fc-a58c-109a1e68cd73',
+      'thread_ts': '1ef32729-3cc3-6647-8002-14dcb621b46e'}}
+
+
+
+### Invoking after receiving human input
+
+We can now tell the agent to continue. We can just pass in None as the input to the graph, since no additional input is needed:
+
+=== "Python"
+
+    ```python
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        assistant_id, # graph_id
+        input=None,
+        stream_mode="updates",
+    ):
+        if chunk.data and chunk.event != "metadata": 
+            print(chunk.data)
+    ```
+=== "Javascript"
+
+    ```js
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      assistantId,
+      {
+        input: null,
+        streamMode: "updates",
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.data && chunk.event !== "metadata") {
+        console.log(chunk.data);
+      }
+    }
+    ```
+
+Output:
+
+    {'agent': {'messages': [{'content': [{'text': "Thank you for letting me know that you're in San Francisco. Now, I'll use the search function to look up the weather in San Francisco.", 'type': 'text'}, {'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-241baed7-db5e-44ce-ac3c-56431705c22b', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+    {'action': {'messages': [{'content': '["I looked up: current weather in San Francisco. Result: It\'s sunny in San Francisco, but you better look out if you\'re a Gemini 😈."]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '8b699b95-8546-4557-8e66-14ea71a15ed8', 'tool_call_id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}]}}
+    {'agent': {'messages': [{'content': "Based on the search results, I can provide you with information about the current weather in San Francisco:\n\nThe weather in San Francisco is currently sunny. It's a beautiful day in the city! \n\nHowever, I should note that the search result included an unusual comment about Gemini zodiac signs. This appears to be either a joke or potentially irrelevant information added by the search engine. For accurate and detailed weather information, you might want to check a reliable weather service or app for San Francisco.\n\nIs there anything else you'd like to know about the weather or San Francisco?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b4d7309f-f849-46aa-b6ef-475bcabd2be9', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
+

docs/docs/cloud/how-tos/index.md

@@ -11,46 +11,46 @@ Welcome to the LangGraph Cloud how-to guides! These guides provide practical, st
 
 LangGraph Cloud gives you best in class observability, testing, and hosting services. Read more about them in these how to guides:
 
-- [How to set up app for deployment](https://langchain-ai.github.io/langgraph/cloud/deployment/setup/)
-- [How to deploy to LangGraph cloud](https://langchain-ai.github.io/langgraph/cloud/deployment/cloud/)
-- [How to self-host](https://langchain-ai.github.io/langgraph/cloud/deployment/self_hosted/)
+- [How to set up app for deployment](../deployment/setup.md)
+- [How to deploy to LangGraph cloud](../deployment/cloud.md)
+- [How to self-host](../deployment/self_hosted.md)
 
 ## Streaming
 
 Streaming the results of your LLM application is vital for ensuring a good user experience, especially when your graph may call multiple models and take a long time to fully complete a run. Read about how to stream values from your graph in these how to guides:
 
-- [How to stream values](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_values/)
-- [How to stream updates](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_updates/)
-- [How to stream messages](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_messages/)
-- [How to stream events](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_events/)
-- [How to stream in debug mode](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_debug/)
-- [How to stream multiple modes](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/stream_multiple/)
+- [How to stream values](./stream_values.md)
+- [How to stream updates](./stream_updates.md)
+- [How to stream messages](./stream_messages.md)
+- [How to stream events](./stream_events.md)
+- [How to stream in debug mode](./stream_debug.md)
+- [How to stream multiple modes](./stream_multiple.md)
 
 ## Double-texting
 
 Graph execution can take a while, and sometimes users may change their mind about the input they wanted to send before their original input has finished running. For example, a user might notice a typo in their original request and will edit the prompt and resend it. Deciding what to do in these cases is important for ensuring a smooth user experience and preventing your graphs from behaving in unexpected ways. The following how-to guides provide information on the various options LangGraph Cloud gives you for dealing with double-texting:
 
-- [How to use the interrupt option](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/interrupt_concurrent/)
-- [How to use the rollback option](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/rollback_concurrent/)
-- [How to use the reject option](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/reject_concurrent/)
-- [How to use the rnqueue option](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/enqueue_concurrent/)
+- [How to use the interrupt option](./interrupt_concurrent.md)
+- [How to use the rollback option](./rollback_concurrent.md)
+- [How to use the reject option](./reject_concurrent.md)
+- [How to use the enqueue option](./enqueue_concurrent.md)
 
 ## Human-in-the-loop
 
 When creating complex graphs, leaving every decision up to the LLM can be dangerous, especially when the decisions involve invoking certain tools or accessing specific documents. To remedy this, LangGraph allows you to insert human-in-the-loop behavior to ensure your graph does not have undesired outcomes. Read more about the different ways you can add human-in-the-loop capabilities to your LangGraph Cloud projects in these how-to guides:
 
-- [How to add a breakpoint](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/human_in_the_loop_breakpoint/)
-- [How to wait for user input](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/human_in_the_loop_user_input/)
-- [How to edit graph state](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/human_in_the_loop_edit_state/)
-- [How to replay and branch from prior states](https://langchain-ai.github.io/langgraph/cloud/how-tos/cloud_examples/human_in_the_loop_time_travel/)
+- [How to add a breakpoint](./human_in_the_loop_breakpoint.md)
+- [How to wait for user input](./human_in_the_loop_user_input.md)
+- [How to edit graph state](./human_in_the_loop_edit_state.md)
+- [How to replay and branch from prior states](./human_in_the_loop_time_travel.md)
 
 ## LangGraph Studio
 
 LangGraph Studio is a built-in UI for visualizing, testing, and debugging your agents.
 
-- [How to enter LangGraph Studio](https://langchain-ai.github.io/langgraph/cloud/how-tos/test_deployment/)
-- [How to test your graph in LangGraph Studio](https://langchain-ai.github.io/langgraph/cloud/how-tos/invoke_studio/)
-- [Interact with threads in LangGraph Studio](https://langchain-ai.github.io/langgraph/cloud/how-tos/threads_studio/)
+- [How to enter LangGraph Studio](./test_deployment.md)
+- [How to test your graph in LangGraph Studio](./invoke_studio.md)
+- [Interact with threads in LangGraph Studio](./threads_studio.md)
 
 ## Different Types of Runs:
 

docs/docs/cloud/how-tos/interrupt_concurrent.md

@@ -0,0 +1,176 @@
+## Interrupt
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](../concepts/api.md#double-texting).
+
+The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can start our two runs and join the second on euntil it has completed:
+
+=== "Python"
+
+    ```python
+    # the first run will be interrupted
+    interrupted_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategychrom="interrupt",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let interruptedRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "interrupt" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has partial data from the first run + data from the second run
+
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)
+     Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18", "content": "High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ..."}]
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)
+     Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q
+      Args:
+        query: weather in new york city
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/new-york/10021/june-weather/349727", "content": "Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:
+    
+    - This is a monthly weather forecast for New York City for the month of June.
+    - It includes daily high and low temperatures to help plan ahead.
+    - Historical averages for June in NYC are also provided as a reference point.
+    - More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.
+    
+    So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!
+
+
+Verify that the original, interrupted run was interrupted
+
+=== "Python"
+
+    ```python
+    print((await client.runs.get(thread["thread_id"], interrupted_run["run_id"]))["status"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    console.log((await client.runs.get(thread['thread_id'], interruptedRun["run_id"]))["status"])
+    ```
+
+Output:
+
+    'interrupted'
+

docs/docs/cloud/how-tos/reject_concurrent.md

@@ -0,0 +1,155 @@
+## Reject
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now we can run a thread and try to run a second one with the "reject" option, which should fail since we have already started a run:
+
+
+=== "Python"
+
+    ```python
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    try:
+        await client.runs.create(
+            thread["thread_id"],
+            assistant_id,
+            input={
+                "messages": [{"role": "human", "content": "what's the weather in nyc?"}]
+            },
+            multitask_strategy="reject",
+        )
+    except httpx.HTTPStatusError as e:
+        print("Failed to start concurrent run", e)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const run = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    );
+    
+    try {
+      await client.runs.create(
+        thread["thread_id"],
+        assistantId,
+        { 
+          input: {"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+          multitask_strategy:"reject"
+        },
+      );
+    } catch (e) {
+      console.error("Failed to start concurrent run", e);
+    }
+    ```
+
+    Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'
+    For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409
+
+
+We can verify that the original thread finished executing:
+
+=== "Python"
+
+    ```python
+    # wait until the original run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state["values"]["messages"]) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in sf?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)
+     Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1
+      Args:
+        query: weather in san francisco
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629", "content": "Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead."}]
+    ================================== Ai Message ==================================
+    
+    According to the search results from Tavily, the current weather in San Francisco is:
+    
+    The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.
+    
+    Some key points about the typical June weather in San Francisco:
+    
+    - Mild temperatures with highs in the 60s F and lows in the 50s F
+    - Foggy mornings that often burn off to sunny afternoons
+    - Little to no rainfall, as June falls in the dry season
+    - Breezy conditions, with winds off the Pacific Ocean
+    - Layers are recommended for changing weather conditions
+    
+    So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.
+

docs/docs/cloud/how-tos/rollback_concurrent.md

@@ -0,0 +1,161 @@
+## Rollback
+
+This guide assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide][double-texting].
+
+The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.
+
+First, we will define a quick helper function for printing out JS model outputs (you can skip this if using Python):
+
+```js
+function prettyPrint(m) {
+  const padded = " " + m['type'] + " ";
+  const sepLen = Math.floor((80 - padded.length) / 2);
+  const sep = "=".repeat(sepLen);
+  const secondSep = sep + (padded.length % 2 ? "=" : "");
+  
+  console.log(`${sep}${padded}${secondSep}`);
+  console.log("\n\n");
+  console.log(m.content);
+}
+```
+
+Now, let's import our required packages and instantiate our client, assistant, and thread.
+
+=== "Python"
+
+    ```python
+    import asyncio
+
+    import httpx
+    from langchain_core.messages import convert_to_messages
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    const assistantId = "agent";
+    const thread = await client.threads.create();
+    ```
+
+Now let's run a thread with the multitask parameter set to "rollback":
+
+=== "Python"
+
+    ```python
+    # the first run will be rolled back
+    rolled_back_run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in sf?"}]},
+    )
+    await asyncio.sleep(2)
+    run = await client.runs.create(
+        thread["thread_id"],
+        assistant_id,
+        input={"messages": [{"role": "human", "content": "what's the weather in nyc?"}]},
+        multitask_strategy="rollback",
+    )
+    # wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"])
+    ```
+
+=== "Javascript"
+
+    ```js
+    // the first run will be interrupted
+    let rolledBackRun = await client.runs.create(
+      thread["thread_id"],
+      assistantId,
+      { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } }
+    );
+    await new Promise(resolve => setTimeout(resolve, 2000)); 
+
+    let run = await client.runs.create(
+      thread["thread_id"],
+      assistant_id,
+      { 
+        input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] },
+        multitaskStrategy: "rollback" 
+      }
+    );
+
+    // wait until the second run completes
+    await client.runs.join(thread["thread_id"], run["run_id"]);
+    ```
+
+We can see that the thread has data only from the second run
+
+=== "Python"
+
+    ```python
+    state = await client.threads.get_state(thread["thread_id"])
+
+    for m in convert_to_messages(state["values"]["messages"]):
+        m.pretty_print()
+    ```
+
+=== "Javascript"
+
+    ```js
+    const state = await client.threads.getState(thread["thread_id"]);
+
+    for (const m of state['values']['messages']) {
+      prettyPrint(m);
+    }
+    ```
+
+Output:
+
+    ================================ Human Message =================================
+    
+    what's the weather in nyc?
+    ================================== Ai Message ==================================
+    
+    [{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
+    Tool Calls:
+      tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)
+     Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD
+      Args:
+        query: weather in nyc
+    ================================= Tool Message =================================
+    Name: tavily_search_results_json
+    
+    [{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
+    ================================== Ai Message ==================================
+    
+    The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.
+
+
+Verify that the original, rolled back run was deleted
+
+=== "Python"
+
+    ```python
+    try:
+        await client.runs.get(thread["thread_id"], rolled_back_run["run_id"])
+    except httpx.HTTPStatusError as _:
+        print("Original run was correctly deleted")
+    ```
+
+=== "Javascript"
+
+    ```js
+    try {
+      await client.runs.get(thread["thread_id"], rolledBackRun["run_id"]);
+    } catch (e) {
+      console.log("Original run was correctly deleted");
+    }
+    ```
+
+Output:
+
+    Original run was correctly deleted
+

docs/docs/cloud/how-tos/stream_debug.md

@@ -0,0 +1,161 @@
+# How to stream debug events
+
+This guide covers how to stream debug events from your graph (`stream_mode="debug"`).
+
+First let's set up our client and thread:
+
+=== "Python"
+    
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3',
+     'created_at': '2024-06-21T22:10:27.696862+00:00',
+     'updated_at': '2024-06-21T22:10:27.696862+00:00',
+     'metadata': {}}
+
+Streaming debug events produces responses containing `type` and `timestamp` keys. Debug events correspond to different steps in the graph's execution (e.g. `task`, `task_result`, `checkpoint`).
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream debug
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="debug",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream debug
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "debug"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.256850+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a2e-6bb6-bfff-8423bcf47561', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.259723+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a35-6c86-8000-f4a85315dbeb', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.260021+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.267632+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.268469+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a4b-60ae-8001-dd378f965bf7', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.268659+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.272916+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.273113+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a56-6832-8002-8ab17e662980', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-21T22:11:09.273192+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.277262+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.277519+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a61-6462-8003-1316d9875b7f', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_events.md

@@ -0,0 +1,298 @@
+# How to stream events
+This guide covers how to stream events from your graph (`stream_mode="events"`). Depending on the use case and user experience of your LangGraph application, your application may process event types differently.
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+
+    {'thread_id': '3f4c64e0-f792-4a5e-aa07-a4404e06e0bd',
+     'created_at': '2024-06-24T22:16:29.301522+00:00',
+     'updated_at': '2024-06-24T22:16:29.301522+00:00',
+     'metadata': {}}
+
+
+
+Streaming events produces responses containing an `event` key (in addition to other keys such as `data`). See the LangChain [`Runnable.astream_events()` reference](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.astream_events) for all event types.
+
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:6'], 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}], 'sleep': None}}, 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:7'], 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:8'], 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'name': 'LangGraph', 'tags': [], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+## Token-by-Token Streaming
+
+Token-by-token streaming can be implemented with the `events` streaming mode. The `on_chat_model_stream` event type should be processed to stream LLM responses token-by-token.
+
+=== "Python"
+
+    ```python
+    llm_response = ""
+
+    # stream token-by-token
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode="events",
+    ):
+        if (
+            chunk.event == "events" and
+            chunk.data["event"] == "on_chat_model_stream"
+        ):
+            llm_response += chunk.data["data"]["chunk"]["content"]
+            print(llm_response)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const llmResponse = "";
+    // stream events
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "events"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      if (chunk.event === "events" && chunk.data.event === "on_chat_model_stream") {
+        llmResponse += chunk.data.data.chunk.content;
+        console.log(llmResponse);
+      }
+    }
+    ```
+
+Output:
+
+    b
+    be
+    beg
+    begi
+    begin
+    begine
+    beginen
+    beginend
+

docs/docs/cloud/how-tos/stream_messages.md

@@ -0,0 +1,390 @@
+# How to stream messages from your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="messages"`.
+
+In order to use this mode, the state of the graph you are interacting with MUST have a `messages` key that is a list of messages.
+E.g., the state should look something like:
+
+=== "Python"
+
+    ```python
+    from typing import TypedDict, Annotated
+    from langgraph.graph import add_messages
+    from langchain_core.messages import AnyMessage
+
+    class State(TypedDict):
+        messages: Annotated[list[AnyMessage], add_messages]
+    ```
+
+
+Alternatively, you can use an instance or subclass of `from langgraph.graph import MessagesState` (`MessagesState` is equivalent to the implementation above).
+
+> [!NOTE]
+> LangGraph Cloud only supports hosting graphs written in Python at the moment.
+
+With `stream_mode="messages"` two things will be streamed back:
+
+- It outputs messages produced by any chat model called inside (unless tagged in a special way)
+- It outputs messages returned from nodes (to allow for nodes to return `ToolMessages` and the like
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'e1431c95-e241-4d1d-a252-27eceb1e5c86',
+     'created_at': '2024-06-21T15:48:59.808924+00:00',
+     'updated_at': '2024-06-21T15:48:59.808924+00:00',
+     'metadata': {}}
+
+Let's also define a helper function for better formatting of the tool calls in messages
+
+=== "Python"
+
+    ```python
+    def format_tool_calls(tool_calls):
+        if tool_calls:
+            formatted_calls = []
+            for call in tool_calls:
+                formatted_calls.append(
+                    f"Tool Call ID: {call['id']}, Function: {call['name']}, Arguments: {call['args']}"
+                )
+            return "\n".join(formatted_calls)
+        return "No tool calls"
+    ```
+
+=== "Javascript"
+
+    ```js
+    function formatToolCalls(toolCalls) {
+      if (toolCalls && toolCalls.length > 0) {
+        const formattedCalls = toolCalls.map(call => {
+          return `Tool Call ID: ${call.id}, Function: ${call.name}, Arguments: ${call.args}`;
+        });
+        return formattedCalls.join("\n");
+      }
+      return "No tool calls";
+    }
+    ```
+
+Now we can stream by messages, which will return complete messages (at the end of node execution) as well as tokens for any messages generated inside a node:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "user", "content": "what's the weather in sf"}]}
+    config = {"configurable": {"model_name": "openai"}}
+
+    async for event in client.runs.stream(
+        thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        config=config,
+        stream_mode="messages",
+    ):
+        if event.event == "metadata":
+            print(f"Metadata: Run ID - {event.data['run_id']}")
+            print("-" * 50)
+        elif event.event == "messages/partial":
+            for data_item in event.data:
+                if "role" in data_item and data_item["role"] == "user":
+                    print(f"Human: {data_item['content']}")
+                else:
+                    tool_calls = data_item.get("tool_calls", [])
+                    invalid_tool_calls = data_item.get("invalid_tool_calls", [])
+                    content = data_item.get("content", "")
+                    response_metadata = data_item.get("response_metadata", {})
+
+                    if content:
+                        print(f"AI: {content}")
+
+                    if tool_calls:
+                        print("Tool Calls:")
+                        print(format_tool_calls(tool_calls))
+
+                    if invalid_tool_calls:
+                        print("Invalid Tool Calls:")
+                        print(format_tool_calls(invalid_tool_calls))
+
+                    if response_metadata:
+                        finish_reason = response_metadata.get("finish_reason", "N/A")
+                        print(f"Response Metadata: Finish Reason - {finish_reason}")
+            print("-" * 50)
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in sf",
+        }
+      ]
+    }
+    const config = {"configurable": {"model_name": "openai"}}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        config,
+        streamMode: "messages"
+      }
+    );
+    for await (const event of streamResponse) {
+      if (event.event === "metadata") {
+        console.log(`Metadata: Run ID - ${event.data.run_id}`);
+        console.log("-".repeat(50));
+      } else if (event.event === "messages/partial") {
+        event.data.forEach(dataItem => {
+          if (dataItem.role && dataItem.role === "user") {
+            console.log(`Human: ${dataItem.content}`);
+          } else {
+            const toolCalls = dataItem.tool_calls || [];
+            const invalidToolCalls = dataItem.invalid_tool_calls || [];
+            const content = dataItem.content || "";
+            const responseMetadata = dataItem.response_metadata || {};
+
+            if (content) {
+              console.log(`AI: ${content}`);
+            }
+
+            if (toolCalls.length > 0) {
+              console.log("Tool Calls:");
+              console.log(formatToolCalls(toolCalls));
+            }
+
+            if (invalidToolCalls.length > 0) {
+              console.log("Invalid Tool Calls:");
+              console.log(formatToolCalls(invalidToolCalls));
+            }
+
+            if (responseMetadata) {
+              const finishReason = responseMetadata.finish_reason || "N/A";
+              console.log(`Response Metadata: Finish Reason - ${finishReason}`);
+            }
+          }
+        });
+        console.log("-".repeat(50));
+      }
+    }
+    ```
+
+Output:
+
+    Metadata: Run ID - 1ef2fe5c-6a1d-6575-bc09-d7832711c17e
+    --------------------------------------------------
+    Invalid Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: 
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': ''}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    --------------------------------------------------
+    Tool Calls:
+    Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}
+    Response Metadata: Finish Reason - tool_calls
+    --------------------------------------------------
+    --------------------------------------------------
+    AI: The
+    --------------------------------------------------
+    AI: The current
+    --------------------------------------------------
+    AI: The current weather
+    --------------------------------------------------
+    AI: The current weather in
+    --------------------------------------------------
+    AI: The current weather in San
+    --------------------------------------------------
+    AI: The current weather in San Francisco
+    --------------------------------------------------
+    AI: The current weather in San Francisco is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is over
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-s
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-south
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 k
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%,
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles).
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    --------------------------------------------------
+    AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.
+    Response Metadata: Finish Reason - stop
+    --------------------------------------------------
+

docs/docs/cloud/how-tos/stream_multiple.md

@@ -0,0 +1,440 @@
+# How to configure multiple streaming modes at the same time
+
+This guide covers how to configure multiple streaming modes at the same time.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+When configuring multiple streaming modes for a run, responses for each respective mode will be produced. In the following example, note that a `list` of modes (`messages`, `events`, `debug`) is passed to the `stream_mode` parameter and the response contains `events`, `debug`, `messages/complete`, `messages/metadata`, and `messages/partial` event types.
+
+=== "Python"
+
+    ```python
+    # create input
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "What's the weather in SF?",
+            }
+        ]
+    }
+
+    # stream events with multiple streaming modes
+    async for chunk in client.runs.stream(
+        thread_id=thread["thread_id"],
+        assistant_id="agent",
+        input=input,
+        stream_mode=["messages", "events", "debug"],
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    // create input
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in SF?",
+        }
+      ]
+    }
+
+    // stream events with multiple streaming modes
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: ["messages", "events", "debug"]
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': "What's the weather in SF?"}]}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:1'], 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-2424dd6d-5cf5-4244-8d98-357640ce6e12': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'be', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'beg', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begi', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}}, 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:2'], 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:3'], 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/metadata...
+    {'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'en', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: messages/partial...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: messages/complete...
+    [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]
+    
+    
+    
+    Receiving new event of type: debug...
+    {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: events...
+    {'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': "What's the weather in SF?", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+

docs/docs/cloud/how-tos/stream_updates.md

@@ -0,0 +1,119 @@
+# How to stream state updates of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="updates"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+
+Output:
+
+    {'thread_id': '979e3c89-a702-4882-87c2-7a59a250ce16',
+     'created_at': '2024-06-21T15:22:07.453100+00:00',
+     'updated_at': '2024-06-21T15:22:07.453100+00:00',
+     'metadata': {}}
+
+Now we can stream by updates, which outputs updates made to the state by each node after it has executed:
+
+
+=== "Python"
+
+    ```python
+    input = {
+        "messages": [
+            {
+                "role": "human",
+                "content": "what's the weather in la"
+            }
+        ]
+    }
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="updates",
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+
+    ```js
+    const input = {
+      "messages": [
+        {
+          "role": "human",
+          "content": "What's the weather in la",
+        }
+      ]
+    }
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "updates"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'cfc96c16-ed9a-44bd-b5bb-c30e3c0725f0'}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': [{'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-1a9d32b0-7007-4a36-abde-8df812a0ed94', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'action': {'messages': [{'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716062239, \'localtime\': \'2024-05-18 12:57\'}, \'current\': {\'last_updated_epoch\': 1716061500, \'last_updated\': \'2024-05-18 12:45\', \'temp_c\': 18.9, \'temp_f\': 66.0, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 2.2, \'wind_kph\': 3.6, \'wind_degree\': 10, \'wind_dir\': \'N\', \'pressure_mb\': 1017.0, \'pressure_in\': 30.02, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 18.9, \'feelslike_f\': 66.0, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 6.0, \'gust_mph\': 7.5, \'gust_kph\': 12.0}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': 'a36e8cd1-0e96-4417-9c15-f10a945d2b42', 'tool_call_id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}]}}
+    
+    
+    
+    Receiving new event of type: data...
+    {'agent': {'messages': [{'content': 'The weather in Los Angeles is currently overcast with a temperature of around 66°F (18.9°C). There are light winds from the north at around 2-3 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-d5c1c2f0-b12d-41ce-990b-f36570e7483d', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}}
+    
+    
+    
+    Receiving new event of type: end...
+    None

docs/docs/cloud/how-tos/stream_values.md

@@ -0,0 +1,190 @@
+# How to stream full state of your graph
+
+LangGraph Cloud supports multiple streaming modes. The main ones are:
+
+- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.
+- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.
+- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.
+
+
+This guide covers `stream_mode="values"`.
+
+First let's set up our client and thread:
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    client = get_client(url="whatever-your-deployment-url-is")
+    # create thread
+    thread = await client.threads.create()
+    print(thread)
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    const client = new Client({ apiUrl: "whatever-your-deployment-url-is" });
+    // create thread
+    const thread = await client.threads.create();
+    console.log(thread)
+    ```
+
+Output:
+
+    {'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',
+     'created_at': '2024-06-24T21:30:07.980789+00:00',
+     'updated_at': '2024-06-24T21:30:07.980789+00:00',
+     'metadata': {}}
+
+Now we can stream by values, which streams the full state of the graph after each node has finished executing:
+
+=== "Python"
+
+    ```python
+    input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    # stream values
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent", 
+        input=input,
+        stream_mode="values"
+    ):
+        print(f"Receiving new event of type: {chunk.event}...")
+        print(chunk.data)
+        print("\n\n")
+    ```
+
+=== "Javascript"
+    
+
+    ```js
+    const input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
+
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      console.log(f"Receiving new event of type: {chunk.event}...")
+      console.log(chunk.data)
+      console.log("\n\n")
+    }
+    ```
+
+
+Output:
+
+    Receiving new event of type: metadata...
+    {'run_id': 'f08791ce-0a3d-44e0-836c-ff62cd2e2786'}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'role': 'human', 'content': 'what's the weather in la'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}]}
+    
+    
+    
+    Receiving new event of type: values...
+    {'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}, {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-4d6d4c23-5aad-4042-b0d9-19407a9e08e3', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}
+    
+    
+    
+    Receiving new event of type: end...
+    None
+    
+    
+    
+
+
+If we want to just get the final result, we can use this endpoint and just keep track of the last value we received
+
+
+=== "Python"
+
+    ```python
+    final_answer = None
+    async for chunk in client.runs.stream(
+        thread["thread_id"],
+        "agent",
+        input=input,
+        stream_mode="values"
+    ):
+        if chunk.event == "values":
+            final_answer = chunk.data
+    ```
+
+=== "Javascript"
+
+    ```js
+    let finalAnswer;
+    const streamResponse = client.runs.stream(
+      thread["thread_id"],
+      "agent",
+      {
+        input,
+        streamMode: "values"
+      }
+    );
+    for await (const chunk of streamResponse) {
+      finalAnswer = chunk.data;
+    }
+    ```
+
+Output:
+
+    {'messages': [{'content': 'what's the weather in la',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'human',
+       'name': None,
+       'id': 'e78c2f94-d810-42fc-a399-11f6bb1b1092',
+       'example': False},
+      {'content': [{'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom',
+         'input': {'query': 'weather in los angeles'},
+         'name': 'tavily_search_results_json',
+         'type': 'tool_use'}],
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-80767ab8-09fc-40ec-9e45-657ddef5e0b1',
+       'example': False,
+       'tool_calls': [{'name': 'tavily_search_results_json',
+         'args': {'query': 'weather in los angeles'},
+         'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'}],
+       'invalid_tool_calls': []},
+      {'content': '[{"url": "https://www.weatherapi.com/", "content": "{\'location\': {\'name\': \'Los Angeles\', \'region\': \'California\', \'country\': \'United States of America\', \'lat\': 34.05, \'lon\': -118.24, \'tz_id\': \'America/Los_Angeles\', \'localtime_epoch\': 1716310320, \'localtime\': \'2024-05-21 9:52\'}, \'current\': {\'last_updated_epoch\': 1716309900, \'last_updated\': \'2024-05-21 09:45\', \'temp_c\': 16.7, \'temp_f\': 62.1, \'is_day\': 1, \'condition\': {\'text\': \'Overcast\', \'icon\': \'//cdn.weatherapi.com/weather/64x64/day/122.png\', \'code\': 1009}, \'wind_mph\': 8.1, \'wind_kph\': 13.0, \'wind_degree\': 250, \'wind_dir\': \'WSW\', \'pressure_mb\': 1015.0, \'pressure_in\': 29.97, \'precip_mm\': 0.0, \'precip_in\': 0.0, \'humidity\': 65, \'cloud\': 100, \'feelslike_c\': 16.7, \'feelslike_f\': 62.1, \'vis_km\': 16.0, \'vis_miles\': 9.0, \'uv\': 5.0, \'gust_mph\': 12.5, \'gust_kph\': 20.2}}"}]',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'tool',
+       'name': 'tavily_search_results_json',
+       'id': 'af25e94a-c119-48c3-bbd3-096e42f472ac',
+       'tool_call_id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'},
+      {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.',
+       'additional_kwargs': {},
+       'response_metadata': {},
+       'type': 'ai',
+       'name': None,
+       'id': 'run-b90f0037-e56a-4f3b-ad92-00d10d079a9e',
+       'example': False,
+       'tool_calls': [],
+       'invalid_tool_calls': []}]}

docs/docs/cloud/index.md

@@ -12,7 +12,7 @@
 
 LangGraph Cloud is a managed service for deploying and hosting LangGraph applications. Deploying applications with LangGraph Cloud shortens the time-to-market for developers. With one click, deploy a production-ready API with built-in persistence for your LangGraph application. LangGraph Cloud APIs are horizontally scalable and deployed with durable storage.
 
-The LangGraph Cloud API exposes functionality of your LangGraph application through [Assistants](./concepts/index.md#assistants). An assistant abstracts the cognitive architecture of your graph. Invoke an assistant by calling the pre-built [API endpoints](./reference/api/api_ref.md).
+The LangGraph Cloud API exposes functionality of your LangGraph application through [Assistants](./concepts/api.md#assistants). An assistant abstracts the cognitive architecture of your graph. Invoke an assistant by calling the pre-built [API endpoints](./reference/api/api_ref.md).
 
 LangGraph Cloud is seamlessly integrated with [LangSmith](https://www.langchain.com/langsmith) and is accessible from within the LangSmith UI.
 
@@ -31,5 +31,5 @@ The LangGraph Cloud API supports key LangGraph features in addition to new funct
 
 - [Tutorials](./quick_start.md): Learn to build and deploy applications for LangGraph Cloud.
 - [How-to Guides](./how-tos/index.md): Learn how to set up a LangGraph application for deployment and implement features of the LangGraph Cloud API such as streaming tokens, configuring double texting, and creating cron jobs. Go here if you want to copy and run a specific code snippet.
-- [Conceptual Guides](./concepts/index.md): In-depth explanations of the core data models (e.g. assistants) and key features (e.g. double texting) of the LangGraph Cloud API.
+- [Conceptual Guides](./concepts/api.md): In-depth explanations of the core data models (e.g. assistants), key features of the LangGraph Cloud API (e.g. double texting), and the architecture of a LangGraph Cloud deployment.
 - [Reference](./reference/api/api_ref.md): References for the LangGraph Cloud API, the corresponding Python and JS/TS SDKs, the LangGraph CLI, and deployment environment variables.

docs/docs/cloud/quick_start.md

@@ -1,4 +1,5 @@
 # Quick Start
+
 This quick start guide will cover how to build a simple agent that can look up things on the internet. We will then deploy it to LangGraph Cloud, use the LangGraph Studio to visualize and test it out, and use the LangGraph SDK to interact with it.
 
 ## Set up requirements
@@ -9,10 +10,9 @@ This tutorial will use:
 - Tavily for the search engine - sign up and get an API key [here](https://app.tavily.com/)
 - LangSmith for hosting - sign up and get an API key [here](https://smith.langchain.com/)
 
-
 ## Set up local files
 
-1. Create a new application with the following directory and files:
+1.  Create a new application with the following directory and files:
 
         <my-app>/
         |-- agent.py            # code for your LangGraph agent
@@ -20,52 +20,53 @@ This tutorial will use:
         |-- langgraph.json      # configuration file for LangGraph
         |-- .env                # environment files with API keys
 
-2. The `agent.py` file should contain Python code for defining your graph. The following code is a simple example, the important thing is that at some point in your file you compile your graph and assign the compiled graph to a variable (in this case the `graph` variable). This example code uses `create_react_agent`, a prebuilt agent, read more about it [here](..//concepts/agentic_concepts.md#react-agent).
+2.  The `agent.py` file should contain Python code for defining your graph. The following code is a simple example, the important thing is that at some point in your file you compile your graph and assign the compiled graph to a variable (in this case the `graph` variable). This example code uses `create_react_agent`, a prebuilt agent, read more about it [here](..//concepts/agentic_concepts.md#react-agent).
 
     ```python
     from langchain_anthropic import ChatAnthropic
     from langchain_community.tools.tavily_search import TavilySearchResults
     from langgraph.prebuilt import create_react_agent
-   
+
     model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
-   
+
     tools = [TavilySearchResults(max_results=2)]
-   
+
     graph = create_react_agent(model, tools)
     ```
 
-3. The `requirements.txt` file should contain any dependencies for your graph(s). In this case we only require four packages for our graph to run:
+3.  The `requirements.txt` file should contain any dependencies for your graph(s). In this case we only require four packages for our graph to run:
 
         langgraph
         langchain_anthropic
         tavily-python
         langchain_community
 
-4. The `langgraph.json` file is a configuration file that describes what graph(s) you are going to host. In this case we only have one graph to host: the compiled `graph` object from `agent.py`.
+4.  The [`langgraph.json`][langgraph.json] file is a configuration file that describes what graph(s) you are going to host. In this case we only have one graph to host: the compiled `graph` object from `agent.py`.
 
     ```json
     {
-        "dependencies": ["."],
-        "graphs": {
-            "agent": "./agent.py:graph"
-        },
-        "env": ".env"
+      "dependencies": ["."],
+      "graphs": {
+        "agent": "./agent.py:graph"
+      },
+      "env": ".env"
     }
     ```
 
     Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
-5. The `.env` file should have any environment variables needed to run your graph. This will only be used for local testing, so if you are not testing locally you can skip this step. NOTE: if you do add this, you should NOT check this into git. For this graph, we need two environment variables:
+
+5.  The `.env` file should have any environment variables needed to run your graph. This will only be used for local testing, so if you are not testing locally you can skip this step. NOTE: if you do add this, you should NOT check this into git. For this graph, we need two environment variables:
 
     ```shell
     ANTHROPIC_API_KEY=...
     TAVILY_API_KEY=...
     ```
 
-Now that we have set everything up on our local file system, we are ready to host our graph. 
+Now that we have set everything up on our local file system, we are ready to host our graph.
 
 ## Test the graph build locally
 
-Before deploying to the cloud, we probably want to test the building of our graph locally. This is useful to make sure we have configured our CLI configuration file correctly and our graph runs.
+Before deploying to the cloud, we probably want to test the building of our graph locally. This is useful to make sure we have configured our [CLI configuration file][langgraph.json] correctly and our graph runs.
 
 In order to do this we can first install the LangGraph CLI
 
@@ -73,13 +74,13 @@ In order to do this we can first install the LangGraph CLI
 pip install langgraph-cli
 ```
 
-We can then stand up a simple test server. The server this stands up is INCREDIBLY simple - it is just a single endpoint and has no persistence. **This should not be used for hosting your application, only for testing the build and basic functionality.**
+We can then test our API server locally. This requires access to LangGraph closed beta. In order to run the server locally, you will need to add your `LANGSMITH_API_KEY` to the .env file so we can validate you have access to LangGraph closed beta.
 
 ```shell
-langgraph test
+langgraph up
 ```
 
-This will test building of the agent server. If this runs successfully, you should see something like:
+This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
 
 ```shell
 Ready!
@@ -87,7 +88,7 @@ Ready!
 2024-06-26 19:20:41,056:INFO:uvicorn.access 127.0.0.1:44138 - "GET /ok HTTP/1.1" 200
 ```
 
-You can now test this out! Again, we only expose a single simple endpoint (for streaming stateless runs). This is intended to allow you to test that the agent is properly set up, but should **NOT** but used for production purposes. To test it out, you can go to another terminal window and run:
+You can now test this out! **Note: this local server is intended SOLELY for local testing purposes and is not performant enough for production applications, so please do not use it as such.** To test it out, you can go to another terminal window and run:
 
 ```shell
 curl --request POST \
@@ -124,13 +125,13 @@ Turn the `<my-app>` directory into a GitHub repo. You can use the GitHub CLI if
 
 ### Deploy from GitHub with LangGraph Cloud
 
-Once you have created your github repository with a Python file containing your compiled graph as well as a `langgraph.json` file containing the configuration for hosting your graph, you can head over to LangSmith and click on the 🚀 icon on the left navbar to create a new deployment. Then click the `+ New Deployment` button. 
+Once you have created your github repository with a Python file containing your compiled graph as well as a `langgraph.json` file containing the configuration for hosting your graph, you can head over to LangSmith and click on the 🚀 icon on the left navbar to create a new deployment. Then click the `+ New Deployment` button.
 
 ![Langsmith Workflow](./img/cloud_deployment.png)
 
-***If you have not deployed to LangGraph Cloud before:*** there will be a button that shows up saying Import from GitHub. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
+**_If you have not deployed to LangGraph Cloud before:_** there will be a button that shows up saying Import from GitHub. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
 
-***Once you have set up your GitHub connection:*** the new deployment page will look as follows:
+**_Once you have set up your GitHub connection:_** the new deployment page will look as follows:
 
 ![Deployment before being filled out](./deployment/img/deployment_page.png)
 
@@ -140,7 +141,7 @@ To deploy your application, you should do the following:
 2. Search for your repo to deploy in the search bar and select it
 3. Choose any name
 4. In the `LangGraph API config file` field, enter the path to your `langgraph.json` file (which in this case is just `langgraph.json`)
-5. For Git Reference, you can select either the git branch for the code you want to deploy, or the exact commit SHA. 
+5. For Git Reference, you can select either the git branch for the code you want to deploy, or the exact commit SHA.
 6. If your chain relies on environment variables, add those in. They will be propagated to the underlying server so your code can access them. In this case, we need `ANTHROPIC_API_KEY` and `TAVILY_API_KEY`.
 
 Putting this all together, you should have something as follows for your deployment details:
@@ -157,7 +158,7 @@ After your deployment is complete, your deployments page should look as follows:
 
 ![Deployed page](./deployment/img/deployed_page.png)
 
-You can see that by default, you get access to the `Trace Count` monitoring chart and `Recent Traces` run view. These are powered by LangSmith. 
+You can see that by default, you get access to the `Trace Count` monitoring chart and `Recent Traces` run view. These are powered by LangSmith.
 
 You can click on `All Charts` to view all monitoring info for your server, or click on `See tracing project` to get more information on an individual trace.
 
@@ -181,18 +182,16 @@ On this page you can test out your graph by passing in starting states and click
 
 ## Use with the SDK
 
-Once you have tested that your hosted graph works as expected using LangGraph Studio, you can start using your hosted graph all over your organization by using the LangGraph SDK. Let's see how we can access our hosted graph and execute our run from a python file. 
+Once you have tested that your hosted graph works as expected using LangGraph Studio, you can start using your hosted graph all over your organization by using the LangGraph SDK. Let's see how we can access our hosted graph and execute our run from a python file.
 
 First, make sure you have the SDK installed by calling `pip install langgraph_sdk`.
 
-Before using, you need to get the URL of your LangGraph deployment. You can find this on the auto generated documentation page here:
-
-![Base URL of LangGraph deployment](./deployment/img/base_url.png)
+Before using, you need to get the URL of your LangGraph deployment. You can find this in the `Deployment` view. Click the URL to copy it to the clipboard.
 
 You also need to make sure you have set up your API key properly so you can authenticate with LangGraph Cloud.
 
 ```shell
-export LANGCHAIN_API_KEY=...
+export LANGSMITH_API_KEY=...
 ```
 
 The first thing to do when using the SDK is to setup our client, access our assistant, and create a thread to execute a run on:
@@ -224,31 +223,30 @@ async for chunk in client.runs.stream(
         input=input,
         stream_mode="updates",
     ):
-    if chunk.data and "run_id" not in chunk.data:
-            print(chunk.data)
+    if chunk.data and chunk.event != "metadata":
+        print(chunk.data)
 ```
 
     {'agent': {'messages': [{'content': "Hi Bagatur! It's nice to meet you. How can I assist you today?", 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_9cb5d38cf7'}, 'type': 'ai', 'name': None, 'id': 'run-c89118b7-1b1e-42b9-a85d-c43fe99881cd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}
 
-
 ## What's Next
 
 Congratulations! If you've worked your way through this tutorial you are well on your way to becoming a LangGraph Cloud expert. Here are some other resources to check out to help you out on the path to expertise:
 
 ### LangGraph Cloud How-tos
 
-If you want to learn more about streaming from hosted graphs, check out the Streaming [how-to guides](https://langchain-ai.github.io/langgraph/cloud/how-tos/#streaming).
+If you want to learn more about streaming from hosted graphs, check out the Streaming [how-to guides](how-tos/index.md#streaming).
 
-To learn more about double-texting and all the ways you can handle it in your application, read up on these [how-to guides](https://langchain-ai.github.io/langgraph/cloud/how-tos/#double-texting).
+To learn more about double-texting and all the ways you can handle it in your application, read up on these [how-to guides](how-tos/index.md#double-texting).
 
-To learn about how to include different human-in-the-loop behavior in your graph, take a look at [these how-tos](https://langchain-ai.github.io/langgraph/cloud/how-tos/#human-in-the-loop).
+To learn about how to include different human-in-the-loop behavior in your graph, take a look at [these how-tos](how-tos/index.md#human-in-the-loop).
 
 ### LangGraph Tutorials
 
 Before hosting, you have to write a graph to host. Here are some tutorials to get you more comfortable with writing LangGraph graphs and give you inspiration for the types of graphs you want to host.
 
-[This tutorial](https://langchain-ai.github.io/langgraph/tutorials/customer-support/customer-support/) walks you through how to write a customer support bot using LangGraph.
+[This tutorial](../tutorials/customer-support/customer-support.ipynb) walks you through how to write a customer support bot using LangGraph.
 
-If you are interested in writing a SQL agent, check out [this tutorial](https://langchain-ai.github.io/langgraph/tutorials/sql-agent/).
+If you are interested in writing a SQL agent, check out [this tutorial](../tutorials/sql-agent.ipynb).
 
-Check out the [LangGraph tutorials](https://langchain-ai.github.io/langgraph/tutorials/) page to read about more exciting use cases.
+Check out the [LangGraph tutorials](../tutorials/index.md) page to read about more exciting use cases.

docs/docs/cloud/reference/api/openapi.json

@@ -59,7 +59,7 @@
           "content": {
             "application/json": {
               "schema": {
-                "$ref": "#/components/schemas/SearchRequest"
+                "$ref": "#/components/schemas/AssistantSearchRequest"
               }
             }
           },
@@ -388,7 +388,7 @@
           "content": {
             "application/json": {
               "schema": {
-                "$ref": "#/components/schemas/SearchRequest"
+                "$ref": "#/components/schemas/ThreadSearchRequest"
               }
             }
           },
@@ -1463,6 +1463,52 @@
         }
       }
     },
+    "/runs/crons/search": {
+      "post": {
+        "tags": [
+          "crons/search"
+        ],
+        "summary": "Search Crons",
+        "description": "Search all active crons",
+        "operationId": "search_crons_runs_crons_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/CronSearch"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "items": {
+                    "$ref": "#/components/schemas/Cron"
+                  },
+                  "type": "array",
+                  "title": "Response Search Crons Search Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
+    },
     "/runs/stream": {
       "post": {
         "tags": [
@@ -1920,6 +1966,39 @@
         "title": "CronCreate",
         "description": "Payload for creating a cron."
       },
+      "CronSearch" : {
+        "properties": {
+          "assistant_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Assistant Id"
+          },
+          "thread_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "Thread Id"
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "required" : [],
+        "title": "CronSearch",
+        "description": "Payload for listing crons"
+      },
       "GraphSchema": {
         "properties": {
           "graph_id": {
@@ -2335,7 +2414,76 @@
         },
         "type": "object",
         "title": "SearchRequest",
-        "description": "Payload for listing assistants/threads/runs."
+        "description": "Payload for listing runs."
+      },
+      "AssistantSearchRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Metadata to search for."
+          },
+          "graph_id": {
+            "type": "string",
+            "title": "Graph Id",
+            "description": "Filter by graph ID."
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "title": "SearchRequest",
+        "description": "Payload for listing assistants."
+      },
+      "ThreadSearchRequest": {
+        "properties": {
+          "metadata": {
+            "type": "object",
+            "title": "Metadata",
+            "description": "Metadata to search for."
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "idle",
+              "busy",
+              "interrupted"
+            ],
+            "title": "Status",
+            "description": "Filter by thread status."
+          },
+          "limit": {
+            "type": "integer",
+            "title": "Limit",
+            "description": "Maximum number to return.",
+            "default": 10,
+            "minimum": 1,
+            "maximum": 1000
+          },
+          "offset": {
+            "type": "integer",
+            "title": "Offset",
+            "description": "Offset to start from.",
+            "default": 0,
+            "minimum": 0
+          }
+        },
+        "type": "object",
+        "title": "SearchRequest",
+        "description": "Payload for listing threads."
       },
       "Thread": {
         "properties": {
@@ -2357,6 +2505,15 @@
           "metadata": {
             "type": "object",
             "title": "Metadata"
+          },
+          "status": {
+            "type": "string",
+            "enum": [
+              "idle",
+              "busy",
+              "interrupted"
+            ],
+            "title": "Status"
           }
         },
         "type": "object",

docs/docs/cloud/reference/cli.md

@@ -6,6 +6,7 @@ The LangGraph CLI includes commands to build and run a LangGraph Cloud API serve
 2. Install the `langgraph-cli` Python package (e.g. `pip install langgraph-cli`).
 3. Run the command `langgraph --help` to confirm that the CLI is installed.
 
+[](){#langgraph.json}
 ## Configuration File
 The LangGraph CLI requires a JSON configuration file with the following keys:
 
@@ -82,6 +83,31 @@ langgraph build [OPTIONS]
 | `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
 | `--help` | | Display command documentation. |
 
+### `up`
+Start langgraph API server. For local testing, requires a LangSmith API key with access to LangGraph Cloud closed beta. Requires a license key for production use.
+
+**Usage**
+```
+langgraph up [OPTIONS]
+```
+
+**Options**
+
+| Option | Default | Description |
+| ------ | ------- | ----------- |
+| `--wait` | | Wait for services to start before returning. Implies --detach |
+| `--postgres-uri TEXT` | Local database | Postgres URI to use for the database. |
+| `--watch` | | Restart on file changes |
+| `--debugger-base-url TEXT` | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API. |
+| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port |
+| `--verbose` | | Show more output from the server logs. |
+| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
+| `-d, --docker-compose FILE` | | Path to docker-compose.yml file with additional services to launch. |
+| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph test --port 8000` |
+| `--pull / --no-pull` | `pull` | Pull latest images. Use --no-pull for running the server with locally-built images. Example: `langgraph up --no-pull` |
+| `--recreate / --no-recreate` | `no-recreate` | Recreate containers even if their configuration and image haven't changed |
+| `--help` | | Display command documentation. | 
+
 ### `test`
 Test your LangGraph in the cloud. The only function you can call from the SDK after testing your graph is `client.runs.stream(thread_id=None, ...)`
 

docs/docs/concepts/index.md

@@ -1,8 +1,8 @@
 # Conceptual Guides
 
-In this guide we will explore the concepts behind build agentic and multi-agent systems with LangGraph. We assume you have already learned the basic covered in the [introduction tutorial](https://langchain-ai.github.io/langgraph/tutorials/introduction) and want to deepen your understanding of LangGraph's underlying design and inner workings.
+In this guide we will explore the concepts behind build agentic and multi-agent systems with LangGraph. We assume you have already learned the basic covered in the [introduction tutorial](../tutorials/introduction.ipynb) and want to deepen your understanding of LangGraph's underlying design and inner workings.
 
-There are three main parts to this concept guide. First, we'll discuss at a very high level what it means to be agentic. Next, we'll look at lower-level concepts in LangGraph that are core for understanding how to build your own agentic systems. Finally, we'll discuss common agentic patterns and how you can achieve those with LangGraph. These will be mostly conceptual guides - for more technical, hands-on guides see our [how-to guides](https://langchain-ai.github.io/langgraph/how-tos/)
+There are three main parts to this concept guide. First, we'll discuss at a very high level what it means to be agentic. Next, we'll look at lower-level concepts in LangGraph that are core for understanding how to build your own agentic systems. Finally, we'll discuss common agentic patterns and how you can achieve those with LangGraph. These will be mostly conceptual guides - for more technical, hands-on guides see our [how-to guides](../how-tos/index.md)
 
 
 LangGraph for Agentic Applications

docs/docs/concepts/low_level.md

@@ -14,7 +14,9 @@ By composing `Nodes` and `Edges`, you can create complex, looping workflows that
 
 In short: _nodes do the work. edges tell what to do next_.
 
-LangGraph's underlying graph algorithm uses [message passing](https://en.wikipedia.org/wiki/Message_passing) to define a general program. When a `Node` completes, it sends a message along one or more edges to other node(s). These nodes run their functions, pass the resulting messages to the next set of nodes, and on and on it goes. Inspired by [Pregel](https://research.google/pubs/pregel-a-system-for-large-scale-graph-processing/), the program proceeds in discrete "super-steps" that are all executed conceptually in parallel. Whenever the graph is run, all the nodes start in an `inactive` state. Whenever an incoming edge (or "channel") receives a new message (state), the node becomes `active`, runs the function, and responds with updates. At the end of each superstep, each node votes to `halt` by marking itself as `inactive` if it has no more incoming messages. The graph terminates when all nodes are `inactive` and when no messages are in transit.
+LangGraph's underlying graph algorithm uses [message passing](https://en.wikipedia.org/wiki/Message_passing) to define a general program. When a Node completes its operation, it sends messages along one or more edges to other node(s). These recipient nodes then execute their functions, pass the resulting messages to the next set of nodes, and the process continues. Inspired by Google's [Pregel](https://research.google/pubs/pregel-a-system-for-large-scale-graph-processing/) system, the program proceeds in discrete "super-steps."
+
+A super-step can be considered a single iteration over the graph nodes. Nodes that run in parallel are part of the same super-step, while nodes that run sequentially belong to separate super-steps. At the start of graph execution, all nodes begin in an `inactive` state. A node becomes `active` when it receives a new message (state) on any of its incoming edges (or "channels"). The active node then runs its function and responds with updates. At the end of each super-step, nodes with no incoming messages vote to `halt` by marking themselves as `inactive`. The graph execution terminates when all nodes are `inactive` and no messages are in transit.
 
 ### StateGraph
 
@@ -193,13 +195,7 @@ graph.add_edge("node_a", routing_function, {True: "node_b", False: "node_c"})
 
 ### Entry Point
 
-The entry point is first node to call when the graph starts. You can use [`set_entry_point`][langgraph.graph.StateGraph.set_entry_point] to specify this.
-
-```python
-graph.set_entry_point("node_a")
-```
-
-This is equivalent to adding an edge between the `START` node and this node. You may want to use `START` directly when you want to have **multiple** nodes be called first.
+The entry point is the first node(s) that are run when the graph starts. You can use the [`add_edge`][langgraph.graph.StateGraph.add_edge] method from the virtual [`START`][start] node to the first node to execute to specify where to enter the graph.
 
 ```python
 from langgraph.graph import START
@@ -209,17 +205,18 @@ graph.add_edge(START, "node_a")
 
 ### Conditional Entry Point
 
-The conditional entry point is used when you want to specify a function to call to determine which node(s) should be called first.
-You can use [`set_conditional_entry_point`][langgraph.graph.StateGraph.set_conditional_entry_point] to specify this.
+A conditional entry point lets you start at different nodes depending on custom logic. You can use [`add_conditional_edges`][langgraph.graph.StateGraph.add_conditional_edges] from the virtual [`START`][start] node to accomplish this.
 
 ```python
-graph.set_conditional_entry_point(routing_function)
+from langgraph.graph import START
+
+graph.add_conditional_edges(START, routing_function)
 ```
 
 You can optionally provide a dictionary that maps the `routing_function`'s output to the name of the next node.
 
 ```python
-graph.set_conditional_entry_point(routing_function, {True: "node_b", False: "node_c"})
+graph.add_conditional_edges(START, routing_function, {True: "node_b", False: "node_c"})
 ```
 
 ## `Send`
@@ -237,11 +234,9 @@ graph.add_conditional_edges("node_a", continue_to_jokes)
 
 ## Checkpointer
 
-One of the main benefits of LangGraph is that it comes backed by a persistence layer. This is accomplished via [checkpointers][basecheckpointsaver].
+LangGraph has a built-in persistence layer, implemented through [checkpointers][basecheckpointsaver]. When you use a checkpointer with a graph, you can interact with the state of that graph. When you use a checkpointer with a graph, you can interact with and manage the graph's state. The checkpointer saves a _checkpoint_ of the graph state at every super-step, enabling several powerful capabilities:
 
-Checkpointers can be used to save a _checkpoint_ of the state of a graph after all steps of the graph. This allows for several things.
-
-First, it allows for [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop), as it allows humans to inspect, interrupt, and approve steps. Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state.
+First, checkpointers facilitate [human-in-the-loop workflows](agentic_concepts.md#human-in-the-loop) workflows by allowing humans to inspect, interrupt, and approve steps.Checkpointers are needed for these workflows as the human has to be able to view the state of a graph at any point in time, and the graph has to be to resume execution after the human has made any updates to the state.
 
 Second, it allows for ["memory"](agentic_concepts.md#memory) between interactions. You can use checkpointers to create threads and save the state of a thread after a graph executes. In the case of repeated human interactions (like conversations) any follow up messages can be sent to that checkpoint, which will retain its memory of previous ones.
 
@@ -249,8 +244,7 @@ See [this guide](../how-tos/persistence.ipynb) for how to add a checkpointer to
 
 ## Threads
 
-When using a checkpointer, you must specify a `thread_id` or `thread_ts` when running the graph.
-Threads are used to checkpoint multiple different runs. This can be used to enable a multi-tenant chat applications.
+Threads enable the checkpointing of multiple different runs, making them essential for multi-tenant chat applications and other scenarios where maintaining separate states is necessary. A thread is a unique ID assigned to a series of checkpoints saved by a checkpointer. When using a checkpointer, you must specify a `thread_id` or `thread_ts` when running the graph.
 
 `thread_id` is simply the ID of a thread. This is always required
 
@@ -267,14 +261,7 @@ See [this guide](../how-tos/persistence.ipynb) for how to use threads.
 
 ## Checkpointer state
 
-When you use a checkpointer with a graph, you can interact with the state of that graph.
-This usually done when enabling different human-in-the-loop interaction patterns.
-Each time you run the graph, the checkpointer creates several checkpoints every time a
-node or set of nodes finishes running.
-The most recent checkpoint is the current state of the thread.
-When interacting with the checkpointer state, you must specify a [thread identifier](#threads).
-
-Each checkpoint has two properties:
+ When interacting with the checkpointer state, you must specify a [thread identifier](#threads).Each checkpoint saved by the checkpointer has two properties:
 
 - **values**: This is the value of the state at this point in time.
 - **next**: This is a tuple of the nodes to execute next in the graph.

docs/docs/how-tos/index.md

@@ -22,8 +22,12 @@ These how-to guides show how to achieve that controllability.
 LangGraph makes it easy to persist state across graph runs. The guide below shows how to add persistence to your graph.
 
 - [How to add persistence ("memory") to your graph](persistence.ipynb)
-- [How to manage conversation history](managing-conversation-history.ipynb)
+- [How to manage conversation history](memory/manage-conversation-history.ipynb)
+- [How to delete messages](memory/delete-messages.ipynb)
+- [How to add summary conversation memory](memory/add-summary-conversation-history.ipynb)
 - [How to create a custom checkpointer using Postgres](persistence_postgres.ipynb)
+- [How to create a custom checkpointer using MongoDB](persistence_mongodb.ipynb)
+- [How to create a custom checkpointer using Redis](persistence_redis.ipynb)
 
 ## Human in the Loop
 
@@ -43,16 +47,20 @@ These guides show how to use different streaming modes.
 - [How to stream full state of your graph](stream-values.ipynb)
 - [How to stream state updates of your graph](stream-updates.ipynb)
 - [How to stream LLM tokens](streaming-tokens.ipynb)
+- [How to stream LLM tokens without LangChain models](streaming-tokens-without-langchain.ipynb)
 - [How to stream arbitrarily nested content](streaming-content.ipynb)
 - [How to configure multiple streaming modes at the same time](stream-multiple.ipynb)
 - [How to stream events from within a tool](streaming-events-from-within-tools.ipynb)
+- [How to stream events from within a tool without LangChain models](streaming-events-from-within-tools-without-langchain.ipynb)
 - [How to stream events from the final node](streaming-from-final-node.ipynb)
 
 ## Other
 - [How to run graph asynchronously](async.ipynb)
 - [How to visualize your graph](visualization.ipynb)
 - [How to add runtime configuration to your graph](configuration.ipynb)
+- [How to pass runtime values to tools](pass-run-time-values-to-tools.ipynb)
 - [How to use a Pydantic model as your state](state-model.ipynb)
+- [How to use a context object in state](state-context-key.ipynb)
 
 ## Prebuilt ReAct Agent
 

docs/docs/reference/checkpoints.md

@@ -1,6 +1,6 @@
 # Checkpoints
 
-You can [compile](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph.compile) any LangGraph workflow with a [CheckPointer](https://langchain-ai.github.io/langgraph/reference/checkpoints/#basecheckpointsaver) to give your agent "memory" by persisting its state. This permits things like:
+You can [compile][langgraph.graph.MessageGraph.compile] any LangGraph workflow with a [CheckPointer][basecheckpointsaver] to give your agent "memory" by persisting its state. This permits things like:
 
 - Remembering things across multiple interactions
 - Interrupting to wait for user input

docs/mkdocs.yml

@@ -1,18 +1,17 @@
-site_name: LangGraph
+site_name: ""
 site_description: Build language agents as graphs
 site_url: https://langchain-ai.github.io/langgraph/
 repo_url: https://github.com/langchain-ai/langgraph
 theme:
   name: material
   custom_dir: overrides
-  logo: static/wordmark.png
+  logo_dark_mode: static/wordmark_light.svg
+  logo_light_mode: static/wordmark_dark.svg
   favicon: static/favicon.png
   icon:
     repo: fontawesome/brands/git-alt
   features:
     - announce.dismiss
-    - content.action.edit
-    - content.action.view
     - content.code.annotate
     - content.code.copy
     - content.code.select
@@ -132,8 +131,12 @@ nav:
           - Create map-reduce branches for parallel execution: how-tos/map-reduce.ipynb
       - Persistence:
           - Add persistence ("memory"): how-tos/persistence.ipynb
-          - Manage conversation history: how-tos/managing-conversation-history.ipynb
+          - Manage conversation history: how-tos/memory/manage-conversation-history.ipynb
+          - Delete messages: how-tos/memory/delete-messages.ipynb
+          - Add summary of the conversation history: how-tos/memory/add-summary-conversation-history.ipynb
           - Create custom checkpointer using Postgres: how-tos/persistence_postgres.ipynb
+          - Create custom checkpointer using MongoDB: how-tos/persistence_mongodb.ipynb
+          - Create custom checkpointer using Redis: how-tos/persistence_redis.ipynb
       - Human-in-the-loop:
           - Add breakpoints: how-tos/human_in_the_loop/breakpoints.ipynb
           - Wait for user input: how-tos/human_in_the_loop/wait-user-input.ipynb
@@ -143,15 +146,19 @@ nav:
           - Stream full state: how-tos/stream-values.ipynb
           - Stream state updates: how-tos/stream-updates.ipynb
           - Stream LLM tokens: how-tos/streaming-tokens.ipynb
+          - Stream LLM tokens without LangChain models: how-tos/streaming-tokens-without-langchain.ipynb
           - Stream arbitrarily nested content: how-tos/streaming-content.ipynb
           - Configure multiple streaming modes: how-tos/stream-multiple.ipynb
           - Stream events from within tools: how-tos/streaming-events-from-within-tools.ipynb
+          - Stream events from within tools without LangChain models: how-tos/streaming-events-from-within-tools-without-langchain.ipynb
           - Stream events from the final node: how-tos/streaming-from-final-node.ipynb
       - Other:
           - Run graph asynchronously: how-tos/async.ipynb
           - Visualize your graph: how-tos/visualization.ipynb
           - Add runtime configuration: how-tos/configuration.ipynb
+          - Pass runtime values to tools: how-tos/pass-run-time-values-to-tools.ipynb
           - Use Pydantic model as state: how-tos/state-model.ipynb
+          - Use a context object in state: how-tos/state-context-key.ipynb
       - Prebuilt ReAct Agent:
           - Create a ReAct agent: how-tos/create-react-agent.ipynb
           - Add memory to a ReAct agent: how-tos/create-react-agent-memory.ipynb
@@ -177,25 +184,26 @@ nav:
           - Deployment:
               - Setup App: "cloud/deployment/setup.md"
               - Setup App (pyproject.toml): "cloud/deployment/setup_pyproject.md"
+              - Test App Locally: "cloud/deployment/test_locally.md"
               - Deploy to Cloud: "cloud/deployment/cloud.md"
               - Self-Host: "cloud/deployment/self_hosted.md"
           - Streaming:
-              - Stream Values: "cloud/how-tos/cloud_examples/stream_values.ipynb"
-              - Stream Updates: "cloud/how-tos/cloud_examples/stream_updates.ipynb"
-              - Stream Messages: "cloud/how-tos/cloud_examples/stream_messages.ipynb"
-              - Stream Events: "cloud/how-tos/cloud_examples/stream_events.ipynb"
-              - Stream Debug: "cloud/how-tos/cloud_examples/stream_debug.ipynb"
-              - Multiple Modes: "cloud/how-tos/cloud_examples/stream_multiple.ipynb"
+              - Stream Values: "cloud/how-tos/stream_values.md"
+              - Stream Updates: "cloud/how-tos/stream_updates.md"
+              - Stream Messages: "cloud/how-tos/stream_messages.md"
+              - Stream Events: "cloud/how-tos/stream_events.md"
+              - Stream Debug: "cloud/how-tos/stream_debug.md"
+              - Multiple Modes: "cloud/how-tos/stream_multiple.md"
           - Double Texting:
-              - Interrupt: "cloud/how-tos/cloud_examples/interrupt_concurrent.ipynb"
-              - Rollback: "cloud/how-tos/cloud_examples/rollback_concurrent.ipynb"
-              - Reject: "cloud/how-tos/cloud_examples/reject_concurrent.ipynb"
-              - Enqueue: "cloud/how-tos/cloud_examples/enqueue_concurrent.ipynb"
+              - Interrupt: "cloud/how-tos/interrupt_concurrent.md"
+              - Rollback: "cloud/how-tos/rollback_concurrent.md"
+              - Reject: "cloud/how-tos/reject_concurrent.md"
+              - Enqueue: "cloud/how-tos/enqueue_concurrent.md"
           - Human-in-the-Loop: 
-              - Add Breakpoint: "cloud/how-tos/cloud_examples/human_in_the_loop_breakpoint.ipynb"
-              - Wait for User Input: "cloud/how-tos/cloud_examples/human_in_the_loop_user_input.ipynb"
-              - Edit Graph State: "cloud/how-tos/cloud_examples/human_in_the_loop_edit_state.ipynb"
-              - Replay and Branch from Prior States: "cloud/how-tos/cloud_examples/human_in_the_loop_time_travel.ipynb"
+              - Add Breakpoint: "cloud/how-tos/human_in_the_loop_breakpoint.md"
+              - Wait for User Input: "cloud/how-tos/human_in_the_loop_user_input.md"
+              - Edit Graph State: "cloud/how-tos/human_in_the_loop_edit_state.md"
+              - Replay and Branch from Prior States: "cloud/how-tos/human_in_the_loop_time_travel.md"
           - LangGraph Studio:
               - Test Cloud Deployment: "cloud/how-tos/test_deployment.md"
               - Invoke graph in LangGraph Studio: "cloud/how-tos/invoke_studio.md"
@@ -209,7 +217,9 @@ nav:
               - Configure Agents: "cloud/how-tos/cloud_examples/configuration_cloud.ipynb"
               - Convert LangGraph calls to LangGraph Cloud calls: "cloud/how-tos/cloud_examples/langgraph_to_langgraph_cloud.ipynb"
               - Integrate Webhooks: 'cloud/how-tos/cloud_examples/webhooks.ipynb'
-      - Conceptual Guides: "cloud/concepts/index.md"
+      - Conceptual Guides:
+          - API Concepts: "cloud/concepts/api.md"
+          - Cloud Concepts: "cloud/concepts/cloud.md"
       - Reference:
           - API: "cloud/reference/api/api_ref.md"
           - SDK:
@@ -226,6 +236,9 @@ markdown_extensions:
   - def_list
   - footnotes
   - md_in_html
+  - pymdownx.superfences
+  - pymdownx.tabbed:
+      alternate_style: true
   - toc:
       permalink: true
   - pymdownx.arithmatex:

docs/overrides/main.html

@@ -21,12 +21,6 @@
       background-color: #FFFFFF;
     }
 
-    .navbar {
-      background-color: #FFFFFF;
-      color: #333333;
-      box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
-    }
-
     .md-footer {
       background-color: #F5F5F5;
       color: #666666;
@@ -100,6 +94,29 @@
       color: #BDBDBD;
     }
 
+    [data-md-color-scheme="slate"] .md-header {
+      background-color: #1E1E1E;
+      color: #BDBDBD;
+    }
+
+    [data-md-color-scheme="slate"] .md-tabs {
+      background-color: #1E1E1E;
+      color: #BDBDBD;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__input {
+      background-color: #F5F5F5;
+      color: #333333;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__icon {
+      color: #333333;
+    }
+
+    [data-md-color-scheme="slate"] .md-search__input::placeholder {
+      color: #333333;
+    }
+
     [data-md-color-scheme="slate"] .md-footer-meta {
       background-color: #1E1E1E;
     }
@@ -111,6 +128,7 @@
     [data-md-color-scheme="slate"] .md-typeset a:hover {
       color: #90CAF9;
     }
+
     .notebook-links {
       display: flex;
       justify-content: flex-end;
@@ -119,7 +137,22 @@
     .notebook-links .md-content__button {
       margin-left: 0.5rem;
     }
-    
+
+    [data-md-color-scheme=default] .logo-dark {
+      display: none !important;
+    }
+
+    [data-md-color-scheme=slate] .logo-light {
+      display: none !important;
+    }
+
+    .jupyter-wrapper .jp-CodeCell .jp-Cell-inputWrapper .jp-InputPrompt.jp-InputArea-prompt {
+      display: none !important;
+    }
+
+    .jupyter-wrapper .jp-Notebook .jp-Cell .jp-OutputPrompt {
+      display: none !important;
+    }
   </style>
 {% endblock %}
 
@@ -134,4 +167,15 @@
 </div>
 
 {{ super() }}
-{% endblock content %}
+{% endblock content %}
+
+
+{% block htmltitle %}
+  {% if page.meta and page.meta.title %}
+    <title>{{ page.meta.title }}</title>
+  {% elif page.title and not page.is_homepage %}
+    <title>{{ page.title | striptags }}</title>
+  {% else %}
+    <title>{{ config.site_name }}</title>
+  {% endif %}
+{% endblock %}

docs/overrides/partials/logo.html

@@ -0,0 +1,4 @@
+{% if config.theme.logo_light_mode %}
+  <img src="{{ config.theme.logo_light_mode | url }}" alt="logo" class="logo-light" />
+  <img src="{{ config.theme.logo_dark_mode | url }}" alt="logo" class="logo-dark" />
+{% endif %}

examples/agent_executor/base.ipynb

@@ -25,10 +25,7 @@
    "id": "fdd4ce41-4152-423b-b3f7-be3b4d568cf4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai langchainhub tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai langchainhub tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -44,13 +41,7 @@
    "id": "6398c4c1-da78-4595-8a5a-051ed2d1de72",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -66,10 +57,7 @@
    "id": "dcbf79ad-4de5-43b0-a3a1-25b33711e46c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -87,23 +75,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -126,27 +98,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -181,42 +133,7 @@
    "id": "d61a970d-edf4-4eef-9678-28bab7c72331",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -234,50 +151,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -300,12 +174,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -313,7 +182,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/force-calling-a-tool-first.ipynb

@@ -30,10 +30,7 @@
    "id": "694cfc4c-22a7-495d-930d-56b21d850ff9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "30c06a84-291a-4f58-9d31-53d3b56a3def",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "a8fb285a-7e6e-46fc-a273-43ab1a676189",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,42 +138,7 @@
    "id": "d61a970d-edf4-4eef-9678-28bab7c72331",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -250,9 +167,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "tools[0].name"
-   ]
+   "source": ["tools[0].name"]
   },
   {
    "cell_type": "code",
@@ -260,21 +175,7 @@
    "id": "df25d899-2338-4f31-a8bf-0582a2eec325",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentActionMessageLog\n",
-    "\n",
-    "\n",
-    "def first_agent(inputs):\n",
-    "    action = AgentActionMessageLog(\n",
-    "        # We force call this tool\n",
-    "        tool=\"tavily_search_results_json\",\n",
-    "        # We just pass in the `input` key to this tool\n",
-    "        tool_input=inputs[\"input\"],\n",
-    "        log=\"\",\n",
-    "        message_log=[],\n",
-    "    )\n",
-    "    return {\"agent_outcome\": action}"
-   ]
+   "source": ["from langchain_core.agents import AgentActionMessageLog\n\n\ndef first_agent(inputs):\n    action = AgentActionMessageLog(\n        # We force call this tool\n        tool=\"tavily_search_results_json\",\n        # We just pass in the `input` key to this tool\n        tool_input=inputs[\"input\"],\n        log=\"\",\n        message_log=[],\n    )\n    return {\"agent_outcome\": action}"]
   },
   {
    "cell_type": "markdown",
@@ -296,54 +197,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "workflow.add_node(\"first_agent\", first_agent)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"first_agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# After the first agent, we want to take an action\n",
-    "workflow.add_edge(\"first_agent\", \"action\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\nworkflow.add_node(\"first_agent\", first_agent)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"first_agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# After the first agent, we want to take an action\nworkflow.add_edge(\"first_agent\", \"action\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -366,12 +220,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -379,7 +228,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/human-in-the-loop.ipynb

@@ -30,10 +30,7 @@
    "id": "3fa9e224-2f00-49e2-bca3-e9cb8d9f3d41",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "d180f0d0-385f-4ce3-994c-11e1d64595b5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "72ad0539-ecd8-4eb1-b2c1-2242e5fc556f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,21 +138,7 @@
    "id": "2b757f84-1175-445e-8f8c-e5aeb765a03d",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)\n",
-    "\n",
-    "\n",
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    agent_outcome = agent_runnable.invoke(data)\n",
-    "    return {\"agent_outcome\": agent_outcome}"
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)\n\n\n# Define the agent\ndef run_agent(data):\n    agent_outcome = agent_runnable.invoke(data)\n    return {\"agent_outcome\": agent_outcome}"]
   },
   {
    "cell_type": "markdown",
@@ -218,30 +156,7 @@
    "id": "2fecf5e0-9604-4992-9c82-b9627466cd32",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    response = input(prompt=f\"[y/n] continue with: {agent_action}?\")\n",
-    "    if response == \"n\":\n",
-    "        raise ValueError\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    response = input(prompt=f\"[y/n] continue with: {agent_action}?\")\n    if response == \"n\":\n        raise ValueError\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -259,50 +174,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -338,12 +210,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -351,7 +218,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/agent_executor/managing-agent-steps.ipynb

@@ -30,10 +30,7 @@
    "id": "aa752131-27e3-4bd8-9f21-d6749a7e74f4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "5732e68f-4ae2-4db9-bf9c-454b4cc9ec01",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "652d4600-8f95-493f-b9b9-d4095aed9218",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -92,23 +80,7 @@
    "id": "4499eb16-bca8-4a60-9a3a-2f34ae3f7078",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import create_openai_functions_agent\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]\n",
-    "\n",
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n",
-    "\n",
-    "# Construct the OpenAI Functions agent\n",
-    "agent_runnable = create_openai_functions_agent(llm, tools, prompt)"
-   ]
+   "source": ["from langchain import hub\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_openai.chat_models import ChatOpenAI\n\ntools = [TavilySearchResults(max_results=1)]\n\n# Get the prompt to use - you can modify this!\nprompt = hub.pull(\"hwchase17/openai-functions-agent\")\n\n# Choose the LLM that will drive the agent\nllm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", streaming=True)\n\n# Construct the OpenAI Functions agent\nagent_runnable = create_openai_functions_agent(llm, tools, prompt)"]
   },
   {
    "cell_type": "markdown",
@@ -131,27 +103,7 @@
    "id": "c941fb10-dbe5-4d6a-ab7d-133d01c33cc4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict, Union\n",
-    "\n",
-    "from langchain_core.agents import AgentAction, AgentFinish\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    # The input string\n",
-    "    input: str\n",
-    "    # The list of previous messages in the conversation\n",
-    "    chat_history: list[BaseMessage]\n",
-    "    # The outcome of a given call to the agent\n",
-    "    # Needs `None` as a valid type, since this is what this will start as\n",
-    "    agent_outcome: Union[AgentAction, AgentFinish, None]\n",
-    "    # List of actions and corresponding observations\n",
-    "    # Here we annotate this with `operator.add` to indicate that operations to\n",
-    "    # this state should be ADDED to the existing values (not overwrite it)\n",
-    "    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict, Union\n\nfrom langchain_core.agents import AgentAction, AgentFinish\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    # The input string\n    input: str\n    # The list of previous messages in the conversation\n    chat_history: list[BaseMessage]\n    # The outcome of a given call to the agent\n    # Needs `None` as a valid type, since this is what this will start as\n    agent_outcome: Union[AgentAction, AgentFinish, None]\n    # List of actions and corresponding observations\n    # Here we annotate this with `operator.add` to indicate that operations to\n    # this state should be ADDED to the existing values (not overwrite it)\n    intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -186,15 +138,7 @@
    "id": "77e3c059-e31f-4c8f-81bf-edb58688e12b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.agents import AgentFinish\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor\n",
-    "\n",
-    "# This a helper class we have that is useful for running tools\n",
-    "# It takes in an agent action and calls that tool and returns the result\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langchain_core.agents import AgentFinish\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor\n\n# This a helper class we have that is useful for running tools\n# It takes in an agent action and calls that tool and returns the result\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -212,36 +156,7 @@
    "id": "a9f66a3e-aba1-4893-95b1-a433c7091d5e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the agent\n",
-    "def run_agent(data):\n",
-    "    inputs = data.copy()\n",
-    "    if len(inputs[\"intermediate_steps\"]) > 5:\n",
-    "        inputs[\"intermediate_steps\"] = inputs[\"intermediate_steps\"][-5:]\n",
-    "    agent_outcome = agent_runnable.invoke(inputs)\n",
-    "    return {\"agent_outcome\": agent_outcome}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def execute_tools(data):\n",
-    "    # Get the most recent agent_outcome - this is the key added in the `agent` above\n",
-    "    agent_action = data[\"agent_outcome\"]\n",
-    "    output = tool_executor.invoke(agent_action)\n",
-    "    return {\"intermediate_steps\": [(agent_action, str(output))]}\n",
-    "\n",
-    "\n",
-    "# Define logic that will be used to determine which conditional edge to go down\n",
-    "def should_continue(data):\n",
-    "    # If the agent outcome is an AgentFinish, then we return `exit` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    if isinstance(data[\"agent_outcome\"], AgentFinish):\n",
-    "        return \"end\"\n",
-    "    # Otherwise, an AgentAction is returned\n",
-    "    # Here we return `continue` string\n",
-    "    # This will be used when setting up the graph to define the flow\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["# Define the agent\ndef run_agent(data):\n    inputs = data.copy()\n    if len(inputs[\"intermediate_steps\"]) > 5:\n        inputs[\"intermediate_steps\"] = inputs[\"intermediate_steps\"][-5:]\n    agent_outcome = agent_runnable.invoke(inputs)\n    return {\"agent_outcome\": agent_outcome}\n\n\n# Define the function to execute tools\ndef execute_tools(data):\n    # Get the most recent agent_outcome - this is the key added in the `agent` above\n    agent_action = data[\"agent_outcome\"]\n    output = tool_executor.invoke(agent_action)\n    return {\"intermediate_steps\": [(agent_action, str(output))]}\n\n\n# Define logic that will be used to determine which conditional edge to go down\ndef should_continue(data):\n    # If the agent outcome is an AgentFinish, then we return `exit` string\n    # This will be used when setting up the graph to define the flow\n    if isinstance(data[\"agent_outcome\"], AgentFinish):\n        return \"end\"\n    # Otherwise, an AgentAction is returned\n    # Here we return `continue` string\n    # This will be used when setting up the graph to define the flow\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -259,50 +174,7 @@
    "id": "c4054dde-4618-49b7-998a-daa0c1d6d6c0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", run_agent)\n",
-    "workflow.add_node(\"action\", execute_tools)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", run_agent)\nworkflow.add_node(\"action\", execute_tools)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -325,12 +197,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\n",
-    "for s in app.stream(inputs):\n",
-    "    print(list(s.values())[0])\n",
-    "    print(\"----\")"
-   ]
+   "source": ["inputs = {\"input\": \"what is the weather in sf\", \"chat_history\": []}\nfor s in app.stream(inputs):\n    print(list(s.values())[0])\n    print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -338,7 +205,7 @@
    "id": "2eb662bc-de7d-4a57-a3e8-2f00dcf4ff8b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/async.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# How to run graph asynchronously\n",
     "\n",
-    "In this example we will build a ReAct agent with native [async](https://docs.python.org/3/library/asyncio.html) implementations of the core logic. When Chat Models have async clients, this can give us some nice performance improvements if you\n",
+    "In this example we will build a ReAct agent with native [async](https://docs.python.org/3/library/asyncio.html) implementations of the core logic. When chat models have async clients, this can give us some nice performance improvements if you\n",
     "are running concurrent branches in your graph or if your graph is running within a larger web server process.\n",
     "\n",
     "In general, you don't need to change anything about your graph to add `async` support. That's one of the beauties of [Runnables](https://python.langchain.com/docs/expression_language/interface/). \n",
@@ -37,10 +37,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_anthropic"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_anthropic"]
   },
   {
    "cell_type": "markdown",
@@ -56,18 +53,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"ANTHROPIC_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"ANTHROPIC_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -83,10 +69,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -112,22 +95,7 @@
    "id": "6768a3ab",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# Add messages essentially does this with more\n",
-    "# robust handling\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# Add messages essentially does this with more\n# robust handling\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -147,19 +115,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -176,11 +132,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -204,11 +156,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-haiku-20240307\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(model=\"claude-3-haiku-20240307\")"]
   },
   {
    "cell_type": "markdown",
@@ -226,9 +174,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -267,29 +213,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state: State) -> Literal[\"end\", \"continue\"]:\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no tool call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "async def call_model(state: State):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = await model.ainvoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["from typing import Literal\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state: State) -> Literal[\"end\", \"continue\"]:\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no tool call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\nasync def call_model(state: State):\n    messages = state[\"messages\"]\n    response = await model.ainvoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -307,50 +231,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(State)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(State)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -369,11 +250,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph().draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph().draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -406,12 +283,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "await app.ainvoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nawait app.ainvoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -480,16 +352,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "async for output in app.astream(inputs, stream_mode=\"updates\"):\n",
-    "    # stream_mode=\"updates\" yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value[\"messages\"][-1].pretty_print())\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nasync for output in app.astream(inputs, stream_mode=\"updates\"):\n    # stream_mode=\"updates\" yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value[\"messages\"][-1].pretty_print())\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -546,20 +409,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"].content, end=\"|\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"].content, end=\"|\")"]
   },
   {
    "cell_type": "code",
@@ -567,7 +417,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/anthropic.ipynb

@@ -27,10 +27,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langchain langchain_anthropic tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langchain langchain_anthropic tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -46,13 +43,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -68,10 +59,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -95,11 +83,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -123,11 +107,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(temperature=0, model_name=\"claude-3-opus-20240229\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(temperature=0, model_name=\"claude-3-opus-20240229\")"]
   },
   {
    "cell_type": "markdown",
@@ -154,9 +134,7 @@
      ]
     }
    ],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "code",
@@ -164,16 +142,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -208,33 +177,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there are no tool calls, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there are no tool calls, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -252,50 +195,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -328,12 +228,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -383,16 +278,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/base.ipynb

@@ -26,10 +26,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -45,13 +42,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -67,10 +58,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -90,11 +78,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -112,11 +96,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -140,13 +120,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -164,9 +138,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -192,16 +164,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -236,53 +199,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a FunctionMessage\n",
-    "    function_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [function_message]}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a FunctionMessage\n    function_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [function_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -300,50 +217,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -362,15 +236,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -403,12 +269,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -458,16 +319,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -604,21 +456,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n",
-    "\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"])"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"])"]
   },
   {
    "cell_type": "code",
@@ -626,7 +464,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/dynamically-returning-directly.ipynb

@@ -38,10 +38,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -57,13 +54,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -79,10 +70,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -106,19 +94,7 @@
    "id": "4a1b9990-3b11-4a51-bd51-76117afd38b9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class SearchTool(BaseModel):\n",
-    "    \"\"\"Look up things online, optionally returning directly\"\"\"\n",
-    "\n",
-    "    query: str = Field(description=\"query to look up online\")\n",
-    "    return_direct: bool = Field(\n",
-    "        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n",
-    "        default=False,\n",
-    "    )"
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass SearchTool(BaseModel):\n    \"\"\"Look up things online, optionally returning directly\"\"\"\n\n    query: str = Field(description=\"query to look up online\")\n    return_direct: bool = Field(\n        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n        default=False,\n    )"]
   },
   {
    "cell_type": "code",
@@ -126,12 +102,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "search_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\n",
-    "tools = [search_tool]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\nsearch_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\ntools = [search_tool]"]
   },
   {
    "cell_type": "markdown",
@@ -149,11 +120,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -177,13 +144,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -201,9 +162,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -229,16 +188,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -273,11 +223,7 @@
    "id": "03308b6b-de72-4cdc-b6c6-47e654df340e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation"]
   },
   {
    "cell_type": "markdown",
@@ -295,22 +241,7 @@
    "id": "55e088b1-f3c8-4798-9ca8-5b0be961b49a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we check if it's suppose to return direct\n",
-    "    else:\n",
-    "        arguments = last_message.tool_calls[0][\"args\"]\n",
-    "        if arguments.get(\"return_direct\", False):\n",
-    "            return \"final\"\n",
-    "        else:\n",
-    "            return \"continue\""
-   ]
+   "source": ["# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we check if it's suppose to return direct\n    else:\n        arguments = last_message.tool_calls[0][\"args\"]\n        if arguments.get(\"return_direct\", False):\n            return \"final\"\n        else:\n            return \"continue\""]
   },
   {
    "cell_type": "code",
@@ -318,14 +249,7 @@
    "id": "2b45da72-1afa-4cd7-9b7f-49a7c99cdb8a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -343,33 +267,7 @@
    "id": "dd876f5d-88d6-4f93-b1d0-f2f0b6f4d991",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    tool_name = tool_call[\"name\"]\n",
-    "    arguments = tool_call[\"args\"]\n",
-    "    if tool_name == \"tavily_search_results_json\":\n",
-    "        if \"return_direct\" in arguments:\n",
-    "            del arguments[\"return_direct\"]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_name,\n",
-    "        tool_input=arguments,\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a ToolMessage\n",
-    "    tool_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [tool_message]}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    tool_name = tool_call[\"name\"]\n    arguments = tool_call[\"args\"]\n    if tool_name == \"tavily_search_results_json\":\n        if \"return_direct\" in arguments:\n            del arguments[\"return_direct\"]\n    action = ToolInvocation(\n        tool=tool_name,\n        tool_input=arguments,\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a ToolMessage\n    tool_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [tool_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -391,54 +289,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "workflow.add_node(\"final\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Final call\n",
-    "        \"final\": \"final\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "workflow.add_edge(\"final\", END)\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\nworkflow.add_node(\"final\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Final call\n        \"final\": \"final\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\nworkflow.add_edge(\"final\", END)\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -457,15 +308,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -509,18 +352,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -547,24 +379,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\n",
-    "    \"messages\": [\n",
-    "        HumanMessage(\n",
-    "            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n",
-    "        )\n",
-    "    ]\n",
-    "}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\n    \"messages\": [\n        HumanMessage(\n            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n        )\n    ]\n}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -572,7 +387,7 @@
    "id": "49ccc134-4abe-4982-8ecd-d70fc56a4d2d",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/force-calling-a-tool-first.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,18 +46,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"OPENAI_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -76,10 +62,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -99,19 +82,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -129,11 +100,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -157,11 +124,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -179,9 +142,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -207,16 +168,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -251,69 +203,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "# We recommend you use ToolNode\n",
-    "# for this, but we are showing the\n",
-    "# manual way here for clarity\n",
-    "def call_tool(state: AgentState):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state: AgentState):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state: AgentState):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\n# We recommend you use ToolNode\n# for this, but we are showing the\n# manual way here for clarity\ndef call_tool(state: AgentState):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -331,30 +221,7 @@
    "id": "1bfd2b22-292a-4f4d-91a0-46bb704f5e38",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# This is the new first - the first call of the model we want to explicitly hard-code some action\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "def first_model(state: AgentState):\n",
-    "    human_input = state[\"messages\"][-1].content\n",
-    "    return {\n",
-    "        \"messages\": [\n",
-    "            AIMessage(\n",
-    "                content=\"\",\n",
-    "                tool_calls=[\n",
-    "                    {\n",
-    "                        \"name\": \"tavily_search_results_json\",\n",
-    "                        \"args\": {\n",
-    "                            \"query\": human_input,\n",
-    "                        },\n",
-    "                        \"id\": \"tool_abcd123\",\n",
-    "                    }\n",
-    "                ],\n",
-    "            )\n",
-    "        ]\n",
-    "    }"
-   ]
+   "source": ["# This is the new first - the first call of the model we want to explicitly hard-code some action\nfrom langchain_core.messages import AIMessage\n\n\ndef first_model(state: AgentState):\n    human_input = state[\"messages\"][-1].content\n    return {\n        \"messages\": [\n            AIMessage(\n                content=\"\",\n                tool_calls=[\n                    {\n                        \"name\": \"tavily_search_results_json\",\n                        \"args\": {\n                            \"query\": human_input,\n                        },\n                        \"id\": \"tool_abcd123\",\n                    }\n                ],\n            )\n        ]\n    }"]
   },
   {
    "cell_type": "markdown",
@@ -376,56 +243,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the new entrypoint\n",
-    "workflow.add_node(\"first_agent\", first_model)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"first_agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# After we call the first agent, we know we want to go to action\n",
-    "workflow.add_edge(\"first_agent\", \"action\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the new entrypoint\nworkflow.add_node(\"first_agent\", first_model)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"first_agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# After we call the first agent, we know we want to go to action\nworkflow.add_edge(\"first_agent\", \"action\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -444,11 +262,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph(xray=True).draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph(xray=True).draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -670,17 +484,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs, stream_mode=\"values\"):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    messages = output[\"messages\"]\n",
-    "    for message in messages:\n",
-    "        message.pretty_print()\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs, stream_mode=\"values\"):\n    # stream() yields dictionaries with output keyed by node name\n    messages = output[\"messages\"]\n    for message in messages:\n        message.pretty_print()\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -688,7 +492,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/human-in-the-loop.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -58,13 +55,7 @@
      ]
     }
    ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -88,10 +79,7 @@
      ]
     }
    ],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -111,11 +99,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -133,11 +117,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -161,13 +141,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -185,9 +159,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -213,16 +185,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -257,31 +220,7 @@
    "id": "b547109f-f9e8-4e77-a7e7-ed2bae7a72ab",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "code",
@@ -289,41 +228,7 @@
    "id": "73fd6432-42e8-472a-89ca-bb5ddbbcc35a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -345,51 +250,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.checkpoint.memory import MemorySaver\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile(checkpointer=MemorySaver(), interrupt_before=[\"action\"])"
-   ]
+   "source": ["from langgraph.checkpoint.memory import MemorySaver\nfrom langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile(checkpointer=MemorySaver(), interrupt_before=[\"action\"])"]
   },
   {
    "cell_type": "code",
@@ -408,15 +269,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -460,30 +313,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "config = {\"configurable\": {\"thread_id\": \"thread-1\"}}\n",
-    "while True:\n",
-    "    for output in app.stream(inputs, config):\n",
-    "        # stream() yields dictionaries with output keyed by node name\n",
-    "        for key, value in output.items():\n",
-    "            print(f\"Output from node '{key}':\")\n",
-    "            print(\"---\")\n",
-    "            print(value)\n",
-    "        print(\"\\n---\\n\")\n",
-    "    snapshot = app.get_state(config)\n",
-    "    # If \"next\" is present, it means we've interrupted mid-execution\n",
-    "    if not snapshot.next:\n",
-    "        break\n",
-    "    inputs = None\n",
-    "    response = input(\n",
-    "        \"Do you approve the next step? Type y if you do, anything else to stop: \"\n",
-    "    )\n",
-    "    if response != \"y\":\n",
-    "        break"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nconfig = {\"configurable\": {\"thread_id\": \"thread-1\"}}\nwhile True:\n    for output in app.stream(inputs, config):\n        # stream() yields dictionaries with output keyed by node name\n        for key, value in output.items():\n            print(f\"Output from node '{key}':\")\n            print(\"---\")\n            print(value)\n        print(\"\\n---\\n\")\n    snapshot = app.get_state(config)\n    # If \"next\" is present, it means we've interrupted mid-execution\n    if not snapshot.next:\n        break\n    inputs = None\n    response = input(\n        \"Do you approve the next step? Type y if you do, anything else to stop: \"\n    )\n    if response != \"y\":\n        break"]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/managing-agent-steps.ipynb

@@ -30,10 +30,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -49,13 +46,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -71,10 +62,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -94,11 +82,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -116,11 +100,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -144,13 +124,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -168,9 +142,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -196,16 +168,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -240,23 +203,7 @@
    "id": "e718a9c5-6596-457f-ac25-a25d8cb8c259",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -274,14 +221,7 @@
    "id": "714e4135-7cb5-4f17-b2ae-46f7e98bde61",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"][-5:]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"][-5:]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "code",
@@ -289,41 +229,7 @@
    "id": "b3ca9564-63cc-4309-b158-5e8d3e907164",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -341,50 +247,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -403,15 +266,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -455,18 +310,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -474,7 +318,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/prebuilt-tool-node.ipynb

@@ -27,10 +27,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -46,13 +43,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -68,10 +59,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -95,11 +83,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -123,11 +107,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -145,9 +125,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -173,16 +151,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -217,33 +186,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there are no tool calls, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there are no tool calls, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -261,50 +204,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -337,12 +237,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "app.invoke(inputs)"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\napp.invoke(inputs)"]
   },
   {
    "cell_type": "markdown",
@@ -392,16 +287,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "markdown",
@@ -496,21 +382,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n",
-    "\n",
-    "async for output in app.astream_log(inputs, include_types=[\"llm\"]):\n",
-    "    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n",
-    "    for op in output.ops:\n",
-    "        if op[\"path\"] == \"/streamed_output/-\":\n",
-    "            # this is the output from .stream()\n",
-    "            ...\n",
-    "        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n",
-    "            \"/streamed_output/-\"\n",
-    "        ):\n",
-    "            # because we chose to only include LLMs, these are LLM tokens\n",
-    "            print(op[\"value\"])"
-   ]
+   "source": ["inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf?\")]}\n\nasync for output in app.astream_log(inputs, include_types=[\"llm\"]):\n    # astream_log() yields the requested logs (here LLMs) in JSONPatch format\n    for op in output.ops:\n        if op[\"path\"] == \"/streamed_output/-\":\n            # this is the output from .stream()\n            ...\n        elif op[\"path\"].startswith(\"/logs/\") and op[\"path\"].endswith(\n            \"/streamed_output/-\"\n        ):\n            # because we chose to only include LLMs, these are LLM tokens\n            print(op[\"value\"])"]
   },
   {
    "cell_type": "code",
@@ -518,7 +390,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chat_agent_executor_with_function_calling/respond-in-format.ipynb

@@ -38,22 +38,7 @@
    "id": "de1db3c1",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# Add messages essentially does this with more\n",
-    "# robust handling\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# Add messages essentially does this with more\n# robust handling\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -73,19 +58,7 @@
    "id": "23a2ca43",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\"The answer to your question lies within.\"]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\"The answer to your question lies within.\"]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -102,11 +75,7 @@
    "id": "979512e4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -130,11 +99,7 @@
    "id": "1c8132c5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "\n",
-    "model = ChatAnthropic(model=\"claude-3-haiku-20240307\")"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(model=\"claude-3-haiku-20240307\")"]
   },
   {
    "cell_type": "markdown",
@@ -152,9 +117,7 @@
    "id": "055d84bf",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -172,10 +135,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -191,13 +151,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -213,10 +167,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -236,11 +187,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -258,11 +205,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -286,13 +229,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -315,19 +252,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class Response(BaseModel):\n",
-    "    \"\"\"Final response to the user\"\"\"\n",
-    "\n",
-    "    temperature: float = Field(description=\"the temperature\")\n",
-    "    other_notes: str = Field(description=\"any other notes about the weather\")\n",
-    "\n",
-    "\n",
-    "model = model.bind_tools(tools + [Response])"
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass Response(BaseModel):\n    \"\"\"Final response to the user\"\"\"\n\n    temperature: float = Field(description=\"the temperature\")\n    other_notes: str = Field(description=\"any other notes about the weather\")\n\n\nmodel = model.bind_tools(tools + [Response])"]
   },
   {
    "cell_type": "markdown",
@@ -353,16 +278,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -401,70 +317,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state) -> Literal[\"continue\", \"end\"]:\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we need to check what type of function call it is\n",
-    "    if last_message.tool_calls[0][\"name\"] == \"Response\":\n",
-    "        return \"end\"\n",
-    "    # Otherwise we continue\n",
-    "    return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["from typing import Literal\n\nfrom langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state) -> Literal[\"continue\", \"end\"]:\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we need to check what type of function call it is\n    if last_message.tool_calls[0][\"name\"] == \"Response\":\n        return \"end\"\n    # Otherwise we continue\n    return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -482,50 +335,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -544,15 +354,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -596,18 +398,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value[\"messages\"][-1])\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value[\"messages\"][-1])\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -615,7 +406,7 @@
    "id": "eed4360d-2cdf-497b-b03f-8bc51062f780",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb

@@ -26,10 +26,7 @@
    "id": "0d30b6f7-3bec-4d9f-af50-43dfdc81ae6c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# %%capture --no-stderr\n",
-    "# %pip install -U langgraph langchain langchain_openai"
-   ]
+   "source": ["# %%capture --no-stderr\n# %pip install -U langgraph langchain langchain_openai"]
   },
   {
    "cell_type": "code",
@@ -37,24 +34,7 @@
    "id": "30c2f3de-c730-4aec-85a6-af2c2f058803",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_if_undefined(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n",
-    "\n",
-    "\n",
-    "_set_if_undefined(\"OPENAI_API_KEY\")\n",
-    "_set_if_undefined(\"LANGCHAIN_API_KEY\")\n",
-    "\n",
-    "# Optional, add tracing in LangSmith.\n",
-    "# This will help you visualize and debug the control flow\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"Agent Simulation Evaluation\""
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_if_undefined(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n\n\n_set_if_undefined(\"OPENAI_API_KEY\")\n_set_if_undefined(\"LANGCHAIN_API_KEY\")\n\n# Optional, add tracing in LangSmith.\n# This will help you visualize and debug the control flow\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_PROJECT\"] = \"Agent Simulation Evaluation\""]
   },
   {
    "cell_type": "markdown",
@@ -75,24 +55,7 @@
    "id": "828479af-cf9c-4888-a365-599643a96b55",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "import openai\n",
-    "\n",
-    "\n",
-    "# This is flexible, but you can define your agent here, or call your agent API here.\n",
-    "def my_chat_bot(messages: List[dict]) -> dict:\n",
-    "    system_message = {\n",
-    "        \"role\": \"system\",\n",
-    "        \"content\": \"You are a customer support agent for an airline.\",\n",
-    "    }\n",
-    "    messages = [system_message] + messages\n",
-    "    completion = openai.chat.completions.create(\n",
-    "        messages=messages, model=\"gpt-3.5-turbo\"\n",
-    "    )\n",
-    "    return completion.choices[0].message.model_dump()"
-   ]
+   "source": ["from typing import List\n\nimport openai\n\n\n# This is flexible, but you can define your agent here, or call your agent API here.\ndef my_chat_bot(messages: List[dict]) -> dict:\n    system_message = {\n        \"role\": \"system\",\n        \"content\": \"You are a customer support agent for an airline.\",\n    }\n    messages = [system_message] + messages\n    completion = openai.chat.completions.create(\n        messages=messages, model=\"gpt-3.5-turbo\"\n    )\n    return completion.choices[0].message.model_dump()"]
   },
   {
    "cell_type": "code",
@@ -114,9 +77,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "my_chat_bot([{\"role\": \"user\", \"content\": \"hi!\"}])"
-   ]
+   "source": ["my_chat_bot([{\"role\": \"user\", \"content\": \"hi!\"}])"]
   },
   {
    "cell_type": "markdown",
@@ -135,33 +96,7 @@
    "id": "32c147df-7f90-4b0d-9a6b-671677020353",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "system_prompt_template = \"\"\"You are a customer of an airline company. \\\n",
-    "You are interacting with a user who is a customer support person. \\\n",
-    "\n",
-    "{instructions}\n",
-    "\n",
-    "When you are finished with the conversation, respond with a single word 'FINISHED'\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt_template),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
-    "    ]\n",
-    ")\n",
-    "instructions = \"\"\"Your name is Harrison. You are trying to get a refund for the trip you took to Alaska. \\\n",
-    "You want them to give you ALL the money back. \\\n",
-    "This trip happened 5 years ago.\"\"\"\n",
-    "\n",
-    "prompt = prompt.partial(name=\"Harrison\", instructions=instructions)\n",
-    "\n",
-    "model = ChatOpenAI()\n",
-    "\n",
-    "simulated_user = prompt | model"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\nfrom langchain_openai import ChatOpenAI\n\nsystem_prompt_template = \"\"\"You are a customer of an airline company. \\\nYou are interacting with a user who is a customer support person. \\\n\n{instructions}\n\nWhen you are finished with the conversation, respond with a single word 'FINISHED'\"\"\"\n\nprompt = ChatPromptTemplate.from_messages(\n    [\n        (\"system\", system_prompt_template),\n        MessagesPlaceholder(variable_name=\"messages\"),\n    ]\n)\ninstructions = \"\"\"Your name is Harrison. You are trying to get a refund for the trip you took to Alaska. \\\nYou want them to give you ALL the money back. \\\nThis trip happened 5 years ago.\"\"\"\n\nprompt = prompt.partial(name=\"Harrison\", instructions=instructions)\n\nmodel = ChatOpenAI()\n\nsimulated_user = prompt | model"]
   },
   {
    "cell_type": "code",
@@ -180,12 +115,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "messages = [HumanMessage(content=\"Hi! How can I help you?\")]\n",
-    "simulated_user.invoke({\"messages\": messages})"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\nmessages = [HumanMessage(content=\"Hi! How can I help you?\")]\nsimulated_user.invoke({\"messages\": messages})"]
   },
   {
    "cell_type": "markdown",
@@ -223,19 +153,7 @@
    "id": "69e2a3a3-40f3-4223-9136-113738440be9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.adapters.openai import convert_message_to_dict\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "def chat_bot_node(messages):\n",
-    "    # Convert from LangChain format to the OpenAI format, which our chatbot function expects.\n",
-    "    messages = [convert_message_to_dict(m) for m in messages]\n",
-    "    # Call the chat bot\n",
-    "    chat_bot_response = my_chat_bot(messages)\n",
-    "    # Respond with an AI Message\n",
-    "    return AIMessage(content=chat_bot_response[\"content\"])"
-   ]
+   "source": ["from langchain_community.adapters.openai import convert_message_to_dict\nfrom langchain_core.messages import AIMessage\n\n\ndef chat_bot_node(messages):\n    # Convert from LangChain format to the OpenAI format, which our chatbot function expects.\n    messages = [convert_message_to_dict(m) for m in messages]\n    # Call the chat bot\n    chat_bot_response = my_chat_bot(messages)\n    # Respond with an AI Message\n    return AIMessage(content=chat_bot_response[\"content\"])"]
   },
   {
    "cell_type": "markdown",
@@ -251,25 +169,7 @@
    "id": "7cad7527-ffa5-4c30-8585-b54a7a18bd98",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def _swap_roles(messages):\n",
-    "    new_messages = []\n",
-    "    for m in messages:\n",
-    "        if isinstance(m, AIMessage):\n",
-    "            new_messages.append(HumanMessage(content=m.content))\n",
-    "        else:\n",
-    "            new_messages.append(AIMessage(content=m.content))\n",
-    "    return new_messages\n",
-    "\n",
-    "\n",
-    "def simulated_user_node(messages):\n",
-    "    # Swap roles of messages\n",
-    "    new_messages = _swap_roles(messages)\n",
-    "    # Call the simulated user\n",
-    "    response = simulated_user.invoke({\"messages\": new_messages})\n",
-    "    # This response is an AI message - we need to flip this to be a human message\n",
-    "    return HumanMessage(content=response.content)"
-   ]
+   "source": ["def _swap_roles(messages):\n    new_messages = []\n    for m in messages:\n        if isinstance(m, AIMessage):\n            new_messages.append(HumanMessage(content=m.content))\n        else:\n            new_messages.append(AIMessage(content=m.content))\n    return new_messages\n\n\ndef simulated_user_node(messages):\n    # Swap roles of messages\n    new_messages = _swap_roles(messages)\n    # Call the simulated user\n    response = simulated_user.invoke({\"messages\": new_messages})\n    # This response is an AI message - we need to flip this to be a human message\n    return HumanMessage(content=response.content)"]
   },
   {
    "cell_type": "markdown",
@@ -292,15 +192,7 @@
    "id": "28004fbf-a2f3-46b7-bde7-46c7adaf97fb",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def should_continue(messages):\n",
-    "    if len(messages) > 6:\n",
-    "        return \"end\"\n",
-    "    elif messages[-1].content == \"FINISHED\":\n",
-    "        return \"end\"\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["def should_continue(messages):\n    if len(messages) > 6:\n        return \"end\"\n    elif messages[-1].content == \"FINISHED\":\n        return \"end\"\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -318,29 +210,7 @@
    "id": "0b597e4b-4cbb-4bbc-82e5-f7e31275964c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, MessageGraph\n",
-    "\n",
-    "graph_builder = MessageGraph()\n",
-    "graph_builder.add_node(\"user\", simulated_user_node)\n",
-    "graph_builder.add_node(\"chat_bot\", chat_bot_node)\n",
-    "# Every response from  your chat bot will automatically go to the\n",
-    "# simulated user\n",
-    "graph_builder.add_edge(\"chat_bot\", \"user\")\n",
-    "graph_builder.add_conditional_edges(\n",
-    "    \"user\",\n",
-    "    should_continue,\n",
-    "    # If the finish criteria are met, we will stop the simulation,\n",
-    "    # otherwise, the virtual user's message will be sent to your chat bot\n",
-    "    {\n",
-    "        \"end\": END,\n",
-    "        \"continue\": \"chat_bot\",\n",
-    "    },\n",
-    ")\n",
-    "# The input will first go to your chat bot\n",
-    "graph_builder.set_entry_point(\"chat_bot\")\n",
-    "simulation = graph_builder.compile()"
-   ]
+   "source": ["from langgraph.graph import END, MessageGraph, START\n\ngraph_builder = MessageGraph()\ngraph_builder.add_node(\"user\", simulated_user_node)\ngraph_builder.add_node(\"chat_bot\", chat_bot_node)\n# Every response from  your chat bot will automatically go to the\n# simulated user\ngraph_builder.add_edge(\"chat_bot\", \"user\")\ngraph_builder.add_conditional_edges(\n    \"user\",\n    should_continue,\n    # If the finish criteria are met, we will stop the simulation,\n    # otherwise, the virtual user's message will be sent to your chat bot\n    {\n        \"end\": END,\n        \"continue\": \"chat_bot\",\n    },\n)\n# The input will first go to your chat bot\ngraph_builder.add_edge(START, \"chat_bot\")\nsimulation = graph_builder.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -381,13 +251,7 @@
      ]
     }
    ],
-   "source": [
-    "for chunk in simulation.stream([]):\n",
-    "    # Print out all events aside from the final end chunk\n",
-    "    if END not in chunk:\n",
-    "        print(chunk)\n",
-    "        print(\"----\")"
-   ]
+   "source": ["for chunk in simulation.stream([]):\n    # Print out all events aside from the final end chunk\n    if END not in chunk:\n        print(chunk)\n        print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -395,7 +259,7 @@
    "id": "dde4f2b5-cfe8-4ff0-99ea-fe2c5fed70c0",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/chatbot-simulation-evaluation/simulation_utils.py

@@ -9,7 +9,7 @@ from langchain_core.runnables import chain as as_runnable
 from langchain_openai import ChatOpenAI
 from typing_extensions import TypedDict
 
-from langgraph.graph import END, StateGraph
+from langgraph.graph import END, StateGraph, START
 
 
 def langchain_to_openai_messages(messages: List[BaseMessage]):
@@ -116,7 +116,7 @@ def create_chat_simulator(
         should_continue or functools.partial(_should_continue, max_turns=max_turns),
     )
     # If your dataset has a 'leading question/input', then we route first to the assistant, otherwise, we let the user take the lead.
-    graph_builder.set_entry_point("assistant" if input_key is not None else "user")
+    graph_builder.add_edge(START, "assistant" if input_key is not None else "user")
 
     return (
         RunnableLambda(_prepare_example).bind(input_key=input_key)

examples/chatbots/customer-support.ipynb

@@ -2,10 +2,739 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "4c37bb65-6e2c-42e4-bfa7-9df10e2652a0",
+   "id": "d9d1a28b-c2a1-4246-b1c2-c58d6938f798",
    "metadata": {},
    "source": [
-    "This example has moved! Check out the [Customer Support Tutorial](../customer-support/customer-support.ipynb) for more information."
+    "# Customer Support\n",
+    "\n",
+    "Here, we show an example of building a customer support chatbot.\n",
+    "\n",
+    "This customer support chatbot interacts with SQL database to answer questions.\n",
+    "We will use a mock SQL database to get started: the [Chinook](https://www.sqlitetutorial.net/sqlite-sample-database/) database.\n",
+    "This database is about sales from a music store: what songs and album exists, customer orders, things like that.\n",
+    "\n",
+    "This chatbot has two different states: \n",
+    "1. Music: the user can inquire about different songs and albums present in the store\n",
+    "2. Account: the user can ask questions about their account\n",
+    "\n",
+    "Under the hood, this is handled by two separate agents. \n",
+    "Each has a specific prompt and tools related to their objective. \n",
+    "There is also a generic agent who is responsible for routing between these two agents as needed.\n",
+    "\n",
+    "Note: This is a very simple example! For a more complete tutorial on building a customer support bot, check out the [Customer Support Tutorial](../customer-support/customer-support.ipynb) for more information."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35abc013-2613-4a49-a806-939dcf13ccf3",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langgraph langchain-community langchain-openai scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9431e7f1-07fa-49d9-ac45-29613703dcc1",
+   "metadata": {},
+   "source": [
+    "## Load the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3d1ef253-6b0c-4481-868c-e1fe84f2c8ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "url = \"https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db\"\n",
+    "response = requests.get(url)\n",
+    "\n",
+    "with open(\"Chinook.db\", \"wb\") as file:\n",
+    "    file.write(response.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "61f7ef9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Album',\n",
+       " 'Artist',\n",
+       " 'Customer',\n",
+       " 'Employee',\n",
+       " 'Genre',\n",
+       " 'Invoice',\n",
+       " 'InvoiceLine',\n",
+       " 'MediaType',\n",
+       " 'Playlist',\n",
+       " 'PlaylistTrack',\n",
+       " 'Track']"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_community.utilities import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
+    "db.get_usable_table_names()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1cf668e4-8cb4-4de1-bc5e-c90284bf74bc",
+   "metadata": {},
+   "source": [
+    "## Load an LLM\n",
+    "\n",
+    "We will load a language model to use.\n",
+    "For this demo we will use OpenAI."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d9ea4e80-30e6-4d46-b480-35f0be2fb055",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0, streaming=True, model=\"gpt-4o\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73907422-7e05-431e-b06d-256c9ec1f6f6",
+   "metadata": {},
+   "source": [
+    "## Load Other Modules\n",
+    "\n",
+    "Load other modules we will use.\n",
+    "\n",
+    "All of the tools our agents will use will be custom tools. As such, we will use the `@tool` decorator to create custom tools.\n",
+    "\n",
+    "We will pass in messages to the agent, so we load `HumanMessage` and `SystemMessage`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ea958e9f-ab1f-49b5-bd85-16332055297c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "35271d4d-2a1c-41be-9359-a3a7c3fed3d9",
+   "metadata": {},
+   "source": [
+    "## Define the Customer Agent\n",
+    "\n",
+    "This agent is responsible for looking up customer information.\n",
+    "It will have a specific prompt as well a specific tool to look up information about that customer (after asking for their user id)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "975b039a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This tool is given to the agent to look up information about a customer\n",
+    "def get_customer_info(customer_id: int):\n",
+    "    \"\"\"Look up customer info given their ID. ALWAYS make sure you have the customer ID before invoking this.\"\"\"\n",
+    "    return db.run(f\"SELECT * FROM Customer WHERE CustomerID = {customer_id};\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1d5fa446",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "customer_prompt = \"\"\"Your job is to help a user update their profile.\n",
+    "\n",
+    "You only have certain tools you can use. These tools require specific input. If you don't know the required input, then ask the user for it.\n",
+    "\n",
+    "If you are unable to help the user, you can \"\"\"\n",
+    "\n",
+    "\n",
+    "def get_customer_messages(messages):\n",
+    "    return [SystemMessage(content=customer_prompt)] + messages\n",
+    "\n",
+    "\n",
+    "customer_chain = get_customer_messages | model.bind_tools([get_customer_info])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "904a9485-3857-458e-8b9d-33bc33842bc9",
+   "metadata": {},
+   "source": [
+    "## Define the Music Agent\n",
+    "\n",
+    "This agent is responsible for figuring out information about music. To do that, we will create a prompt and various tools for looking up information about music\n",
+    "\n",
+    "First, we will create indexes for looking up artists and track names.\n",
+    "This will allow us to look up artists and tracks without having to spell their names exactly right."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a8604a3b-b484-4b2b-a914-4236cb98c524",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.vectorstores import SKLearnVectorStore\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "artists = db._execute(\"select * from Artist\")\n",
+    "songs = db._execute(\"select * from Track\")\n",
+    "artist_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in artists], OpenAIEmbeddings(), metadatas=artists\n",
+    ").as_retriever()\n",
+    "song_retriever = SKLearnVectorStore.from_texts(\n",
+    "    [a[\"Name\"] for a in songs], OpenAIEmbeddings(), metadatas=songs\n",
+    ").as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac7eb264-c572-4925-ad55-a1d52a18b1c0",
+   "metadata": {},
+   "source": [
+    "First, let's create a tool for getting albums by artist."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0a2a2b74",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_albums_by_artist(artist):\n",
+    "    \"\"\"Get albums by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.get_relevant_documents(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Title, Name FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45e85066-f2fc-490e-992d-cd66c9cd6486",
+   "metadata": {},
+   "source": [
+    "Next, lets create a tool for getting tracks by an artist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "da533f50",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_tracks_by_artist(artist):\n",
+    "    \"\"\"Get songs by an artist (or similar artists).\"\"\"\n",
+    "    docs = artist_retriever.invoke(artist)\n",
+    "    artist_ids = \", \".join([str(d.metadata[\"ArtistId\"]) for d in docs])\n",
+    "    return db.run(\n",
+    "        f\"SELECT Track.Name as SongName, Artist.Name as ArtistName FROM Album LEFT JOIN Artist ON Album.ArtistId = Artist.ArtistId LEFT JOIN Track ON Track.AlbumId = Album.AlbumId WHERE Album.ArtistId in ({artist_ids});\",\n",
+    "        include_columns=True,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb0e50ab-b059-427c-924b-f8072d8db23c",
+   "metadata": {},
+   "source": [
+    "Finally, let's create a tool for looking up songs by their name."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b3c07010",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_for_songs(song_title):\n",
+    "    \"\"\"Check if a song exists by its name.\"\"\"\n",
+    "    return song_retriever.invoke(song_title)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "88388ff8-38b5-4e4e-a24d-de8c3670bd2b",
+   "metadata": {},
+   "source": [
+    "Create the chain to call the relevant tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "72a14d5c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "song_system_message = \"\"\"Your job is to help a customer find any songs they are looking for. \n",
+    "\n",
+    "You only have certain tools you can use. If a customer asks you to look something up that you don't know how, politely tell them what you can help with.\n",
+    "\n",
+    "When looking up artists and songs, sometimes the artist/song will not be found. In that case, the tools will return information \\\n",
+    "on similar songs and artists. This is intentional, it is not the tool messing up.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_song_messages(messages):\n",
+    "    return [SystemMessage(content=song_system_message)] + messages\n",
+    "\n",
+    "\n",
+    "song_recc_chain = get_song_messages | model.bind_tools(\n",
+    "    [get_albums_by_artist, get_tracks_by_artist, check_for_songs]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "cff15eb0-62c7-451d-a5f9-4576b24c879e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_aXa9rSRXvTCJabrMY6AqkSV8', 'function': {'arguments': '{\"artist\":\"Amy Winehouse\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'}, id='run-60633269-fd02-43e8-b434-28e3b8b69fb1-0', tool_calls=[{'name': 'get_tracks_by_artist', 'args': {'artist': 'Amy Winehouse'}, 'id': 'call_aXa9rSRXvTCJabrMY6AqkSV8'}])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find songs by amy whinehouse?\")]\n",
+    "song_recc_chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a42c293-0816-4f3c-b4a3-5b9f3a0665d1",
+   "metadata": {},
+   "source": [
+    "## Define the Generic Agent\n",
+    "\n",
+    "We now define a generic agent that is responsible for handling initial inquiries and routing to the right sub agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "73e74268",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import AIMessage, HumanMessage, SystemMessage\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Router(BaseModel):\n",
+    "    \"\"\"Call this if you are able to route the user to the appropriate representative.\"\"\"\n",
+    "\n",
+    "    choice: str = Field(description=\"should be one of: music, customer\")\n",
+    "\n",
+    "\n",
+    "system_message = \"\"\"Your job is to help as a customer service representative for a music store.\n",
+    "\n",
+    "You should interact politely with customers to try to figure out how you can help. You can help in a few ways:\n",
+    "\n",
+    "- Updating user information: if a customer wants to update the information in the user database. Call the router with `customer`\n",
+    "- Recommending music: if a customer wants to find some music or information about music. Call the router with `music`\n",
+    "\n",
+    "If the user is asking or wants to ask about updating or accessing their information, send them to that route.\n",
+    "If the user is asking or wants to ask about music, send them to that route.\n",
+    "Otherwise, respond.\"\"\"\n",
+    "\n",
+    "\n",
+    "def get_messages(messages):\n",
+    "    return [SystemMessage(content=system_message)] + messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "ddf27314",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = get_messages | model.bind_tools([Router])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3c896f34",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_0aaFPPCWDiAoPyXQX2PS8TcJ', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'}, id='run-73d51d75-b7c5-49fe-b558-105ede7c75d1-0', tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_0aaFPPCWDiAoPyXQX2PS8TcJ'}])"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! can you help me find a good song?\")]\n",
+    "chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "40d86f59",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_Okla9DfMHIPs5TslS6KPaoBA', 'function': {'arguments': '{\"choice\":\"customer\"}', 'name': 'Router'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'}, id='run-0d82d4f8-f4eb-4b16-add8-3e7fdffd6332-0', tool_calls=[{'name': 'Router', 'args': {'choice': 'customer'}, 'id': 'call_Okla9DfMHIPs5TslS6KPaoBA'}])"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "msgs = [HumanMessage(content=\"hi! what's the email you have for me?\")]\n",
+    "chain.invoke(msgs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "bd6ddd8b-7500-46a7-811d-3bcb937bda51",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import AIMessage\n",
+    "\n",
+    "\n",
+    "def add_name(message, name):\n",
+    "    _dict = message.dict()\n",
+    "    _dict[\"name\"] = name\n",
+    "    return AIMessage(**_dict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "27494de5-8345-4c23-bc0e-81e0dd5d47d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "from langgraph.graph import END\n",
+    "\n",
+    "\n",
+    "def _get_last_ai_message(messages):\n",
+    "    for m in messages[::-1]:\n",
+    "        if isinstance(m, AIMessage):\n",
+    "            return m\n",
+    "    return None\n",
+    "\n",
+    "\n",
+    "def _is_tool_call(msg):\n",
+    "    return hasattr(msg, \"additional_kwargs\") and \"tool_calls\" in msg.additional_kwargs\n",
+    "\n",
+    "\n",
+    "def _route(messages):\n",
+    "    last_message = messages[-1]\n",
+    "    if isinstance(last_message, AIMessage):\n",
+    "        if not last_message.tool_calls:\n",
+    "            return END\n",
+    "        else:\n",
+    "            if last_message.name == \"general\":\n",
+    "                if len(last_message.tool_calls) > 1:\n",
+    "                    raise ValueError(\"Too many tools\")\n",
+    "                return last_message.tool_calls[0][\"args\"][\"choice\"]\n",
+    "            else:\n",
+    "                return \"tools\"\n",
+    "    last_m = _get_last_ai_message(messages)\n",
+    "    if last_m is None:\n",
+    "        return \"general\"\n",
+    "    if last_m.name == \"music\":\n",
+    "        return \"music\"\n",
+    "    elif last_m.name == \"customer\":\n",
+    "        return \"customer\"\n",
+    "    else:\n",
+    "        return \"general\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "8aec704a-46fe-4fb3-bdee-11c3bbffc370",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import ToolNode\n",
+    "\n",
+    "tools = [get_albums_by_artist, get_tracks_by_artist, check_for_songs, get_customer_info]\n",
+    "tool_node = ToolNode(tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "4d5b75c6-73e0-4922-a765-a15be63f869e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _filter_out_routes(messages):\n",
+    "    ms = []\n",
+    "    for m in messages:\n",
+    "        if _is_tool_call(m):\n",
+    "            if m.name == \"general\":\n",
+    "                continue\n",
+    "        ms.append(m)\n",
+    "    return ms"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "fd4dbf98-dbb3-411a-bad6-2bb334072aaf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from functools import partial\n",
+    "\n",
+    "general_node = _filter_out_routes | chain | partial(add_name, name=\"general\")\n",
+    "music_node = _filter_out_routes | song_recc_chain | partial(add_name, name=\"music\")\n",
+    "customer_node = _filter_out_routes | customer_chain | partial(add_name, name=\"customer\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "dcade924",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "\n",
+    "from langgraph.graph import MessageGraph\n",
+    "\n",
+    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "graph = MessageGraph()\n",
+    "nodes = {\n",
+    "    \"general\": \"general\",\n",
+    "    \"music\": \"music\",\n",
+    "    END: END,\n",
+    "    \"tools\": \"tools\",\n",
+    "    \"customer\": \"customer\",\n",
+    "}\n",
+    "# Define a new graph\n",
+    "workflow = MessageGraph()\n",
+    "workflow.add_node(\"general\", general_node)\n",
+    "workflow.add_node(\"music\", music_node)\n",
+    "workflow.add_node(\"customer\", customer_node)\n",
+    "workflow.add_node(\"tools\", tool_node)\n",
+    "workflow.add_conditional_edges(\"general\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"tools\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"music\", _route, nodes)\n",
+    "workflow.add_conditional_edges(\"customer\", _route, nodes)\n",
+    "workflow.set_conditional_entry_point(_route, nodes)\n",
+    "graph = workflow.compile()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "ac65d6d2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  what music do you have?\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_iste6NuKvZou8O9QudOectOU', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='general' id='run-9eb940ff-6592-43ae-aa34-22c3d630ac65-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_iste6NuKvZou8O9QudOectOU'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"I can help you find songs and albums by specific artists, or check if a particular song exists. Just let me know the name of the artist or song you're interested in!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='music' id='run-91f560e7-ffa5-437f-afda-27490cbd1efe-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  how about shakira?\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_fH4oKyA3U9aQy3p31MYXv2VP', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='general' id='run-6f2eee09-9e3e-4011-a045-196cc5baa1ee-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_fH4oKyA3U9aQy3p31MYXv2VP'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_qivZqsI8zQAqSDP2jsvHyR7T', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_albums_by_artist'}, 'type': 'function'}, {'index': 1, 'id': 'call_GER0B3vlAjxcvYOYq1NGlV4r', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'} name='music' id='run-38e2eca8-771c-48a2-83be-023fd17fc6f6-0' tool_calls=[{'name': 'get_albums_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_qivZqsI8zQAqSDP2jsvHyR7T'}, {'name': 'get_tracks_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_GER0B3vlAjxcvYOYq1NGlV4r'}]\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/wfh/code/lc/langchain/libs/core/langchain_core/_api/deprecation.py:139: LangChainDeprecationWarning: The method `BaseRetriever.get_relevant_documents` was deprecated in langchain-core 0.1.46 and will be removed in 0.3.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'tools':\n",
+      "---\n",
+      "[ToolMessage(content=\"[{'Title': 'Supernatural', 'Name': 'Santana'}, {'Title': 'Santana - As Years Go By', 'Name': 'Santana'}, {'Title': 'Santana Live', 'Name': 'Santana'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 01', 'Name': 'Lulu Santos'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 02', 'Name': 'Lulu Santos'}]\", name='get_albums_by_artist', id='14ad12f3-afa1-4375-a89d-e878babf2d95', tool_call_id='call_qivZqsI8zQAqSDP2jsvHyR7T'), ToolMessage(content='[{\\'SongName\\': \\'(Da Le) Yaleo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Love Of My Life\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Put Your Lights On\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Africa Bamba\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Smooth\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Do You Like The Way\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Maria Maria\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Migra\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Corazon Espinado\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Wishing It Was\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Farol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Primavera\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Calling\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Jingo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Corazon Manda\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'La Puesta Del Sol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Persuasion\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'As The Years Go by\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Soul Sacrifice\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Fried Neckbones And Home Fries\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Santana Jam\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Evil Ways\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"We\\'ve Got To Get Together/Jingo\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Rock Me\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"Just Ain\\'t Good Enough\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Funky Piano\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Way You Do To Mer\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Assim Caminha A Humanidade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Pro Outro\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Casa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Condição\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Satisfação\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Brumário\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sábado À Noite\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'A Cura\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Atrás Do Trio Elétrico\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Bem\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Toda Forma De Amor\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sereia\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Se Você Pensa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Lá Vem O Sol (Here Comes The Sun)\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Honolulu\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Dancin´Days\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aviso Aos Navegantes\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Hyperconectividade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Descobridor Dos Sete Mares\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Certo Alguém\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fullgás\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aquilo\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Senta A Pua\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Ro-Que-Se-Da-Ne\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Igual\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fogo De Palha\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Assaltaram A Gramática\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Último Romântico (Ao Vivo)\\', \\'ArtistName\\': \\'Lulu Santos\\'}]', name='get_tracks_by_artist', id='4ddcebc3-8e4e-42d4-8ae4-3ce3a62b548c', tool_call_id='call_GER0B3vlAjxcvYOYq1NGlV4r')]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"It seems I couldn't find specific albums or songs by Shakira, but I did find some related artists and their works. Here are some albums and songs by Santana and Lulu Santos:\\n\\n### Albums:\\n- **Santana:**\\n  - Supernatural\\n  - Santana - As Years Go By\\n  - Santana Live\\n\\n- **Lulu Santos:**\\n  - Lulu Santos - RCA 100 Anos De Música - Álbum 01\\n  - Lulu Santos - RCA 100 Anos De Música - Álbum 02\\n\\n### Songs:\\n- **Santana:**\\n  - (Da Le) Yaleo\\n  - Love Of My Life\\n  - Put Your Lights On\\n  - Africa Bamba\\n  - Smooth\\n  - Maria Maria\\n  - Corazon Espinado\\n  - Jingo\\n  - Evil Ways\\n\\n- **Lulu Santos:**\\n  - Assim Caminha A Humanidade\\n  - Um Pro Outro\\n  - Casa\\n  - Condição\\n  - Satisfação\\n  - A Cura\\n  - Atrás Do Trio Elétrico\\n  - Toda Forma De Amor\\n  - Sereia\\n  - Se Você Pensa\\n\\nIf you have any other specific artists or songs in mind, feel free to let me know!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='music' id='run-3d90d7cc-e7f7-48dc-bffd-00765c3f5d13-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  hm cool\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Output from node 'general':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_Nc5d0TWNbpnVJFeYJdQFuFGd', 'function': {'arguments': '{\"choice\":\"music\"}', 'name': 'Router'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4008e3b719'} name='general' id='run-19a3588e-f04c-48db-a54f-95d6b930ee3e-0' tool_calls=[{'name': 'Router', 'args': {'choice': 'music'}, 'id': 'call_Nc5d0TWNbpnVJFeYJdQFuFGd'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_weMHkgu3GYaMwXZM6hnCZd0z', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_albums_by_artist'}, 'type': 'function'}, {'index': 1, 'id': 'call_rXlVbPiEHbt10CNDUJ5GA2ZQ', 'function': {'arguments': '{\"artist\": \"Shakira\"}', 'name': 'get_tracks_by_artist'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_ce0793330f'} name='music' id='run-71bf8550-b5a8-423f-b463-83d9ff51391b-0' tool_calls=[{'name': 'get_albums_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_weMHkgu3GYaMwXZM6hnCZd0z'}, {'name': 'get_tracks_by_artist', 'args': {'artist': 'Shakira'}, 'id': 'call_rXlVbPiEHbt10CNDUJ5GA2ZQ'}]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'tools':\n",
+      "---\n",
+      "[ToolMessage(content=\"[{'Title': 'Supernatural', 'Name': 'Santana'}, {'Title': 'Santana - As Years Go By', 'Name': 'Santana'}, {'Title': 'Santana Live', 'Name': 'Santana'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 01', 'Name': 'Lulu Santos'}, {'Title': 'Lulu Santos - RCA 100 Anos De Música - Álbum 02', 'Name': 'Lulu Santos'}]\", name='get_albums_by_artist', id='52ada997-83f6-4500-b0a7-1104d4d38eb9', tool_call_id='call_weMHkgu3GYaMwXZM6hnCZd0z'), ToolMessage(content='[{\\'SongName\\': \\'(Da Le) Yaleo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Love Of My Life\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Put Your Lights On\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Africa Bamba\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Smooth\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Do You Like The Way\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Maria Maria\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Migra\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Corazon Espinado\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Wishing It Was\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Farol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Primavera\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Calling\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Jingo\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'El Corazon Manda\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'La Puesta Del Sol\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Persuasion\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'As The Years Go by\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Soul Sacrifice\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Fried Neckbones And Home Fries\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Santana Jam\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Evil Ways\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"We\\'ve Got To Get Together/Jingo\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Rock Me\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \"Just Ain\\'t Good Enough\", \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Funky Piano\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'The Way You Do To Mer\\', \\'ArtistName\\': \\'Santana\\'}, {\\'SongName\\': \\'Assim Caminha A Humanidade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Pro Outro\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Casa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Condição\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Satisfação\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Brumário\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sábado À Noite\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'A Cura\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Atrás Do Trio Elétrico\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Bem\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Toda Forma De Amor\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Sereia\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Se Você Pensa\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Lá Vem O Sol (Here Comes The Sun)\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Honolulu\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Dancin´Days\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aviso Aos Navegantes\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Hyperconectividade\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Descobridor Dos Sete Mares\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Um Certo Alguém\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fullgás\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Aquilo\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Senta A Pua\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Ro-Que-Se-Da-Ne\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Tudo Igual\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Fogo De Palha\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'Assaltaram A Gramática\\', \\'ArtistName\\': \\'Lulu Santos\\'}, {\\'SongName\\': \\'O Último Romântico (Ao Vivo)\\', \\'ArtistName\\': \\'Lulu Santos\\'}]', name='get_tracks_by_artist', id='7583e077-2fb4-44bf-bb00-b89d599ae84d', tool_call_id='call_rXlVbPiEHbt10CNDUJ5GA2ZQ')]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Output from node 'music':\n",
+      "---\n",
+      "content=\"It seems like I couldn't find specific albums or songs by Shakira. However, I did find some related artists and their works. Here are some albums and songs by Santana and Lulu Santos:\\n\\n### Albums:\\n1. **Santana**\\n   - Supernatural\\n   - Santana - As Years Go By\\n   - Santana Live\\n\\n2. **Lulu Santos**\\n   - RCA 100 Anos De Música - Álbum 01\\n   - RCA 100 Anos De Música - Álbum 02\\n\\n### Songs:\\n1. **Santana**\\n   - (Da Le) Yaleo\\n   - Love Of My Life\\n   - Put Your Lights On\\n   - Africa Bamba\\n   - Smooth\\n   - Maria Maria\\n   - Corazon Espinado\\n   - Jingo\\n   - Evil Ways\\n\\n2. **Lulu Santos**\\n   - Assim Caminha A Humanidade\\n   - Um Pro Outro\\n   - Casa\\n   - Condição\\n   - Satisfação\\n   - A Cura\\n   - Atrás Do Trio Elétrico\\n   - Toda Forma De Amor\\n   - Sereia\\n\\nIf you have any other artists or songs in mind, feel free to let me know!\" response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_d576307f90'} name='music' id='run-2418b45b-2762-49ca-b166-a0fee309ed9e-0'\n",
+      "\n",
+      "---\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "User (q/Q to quit):  q\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "AI: Byebye\n"
+     ]
+    }
+   ],
+   "source": [
+    "import uuid\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "from langgraph.graph.graph import START\n",
+    "\n",
+    "history = []\n",
+    "while True:\n",
+    "    user = input(\"User (q/Q to quit): \")\n",
+    "    if user in {\"q\", \"Q\"}:\n",
+    "        print(\"AI: Byebye\")\n",
+    "        break\n",
+    "    history.append(HumanMessage(content=user))\n",
+    "    async for output in graph.astream(history):\n",
+    "        for key, value in output.items():\n",
+    "            print(f\"Output from node '{key}':\")\n",
+    "            print(\"---\")\n",
+    "            print(value)\n",
+    "        print(\"\\n---\\n\")"
    ]
   }
  ],

examples/cloud_examples/cron_jobs.ipynb

@@ -20,9 +20,10 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()\n",
     "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
+    "assistants = [a for a in assistants if not a[\"config\"]]\n",
     "assistant = assistants[0]\n",
     "thread = await client.threads.create()"
    ]
@@ -43,7 +44,12 @@
    "outputs": [],
    "source": [
     "# This schedules a job to run at 15:27 (3:27PM) every day\n",
-    "cron_1 = await client.crons.create_for_thread(thread['thread_id'],assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
+    "cron_1 = await client.crons.create_for_thread(\n",
+    "    thread[\"thread_id\"],\n",
+    "    assistant[\"assistant_id\"],\n",
+    "    schedule=\"27 15 * * *\",\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"What time is it?\"}]},\n",
+    ")"
    ]
   },
   {
@@ -59,7 +65,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "await client.crons.delete(cron_1['cron_id'])"
+    "await client.crons.delete(cron_1[\"cron_id\"])"
    ]
   },
   {
@@ -78,7 +84,11 @@
    "outputs": [],
    "source": [
     "# This schedules a job to run at 15:27 (3:27PM) every day\n",
-    "cron_2 = await client.crons.create(assistant['assistant_id'],schedule=\"27 15 * * *\",input={'messages':[{\"role\":\"user\",\"content\":\"What time is it?\"}]})"
+    "cron_2 = await client.crons.create(\n",
+    "    assistant[\"assistant_id\"],\n",
+    "    schedule=\"27 15 * * *\",\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"What time is it?\"}]},\n",
+    ")"
    ]
   },
   {
@@ -94,7 +104,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "await client.crons.delete(cron_2['cron_id'])"
+    "await client.crons.delete(cron_2[\"cron_id\"])"
    ]
   }
  ],

examples/cloud_examples/enqueue_concurrent.ipynb

@@ -1,190 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Enqueue\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `enqueue` option for double texting, which adds the interruptions to a queue and executes them in the order they are received by the client. Below is a quick example of using the `enqueue` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# this run will be interrupted\n",
-    "first_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "second_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"enqueue\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the thread has data from both runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], second_run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01Dez1sJre4oA2Y7NsKJV6VT', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01Dez1sJre4oA2Y7NsKJV6VT)\n",
-      " Call ID: toolu_01Dez1sJre4oA2Y7NsKJV6VT\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/san-francisco/94103/weather-forecast/347629\", \"content\": \"Get the current and future weather conditions for San Francisco, CA, including temperature, precipitation, wind, air quality and more. See the hourly and 10-day outlook, radar maps, alerts and allergy information.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to AccuWeather, the current weather conditions in San Francisco are:\n",
-      "\n",
-      "Temperature: 57°F (14°C)\n",
-      "Conditions: Mostly Sunny\n",
-      "Wind: WSW 10 mph\n",
-      "Humidity: 72%\n",
-      "\n",
-      "The forecast for the next few days shows partly sunny skies with highs in the upper 50s to mid 60s F (14-18°C) and lows in the upper 40s to low 50s F (9-11°C). Typical mild, dry weather for San Francisco this time of year.\n",
-      "\n",
-      "Some key details from the AccuWeather forecast:\n",
-      "\n",
-      "Today: Mostly sunny, high of 62°F (17°C)\n",
-      "Tonight: Partly cloudy, low of 49°F (9°C) \n",
-      "Tomorrow: Partly sunny, high of 59°F (15°C)\n",
-      "Saturday: Mostly sunny, high of 64°F (18°C)\n",
-      "Sunday: Partly sunny, high of 61°F (16°C)\n",
-      "\n",
-      "So in summary, expect seasonable spring weather in San Francisco over the next several days, with a mix of sun and clouds and temperatures ranging from the upper 40s at night to the low 60s during the days. Typical dry conditions with no rain in the forecast.\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'text': 'Here are the current weather conditions and forecast for New York City:', 'type': 'text'}, {'id': 'toolu_01FFft5Sx9oS6AdVJuRWWcGp', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01FFft5Sx9oS6AdVJuRWWcGp)\n",
-      " Call ID: toolu_01FFft5Sx9oS6AdVJuRWWcGp\n",
-      "  Args:\n",
-      "    query: weather in new york city\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to the weather data from WeatherAPI:\n",
-      "\n",
-      "Current Conditions in New York City (as of 2:00 PM local time):\n",
-      "- Temperature: 85°F (29°C)\n",
-      "- Conditions: Sunny\n",
-      "- Wind: 2 mph (4 km/h) from the SSE\n",
-      "- Humidity: 63%\n",
-      "- Heat Index: 85°F (30°C)\n",
-      "\n",
-      "The forecast shows sunny and warm conditions persisting over the next few days:\n",
-      "\n",
-      "Today: Sunny, high of 85°F (29°C)\n",
-      "Tonight: Clear, low of 68°F (20°C)\n",
-      "Tomorrow: Sunny, high of 88°F (31°C) \n",
-      "Thursday: Mostly sunny, high of 90°F (32°C)\n",
-      "Friday: Partly cloudy, high of 87°F (31°C)\n",
-      "\n",
-      "So New York City is experiencing beautiful sunny weather with seasonably warm temperatures in the mid-to-upper 80s Fahrenheit (around 30°C). Humidity is moderate in the 60% range. Overall, ideal late spring/early summer conditions for being outdoors in the city over the next several days.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/human_in_the_loop_breakpoint.ipynb

@@ -1,116 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Add Breakpoints\n",
-    "\n",
-    "When creating LangGraph agents, it is often nice to add a human-in-the-loop component.\n",
-    "This can be helpful when giving them access to tools.\n",
-    "Often in these situations you may want to manually approve an action before taking.\n",
-    "\n",
-    "This can be in several ways, but the primary supported way is to add an \"interrupt\" before a node is executed.\n",
-    "This interrupts execution at that node.\n",
-    "You can then resume from that spot to continue.  "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "### Code for your graph\n",
-    "\n",
-    "In this how-to we use a simple ReAct style hosted graph (you can see the full code for defining it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/)). The important thing is that there are two nodes (one named `agent` that calls the LLM, and one named `action` that calls the tool), and a routing function from `agent` that determines whether to call `action` next or just end the graph run (the `action` node always calls the `agent` node after execution).\n",
-    "\n",
-    "### SDK Initialization"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "assistant_id = assistant['assistant_id']\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Adding a breakpoint\n",
-    "\n",
-    "We now want to add a breakpoint in our graph run, which we will do before a tool is called.\n",
-    "We can do this by adding `interrupt_before=[\"action\"]`, which tells us to interrupt before calling the action node.\n",
-    "We can do this either when compiling the graph or when kicking off a run.\n",
-    "Here we will do it when kicking of a run, if you would like to to do it at compile time you need to edit the python file where your graph is defined and add the `interrupt_before` parameter when you call `.compile`.\n",
-    "\n",
-    "First let's access our hosted Langgraph instance through the SDK:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And, now let's compile it with a breakpoint before the tool node:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '3b77ef83-687a-4840-8858-0371f91a92c3'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': [{'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-e5d17791-4d37-4ad2-815f-a0c4cba62585', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in san francisco'}, 'id': 'toolu_01HwZqM1ptX6E15A5LAmyZTB'}], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf\"}]}\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"action\"],\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_edit_state.ipynb

@@ -1,173 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Edit State of a Deployed Graph\n",
-    "\n",
-    "When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to edit the graph state before continuing (for example, to edit what tool is being called, or how it is being called).\n",
-    "\n",
-    "This can be in several ways, but the primary supported way is to add an \"interrupt\" before a node is executed. This interrupts execution at that node. You can then use update_state to update the state, and then resume from that spot to continue.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/edit-graph-state/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. \n",
-    "\n",
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Editing state\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Now let's invoke our graph, making sure to interrupt before the `action` node."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll search for the current weather in San Francisco for you using the search function. Here's how I'll do that:\", 'type': 'text'}, {'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-6dbb0167-f8f6-4e2a-ab68-229b2d1fbb64', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"search for weather in SF\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"action\"],\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Edit the state\n",
-    "\n",
-    "Now, let's assume we actually meant to search for the weather in Sidi Frej (another city with the initials SF). We can edit the state to properly reflect that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'configurable': {'thread_id': '88d58d3f-4151-47a9-a8e0-e42fdd3527b8',\n",
-       "  'thread_ts': '1ef3274b-a809-6913-8002-91536ce6554d'}}"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# First, lets get the current state\n",
-    "current_state = await client.threads.get_state(thread['thread_id'])\n",
-    "\n",
-    "# Let's now get the last message in the state\n",
-    "# This is the one with the tool calls that we want to update\n",
-    "last_message = current_state['values']['messages'][-1]\n",
-    "\n",
-    "# Let's now update the args for that tool call\n",
-    "last_message['tool_calls'][0]['args'] = {'query': 'current weather in Sidi Frej'}\n",
-    "\n",
-    "# Let's now call `update_state` to pass in this message in the `messages` key\n",
-    "# This will get treated as any other update to the state\n",
-    "# It will get passed to the reducer function for the `messages` key\n",
-    "# That reducer function will use the ID of the message to update it\n",
-    "# It's important that it has the right ID! Otherwise it would get appended\n",
-    "# as a new message\n",
-    "await client.threads.update_state(thread['thread_id'], {\"messages\": last_message})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Resume invocation\n",
-    "\n",
-    "Now we can resume our graph run but with the updated state:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in Sidi Frej. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '1161b8d1-bee4-4188-9be8-698aecb69f10', 'tool_call_id': 'toolu_01KEJMBFozSiZoS4mAcPZeqQ'}]}}\n",
-      "{'agent': {'messages': [{'content': [{'text': 'I apologize for the confusion in my search query. It seems the search function interpreted \"SF\" as \"Sidi Frej\" instead of \"San Francisco\" as we intended. Let me search again with the full city name to get the correct information:', 'type': 'text'}, {'id': 'toolu_0111rrwgfAcmurHZn55qjqTR', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b8c25779-cfb4-46fc-a421-48553551242f', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '6bc632ae-5ee6-4d01-9532-79c524a2d443', 'tool_call_id': 'toolu_0111rrwgfAcmurHZn55qjqTR'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Now, based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. \\n\\nIt's worth noting that the search result included an unusual comment about Gemini, which doesn't seem directly related to the weather. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of weather information, we can focus on the fact that it's sunny in San Francisco right now.\\n\\nIs there anything else you'd like to know about the weather in San Francisco or any other location?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-227a042b-dd97-476e-af32-76a3703af5d8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As you can see it now looks up the current weather in Sidi Frej (although our dummy search node still returns results for SF because we don't actually do a search in this example, we just return the same \"It's sunny in San Francisco ...\" result every time)."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_time_travel.ipynb

@@ -1,235 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Replay and Branch from Prior States\n",
-    "\n",
-    "With Langgraph Cloud you have the ability to return to any of your prior states and either re-run the graph to reproduce issues noticed during testing, or branch out in a different way from what was originally done in the prior states. In this guide we will show a quick example of how to rerun past states and how to branch off from previous states as well.\n",
-    "\n",
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/time-travel/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. \n",
-    "\n",
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 99,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Replay a state\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Before replaying a state - we need to create states to replay from! In order to do this, let's invoke our graph with a simple message:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 100,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll use the search function to look up the current weather in San Francisco for you. Let me do that now.\", 'type': 'text'}, {'id': 'toolu_011vroKUtWU7SBdrngpgpFMn', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ee639877-d97d-40f8-96dc-d0d1ae22d203', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '7bad0e72-5ebe-4b08-9b8a-b99b0fe22fb7', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. This is great news for outdoor activities and enjoying the city's beautiful sights.\\n\\nIt's worth noting that the search result included an unusual comment about Geminis, which isn't typically part of a weather report. This might be due to the search engine including some astrological information or a joke in its results. However, for the purpose of answering your question about the weather, we can focus on the fact that it's sunny in San Francisco.\\n\\nIf you need any more specific information about the weather in San Francisco, such as temperature, wind speed, or forecast for the coming days, please let me know, and I'd be happy to search for that information for you.\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-dbac539a-33c8-4f0c-9e20-91f318371e7c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"Please search the weather in SF\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now let's get our list of states, and invoke from the third state (right before the tool get called):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 101,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "states = await client.threads.get_history(thread['thread_id'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 102,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['action']"
-      ]
-     },
-     "execution_count": 102,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# We can confirm that this state is correct by checking the 'next' attribute and seeing that it is the tool call node\n",
-    "state_to_replay = states[2]\n",
-    "state_to_replay['next']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "To rerun from a state, we need to pass in the `checkpoint_id` into the config of the run like follows:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 103,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'eba650e5-400e-4938-8508-f878dcbcc532', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. This is great news if you're planning any outdoor activities or simply want to enjoy a pleasant day in the city.\\n\\nIt's worth noting that the search result included an unusual comment about Geminis, which doesn't seem directly related to the weather. This appears to be a playful or humorous addition to the weather report, possibly from the source where this information was obtained.\\n\\nIs there anything else you'd like to know about the weather in San Francisco or any other information you need?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-bc6dca3f-a1e2-4f59-a69b-fe0515a348bb', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "    config={\"configurable\":{\"thread_ts\":state_to_replay['checkpoint_id']}}\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As we can see, the graph restarted from the tool node with the same input as our original graph run.\n",
-    "\n",
-    "## Branch off from previous state\n",
-    "\n",
-    "Using LangGraph's checkpointing, you can do more than just replay past states. You can branch off previous locations to let the agent explore alternate trajectories or to let a user \"version control\" changes in a workflow.\n",
-    "\n",
-    "Let's show how to do this to edit the state at a particular point in time. Let's update the state to change the input to the tool"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 104,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Let's now get the last message in the state\n",
-    "# This is the one with the tool calls that we want to update\n",
-    "last_message = state_to_replay['values']['messages'][-1]\n",
-    "\n",
-    "# Let's now update the args for that tool call\n",
-    "last_message['tool_calls'][0]['args'] = {'query': 'current weather in SF'}\n",
-    "\n",
-    "new_state = await client.threads.update_state(thread['thread_id'],{\"messages\":[last_message]},checkpoint_id=state_to_replay['checkpoint_id'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Now we can rerun our graph with this new config, starting from the `new_state`, which is a branch of our `state_to_replay`:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 105,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in SF. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '2baf9941-4fda-4081-9f87-d76795d289f1', 'tool_call_id': 'toolu_011vroKUtWU7SBdrngpgpFMn'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco (SF):\\n\\nThe weather in San Francisco is currently sunny. This means it's a clear day with plenty of sunshine. \\n\\nIt's worth noting that the specific temperature wasn't provided in the search result, but sunny weather in San Francisco typically means comfortable temperatures. San Francisco is known for its mild climate, so even on sunny days, it's often not too hot.\\n\\nThe search result also included a playful reference to astrological signs, mentioning Gemini. However, this is likely just a joke or part of the search engine's presentation and not related to the actual weather conditions.\\n\\nIs there any specific information about the weather in San Francisco you'd like to know more about? I'd be happy to perform another search if you need details on temperature, wind conditions, or the forecast for the coming days.\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a83de52d-ed18-4402-9384-75c462485743', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "    config={\"configurable\":{\"thread_ts\":new_state['configurable']['thread_ts']}}\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "As we can see, the search query changed from San Francisco to SF, just as we had hoped!"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/human_in_the_loop_user_input.ipynb

@@ -1,175 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to Wait for User Input\n",
-    "\n",
-    "One of the main human-in-the-loop interaction patterns is waiting for human input. A key use case involves asking the user clarifying questions. One way to accomplish this is simply go to the `END` node and exit the graph. Then, any user response comes back in as fresh invocation of the graph. This is basically just creating a chatbot architecture.\n",
-    "\n",
-    "The issue with this is it is tough to resume back in a particular point in the graph. Often times the agent is halfway through some process, and just needs a bit of a user input. Although it is possible to design your graph in such a way where you have a `conditional_entry_point` to route user messages back to the right place, that is not super scalable (as it essentially involves having a routing function that can end up almost anywhere).\n",
-    "\n",
-    "A separate way to do this is to have a node explicitly for getting user input. This is easy to implement in a notebook setting - you just put an `input()` call in the node. But that isn't exactly production ready.\n",
-    "\n",
-    "Luckily, LangGraph makes it possible to do similar things in a production way. The basic idea is:\n",
-    "\n",
-    "- Set up a node that represents human input. This can have specific incoming/outgoing edges (as you desire). There shouldn't actually be any logic inside this node.\n",
-    "- Add a breakpoint before the node. This will stop the graph before this node executes (which is good, because there's no real logic in it anyways)\n",
-    "- Use `.update_state` to update the state of the graph. Pass in whatever human response you get. The key here is to use the `as_node` parameter to apply this update **as if you were that node**. This will have the effect of making it so that when you resume execution next it resumes as if that node just acted, and not from the beginning."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "We are not going to show the full code for the graph we are hosting, but you can see it [here](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/wait-user-input/#build-the-agent) if you want to. Once this graph is hosted, we are ready to invoke it and wait for user input. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### SDK initialization\n",
-    "\n",
-    "First, we need to setup our client so that we can communicate with our hosted graph:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "client = get_client()\n",
-    "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
-    "assistant = assistants[0]\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Waiting for user input\n",
-    "\n",
-    "### Initial invocation\n",
-    "\n",
-    "Now, let's invoke our graph by interrupting before `ask_human` node:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Certainly! I'll use the AskHuman function to ask the user about their location, and then I'll use the search function to look up the weather for that location. Let's start by asking the user where they are.\", 'type': 'text'}, {'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR', 'input': {'question': 'Where are you currently located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-a8422215-71d3-4093-afb4-9db141c94ddb', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you currently located?'}, 'id': 'toolu_01RFahzYPvnPWTb2USk2RdKR'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {'messages':[{\"role\":\"user\",\"content\":\"Use the search tool to ask the user where they are, then look up the weather there\"}]}\n",
-    "\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "    interrupt_before=[\"ask_human\"],\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Adding user input to state\n",
-    "\n",
-    "We now want to update this thread with a response from the user. We then can kick off another run.\n",
-    "\n",
-    "Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'configurable': {'thread_id': '10d0ee61-db47-48fc-a58c-109a1e68cd73',\n",
-       "  'thread_ts': '1ef32729-3cc3-6647-8002-14dcb621b46e'}}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "state = await client.threads.get_state(thread['thread_id'])\n",
-    "tool_call_id = state['values']['messages'][-1]['tool_calls'][0]['id']\n",
-    "\n",
-    "# We now create the tool call with the id and the response we want\n",
-    "tool_message = [{\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": \"san francisco\"}]\n",
-    "\n",
-    "await client.threads.update_state(thread['thread_id'], {\"messages\": tool_message}, as_node=\"ask_human\")\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Invoking after receiving human input\n",
-    "\n",
-    "We can now tell the agent to continue. We can just pass in None as the input to the graph, since no additional input is needed:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'agent': {'messages': [{'content': [{'text': \"Thank you for letting me know that you're in San Francisco. Now, I'll use the search function to look up the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-241baed7-db5e-44ce-ac3c-56431705c22b', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in San Francisco'}, 'id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n",
-      "{'action': {'messages': [{'content': '[\"I looked up: current weather in San Francisco. Result: It\\'s sunny in San Francisco, but you better look out if you\\'re a Gemini 😈.\"]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': '8b699b95-8546-4557-8e66-14ea71a15ed8', 'tool_call_id': 'toolu_01K57ofmgG2wyJ8tYJjbq5k7'}]}}\n",
-      "{'agent': {'messages': [{'content': \"Based on the search results, I can provide you with information about the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently sunny. It's a beautiful day in the city! \\n\\nHowever, I should note that the search result included an unusual comment about Gemini zodiac signs. This appears to be either a joke or potentially irrelevant information added by the search engine. For accurate and detailed weather information, you might want to check a reliable weather service or app for San Francisco.\\n\\nIs there anything else you'd like to know about the weather or San Francisco?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-b4d7309f-f849-46aa-b6ef-475bcabd2be9', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}\n"
-     ]
-    }
-   ],
-   "source": [
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
-    "    input=None,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    if chunk.data and \"run_id\" not in chunk.data:\n",
-    "        print(chunk.data)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/interrupt_concurrent.ipynb

@@ -1,181 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Interrupt\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `interrupt` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option does not delete the first run, but rather keeps it in the database but sets its status to `interrupted`. Below is a quick example of using the `interrupt` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import asyncio\n",
-    "\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# the first run will be interrupted\n",
-    "interrupted_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")\n",
-    "await asyncio.sleep(2)\n",
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"interrupt\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can see that the thread has partial data from the first run + data from the second run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih)\n",
-      " Call ID: toolu_01MjNtVJwEcpujRGrf3x6Pih\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18\", \"content\": \"High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ...\"}]\n",
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q)\n",
-      " Call ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q\n",
-      "  Args:\n",
-      "    query: weather in new york city\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/new-york/10021/june-weather/349727\", \"content\": \"Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "The search results provide weather forecasts and information for New York City. Based on the top result from AccuWeather, here are some key details about the weather in NYC:\n",
-      "\n",
-      "- This is a monthly weather forecast for New York City for the month of June.\n",
-      "- It includes daily high and low temperatures to help plan ahead.\n",
-      "- Historical averages for June in NYC are also provided as a reference point.\n",
-      "- More detailed daily or hourly forecasts with precipitation chances, humidity, wind, etc. can be found by visiting the AccuWeather page.\n",
-      "\n",
-      "So in summary, the search provides a convenient overview of the expected weather conditions in New York City over the next month to give you an idea of what to prepare for if traveling or making plans there. Let me know if you need any other details!\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the original, interrupted run was interrupted"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'interrupted'"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "(await client.runs.get(thread[\"thread_id\"], interrupted_run[\"run_id\"]))[\"status\"]"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/langgraph_to_langgraph_cloud.ipynb

@@ -119,6 +119,7 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()"
    ]
   },
@@ -354,7 +355,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in client.runs.stream(None, \"agent\", input=inputs, stream_mode=\"values\"):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    None, \"agent\", input=inputs, stream_mode=\"values\"\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -423,7 +426,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in nyc\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"1\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"1\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -458,7 +463,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's it known for?\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"1\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"1\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -480,7 +487,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's it known for?\")]}\n",
-    "invoke_output = await graph_with_memory.ainvoke(inputs, config={\"configurable\": {\"thread_id\": \"2\"}})\n",
+    "invoke_output = await graph_with_memory.ainvoke(\n",
+    "    inputs, config={\"configurable\": {\"thread_id\": \"2\"}}\n",
+    ")\n",
     "invoke_output[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -724,7 +733,12 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in graph_with_memory.astream(inputs, stream_mode=\"values\", interrupt_before=[\"tools\"], config={\"configurable\": {\"thread_id\": \"3\"}}):\n",
+    "async for chunk in graph_with_memory.astream(\n",
+    "    inputs,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "    config={\"configurable\": {\"thread_id\": \"3\"}},\n",
+    "):\n",
     "    chunk[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -749,7 +763,12 @@
     }
    ],
    "source": [
-    "async for chunk in graph_with_memory.astream(None, stream_mode=\"values\", interrupt_before=[\"tools\"], config={\"configurable\": {\"thread_id\": \"3\"}}):\n",
+    "async for chunk in graph_with_memory.astream(\n",
+    "    None,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "    config={\"configurable\": {\"thread_id\": \"3\"}},\n",
+    "):\n",
     "    chunk[\"messages\"][-1].pretty_print()"
    ]
   },
@@ -794,7 +813,13 @@
    "source": [
     "thread = await client.threads.create()\n",
     "\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], \"agent\", input=inputs, stream_mode=\"values\", interrupt_before=[\"tools\"]):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    thread[\"thread_id\"],\n",
+    "    \"agent\",\n",
+    "    input=inputs,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -821,7 +846,13 @@
     }
    ],
    "source": [
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], \"agent\", input=None, stream_mode=\"values\", interrupt_before=[\"tools\"]):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    thread[\"thread_id\"],\n",
+    "    \"agent\",\n",
+    "    input=None,\n",
+    "    stream_mode=\"values\",\n",
+    "    interrupt_before=[\"tools\"],\n",
+    "):\n",
     "    if chunk.event == \"values\":\n",
     "        messages = convert_to_messages(chunk.data[\"messages\"])\n",
     "        messages[-1].pretty_print()"
@@ -1000,7 +1031,9 @@
    ],
    "source": [
     "inputs = {\"messages\": [(\"human\", \"what's the weather in sf\")]}\n",
-    "async for chunk in client.runs.stream(None, \"agent\", input=inputs, stream_mode=\"events\"):\n",
+    "async for chunk in client.runs.stream(\n",
+    "    None, \"agent\", input=inputs, stream_mode=\"events\"\n",
+    "):\n",
     "    if chunk.event == \"events\" and chunk.data[\"event\"] == \"on_chat_model_stream\":\n",
     "        print(chunk.data[\"data\"][\"chunk\"])"
    ]

examples/cloud_examples/reject_concurrent.ipynb

@@ -1,164 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Reject\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `reject` option for double texting, which rejects the new run of the graph by throwing an error and continues with the original run until completion. Below is a quick example of using the `reject` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import httpx\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Failed to start concurrent run Client error '409 Conflict' for url 'http://localhost:8123/threads/f9e7088b-8028-4e5c-88d2-9cc9a2870e50/runs'\n",
-      "For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/409\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    await client.runs.create(\n",
-    "        thread[\"thread_id\"],\n",
-    "        assistant_id,\n",
-    "        input={\n",
-    "            \"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]\n",
-    "        },\n",
-    "        multitask_strategy=\"reject\",\n",
-    "    )\n",
-    "except httpx.HTTPStatusError as e:\n",
-    "    print(\"Failed to start concurrent run\", e)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can verify that the original thread finished executing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the original run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in sf?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01CyewEifV2Kmi7EFKHbMDr1', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01CyewEifV2Kmi7EFKHbMDr1)\n",
-      " Call ID: toolu_01CyewEifV2Kmi7EFKHbMDr1\n",
-      "  Args:\n",
-      "    query: weather in san francisco\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.accuweather.com/en/us/san-francisco/94103/june-weather/347629\", \"content\": \"Get the monthly weather forecast for San Francisco, CA, including daily high/low, historical averages, to help you plan ahead.\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "According to the search results from Tavily, the current weather in San Francisco is:\n",
-      "\n",
-      "The average high temperature in San Francisco in June is around 65°F (18°C), with average lows around 54°F (12°C). June tends to be one of the cooler and foggier months in San Francisco due to the marine layer of fog that often blankets the city during the summer months.\n",
-      "\n",
-      "Some key points about the typical June weather in San Francisco:\n",
-      "\n",
-      "- Mild temperatures with highs in the 60s F and lows in the 50s F\n",
-      "- Foggy mornings that often burn off to sunny afternoons\n",
-      "- Little to no rainfall, as June falls in the dry season\n",
-      "- Breezy conditions, with winds off the Pacific Ocean\n",
-      "- Layers are recommended for changing weather conditions\n",
-      "\n",
-      "So in summary, you can expect mild, foggy mornings giving way to sunny but cool afternoons in San Francisco this time of year. The marine layer keeps temperatures moderate compared to other parts of California in June.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/rollback_concurrent.ipynb

@@ -1,161 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Rollback\n",
-    "\n",
-    "This notebook assumes knowledge of what double-texting is, which you can learn about in the [double-texting conceptual guide](https://langchain-ai.github.io/langgraph/cloud/concepts/#double-texting).\n",
-    "\n",
-    "The guide covers the `rollback` option for double texting, which interrupts the prior run of the graph and starts a new one with the double-text. This option is very similar to the `interrupt` option, but in this case the first run is completely deleted from the database and cannot be restarted. Below is a quick example of using the `rollback` option.\n",
-    "\n",
-    "First, let's import our required packages and instantiate our client, assistant, and thread."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import asyncio\n",
-    "\n",
-    "import httpx\n",
-    "from langchain_core.messages import convert_to_messages\n",
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()\n",
-    "assistant_id = \"agent\"\n",
-    "thread = await client.threads.create()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# the first run will be interrupted\n",
-    "rolled_back_run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf?\"}]},\n",
-    ")\n",
-    "await asyncio.sleep(2)\n",
-    "run = await client.runs.create(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input={\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in nyc?\"}]},\n",
-    "    multitask_strategy=\"rollback\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# wait until the second run completes\n",
-    "await client.runs.join(thread[\"thread_id\"], run[\"run_id\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We can see that the thread has data only from the second run"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "state = await client.threads.get_state(thread[\"thread_id\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "================================\u001b[1m Human Message \u001b[0m=================================\n",
-      "\n",
-      "what's the weather in nyc?\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "[{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]\n",
-      "Tool Calls:\n",
-      "  tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)\n",
-      " Call ID: toolu_01JzPqefao1gxwajHQ3Yh3JD\n",
-      "  Args:\n",
-      "    query: weather in nyc\n",
-      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
-      "Name: tavily_search_results_json\n",
-      "\n",
-      "[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}\"}]\n",
-      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
-      "\n",
-      "The weather API results show that the current weather in New York City is sunny with a temperature of around 85°F (29°C). The wind is light at around 2-3 mph from the south-southeast. Overall it looks like a nice sunny summer day in NYC.\n"
-     ]
-    }
-   ],
-   "source": [
-    "for m in convert_to_messages(state[\"values\"][\"messages\"]):\n",
-    "    m.pretty_print()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Verify that the original, rolled back run was deleted"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Original run was correctly deleted\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    await client.runs.get(thread[\"thread_id\"], rolled_back_run[\"run_id\"])\n",
-    "except httpx.HTTPStatusError as _:\n",
-    "    print(\"Original run was correctly deleted\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "",
-   "name": ""
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/cloud_examples/stateless_runs.ipynb

@@ -20,9 +20,10 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client()\n",
     "assistants = await client.assistants.search()\n",
-    "assistants = [a for a in assistants if not a['config']]\n",
+    "assistants = [a for a in assistants if not a[\"config\"]]\n",
     "assistant = assistants[0]\n",
     "thread = await client.threads.create()"
    ]
@@ -50,13 +51,17 @@
     }
    ],
    "source": [
-    "input = {\"messages\":[{\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}]}\n",
+    "input = {\n",
+    "    \"messages\": [\n",
+    "        {\"role\": \"user\", \"content\": \"Hello! My name is Bagatur and I am 26 years old.\"}\n",
+    "    ]\n",
+    "}\n",
     "\n",
     "\n",
     "async for chunk in client.runs.stream(\n",
     "    # Don't pass in a thread_id and the stream will be stateless\n",
     "    None,\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
+    "    assistant[\"assistant_id\"],  # graph_id\n",
     "    input=input,\n",
     "    stream_mode=\"updates\",\n",
     "):\n",
@@ -81,7 +86,7 @@
    "source": [
     "stateless_run_result = await client.runs.wait(\n",
     "    None,\n",
-    "    assistant[\"assistant_id\"], # graph_id\n",
+    "    assistant[\"assistant_id\"],  # graph_id\n",
     "    input=input,\n",
     ")"
    ]

examples/cloud_examples/stream_debug.ipynb

@@ -1,176 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to stream debug events\n",
-    "This guide covers how to stream debug events from your graph (`stream_mode=\"debug\"`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3',\n",
-       " 'created_at': '2024-06-21T22:10:27.696862+00:00',\n",
-       " 'updated_at': '2024-06-21T22:10:27.696862+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Streaming debug events produces responses containing `type` and `timestamp` keys. Debug events correspond to different steps in the graph's execution (e.g. `task`, `task_result`, `checkpoint`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.256850+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a2e-6bb6-bfff-8423bcf47561', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.259723+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a35-6c86-8000-f4a85315dbeb', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.260021+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.267632+00:00', 'step': 1, 'payload': {'id': '12ab1026-a551-5f96-9ad3-43424f094774', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.268469+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a4b-60ae-8001-dd378f965bf7', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.268659+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.272916+00:00', 'step': 2, 'payload': {'id': '494ad427-fe8d-5654-91e6-50495a2699f5', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.273113+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a56-6832-8002-8ab17e662980', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-21T22:11:09.273192+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-21T22:11:09.277262+00:00', 'step': 3, 'payload': {'id': '677de327-99b7-5d97-9bbd-0092abb62d46', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-21T22:11:09.277519+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'd0cbe9ad-f11c-443a-9f6f-dca0ae5a0dd3', 'thread_ts': '1ef301b2-9a61-6462-8003-1316d9875b7f', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef301b2-9a0c-68d6-bbb1-0763efc8489a'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '906529f7-fbf2-41c9-a28c-b1fe8f891e4e', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-54bd965b-734a-4a0a-8d4d-840865054810', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '222ed3b8-450f-41cb-ac40-905def3c700a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-006e1758-b1ca-4c90-9ff3-d2e75b9ca9a7', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"debug\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_events.ipynb

@@ -1,313 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to stream events\n",
-    "This guide covers how to stream events from your graph (`stream_mode=\"events\"`). Depending on the use case and user experience of your LangGraph application, your application may process event types differently."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': '3f4c64e0-f792-4a5e-aa07-a4404e06e0bd',\n",
-       " 'created_at': '2024-06-24T22:16:29.301522+00:00',\n",
-       " 'updated_at': '2024-06-24T22:16:29.301522+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Streaming events produces responses containing an `event` key (in addition to other keys such as `data`). See the LangChain [`Runnable.astream_events()` reference](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable.astream_events) for all event types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:6'], 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}]]}}, 'run_id': 'cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'c7fe4d2d-3fb8-4e53-946d-03de13527853', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '7bb08493-d507-4e28-b9e6-4a5eda9d04f0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}], 'sleep': None}}, 'run_id': '7bb08493-d507-4e28-b9e6-4a5eda9d04f0', 'name': 'agent', 'tags': ['graph:step:6'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 6, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:7'], 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': 'f044fd3d-7271-488f-b8aa-e01572ff9112', 'name': 'tool', 'tags': ['graph:step:7'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 7, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:8'], 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '028a68fb-6435-4b46-a156-c3326f73985c', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': 'f2b2dfaf-475d-422b-8bf5-02a31bcc7d1a', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8', '1f4f95d0-0ce1-4061-85d4-946446bbd3e5']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': '1f4f95d0-0ce1-4061-85d4-946446bbd3e5', 'name': 'agent', 'tags': ['graph:step:8'], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 8, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef301a5-b867-67de-9e9e-a32e53c5b1f8']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '51f2874d-f8c7-4040-8b3b-8f15429a56ae', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-5f556aa0-26ea-42e2-b9e4-7ece3a00974e', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1faf5dd0-ae97-4235-963f-5075083a027a', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-ae383611-6a42-475a-912a-09d5972e9e94', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'c67e08e6-e7af-4c4a-aa5e-50c8340ae341', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-cb1b98c1-c9e2-4a30-9d7a-38fa1f6224bd', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '1c9a16d2-5f0a-4eba-a0d2-240484a4ce7e', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-028a68fb-6435-4b46-a156-c3326f73985c', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'name': 'LangGraph', 'tags': [], 'metadata': {'graph_id': 'agent', 'created_by': 'system', 'run_id': '1ef301a5-b867-67de-9e9e-a32e53c5b1f8', 'user_id': '', 'thread_id': '7196a3aa-763c-4a8d-bfda-12fbfe1cd727', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"events\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Token-by-Token Streaming\n",
-    "\n",
-    "Token-by-token streaming can be implemented with the `events` streaming mode. The `on_chat_model_stream` event type should be processed to stream LLM responses token-by-token."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "b\n",
-      "be\n",
-      "beg\n",
-      "begi\n",
-      "begin\n",
-      "begine\n",
-      "beginen\n",
-      "beginend\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "llm_response = \"\"\n",
-    "\n",
-    "# stream token-by-token\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=\"events\",\n",
-    "):\n",
-    "    if (\n",
-    "        chunk.event == \"events\" and\n",
-    "        chunk.data[\"event\"] == \"on_chat_model_stream\"\n",
-    "    ):\n",
-    "        llm_response += chunk.data[\"data\"][\"chunk\"][\"content\"]\n",
-    "        print(llm_response)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_messages.ipynb

@@ -1,397 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream messages from your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"messages\"`.\n",
-    "\n",
-    "In order to use this mode, the state of the graph you are interacting with MUST have a messages key that is a list of messages.\n",
-    "Eg, the state should look something like:\n",
-    "\n",
-    "```python\n",
-    "from typing import TypedDict, Annotated\n",
-    "from langgraph.graph import add_messages\n",
-    "from langchain_core.messages import AnyMessage\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list[AnyMessage], add_messages]\n",
-    "```\n",
-    "\n",
-    "OR it should be an instance or subclass of `from langgraph.graph import MessageState` (`MessageState` is just a helper type hint equivalent to the above).\n",
-    "\n",
-    "With `stream_mode=\"messages\"` two things will be streamed back:\n",
-    "\n",
-    "- It outputs messages produced by any chat model called inside (unless tagged in a special way)\n",
-    "- It outputs messages returned from nodes (to allow for nodes to return `ToolMessages` and the like"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "714e9f92-86b4-4cd8-9d68-cfc45d56ed2c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "56aa5159-5583-4134-9210-709b969bda6f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'e1431c95-e241-4d1d-a252-27eceb1e5c86',\n",
-       " 'created_at': '2024-06-21T15:48:59.808924+00:00',\n",
-       " 'updated_at': '2024-06-21T15:48:59.808924+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "147c3f98-f889-4f05-a090-6b31f2a0b291",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[]"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "runs = await client.runs.list(thread[\"thread_id\"])\n",
-    "runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "040795c6-5d9f-4729-9132-f3b0f94d9e94",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Helper function for formatting messages\n",
-    "\n",
-    "\n",
-    "def format_tool_calls(tool_calls):\n",
-    "    if tool_calls:\n",
-    "        formatted_calls = []\n",
-    "        for call in tool_calls:\n",
-    "            formatted_calls.append(\n",
-    "                f\"Tool Call ID: {call['id']}, Function: {call['name']}, Arguments: {call['args']}\"\n",
-    "            )\n",
-    "        return \"\\n\".join(formatted_calls)\n",
-    "    return \"No tool calls\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Metadata: Run ID - 1ef2fe5c-6a1d-6575-bc09-d7832711c17e\n",
-      "--------------------------------------------------\n",
-      "Invalid Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: \n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': ''}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "--------------------------------------------------\n",
-      "Tool Calls:\n",
-      "Tool Call ID: call_cg14F20jMBqWYrNgEkdWHwB3, Function: tavily_search_results_json, Arguments: {'query': 'current weather in San Francisco'}\n",
-      "Response Metadata: Finish Reason - tool_calls\n",
-      "--------------------------------------------------\n",
-      "--------------------------------------------------\n",
-      "AI: The\n",
-      "--------------------------------------------------\n",
-      "AI: The current\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is over\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-s\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-south\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 k\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%,\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles).\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is \n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.\n",
-      "--------------------------------------------------\n",
-      "AI: The current weather in San Francisco is overcast with a temperature of 13.9°C (57.0°F). The wind is blowing from the south-southwest at 6.9 mph (11.2 kph). The humidity is at 81%, and the visibility is 16 km (9 miles). The UV index is 3.\n",
-      "Response Metadata: Finish Reason - stop\n",
-      "--------------------------------------------------\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"user\", \"content\": \"what's the weather in sf\"}]}\n",
-    "config = {\"configurable\": {\"model_name\": \"openai\"}}\n",
-    "\n",
-    "async for event in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    config=config,\n",
-    "    stream_mode=\"messages\",\n",
-    "):\n",
-    "    if event.event == \"metadata\":\n",
-    "        print(f\"Metadata: Run ID - {event.data['run_id']}\")\n",
-    "        print(\"-\" * 50)\n",
-    "    elif event.event == \"messages/partial\":\n",
-    "        for data_item in event.data:\n",
-    "            if \"role\" in data_item and data_item[\"role\"] == \"user\":\n",
-    "                print(f\"Human: {data_item['content']}\")\n",
-    "            else:\n",
-    "                tool_calls = data_item.get(\"tool_calls\", [])\n",
-    "                invalid_tool_calls = data_item.get(\"invalid_tool_calls\", [])\n",
-    "                content = data_item.get(\"content\", \"\")\n",
-    "                response_metadata = data_item.get(\"response_metadata\", {})\n",
-    "\n",
-    "                if content:\n",
-    "                    print(f\"AI: {content}\")\n",
-    "\n",
-    "                if tool_calls:\n",
-    "                    print(\"Tool Calls:\")\n",
-    "                    print(format_tool_calls(tool_calls))\n",
-    "\n",
-    "                if invalid_tool_calls:\n",
-    "                    print(\"Invalid Tool Calls:\")\n",
-    "                    print(format_tool_calls(invalid_tool_calls))\n",
-    "\n",
-    "                if response_metadata:\n",
-    "                    finish_reason = response_metadata.get(\"finish_reason\", \"N/A\")\n",
-    "                    print(f\"Response Metadata: Finish Reason - {finish_reason}\")\n",
-    "        print(\"-\" * 50)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "langgraph-example-dev",
-   "language": "python",
-   "name": "langgraph-example-dev"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/stream_multiple.ipynb

@@ -1,457 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# How to configure multiple streaming modes at the same time\n",
-    "\n",
-    "This guide covers how to configure multiple streaming modes at the same time."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client\n",
-    "\n",
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4',\n",
-       " 'created_at': '2024-06-24T21:30:07.980789+00:00',\n",
-       " 'updated_at': '2024-06-24T21:30:07.980789+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# create thread\n",
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "When configuring multiple streaming modes for a run, responses for each respective mode will be produced. In the following example, note that a `list` of modes (`messages`, `events`, `debug`) is passed to the `stream_mode` parameter and the response contains `events`, `debug`, `messages/complete`, `messages/metadata`, and `messages/partial` event types."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}, 'name': 'LangGraph', 'tags': [], 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.116009+00:00', 'step': -1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc7c-6daa-bfff-6b9027c1a50e', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': []}, 'metadata': {'source': 'input', 'step': -1, 'writes': {'messages': [{'role': 'human', 'content': \"What's the weather in SF?\"}]}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.117924+00:00', 'step': 0, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc81-68c8-8000-4e18ae7d67a5', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]}, 'metadata': {'source': 'loop', 'step': 0, 'writes': None}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.118042+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}, 'triggers': ['start:agent']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:1'], 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/metadata...\n",
-      "{'run-2424dd6d-5cf5-4244-8d98-357640ce6e12': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'b', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'be', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'g', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'beg', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'i', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'begi', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}]]}}, 'run_id': '2424dd6d-5cf5-4244-8d98-357640ce6e12', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': 'tool', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '227afb0f-f909-4d54-a042-556ca6d98a69', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', '72b74d24-5792-48da-a887-102100d6e2c0']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': None, 'some_byte_array': None, 'dict_with_bytes': None, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}], 'sleep': None}}, 'run_id': '72b74d24-5792-48da-a887-102100d6e2c0', 'name': 'agent', 'tags': ['graph:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 1, 'langgraph_node': 'agent', 'langgraph_triggers': ['start:agent'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.124350+00:00', 'step': 1, 'payload': {'id': '212ed9c2-a454-50c5-a202-12066bbbe7b8', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.124510+00:00', 'step': 1, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc91-6a34-8001-26353c117c25', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 1, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.124572+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}, 'triggers': ['branch:agent:should_continue:tool']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'tool', 'tags': ['graph:step:2'], 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': None, 'tool_call_id': 'tool_call_id'}]}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'sleep': None}}, 'run_id': '91575720-886e-485e-ae2d-d6817e5346bf', 'name': 'tool', 'tags': ['graph:step:2'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 2, 'langgraph_node': 'tool', 'langgraph_triggers': ['branch:agent:should_continue:tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.126828+00:00', 'step': 2, 'payload': {'id': '44139125-a1be-57c2-9cb2-19eb62bbaf2f', 'name': 'tool', 'result': [['messages', [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.126966+00:00', 'step': 2, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bc97-6a06-8002-8e9ffc1ea75a', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}, 'metadata': {'source': 'loop', 'step': 2, 'writes': {'tool': {'messages': [{'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task', 'timestamp': '2024-06-24T21:34:06.127034+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}, 'triggers': ['tool']}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {}, 'name': 'agent', 'tags': ['graph:step:3'], 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/metadata...\n",
-      "{'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575': {'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'e', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'n', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'en', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_stream', 'data': {'chunk': {'content': 'd', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'AIMessageChunk', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None, 'tool_call_chunks': []}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/partial...\n",
-      "[{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chat_model_end', 'data': {'output': {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, 'input': {'messages': [[{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}]]}}, 'run_id': '0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'name': 'FakeListChatModel', 'tags': ['seq:step:1'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0, 'ls_model_type': 'chat'}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_start', 'data': {'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'name': 'should_continue', 'tags': ['seq:step:3'], 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': '__end__', 'input': {'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'run_id': '8af814e9-8136-4aab-acbc-dffc5bcafdfd', 'name': 'should_continue', 'tags': ['seq:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25', 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'data': {'chunk': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}], 'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}}, 'input': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}], 'sleep': None}}, 'run_id': 'b7d0900c-bfc2-43e4-b760-99bbc5bad84e', 'name': 'agent', 'tags': ['graph:step:3'], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca', 'langgraph_step': 3, 'langgraph_node': 'agent', 'langgraph_triggers': ['tool'], 'langgraph_task_idx': 0}, 'parent_ids': ['1ef32717-bc30-6cf2-8a26-33f63567bc25']}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'task_result', 'timestamp': '2024-06-24T21:34:06.133991+00:00', 'step': 3, 'payload': {'id': 'f1ccf371-63b3-5268-a837-7f360a93c4ec', 'name': 'agent', 'result': [['some_bytes', 'c29tZV9ieXRlcw=='], ['some_byte_array', 'c29tZV9ieXRlX2FycmF5'], ['dict_with_bytes', {'more_bytes': 'bW9yZV9ieXRlcw=='}], ['messages', [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]]]}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['values', {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: messages/complete...\n",
-      "[{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: debug...\n",
-      "{'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_stream', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'data': {'chunk': ['debug', {'type': 'checkpoint', 'timestamp': '2024-06-24T21:34:06.134190+00:00', 'step': 3, 'payload': {'config': {'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'callbacks': [None], 'recursion_limit': 25, 'configurable': {'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'thread_ts': '1ef32717-bca9-6418-8003-8d0d0b06845c', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25'}, 'values': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}, 'metadata': {'source': 'loop', 'step': 3, 'writes': {'agent': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}}}}]}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: events...\n",
-      "{'event': 'on_chain_end', 'data': {'output': {'some_bytes': 'c29tZV9ieXRlcw==', 'some_byte_array': 'c29tZV9ieXRlX2FycmF5', 'dict_with_bytes': {'more_bytes': 'bW9yZV9ieXRlcw=='}, 'messages': [{'content': \"What's the weather in SF?\", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': '7da1bafa-f53c-4df8-ba63-8dd517140b9f', 'example': False}, {'content': 'begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-2424dd6d-5cf5-4244-8d98-357640ce6e12', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}, {'content': 'tool_call__begin', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': None, 'id': '639ca779-403d-4915-a066-327e1f634c8b', 'tool_call_id': 'tool_call_id'}, {'content': 'end', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-0f2ef0a1-0fc7-445c-9df4-55e8bb284575', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}, 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'name': 'LangGraph', 'tags': [], 'metadata': {'created_by': 'system', 'run_id': '1ef32717-bc30-6cf2-8a26-33f63567bc25', 'user_id': '', 'graph_id': 'agent', 'thread_id': 'bfc68029-1f7b-400f-beab-6f9032a52da4', 'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca'}, 'parent_ids': []}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create input\n",
-    "input = {\n",
-    "    \"messages\": [\n",
-    "        {\n",
-    "            \"role\": \"human\",\n",
-    "            \"content\": \"What's the weather in SF?\",\n",
-    "        }\n",
-    "    ]\n",
-    "}\n",
-    "\n",
-    "# stream events with multiple streaming modes\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread_id=thread[\"thread_id\"],\n",
-    "    assistant_id=\"agent\",\n",
-    "    input=input,\n",
-    "    stream_mode=[\"messages\", \"events\", \"debug\"],\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

examples/cloud_examples/stream_updates.ipynb

@@ -1,178 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream state updates of your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"updates\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "230c0464-a6e5-420f-9e38-ca514e5634ce",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "56aa5159-5583-4134-9210-709b969bda6f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'thread_id': '979e3c89-a702-4882-87c2-7a59a250ce16',\n",
-       " 'created_at': '2024-06-21T15:22:07.453100+00:00',\n",
-       " 'updated_at': '2024-06-21T15:22:07.453100+00:00',\n",
-       " 'metadata': {}}"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "thread = await client.threads.create()\n",
-    "thread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "147c3f98-f889-4f05-a090-6b31f2a0b291",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[]"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "runs = await client.runs.list(thread[\"thread_id\"])\n",
-    "runs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': 'cfc96c16-ed9a-44bd-b5bb-c30e3c0725f0'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': [{'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-1a9d32b0-7007-4a36-abde-8df812a0ed94', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'action': {'messages': [{'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716062239, \\'localtime\\': \\'2024-05-18 12:57\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716061500, \\'last_updated\\': \\'2024-05-18 12:45\\', \\'temp_c\\': 18.9, \\'temp_f\\': 66.0, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 2.2, \\'wind_kph\\': 3.6, \\'wind_degree\\': 10, \\'wind_dir\\': \\'N\\', \\'pressure_mb\\': 1017.0, \\'pressure_in\\': 30.02, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 18.9, \\'feelslike_f\\': 66.0, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 6.0, \\'gust_mph\\': 7.5, \\'gust_kph\\': 12.0}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': 'a36e8cd1-0e96-4417-9c15-f10a945d2b42', 'tool_call_id': 'toolu_0148tMmDK51iLQfG1yaNwRHM'}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: data...\n",
-      "{'agent': {'messages': [{'content': 'The weather in Los Angeles is currently overcast with a temperature of around 66°F (18.9°C). There are light winds from the north at around 2-3 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-d5c1c2f0-b12d-41ce-990b-f36570e7483d', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "async for chunk in client.runs.stream(\n",
-    "    thread[\"thread_id\"],\n",
-    "    assistant_id,\n",
-    "    input=input,\n",
-    "    stream_mode=\"updates\",\n",
-    "):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "53800469-354a-4739-8e77-b88044c772d5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/stream_values.ipynb

@@ -1,212 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
-   "metadata": {},
-   "source": [
-    "# How to stream full state of your graph\n",
-    "\n",
-    "LangGraph Cloud supports multiple streaming modes. The main ones are:\n",
-    "\n",
-    "- `values`: This streaming mode streams back values of the graph. This is the **full state of the graph** after each node is called.\n",
-    "- `updates`: This streaming mode streams back updates to the graph. This is the **update to the state of the graph** after each node is called.\n",
-    "- `messages`: This streaming mode streams back messages - both complete messages (at the end of a node) as well as **tokens** for any messages generated inside a node. This mode is primarily meant for powering chat applications.\n",
-    "\n",
-    "\n",
-    "This guide covers `stream_mode=\"values\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "521d975b-e94b-4c37-bfa1-82d969e2a4dc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langgraph_sdk import get_client"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "27a1392b-86c3-464e-99a8-90ffc965f3ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client = get_client()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "230c0464-a6e5-420f-9e38-ca514e5634ce",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assistant_id = \"agent\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7da70e20-1a4e-4df2-b996-1927f474c835",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Receiving new event of type: metadata...\n",
-      "{'run_id': 'f08791ce-0a3d-44e0-836c-ff62cd2e2786'}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'role': 'human', 'content': 'what's the weather in la'}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: values...\n",
-      "{'messages': [{'content': 'what's the weather in la', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'human', 'name': None, 'id': 'faa15565-8823-4aa1-87af-e21b40526fae', 'example': False}, {'content': [{'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g', 'input': {'query': 'weather in los angeles'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-3fe1db7a-6b8d-4d83-ba07-8657190ad811', 'example': False, 'tool_calls': [{'name': 'tavily_search_results_json', 'args': {'query': 'weather in los angeles'}, 'id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}], 'invalid_tool_calls': []}, {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'tavily_search_results_json', 'id': '0d5dab31-5ff8-4ae2-a560-bc4bcba7c9d7', 'tool_call_id': 'toolu_01E5mSaZWm5rWJnCqmt63v4g'}, {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.', 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-4d6d4c23-5aad-4042-b0d9-19407a9e08e3', 'example': False, 'tool_calls': [], 'invalid_tool_calls': []}]}\n",
-      "\n",
-      "\n",
-      "\n",
-      "Receiving new event of type: end...\n",
-      "None\n",
-      "\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "thread = await client.threads.create()\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], assistant_id, input=input):\n",
-    "    print(f\"Receiving new event of type: {chunk.event}...\")\n",
-    "    print(chunk.data)\n",
-    "    print(\"\\n\\n\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43e4432d-e96c-4ae4-8085-866fb57bbcb3",
-   "metadata": {},
-   "source": [
-    "If we want to just get the final result, we can use this endpoint and just keep track of the last value we received"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "d2560481-d161-4d4f-b385-4977696c4aa1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "input = {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in la\"}]}\n",
-    "thread = await client.threads.create()\n",
-    "final_answer = None\n",
-    "async for chunk in client.runs.stream(thread[\"thread_id\"], assistant_id, input=input):\n",
-    "    if chunk.event == \"values\":\n",
-    "        final_answer = chunk.data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "9c2d60ea-450f-45cd-b867-0cbb162528f6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'messages': [{'content': 'what's the weather in la',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'human',\n",
-       "   'name': None,\n",
-       "   'id': 'e78c2f94-d810-42fc-a399-11f6bb1b1092',\n",
-       "   'example': False},\n",
-       "  {'content': [{'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom',\n",
-       "     'input': {'query': 'weather in los angeles'},\n",
-       "     'name': 'tavily_search_results_json',\n",
-       "     'type': 'tool_use'}],\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'ai',\n",
-       "   'name': None,\n",
-       "   'id': 'run-80767ab8-09fc-40ec-9e45-657ddef5e0b1',\n",
-       "   'example': False,\n",
-       "   'tool_calls': [{'name': 'tavily_search_results_json',\n",
-       "     'args': {'query': 'weather in los angeles'},\n",
-       "     'id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'}],\n",
-       "   'invalid_tool_calls': []},\n",
-       "  {'content': '[{\"url\": \"https://www.weatherapi.com/\", \"content\": \"{\\'location\\': {\\'name\\': \\'Los Angeles\\', \\'region\\': \\'California\\', \\'country\\': \\'United States of America\\', \\'lat\\': 34.05, \\'lon\\': -118.24, \\'tz_id\\': \\'America/Los_Angeles\\', \\'localtime_epoch\\': 1716310320, \\'localtime\\': \\'2024-05-21 9:52\\'}, \\'current\\': {\\'last_updated_epoch\\': 1716309900, \\'last_updated\\': \\'2024-05-21 09:45\\', \\'temp_c\\': 16.7, \\'temp_f\\': 62.1, \\'is_day\\': 1, \\'condition\\': {\\'text\\': \\'Overcast\\', \\'icon\\': \\'//cdn.weatherapi.com/weather/64x64/day/122.png\\', \\'code\\': 1009}, \\'wind_mph\\': 8.1, \\'wind_kph\\': 13.0, \\'wind_degree\\': 250, \\'wind_dir\\': \\'WSW\\', \\'pressure_mb\\': 1015.0, \\'pressure_in\\': 29.97, \\'precip_mm\\': 0.0, \\'precip_in\\': 0.0, \\'humidity\\': 65, \\'cloud\\': 100, \\'feelslike_c\\': 16.7, \\'feelslike_f\\': 62.1, \\'vis_km\\': 16.0, \\'vis_miles\\': 9.0, \\'uv\\': 5.0, \\'gust_mph\\': 12.5, \\'gust_kph\\': 20.2}}\"}]',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'tool',\n",
-       "   'name': 'tavily_search_results_json',\n",
-       "   'id': 'af25e94a-c119-48c3-bbd3-096e42f472ac',\n",
-       "   'tool_call_id': 'toolu_01SBMoAGr4U9x3ibztm2UUom'},\n",
-       "  {'content': 'Based on the weather API results, the current weather in Los Angeles is overcast with a temperature of around 62°F (17°C). There are light winds from the west-southwest around 8-13 mph. The humidity is 65% and visibility is good at 9 miles. Overall, mild spring weather conditions in LA.',\n",
-       "   'additional_kwargs': {},\n",
-       "   'response_metadata': {},\n",
-       "   'type': 'ai',\n",
-       "   'name': None,\n",
-       "   'id': 'run-b90f0037-e56a-4f3b-ad92-00d10d079a9e',\n",
-       "   'example': False,\n",
-       "   'tool_calls': [],\n",
-       "   'invalid_tool_calls': []}]}"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "final_answer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "39cedbff-0a7f-4a3e-bfc1-595797358769",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/cloud_examples/webhooks.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Use Webhooks\n",
     "\n",
-    "You may wish to use webhooks in your client, especially when using async streams in case you want to update something in your service once the API call to Langgraph Cloud has finished running. To do so, you will need to expose an endpoint that can accept POST requests, and then pass it to your API request in the \"webhook\" parameter.\n",
+    "You may wish to use webhooks in your client, especially when using async streams in case you want to update something in your service once the API call to LangGraph Cloud has finished running. To do so, you will need to expose an endpoint that can accept POST requests, and then pass it to your API request in the \"webhook\" parameter.\n",
     "\n",
     "Currently, the SDK has not exposed this endpoint but you can access it through curl commands as follows.\n",
     "\n",

examples/code_assistant/langgraph_code_assistant.ipynb

@@ -34,9 +34,7 @@
    "id": "e3900420",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "! pip install -U langchain_community langchain-openai langchain-anthropic langchain langgraph bs4"
-   ]
+   "source": ["! pip install -U langchain_community langchain-openai langchain-anthropic langchain langgraph bs4"]
   },
   {
    "cell_type": "markdown",
@@ -54,24 +52,7 @@
    "id": "c2eb35d1-4990-47dc-a5c4-208bae588a82",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from bs4 import BeautifulSoup as Soup\n",
-    "from langchain_community.document_loaders.recursive_url_loader import RecursiveUrlLoader\n",
-    "\n",
-    "# LCEL docs\n",
-    "url = \"https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel\"\n",
-    "loader = RecursiveUrlLoader(\n",
-    "    url=url, max_depth=20, extractor=lambda x: Soup(x, \"html.parser\").text\n",
-    ")\n",
-    "docs = loader.load()\n",
-    "\n",
-    "# Sort the list based on the URLs and get the text\n",
-    "d_sorted = sorted(docs, key=lambda x: x.metadata[\"source\"])\n",
-    "d_reversed = list(reversed(d_sorted))\n",
-    "concatenated_content = \"\\n\\n\\n --- \\n\\n\\n\".join(\n",
-    "    [doc.page_content for doc in d_reversed]\n",
-    ")"
-   ]
+   "source": ["from bs4 import BeautifulSoup as Soup\nfrom langchain_community.document_loaders.recursive_url_loader import RecursiveUrlLoader\n\n# LCEL docs\nurl = \"https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel\"\nloader = RecursiveUrlLoader(\n    url=url, max_depth=20, extractor=lambda x: Soup(x, \"html.parser\").text\n)\ndocs = loader.load()\n\n# Sort the list based on the URLs and get the text\nd_sorted = sorted(docs, key=lambda x: x.metadata[\"source\"])\nd_reversed = list(reversed(d_sorted))\nconcatenated_content = \"\\n\\n\\n --- \\n\\n\\n\".join(\n    [doc.page_content for doc in d_reversed]\n)"]
   },
   {
    "cell_type": "markdown",
@@ -93,45 +74,7 @@
    "id": "3ba3df70-f6b4-4ea5-a210-e10944960bc6",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "### OpenAI\n",
-    "\n",
-    "# Grader prompt\n",
-    "code_gen_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"\"\"You are a coding assistant with expertise in LCEL, LangChain expression language. \\n \n",
-    "    Here is a full set of LCEL documentation:  \\n ------- \\n  {context} \\n ------- \\n Answer the user \n",
-    "    question based on the above provided documentation. Ensure any code you provide can be executed \\n \n",
-    "    with all required imports and variables defined. Structure your answer with a description of the code solution. \\n\n",
-    "    Then list the imports. And finally list the functioning code block. Here is the user question:\"\"\",\n",
-    "        ),\n",
-    "        (\"placeholder\", \"{messages}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "\n",
-    "# Data model\n",
-    "class code(BaseModel):\n",
-    "    \"\"\"Code output\"\"\"\n",
-    "\n",
-    "    prefix: str = Field(description=\"Description of the problem and approach\")\n",
-    "    imports: str = Field(description=\"Code block import statements\")\n",
-    "    code: str = Field(description=\"Code block not including import statements\")\n",
-    "    description = \"Schema for code solutions to questions about LCEL.\"\n",
-    "\n",
-    "\n",
-    "expt_llm = \"gpt-4-0125-preview\"\n",
-    "llm = ChatOpenAI(temperature=0, model=expt_llm)\n",
-    "code_gen_chain = code_gen_prompt | llm.with_structured_output(code)\n",
-    "question = \"How do I build a RAG chain in LCEL?\"\n",
-    "# solution = code_gen_chain_oai.invoke({\"context\":concatenated_content,\"messages\":[(\"user\",question)]})"
-   ]
+   "source": ["from langchain_core.prompts import ChatPromptTemplate\nfrom langchain_core.pydantic_v1 import BaseModel, Field\nfrom langchain_openai import ChatOpenAI\n\n### OpenAI\n\n# Grader prompt\ncode_gen_prompt = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"\"\"You are a coding assistant with expertise in LCEL, LangChain expression language. \\n \n    Here is a full set of LCEL documentation:  \\n ------- \\n  {context} \\n ------- \\n Answer the user \n    question based on the above provided documentation. Ensure any code you provide can be executed \\n \n    with all required imports and variables defined. Structure your answer with a description of the code solution. \\n\n    Then list the imports. And finally list the functioning code block. Here is the user question:\"\"\",\n        ),\n        (\"placeholder\", \"{messages}\"),\n    ]\n)\n\n\n# Data model\nclass code(BaseModel):\n    \"\"\"Code output\"\"\"\n\n    prefix: str = Field(description=\"Description of the problem and approach\")\n    imports: str = Field(description=\"Code block import statements\")\n    code: str = Field(description=\"Code block not including import statements\")\n    description = \"Schema for code solutions to questions about LCEL.\"\n\n\nexpt_llm = \"gpt-4-0125-preview\"\nllm = ChatOpenAI(temperature=0, model=expt_llm)\ncode_gen_chain = code_gen_prompt | llm.with_structured_output(code)\nquestion = \"How do I build a RAG chain in LCEL?\"\n# solution = code_gen_chain_oai.invoke({\"context\":concatenated_content,\"messages\":[(\"user\",question)]})"]
   },
   {
    "cell_type": "code",
@@ -139,118 +82,7 @@
    "id": "cd30b67d-96db-4e51-a540-ae23fcc1f878",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "### Anthropic\n",
-    "\n",
-    "# Prompt to enforce tool use\n",
-    "code_gen_prompt_claude = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"\"\"<instructions> You are a coding assistant with expertise in LCEL, LangChain expression language. \\n \n",
-    "    Here is the LCEL documentation:  \\n ------- \\n  {context} \\n ------- \\n Answer the user  question based on the \\n \n",
-    "    above provided documentation. Ensure any code you provide can be executed with all required imports and variables \\n\n",
-    "    defined. Structure your answer: 1) a prefix describing the code solution, 2) the imports, 3) the functioning code block. \\n\n",
-    "    Invoke the code tool to structure the output correctly. </instructions> \\n Here is the user question:\"\"\",\n",
-    "        ),\n",
-    "        (\"placeholder\", \"{messages}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "\n",
-    "# Data model\n",
-    "class code(BaseModel):\n",
-    "    \"\"\"Code output\"\"\"\n",
-    "\n",
-    "    prefix: str = Field(description=\"Description of the problem and approach\")\n",
-    "    imports: str = Field(description=\"Code block import statements\")\n",
-    "    code: str = Field(description=\"Code block not including import statements\")\n",
-    "    description = \"Schema for code solutions to questions about LCEL.\"\n",
-    "\n",
-    "\n",
-    "# LLM\n",
-    "# expt_llm = \"claude-3-haiku-20240307\"\n",
-    "expt_llm = \"claude-3-opus-20240229\"\n",
-    "llm = ChatAnthropic(\n",
-    "    model=expt_llm,\n",
-    "    default_headers={\"anthropic-beta\": \"tools-2024-04-04\"},\n",
-    ")\n",
-    "\n",
-    "structured_llm_claude = llm.with_structured_output(code, include_raw=True)\n",
-    "\n",
-    "\n",
-    "# Optional: Check for errors in case tool use is flaky\n",
-    "def check_claude_output(tool_output):\n",
-    "    \"\"\"Check for parse error or failure to call the tool\"\"\"\n",
-    "\n",
-    "    # Error with parsing\n",
-    "    if tool_output[\"parsing_error\"]:\n",
-    "        # Report back output and parsing errors\n",
-    "        print(\"Parsing error!\")\n",
-    "        raw_output = str(tool_output[\"raw\"].content)\n",
-    "        error = tool_output[\"parsing_error\"]\n",
-    "        raise ValueError(\n",
-    "            f\"Error parsing your output! Be sure to invoke the tool. Output: {raw_output}. \\n Parse error: {error}\"\n",
-    "        )\n",
-    "\n",
-    "    # Tool was not invoked\n",
-    "    elif not tool_output[\"parsed\"]:\n",
-    "        print(\"Failed to invoke tool!\")\n",
-    "        raise ValueError(\n",
-    "            \"You did not use the provided tool! Be sure to invoke the tool to structure the output.\"\n",
-    "        )\n",
-    "    return tool_output\n",
-    "\n",
-    "\n",
-    "# Chain with output check\n",
-    "code_chain_claude_raw = (\n",
-    "    code_gen_prompt_claude | structured_llm_claude | check_claude_output\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def insert_errors(inputs):\n",
-    "    \"\"\"Insert errors for tool parsing in the messages\"\"\"\n",
-    "\n",
-    "    # Get errors\n",
-    "    error = inputs[\"error\"]\n",
-    "    messages = inputs[\"messages\"]\n",
-    "    messages += [\n",
-    "        (\n",
-    "            \"assistant\",\n",
-    "            f\"Retry. You are required to fix the parsing errors: {error} \\n\\n You must invoke the provided tool.\",\n",
-    "        )\n",
-    "    ]\n",
-    "    return {\n",
-    "        \"messages\": messages,\n",
-    "        \"context\": inputs[\"context\"],\n",
-    "    }\n",
-    "\n",
-    "\n",
-    "# This will be run as a fallback chain\n",
-    "fallback_chain = insert_errors | code_chain_claude_raw\n",
-    "N = 3  # Max re-tries\n",
-    "code_gen_chain_re_try = code_chain_claude_raw.with_fallbacks(\n",
-    "    fallbacks=[fallback_chain] * N, exception_key=\"error\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def parse_output(solution):\n",
-    "    \"\"\"When we add 'include_raw=True' to structured output,\n",
-    "    it will return a dict w 'raw', 'parsed', 'parsing_error'.\"\"\"\n",
-    "\n",
-    "    return solution[\"parsed\"]\n",
-    "\n",
-    "\n",
-    "# Optional: With re-try to correct for failure to invoke tool\n",
-    "code_gen_chain = code_gen_chain_re_try | parse_output\n",
-    "\n",
-    "# No re-try\n",
-    "code_gen_chain = code_gen_prompt_claude | structured_llm_claude | parse_output"
-   ]
+   "source": ["from langchain_anthropic import ChatAnthropic\nfrom langchain_core.prompts import ChatPromptTemplate\nfrom langchain_core.pydantic_v1 import BaseModel, Field\n\n### Anthropic\n\n# Prompt to enforce tool use\ncode_gen_prompt_claude = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"\"\"<instructions> You are a coding assistant with expertise in LCEL, LangChain expression language. \\n \n    Here is the LCEL documentation:  \\n ------- \\n  {context} \\n ------- \\n Answer the user  question based on the \\n \n    above provided documentation. Ensure any code you provide can be executed with all required imports and variables \\n\n    defined. Structure your answer: 1) a prefix describing the code solution, 2) the imports, 3) the functioning code block. \\n\n    Invoke the code tool to structure the output correctly. </instructions> \\n Here is the user question:\"\"\",\n        ),\n        (\"placeholder\", \"{messages}\"),\n    ]\n)\n\n\n# Data model\nclass code(BaseModel):\n    \"\"\"Code output\"\"\"\n\n    prefix: str = Field(description=\"Description of the problem and approach\")\n    imports: str = Field(description=\"Code block import statements\")\n    code: str = Field(description=\"Code block not including import statements\")\n    description = \"Schema for code solutions to questions about LCEL.\"\n\n\n# LLM\n# expt_llm = \"claude-3-haiku-20240307\"\nexpt_llm = \"claude-3-opus-20240229\"\nllm = ChatAnthropic(\n    model=expt_llm,\n    default_headers={\"anthropic-beta\": \"tools-2024-04-04\"},\n)\n\nstructured_llm_claude = llm.with_structured_output(code, include_raw=True)\n\n\n# Optional: Check for errors in case tool use is flaky\ndef check_claude_output(tool_output):\n    \"\"\"Check for parse error or failure to call the tool\"\"\"\n\n    # Error with parsing\n    if tool_output[\"parsing_error\"]:\n        # Report back output and parsing errors\n        print(\"Parsing error!\")\n        raw_output = str(tool_output[\"raw\"].content)\n        error = tool_output[\"parsing_error\"]\n        raise ValueError(\n            f\"Error parsing your output! Be sure to invoke the tool. Output: {raw_output}. \\n Parse error: {error}\"\n        )\n\n    # Tool was not invoked\n    elif not tool_output[\"parsed\"]:\n        print(\"Failed to invoke tool!\")\n        raise ValueError(\n            \"You did not use the provided tool! Be sure to invoke the tool to structure the output.\"\n        )\n    return tool_output\n\n\n# Chain with output check\ncode_chain_claude_raw = (\n    code_gen_prompt_claude | structured_llm_claude | check_claude_output\n)\n\n\ndef insert_errors(inputs):\n    \"\"\"Insert errors for tool parsing in the messages\"\"\"\n\n    # Get errors\n    error = inputs[\"error\"]\n    messages = inputs[\"messages\"]\n    messages += [\n        (\n            \"assistant\",\n            f\"Retry. You are required to fix the parsing errors: {error} \\n\\n You must invoke the provided tool.\",\n        )\n    ]\n    return {\n        \"messages\": messages,\n        \"context\": inputs[\"context\"],\n    }\n\n\n# This will be run as a fallback chain\nfallback_chain = insert_errors | code_chain_claude_raw\nN = 3  # Max re-tries\ncode_gen_chain_re_try = code_chain_claude_raw.with_fallbacks(\n    fallbacks=[fallback_chain] * N, exception_key=\"error\"\n)\n\n\ndef parse_output(solution):\n    \"\"\"When we add 'include_raw=True' to structured output,\n    it will return a dict w 'raw', 'parsed', 'parsing_error'.\"\"\"\n\n    return solution[\"parsed\"]\n\n\n# Optional: With re-try to correct for failure to invoke tool\ncode_gen_chain = code_gen_chain_re_try | parse_output\n\n# No re-try\ncode_gen_chain = code_gen_prompt_claude | structured_llm_claude | parse_output"]
   },
   {
    "cell_type": "code",
@@ -260,14 +92,7 @@
     "scrolled": true
    },
    "outputs": [],
-   "source": [
-    "# Test\n",
-    "question = \"How do I build a RAG chain in LCEL?\"\n",
-    "solution = code_gen_chain.invoke(\n",
-    "    {\"context\": concatenated_content, \"messages\": [(\"user\", question)]}\n",
-    ")\n",
-    "solution"
-   ]
+   "source": ["# Test\nquestion = \"How do I build a RAG chain in LCEL?\"\nsolution = code_gen_chain.invoke(\n    {\"context\": concatenated_content, \"messages\": [(\"user\", question)]}\n)\nsolution"]
   },
   {
    "cell_type": "markdown",
@@ -285,26 +110,7 @@
    "id": "c185f1a2-e943-4bed-b833-4243c9c64092",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import List, TypedDict\n",
-    "\n",
-    "\n",
-    "class GraphState(TypedDict):\n",
-    "    \"\"\"\n",
-    "    Represents the state of our graph.\n",
-    "\n",
-    "    Attributes:\n",
-    "        error : Binary flag for control flow to indicate whether test error was tripped\n",
-    "        messages : With user question, error messages, reasoning\n",
-    "        generation : Code solution\n",
-    "        iterations : Number of tries\n",
-    "    \"\"\"\n",
-    "\n",
-    "    error: str\n",
-    "    messages: List\n",
-    "    generation: str\n",
-    "    iterations: int"
-   ]
+   "source": ["from typing import List, TypedDict\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        error : Binary flag for control flow to indicate whether test error was tripped\n        messages : With user question, error messages, reasoning\n        generation : Code solution\n        iterations : Number of tries\n    \"\"\"\n\n    error: str\n    messages: List\n    generation: str\n    iterations: int"]
   },
   {
    "cell_type": "markdown",
@@ -322,177 +128,7 @@
    "id": "b70e8301-63ae-4f7e-ad8f-c9a052fe3566",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "### Parameter\n",
-    "\n",
-    "# Max tries\n",
-    "max_iterations = 3\n",
-    "# Reflect\n",
-    "# flag = 'reflect'\n",
-    "flag = \"do not reflect\"\n",
-    "\n",
-    "### Nodes\n",
-    "\n",
-    "\n",
-    "def generate(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Generate a code solution\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        state (dict): New key added to state, generation\n",
-    "    \"\"\"\n",
-    "\n",
-    "    print(\"---GENERATING CODE SOLUTION---\")\n",
-    "\n",
-    "    # State\n",
-    "    messages = state[\"messages\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "    error = state[\"error\"]\n",
-    "\n",
-    "    # We have been routed back to generation with an error\n",
-    "    if error == \"yes\":\n",
-    "        messages += [\n",
-    "            (\n",
-    "                \"user\",\n",
-    "                \"Now, try again. Invoke the code tool to structure the output with a prefix, imports, and code block:\",\n",
-    "            )\n",
-    "        ]\n",
-    "\n",
-    "    # Solution\n",
-    "    code_solution = code_gen_chain.invoke(\n",
-    "        {\"context\": concatenated_content, \"messages\": messages}\n",
-    "    )\n",
-    "    messages += [\n",
-    "        (\n",
-    "            \"assistant\",\n",
-    "            f\"{code_solution.prefix} \\n Imports: {code_solution.imports} \\n Code: {code_solution.code}\",\n",
-    "        )\n",
-    "    ]\n",
-    "\n",
-    "    # Increment\n",
-    "    iterations = iterations + 1\n",
-    "    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n",
-    "\n",
-    "\n",
-    "def code_check(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Check code\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        state (dict): New key added to state, error\n",
-    "    \"\"\"\n",
-    "\n",
-    "    print(\"---CHECKING CODE---\")\n",
-    "\n",
-    "    # State\n",
-    "    messages = state[\"messages\"]\n",
-    "    code_solution = state[\"generation\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "\n",
-    "    # Get solution components\n",
-    "    imports = code_solution.imports\n",
-    "    code = code_solution.code\n",
-    "\n",
-    "    # Check imports\n",
-    "    try:\n",
-    "        exec(imports)\n",
-    "    except Exception as e:\n",
-    "        print(\"---CODE IMPORT CHECK: FAILED---\")\n",
-    "        error_message = [(\"user\", f\"Your solution failed the import test: {e}\")]\n",
-    "        messages += error_message\n",
-    "        return {\n",
-    "            \"generation\": code_solution,\n",
-    "            \"messages\": messages,\n",
-    "            \"iterations\": iterations,\n",
-    "            \"error\": \"yes\",\n",
-    "        }\n",
-    "\n",
-    "    # Check execution\n",
-    "    try:\n",
-    "        exec(imports + \"\\n\" + code)\n",
-    "    except Exception as e:\n",
-    "        print(\"---CODE BLOCK CHECK: FAILED---\")\n",
-    "        error_message = [(\"user\", f\"Your solution failed the code execution test: {e}\")]\n",
-    "        messages += error_message\n",
-    "        return {\n",
-    "            \"generation\": code_solution,\n",
-    "            \"messages\": messages,\n",
-    "            \"iterations\": iterations,\n",
-    "            \"error\": \"yes\",\n",
-    "        }\n",
-    "\n",
-    "    # No errors\n",
-    "    print(\"---NO CODE TEST FAILURES---\")\n",
-    "    return {\n",
-    "        \"generation\": code_solution,\n",
-    "        \"messages\": messages,\n",
-    "        \"iterations\": iterations,\n",
-    "        \"error\": \"no\",\n",
-    "    }\n",
-    "\n",
-    "\n",
-    "def reflect(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Reflect on errors\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        state (dict): New key added to state, generation\n",
-    "    \"\"\"\n",
-    "\n",
-    "    print(\"---GENERATING CODE SOLUTION---\")\n",
-    "\n",
-    "    # State\n",
-    "    messages = state[\"messages\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "    code_solution = state[\"generation\"]\n",
-    "\n",
-    "    # Prompt reflection\n",
-    "\n",
-    "    # Add reflection\n",
-    "    reflections = code_gen_chain.invoke(\n",
-    "        {\"context\": concatenated_content, \"messages\": messages}\n",
-    "    )\n",
-    "    messages += [(\"assistant\", f\"Here are reflections on the error: {reflections}\")]\n",
-    "    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n",
-    "\n",
-    "\n",
-    "### Edges\n",
-    "\n",
-    "\n",
-    "def decide_to_finish(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Determines whether to finish.\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        str: Next node to call\n",
-    "    \"\"\"\n",
-    "    error = state[\"error\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "\n",
-    "    if error == \"no\" or iterations == max_iterations:\n",
-    "        print(\"---DECISION: FINISH---\")\n",
-    "        return \"end\"\n",
-    "    else:\n",
-    "        print(\"---DECISION: RE-TRY SOLUTION---\")\n",
-    "        if flag == \"reflect\":\n",
-    "            return \"reflect\"\n",
-    "        else:\n",
-    "            return \"generate\""
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n### Parameter\n\n# Max tries\nmax_iterations = 3\n# Reflect\n# flag = 'reflect'\nflag = \"do not reflect\"\n\n### Nodes\n\n\ndef generate(state: GraphState):\n    \"\"\"\n    Generate a code solution\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation\n    \"\"\"\n\n    print(\"---GENERATING CODE SOLUTION---\")\n\n    # State\n    messages = state[\"messages\"]\n    iterations = state[\"iterations\"]\n    error = state[\"error\"]\n\n    # We have been routed back to generation with an error\n    if error == \"yes\":\n        messages += [\n            (\n                \"user\",\n                \"Now, try again. Invoke the code tool to structure the output with a prefix, imports, and code block:\",\n            )\n        ]\n\n    # Solution\n    code_solution = code_gen_chain.invoke(\n        {\"context\": concatenated_content, \"messages\": messages}\n    )\n    messages += [\n        (\n            \"assistant\",\n            f\"{code_solution.prefix} \\n Imports: {code_solution.imports} \\n Code: {code_solution.code}\",\n        )\n    ]\n\n    # Increment\n    iterations = iterations + 1\n    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n\n\ndef code_check(state: GraphState):\n    \"\"\"\n    Check code\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, error\n    \"\"\"\n\n    print(\"---CHECKING CODE---\")\n\n    # State\n    messages = state[\"messages\"]\n    code_solution = state[\"generation\"]\n    iterations = state[\"iterations\"]\n\n    # Get solution components\n    imports = code_solution.imports\n    code = code_solution.code\n\n    # Check imports\n    try:\n        exec(imports)\n    except Exception as e:\n        print(\"---CODE IMPORT CHECK: FAILED---\")\n        error_message = [(\"user\", f\"Your solution failed the import test: {e}\")]\n        messages += error_message\n        return {\n            \"generation\": code_solution,\n            \"messages\": messages,\n            \"iterations\": iterations,\n            \"error\": \"yes\",\n        }\n\n    # Check execution\n    try:\n        exec(imports + \"\\n\" + code)\n    except Exception as e:\n        print(\"---CODE BLOCK CHECK: FAILED---\")\n        error_message = [(\"user\", f\"Your solution failed the code execution test: {e}\")]\n        messages += error_message\n        return {\n            \"generation\": code_solution,\n            \"messages\": messages,\n            \"iterations\": iterations,\n            \"error\": \"yes\",\n        }\n\n    # No errors\n    print(\"---NO CODE TEST FAILURES---\")\n    return {\n        \"generation\": code_solution,\n        \"messages\": messages,\n        \"iterations\": iterations,\n        \"error\": \"no\",\n    }\n\n\ndef reflect(state: GraphState):\n    \"\"\"\n    Reflect on errors\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation\n    \"\"\"\n\n    print(\"---GENERATING CODE SOLUTION---\")\n\n    # State\n    messages = state[\"messages\"]\n    iterations = state[\"iterations\"]\n    code_solution = state[\"generation\"]\n\n    # Prompt reflection\n\n    # Add reflection\n    reflections = code_gen_chain.invoke(\n        {\"context\": concatenated_content, \"messages\": messages}\n    )\n    messages += [(\"assistant\", f\"Here are reflections on the error: {reflections}\")]\n    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n\n\n### Edges\n\n\ndef decide_to_finish(state: GraphState):\n    \"\"\"\n    Determines whether to finish.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Next node to call\n    \"\"\"\n    error = state[\"error\"]\n    iterations = state[\"iterations\"]\n\n    if error == \"no\" or iterations == max_iterations:\n        print(\"---DECISION: FINISH---\")\n        return \"end\"\n    else:\n        print(\"---DECISION: RE-TRY SOLUTION---\")\n        if flag == \"reflect\":\n            return \"reflect\"\n        else:\n            return \"generate\""]
   },
   {
    "cell_type": "code",
@@ -500,31 +136,7 @@
    "id": "f66b4e00-4731-42c8-bc38-72dd0ff7c92c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "workflow = StateGraph(GraphState)\n",
-    "\n",
-    "# Define the nodes\n",
-    "workflow.add_node(\"generate\", generate)  # generation solution\n",
-    "workflow.add_node(\"check_code\", code_check)  # check code\n",
-    "workflow.add_node(\"reflect\", reflect)  # reflect\n",
-    "\n",
-    "# Build graph\n",
-    "workflow.set_entry_point(\"generate\")\n",
-    "workflow.add_edge(\"generate\", \"check_code\")\n",
-    "workflow.add_conditional_edges(\n",
-    "    \"check_code\",\n",
-    "    decide_to_finish,\n",
-    "    {\n",
-    "        \"end\": END,\n",
-    "        \"reflect\": \"reflect\",\n",
-    "        \"generate\": \"generate\",\n",
-    "    },\n",
-    ")\n",
-    "workflow.add_edge(\"reflect\", \"generate\")\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\nworkflow = StateGraph(GraphState)\n\n# Define the nodes\nworkflow.add_node(\"generate\", generate)  # generation solution\nworkflow.add_node(\"check_code\", code_check)  # check code\nworkflow.add_node(\"reflect\", reflect)  # reflect\n\n# Build graph\nworkflow.add_edge(START, \"generate\")\nworkflow.add_edge(\"generate\", \"check_code\")\nworkflow.add_conditional_edges(\n    \"check_code\",\n    decide_to_finish,\n    {\n        \"end\": END,\n        \"reflect\": \"reflect\",\n        \"generate\": \"generate\",\n    },\n)\nworkflow.add_edge(\"reflect\", \"generate\")\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -532,10 +144,7 @@
    "id": "9bcaafe4-ddcf-4fab-8620-2d9b6c508f98",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "question = \"How can I directly pass a string to a runnable and use it to construct the input needed for my prompt?\"\n",
-    "app.invoke({\"messages\": [(\"user\", question)], \"iterations\": 0})"
-   ]
+   "source": ["question = \"How can I directly pass a string to a runnable and use it to construct the input needed for my prompt?\"\napp.invoke({\"messages\": [(\"user\", question)], \"iterations\": 0})"]
   },
   {
    "cell_type": "markdown",
@@ -563,11 +172,7 @@
    "id": "678e8954-56b5-4cc6-be26-f7f2a060b242",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import langsmith\n",
-    "\n",
-    "client = langsmith.Client()"
-   ]
+   "source": ["import langsmith\n\nclient = langsmith.Client()"]
   },
   {
    "cell_type": "code",
@@ -575,13 +180,7 @@
    "id": "ef7cf662-7a6f-4dee-965c-6309d4045feb",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Clone the dataset to your tenant to use it\n",
-    "public_dataset = (\n",
-    "    \"https://smith.langchain.com/public/326674a6-62bd-462d-88ae-eea49d503f9d/d\"\n",
-    ")\n",
-    "client.clone_public_dataset(public_dataset)"
-   ]
+   "source": ["# Clone the dataset to your tenant to use it\npublic_dataset = (\n    \"https://smith.langchain.com/public/326674a6-62bd-462d-88ae-eea49d503f9d/d\"\n)\nclient.clone_public_dataset(public_dataset)"]
   },
   {
    "cell_type": "markdown",
@@ -597,28 +196,7 @@
    "id": "455a34ea-52cb-4ae5-9f4a-7e4a08cd0c09",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langsmith.schemas import Example, Run\n",
-    "\n",
-    "\n",
-    "def check_import(run: Run, example: Example) -> dict:\n",
-    "    imports = run.outputs.get(\"imports\")\n",
-    "    try:\n",
-    "        exec(imports)\n",
-    "        return {\"key\": \"import_check\", \"score\": 1}\n",
-    "    except Exception:\n",
-    "        return {\"key\": \"import_check\", \"score\": 0}\n",
-    "\n",
-    "\n",
-    "def check_execution(run: Run, example: Example) -> dict:\n",
-    "    imports = run.outputs.get(\"imports\")\n",
-    "    code = run.outputs.get(\"code\")\n",
-    "    try:\n",
-    "        exec(imports + \"\\n\" + code)\n",
-    "        return {\"key\": \"code_execution_check\", \"score\": 1}\n",
-    "    except Exception:\n",
-    "        return {\"key\": \"code_execution_check\", \"score\": 0}"
-   ]
+   "source": ["from langsmith.schemas import Example, Run\n\n\ndef check_import(run: Run, example: Example) -> dict:\n    imports = run.outputs.get(\"imports\")\n    try:\n        exec(imports)\n        return {\"key\": \"import_check\", \"score\": 1}\n    except Exception:\n        return {\"key\": \"import_check\", \"score\": 0}\n\n\ndef check_execution(run: Run, example: Example) -> dict:\n    imports = run.outputs.get(\"imports\")\n    code = run.outputs.get(\"code\")\n    try:\n        exec(imports + \"\\n\" + code)\n        return {\"key\": \"code_execution_check\", \"score\": 1}\n    except Exception:\n        return {\"key\": \"code_execution_check\", \"score\": 0}"]
   },
   {
    "cell_type": "markdown",
@@ -634,22 +212,7 @@
    "id": "c8fa6bcb-b245-4422-b79a-582cd8a7d7ea",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def predict_base_case(example: dict):\n",
-    "    \"\"\"Context stuffing\"\"\"\n",
-    "    solution = code_gen_chain.invoke(\n",
-    "        {\"context\": concatenated_content, \"messages\": [(\"user\", example[\"question\"])]}\n",
-    "    )\n",
-    "    solution_structured = code_gen_chain.invoke([(\"code\", solution)])\n",
-    "    return {\"imports\": solution_structured.imports, \"code\": solution_structured.code}\n",
-    "\n",
-    "\n",
-    "def predict_langgraph(example: dict):\n",
-    "    \"\"\"LangGraph\"\"\"\n",
-    "    graph = app.invoke({\"messages\": [(\"user\", example[\"question\"])], \"iterations\": 0})\n",
-    "    solution = graph[\"generation\"]\n",
-    "    return {\"imports\": solution.imports, \"code\": solution.code}"
-   ]
+   "source": ["def predict_base_case(example: dict):\n    \"\"\"Context stuffing\"\"\"\n    solution = code_gen_chain.invoke(\n        {\"context\": concatenated_content, \"messages\": [(\"user\", example[\"question\"])]}\n    )\n    solution_structured = code_gen_chain.invoke([(\"code\", solution)])\n    return {\"imports\": solution_structured.imports, \"code\": solution_structured.code}\n\n\ndef predict_langgraph(example: dict):\n    \"\"\"LangGraph\"\"\"\n    graph = app.invoke({\"messages\": [(\"user\", example[\"question\"])], \"iterations\": 0})\n    solution = graph[\"generation\"]\n    return {\"imports\": solution.imports, \"code\": solution.code}"]
   },
   {
    "cell_type": "code",
@@ -657,15 +220,7 @@
    "id": "d9c57468-97f6-47d6-a5e9-c09b53bfdd83",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langsmith.evaluation import evaluate\n",
-    "\n",
-    "# Evaluator\n",
-    "code_evalulator = [check_import, check_execution]\n",
-    "\n",
-    "# Dataset\n",
-    "dataset_name = \"test-LCEL-code-gen\""
-   ]
+   "source": ["from langsmith.evaluation import evaluate\n\n# Evaluator\ncode_evalulator = [check_import, check_execution]\n\n# Dataset\ndataset_name = \"test-LCEL-code-gen\""]
   },
   {
    "cell_type": "code",
@@ -673,19 +228,7 @@
    "id": "2dacccf0-d73f-4017-aaf0-9806ffe5bd2c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Run base case\n",
-    "experiment_results_ = evaluate(\n",
-    "    predict_base_case,\n",
-    "    data=dataset_name,\n",
-    "    evaluators=code_evalulator,\n",
-    "    experiment_prefix=f\"test-without-langgraph-{expt_llm}\",\n",
-    "    max_concurrency=2,\n",
-    "    metadata={\n",
-    "        \"llm\": expt_llm,\n",
-    "    },\n",
-    ")"
-   ]
+   "source": ["# Run base case\nexperiment_results_ = evaluate(\n    predict_base_case,\n    data=dataset_name,\n    evaluators=code_evalulator,\n    experiment_prefix=f\"test-without-langgraph-{expt_llm}\",\n    max_concurrency=2,\n    metadata={\n        \"llm\": expt_llm,\n    },\n)"]
   },
   {
    "cell_type": "code",
@@ -693,20 +236,7 @@
    "id": "71d90f9e-9dad-410c-a709-093d275029ae",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Run with langgraph\n",
-    "experiment_results = evaluate(\n",
-    "    predict_langgraph,\n",
-    "    data=dataset_name,\n",
-    "    evaluators=code_evalulator,\n",
-    "    experiment_prefix=f\"test-with-langgraph-{expt_llm}-{flag}\",\n",
-    "    max_concurrency=2,\n",
-    "    metadata={\n",
-    "        \"llm\": expt_llm,\n",
-    "        \"feedback\": flag,\n",
-    "    },\n",
-    ")"
-   ]
+   "source": ["# Run with langgraph\nexperiment_results = evaluate(\n    predict_langgraph,\n    data=dataset_name,\n    evaluators=code_evalulator,\n    experiment_prefix=f\"test-with-langgraph-{expt_llm}-{flag}\",\n    max_concurrency=2,\n    metadata={\n        \"llm\": expt_llm,\n        \"feedback\": flag,\n    },\n)"]
   },
   {
    "cell_type": "markdown",
@@ -728,7 +258,7 @@
    "id": "a42333c3-c098-4576-ae2a-0258de64ece2",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/code_assistant/langgraph_code_assistant_mistral.ipynb

@@ -33,9 +33,7 @@
    "id": "e501686f-323f-4b87-8f9c-8ba89133078b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "! pip install -U langchain_community langchain-mistralai langchain langgraph"
-   ]
+   "source": ["! pip install -U langchain_community langchain-mistralai langchain langgraph"]
   },
   {
    "cell_type": "markdown",
@@ -53,12 +51,7 @@
    "id": "982e4609-86e4-4934-828f-e03d89c20393",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"TOKENIZERS_PARALLELISM\"] = \"true\"\n",
-    "mistral_api_key = os.getenv(\"MISTRAL_API_KEY\")  # Ensure this is set"
-   ]
+   "source": ["import os\n\nos.environ[\"TOKENIZERS_PARALLELISM\"] = \"true\"\nmistral_api_key = os.getenv(\"MISTRAL_API_KEY\")  # Ensure this is set"]
   },
   {
    "cell_type": "markdown",
@@ -76,12 +69,7 @@
    "id": "37b172d2-3a9d-49a8-898c-22ed0cb45c88",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"Mistral-code-gen-testing\""
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\nos.environ[\"LANGCHAIN_API_KEY\"] = \"<your-api-key>\"\nos.environ[\"LANGCHAIN_PROJECT\"] = \"Mistral-code-gen-testing\""]
   },
   {
    "cell_type": "markdown",
@@ -99,42 +87,7 @@
    "id": "a188c8ca-c053-4e6d-b7af-38a3b6b371c7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Select LLM\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "from langchain_mistralai import ChatMistralAI\n",
-    "\n",
-    "mistral_model = \"mistral-large-latest\"\n",
-    "llm = ChatMistralAI(model=mistral_model, temperature=0)\n",
-    "\n",
-    "# Prompt\n",
-    "code_gen_prompt_claude = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"\"\"You are a coding assistant. Ensure any code you provide can be executed with all required imports and variables \\n\n",
-    "            defined. Structure your answer: 1) a prefix describing the code solution, 2) the imports, 3) the functioning code block.\n",
-    "            \\n Here is the user question:\"\"\",\n",
-    "        ),\n",
-    "        (\"placeholder\", \"{messages}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "\n",
-    "# Data model\n",
-    "class code(BaseModel):\n",
-    "    \"\"\"Code output\"\"\"\n",
-    "\n",
-    "    prefix: str = Field(description=\"Description of the problem and approach\")\n",
-    "    imports: str = Field(description=\"Code block import statements\")\n",
-    "    code: str = Field(description=\"Code block not including import statements\")\n",
-    "    description = \"Schema for code solutions to questions about LCEL.\"\n",
-    "\n",
-    "\n",
-    "# LLM\n",
-    "code_gen_chain = llm.with_structured_output(code, include_raw=False)"
-   ]
+   "source": ["# Select LLM\nfrom langchain_core.prompts import ChatPromptTemplate\nfrom langchain_core.pydantic_v1 import BaseModel, Field\nfrom langchain_mistralai import ChatMistralAI\n\nmistral_model = \"mistral-large-latest\"\nllm = ChatMistralAI(model=mistral_model, temperature=0)\n\n# Prompt\ncode_gen_prompt_claude = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"\"\"You are a coding assistant. Ensure any code you provide can be executed with all required imports and variables \\n\n            defined. Structure your answer: 1) a prefix describing the code solution, 2) the imports, 3) the functioning code block.\n            \\n Here is the user question:\"\"\",\n        ),\n        (\"placeholder\", \"{messages}\"),\n    ]\n)\n\n\n# Data model\nclass code(BaseModel):\n    \"\"\"Code output\"\"\"\n\n    prefix: str = Field(description=\"Description of the problem and approach\")\n    imports: str = Field(description=\"Code block import statements\")\n    code: str = Field(description=\"Code block not including import statements\")\n    description = \"Schema for code solutions to questions about LCEL.\"\n\n\n# LLM\ncode_gen_chain = llm.with_structured_output(code, include_raw=False)"]
   },
   {
    "cell_type": "code",
@@ -142,10 +95,7 @@
    "id": "9fc0290d-5a04-4514-8664-91f9dbf2da7b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "question = \"Write a function for fibonacci.\"\n",
-    "messages = [(\"user\", question)]"
-   ]
+   "source": ["question = \"Write a function for fibonacci.\"\nmessages = [(\"user\", question)]"]
   },
   {
    "cell_type": "code",
@@ -164,11 +114,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "# Test\n",
-    "result = code_gen_chain.invoke(messages)\n",
-    "result"
-   ]
+   "source": ["# Test\nresult = code_gen_chain.invoke(messages)\nresult"]
   },
   {
    "cell_type": "markdown",
@@ -184,28 +130,7 @@
    "id": "183d77b8-f180-4815-b39f-8ef507ec0534",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated, TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import AnyMessage, add_messages\n",
-    "\n",
-    "\n",
-    "class GraphState(TypedDict):\n",
-    "    \"\"\"\n",
-    "    Represents the state of our graph.\n",
-    "\n",
-    "    Attributes:\n",
-    "        error : Binary flag for control flow to indicate whether test error was tripped\n",
-    "        messages : With user question, error messages, reasoning\n",
-    "        generation : Code solution\n",
-    "        iterations : Number of tries\n",
-    "    \"\"\"\n",
-    "\n",
-    "    error: str\n",
-    "    messages: Annotated[list[AnyMessage], add_messages]\n",
-    "    generation: str\n",
-    "    iterations: int"
-   ]
+   "source": ["from typing import Annotated, TypedDict\n\nfrom langgraph.graph.message import AnyMessage, add_messages\n\n\nclass GraphState(TypedDict):\n    \"\"\"\n    Represents the state of our graph.\n\n    Attributes:\n        error : Binary flag for control flow to indicate whether test error was tripped\n        messages : With user question, error messages, reasoning\n        generation : Code solution\n        iterations : Number of tries\n    \"\"\"\n\n    error: str\n    messages: Annotated[list[AnyMessage], add_messages]\n    generation: str\n    iterations: int"]
   },
   {
    "cell_type": "markdown",
@@ -221,163 +146,7 @@
    "id": "14bc89d1-3ca6-4847-a048-1803e0e4600e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import uuid\n",
-    "\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "### Parameters\n",
-    "max_iterations = 3\n",
-    "\n",
-    "\n",
-    "### Nodes\n",
-    "def generate(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Generate a code solution\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        state (dict): New key added to state, generation\n",
-    "    \"\"\"\n",
-    "\n",
-    "    print(\"---GENERATING CODE SOLUTION---\")\n",
-    "\n",
-    "    # State\n",
-    "    messages = state[\"messages\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "\n",
-    "    # Solution\n",
-    "    code_solution = code_gen_chain.invoke(messages)\n",
-    "    messages += [\n",
-    "        (\n",
-    "            \"assistant\",\n",
-    "            f\"Here is my attempt to solve the problem: {code_solution.prefix} \\n Imports: {code_solution.imports} \\n Code: {code_solution.code}\",\n",
-    "        )\n",
-    "    ]\n",
-    "\n",
-    "    # Increment\n",
-    "    iterations = iterations + 1\n",
-    "    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n",
-    "\n",
-    "\n",
-    "def code_check(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Check code\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        state (dict): New key added to state, error\n",
-    "    \"\"\"\n",
-    "\n",
-    "    print(\"---CHECKING CODE---\")\n",
-    "\n",
-    "    # State\n",
-    "    messages = state[\"messages\"]\n",
-    "    code_solution = state[\"generation\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "\n",
-    "    # Get solution components\n",
-    "    imports = code_solution.imports\n",
-    "    code = code_solution.code\n",
-    "\n",
-    "    # Check imports\n",
-    "    try:\n",
-    "        exec(imports)\n",
-    "    except Exception as e:\n",
-    "        print(\"---CODE IMPORT CHECK: FAILED---\")\n",
-    "        error_message = [\n",
-    "            (\n",
-    "                \"user\",\n",
-    "                f\"Your solution failed the import test. Here is the error: {e}. Reflect on this error and your prior attempt to solve the problem. (1) State what you think went wrong with the prior solution and (2) try to solve this problem again. Return the FULL SOLUTION. Use the code tool to structure the output with a prefix, imports, and code block:\",\n",
-    "            )\n",
-    "        ]\n",
-    "        messages += error_message\n",
-    "        return {\n",
-    "            \"generation\": code_solution,\n",
-    "            \"messages\": messages,\n",
-    "            \"iterations\": iterations,\n",
-    "            \"error\": \"yes\",\n",
-    "        }\n",
-    "\n",
-    "    # Check execution\n",
-    "    try:\n",
-    "        combined_code = f\"{imports}\\n{code}\"\n",
-    "        print(f\"CODE TO TEST: {combined_code}\")\n",
-    "        # Use a shared scope for exec\n",
-    "        global_scope = {}\n",
-    "        exec(combined_code, global_scope)\n",
-    "    except Exception as e:\n",
-    "        print(\"---CODE BLOCK CHECK: FAILED---\")\n",
-    "        error_message = [\n",
-    "            (\n",
-    "                \"user\",\n",
-    "                f\"Your solution failed the code execution test: {e}) Reflect on this error and your prior attempt to solve the problem. (1) State what you think went wrong with the prior solution and (2) try to solve this problem again. Return the FULL SOLUTION. Use the code tool to structure the output with a prefix, imports, and code block:\",\n",
-    "            )\n",
-    "        ]\n",
-    "        messages += error_message\n",
-    "        return {\n",
-    "            \"generation\": code_solution,\n",
-    "            \"messages\": messages,\n",
-    "            \"iterations\": iterations,\n",
-    "            \"error\": \"yes\",\n",
-    "        }\n",
-    "\n",
-    "    # No errors\n",
-    "    print(\"---NO CODE TEST FAILURES---\")\n",
-    "    return {\n",
-    "        \"generation\": code_solution,\n",
-    "        \"messages\": messages,\n",
-    "        \"iterations\": iterations,\n",
-    "        \"error\": \"no\",\n",
-    "    }\n",
-    "\n",
-    "\n",
-    "### Conditional edges\n",
-    "\n",
-    "\n",
-    "def decide_to_finish(state: GraphState):\n",
-    "    \"\"\"\n",
-    "    Determines whether to finish.\n",
-    "\n",
-    "    Args:\n",
-    "        state (dict): The current graph state\n",
-    "\n",
-    "    Returns:\n",
-    "        str: Next node to call\n",
-    "    \"\"\"\n",
-    "    error = state[\"error\"]\n",
-    "    iterations = state[\"iterations\"]\n",
-    "\n",
-    "    if error == \"no\" or iterations == max_iterations:\n",
-    "        print(\"---DECISION: FINISH---\")\n",
-    "        return \"end\"\n",
-    "    else:\n",
-    "        print(\"---DECISION: RE-TRY SOLUTION---\")\n",
-    "        return \"generate\"\n",
-    "\n",
-    "\n",
-    "### Utilities\n",
-    "\n",
-    "\n",
-    "def _print_event(event: dict, _printed: set, max_length=1500):\n",
-    "    current_state = event.get(\"dialog_state\")\n",
-    "    if current_state:\n",
-    "        print(\"Currently in: \", current_state[-1])\n",
-    "    message = event.get(\"messages\")\n",
-    "    if message:\n",
-    "        if isinstance(message, list):\n",
-    "            message = message[-1]\n",
-    "        if message.id not in _printed:\n",
-    "            msg_repr = message.pretty_repr(html=True)\n",
-    "            if len(msg_repr) > max_length:\n",
-    "                msg_repr = msg_repr[:max_length] + \" ... (truncated)\"\n",
-    "            print(msg_repr)\n",
-    "            _printed.add(message.id)"
-   ]
+   "source": ["import uuid\n\nfrom langchain_core.pydantic_v1 import BaseModel, Field\n\n### Parameters\nmax_iterations = 3\n\n\n### Nodes\ndef generate(state: GraphState):\n    \"\"\"\n    Generate a code solution\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, generation\n    \"\"\"\n\n    print(\"---GENERATING CODE SOLUTION---\")\n\n    # State\n    messages = state[\"messages\"]\n    iterations = state[\"iterations\"]\n\n    # Solution\n    code_solution = code_gen_chain.invoke(messages)\n    messages += [\n        (\n            \"assistant\",\n            f\"Here is my attempt to solve the problem: {code_solution.prefix} \\n Imports: {code_solution.imports} \\n Code: {code_solution.code}\",\n        )\n    ]\n\n    # Increment\n    iterations = iterations + 1\n    return {\"generation\": code_solution, \"messages\": messages, \"iterations\": iterations}\n\n\ndef code_check(state: GraphState):\n    \"\"\"\n    Check code\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        state (dict): New key added to state, error\n    \"\"\"\n\n    print(\"---CHECKING CODE---\")\n\n    # State\n    messages = state[\"messages\"]\n    code_solution = state[\"generation\"]\n    iterations = state[\"iterations\"]\n\n    # Get solution components\n    imports = code_solution.imports\n    code = code_solution.code\n\n    # Check imports\n    try:\n        exec(imports)\n    except Exception as e:\n        print(\"---CODE IMPORT CHECK: FAILED---\")\n        error_message = [\n            (\n                \"user\",\n                f\"Your solution failed the import test. Here is the error: {e}. Reflect on this error and your prior attempt to solve the problem. (1) State what you think went wrong with the prior solution and (2) try to solve this problem again. Return the FULL SOLUTION. Use the code tool to structure the output with a prefix, imports, and code block:\",\n            )\n        ]\n        messages += error_message\n        return {\n            \"generation\": code_solution,\n            \"messages\": messages,\n            \"iterations\": iterations,\n            \"error\": \"yes\",\n        }\n\n    # Check execution\n    try:\n        combined_code = f\"{imports}\\n{code}\"\n        print(f\"CODE TO TEST: {combined_code}\")\n        # Use a shared scope for exec\n        global_scope = {}\n        exec(combined_code, global_scope)\n    except Exception as e:\n        print(\"---CODE BLOCK CHECK: FAILED---\")\n        error_message = [\n            (\n                \"user\",\n                f\"Your solution failed the code execution test: {e}) Reflect on this error and your prior attempt to solve the problem. (1) State what you think went wrong with the prior solution and (2) try to solve this problem again. Return the FULL SOLUTION. Use the code tool to structure the output with a prefix, imports, and code block:\",\n            )\n        ]\n        messages += error_message\n        return {\n            \"generation\": code_solution,\n            \"messages\": messages,\n            \"iterations\": iterations,\n            \"error\": \"yes\",\n        }\n\n    # No errors\n    print(\"---NO CODE TEST FAILURES---\")\n    return {\n        \"generation\": code_solution,\n        \"messages\": messages,\n        \"iterations\": iterations,\n        \"error\": \"no\",\n    }\n\n\n### Conditional edges\n\n\ndef decide_to_finish(state: GraphState):\n    \"\"\"\n    Determines whether to finish.\n\n    Args:\n        state (dict): The current graph state\n\n    Returns:\n        str: Next node to call\n    \"\"\"\n    error = state[\"error\"]\n    iterations = state[\"iterations\"]\n\n    if error == \"no\" or iterations == max_iterations:\n        print(\"---DECISION: FINISH---\")\n        return \"end\"\n    else:\n        print(\"---DECISION: RE-TRY SOLUTION---\")\n        return \"generate\"\n\n\n### Utilities\n\n\ndef _print_event(event: dict, _printed: set, max_length=1500):\n    current_state = event.get(\"dialog_state\")\n    if current_state:\n        print(\"Currently in: \", current_state[-1])\n    message = event.get(\"messages\")\n    if message:\n        if isinstance(message, list):\n            message = message[-1]\n        if message.id not in _printed:\n            msg_repr = message.pretty_repr(html=True)\n            if len(msg_repr) > max_length:\n                msg_repr = msg_repr[:max_length] + \" ... (truncated)\"\n            print(msg_repr)\n            _printed.add(message.id)"]
   },
   {
    "cell_type": "code",
@@ -385,31 +154,7 @@
    "id": "2dff2209-44c7-4e2c-b607-ba6675f9e45f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "builder = StateGraph(GraphState)\n",
-    "\n",
-    "# Define the nodes\n",
-    "builder.add_node(\"generate\", generate)  # generation solution\n",
-    "builder.add_node(\"check_code\", code_check)  # check code\n",
-    "\n",
-    "# Build graph\n",
-    "builder.set_entry_point(\"generate\")\n",
-    "builder.add_edge(\"generate\", \"check_code\")\n",
-    "builder.add_conditional_edges(\n",
-    "    \"check_code\",\n",
-    "    decide_to_finish,\n",
-    "    {\n",
-    "        \"end\": END,\n",
-    "        \"generate\": \"generate\",\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
-    "graph = builder.compile(checkpointer=memory)"
-   ]
+   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\nfrom langgraph.graph import END, StateGraph, START\n\nbuilder = StateGraph(GraphState)\n\n# Define the nodes\nbuilder.add_node(\"generate\", generate)  # generation solution\nbuilder.add_node(\"check_code\", code_check)  # check code\n\n# Build graph\nbuilder.add_edge(START, \"generate\")\nbuilder.add_edge(\"generate\", \"check_code\")\nbuilder.add_conditional_edges(\n    \"check_code\",\n    decide_to_finish,\n    {\n        \"end\": END,\n        \"generate\": \"generate\",\n    },\n)\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")\ngraph = builder.compile(checkpointer=memory)"]
   },
   {
    "cell_type": "code",
@@ -428,15 +173,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(graph.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(graph.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "code",
@@ -444,23 +181,7 @@
    "id": "242aa2f0-2c31-462f-a958-ff9ae0cf7c62",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "_printed = set()\n",
-    "thread_id = str(uuid.uuid4())\n",
-    "config = {\n",
-    "    \"configurable\": {\n",
-    "        # Checkpoints are accessed by thread_id\n",
-    "        \"thread_id\": thread_id,\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "question = \"Write a Python program that prints 'Hello, World!' to the console.\"\n",
-    "events = graph.stream(\n",
-    "    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n",
-    ")\n",
-    "for event in events:\n",
-    "    _print_event(event, _printed)"
-   ]
+   "source": ["_printed = set()\nthread_id = str(uuid.uuid4())\nconfig = {\n    \"configurable\": {\n        # Checkpoints are accessed by thread_id\n        \"thread_id\": thread_id,\n    }\n}\n\nquestion = \"Write a Python program that prints 'Hello, World!' to the console.\"\nevents = graph.stream(\n    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n)\nfor event in events:\n    _print_event(event, _printed)"]
   },
   {
    "cell_type": "markdown",
@@ -478,31 +199,7 @@
    "id": "390b2768-f395-4aea-8b0e-9d36212a31ac",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "_printed = set()\n",
-    "thread_id = str(uuid.uuid4())\n",
-    "config = {\n",
-    "    \"configurable\": {\n",
-    "        # Checkpoints are accessed by thread_id\n",
-    "        \"thread_id\": thread_id,\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "question = \"\"\"Create a Python program that checks if a given string is a palindrome. A palindrome is a word, phrase, number, or other sequence of characters that reads the same forward and backward (ignoring spaces, punctuation, and capitalization).\n",
-    "\n",
-    "Requirements:\n",
-    "The program should define a function is_palindrome(s) that takes a string s as input.\n",
-    "The function should return True if the string is a palindrome and False otherwise.\n",
-    "Ignore spaces, punctuation, and case differences when checking for palindromes.\n",
-    "\n",
-    "Give an example of it working on an example input word.\"\"\"\n",
-    "\n",
-    "events = graph.stream(\n",
-    "    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n",
-    ")\n",
-    "for event in events:\n",
-    "    _print_event(event, _printed)"
-   ]
+   "source": ["_printed = set()\nthread_id = str(uuid.uuid4())\nconfig = {\n    \"configurable\": {\n        # Checkpoints are accessed by thread_id\n        \"thread_id\": thread_id,\n    }\n}\n\nquestion = \"\"\"Create a Python program that checks if a given string is a palindrome. A palindrome is a word, phrase, number, or other sequence of characters that reads the same forward and backward (ignoring spaces, punctuation, and capitalization).\n\nRequirements:\nThe program should define a function is_palindrome(s) that takes a string s as input.\nThe function should return True if the string is a palindrome and False otherwise.\nIgnore spaces, punctuation, and case differences when checking for palindromes.\n\nGive an example of it working on an example input word.\"\"\"\n\nevents = graph.stream(\n    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n)\nfor event in events:\n    _print_event(event, _printed)"]
   },
   {
    "cell_type": "markdown",
@@ -520,26 +217,7 @@
    "id": "0a3f946b-e2f2-44d9-905b-09f36980cf9f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "_printed = set()\n",
-    "thread_id = str(uuid.uuid4())\n",
-    "config = {\n",
-    "    \"configurable\": {\n",
-    "        # Checkpoints are accessed by thread_id\n",
-    "        \"thread_id\": thread_id,\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "question = \"\"\"Write a program that prints the numbers from 1 to 100. \n",
-    "But for multiples of three, print \"Fizz\" instead of the number, and for the multiples of five, print \"Buzz\". \n",
-    "For numbers which are multiples of both three and five, print \"FizzBuzz\".\"\"\"\n",
-    "\n",
-    "events = graph.stream(\n",
-    "    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n",
-    ")\n",
-    "for event in events:\n",
-    "    _print_event(event, _printed)"
-   ]
+   "source": ["_printed = set()\nthread_id = str(uuid.uuid4())\nconfig = {\n    \"configurable\": {\n        # Checkpoints are accessed by thread_id\n        \"thread_id\": thread_id,\n    }\n}\n\nquestion = \"\"\"Write a program that prints the numbers from 1 to 100. \nBut for multiples of three, print \"Fizz\" instead of the number, and for the multiples of five, print \"Buzz\". \nFor numbers which are multiples of both three and five, print \"FizzBuzz\".\"\"\"\n\nevents = graph.stream(\n    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n)\nfor event in events:\n    _print_event(event, _printed)"]
   },
   {
    "cell_type": "markdown",
@@ -557,37 +235,7 @@
    "id": "2bb883df-540b-46ab-9415-fe27db68456f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import uuid\n",
-    "\n",
-    "_printed = set()\n",
-    "thread_id = str(uuid.uuid4())\n",
-    "config = {\n",
-    "    \"configurable\": {\n",
-    "        # Checkpoints are accessed by thread_id\n",
-    "        \"thread_id\": thread_id,\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "question = \"\"\"I want to vectorize a function\n",
-    "\n",
-    "        frame = np.zeros((out_h, out_w, 3), dtype=np.uint8)\n",
-    "        for i, val1 in enumerate(rows):\n",
-    "            for j, val2 in enumerate(cols):\n",
-    "                for j, val3 in enumerate(ch):\n",
-    "                    # Assuming you want to store the pair as tuples in the matrix\n",
-    "                    frame[i, j, k] = image[val1, val2, val3]\n",
-    "\n",
-    "        out.write(np.array(frame))\n",
-    "\n",
-    "with a simple numpy function that does something like this what is it called. Show me a test case with this working.\"\"\"\n",
-    "\n",
-    "events = graph.stream(\n",
-    "    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n",
-    ")\n",
-    "for event in events:\n",
-    "    _print_event(event, _printed)"
-   ]
+   "source": ["import uuid\n\n_printed = set()\nthread_id = str(uuid.uuid4())\nconfig = {\n    \"configurable\": {\n        # Checkpoints are accessed by thread_id\n        \"thread_id\": thread_id,\n    }\n}\n\nquestion = \"\"\"I want to vectorize a function\n\n        frame = np.zeros((out_h, out_w, 3), dtype=np.uint8)\n        for i, val1 in enumerate(rows):\n            for j, val2 in enumerate(cols):\n                for j, val3 in enumerate(ch):\n                    # Assuming you want to store the pair as tuples in the matrix\n                    frame[i, j, k] = image[val1, val2, val3]\n\n        out.write(np.array(frame))\n\nwith a simple numpy function that does something like this what is it called. Show me a test case with this working.\"\"\"\n\nevents = graph.stream(\n    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n)\nfor event in events:\n    _print_event(event, _printed)"]
   },
   {
    "cell_type": "markdown",
@@ -605,34 +253,7 @@
    "id": "ee05da1f-c272-405d-8a7b-552cfc3106e1",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "_printed = set()\n",
-    "thread_id = str(uuid.uuid4())\n",
-    "config = {\n",
-    "    \"configurable\": {\n",
-    "        # Checkpoints are accessed by thread_id\n",
-    "        \"thread_id\": thread_id,\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "question = \"\"\"Create a Python program that allows two players to play a game of Tic-Tac-Toe. The game should be played on a 3x3 grid. The program should:\n",
-    "\n",
-    "- Allow players to take turns to input their moves.\n",
-    "- Check for invalid moves (e.g., placing a marker on an already occupied space).\n",
-    "- Determine and announce the winner or if the game ends in a draw.\n",
-    "\n",
-    "Requirements:\n",
-    "- Use a 2D list to represent the Tic-Tac-Toe board.\n",
-    "- Use functions to modularize the code.\n",
-    "- Validate player input.\n",
-    "- Check for win conditions and draw conditions after each move.\"\"\"\n",
-    "\n",
-    "events = graph.stream(\n",
-    "    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n",
-    ")\n",
-    "for event in events:\n",
-    "    _print_event(event, _printed)"
-   ]
+   "source": ["_printed = set()\nthread_id = str(uuid.uuid4())\nconfig = {\n    \"configurable\": {\n        # Checkpoints are accessed by thread_id\n        \"thread_id\": thread_id,\n    }\n}\n\nquestion = \"\"\"Create a Python program that allows two players to play a game of Tic-Tac-Toe. The game should be played on a 3x3 grid. The program should:\n\n- Allow players to take turns to input their moves.\n- Check for invalid moves (e.g., placing a marker on an already occupied space).\n- Determine and announce the winner or if the game ends in a draw.\n\nRequirements:\n- Use a 2D list to represent the Tic-Tac-Toe board.\n- Use functions to modularize the code.\n- Validate player input.\n- Check for win conditions and draw conditions after each move.\"\"\"\n\nevents = graph.stream(\n    {\"messages\": [(\"user\", question)], \"iterations\": 0}, config, stream_mode=\"values\"\n)\nfor event in events:\n    _print_event(event, _printed)"]
   },
   {
    "cell_type": "markdown",
@@ -650,7 +271,7 @@
    "id": "814fc2a4-8e5b-4faa-8f52-3977226bd09a",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/configuration.ipynb

@@ -28,35 +28,7 @@
    "id": "816523d0-0b59-47cf-9f4c-4838024efe22",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_core.messages import BaseMessage, HumanMessage\n",
-    "\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "model = ChatAnthropic(model_name=\"claude-2.1\")\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
-    "\n",
-    "\n",
-    "def _call_model(state):\n",
-    "    response = model.invoke(state[\"messages\"])\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"model\", _call_model)\n",
-    "workflow.set_entry_point(\"model\")\n",
-    "workflow.add_edge(\"model\", END)\n",
-    "\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_core.messages import BaseMessage, HumanMessage\n\nfrom langgraph.graph import END, StateGraph, START\n\nmodel = ChatAnthropic(model_name=\"claude-2.1\")\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]\n\n\ndef _call_model(state):\n    response = model.invoke(state[\"messages\"])\n    return {\"messages\": [response]}\n\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"model\", _call_model)\nworkflow.add_edge(START, \"model\")\nworkflow.add_edge(\"model\", END)\n\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -76,9 +48,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"
-   ]
+   "source": ["app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"]
   },
   {
    "cell_type": "markdown",
@@ -98,31 +68,7 @@
    "id": "c01f1e7c-8e8b-4e26-98f7-56ac225077b4",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "openai_model = ChatOpenAI()\n",
-    "\n",
-    "models = {\n",
-    "    \"anthropic\": model,\n",
-    "    \"openai\": openai_model,\n",
-    "}\n",
-    "\n",
-    "\n",
-    "def _call_model(state, config):\n",
-    "    m = models[config[\"configurable\"].get(\"model\", \"anthropic\")]\n",
-    "    response = m.invoke(state[\"messages\"])\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"model\", _call_model)\n",
-    "workflow.set_entry_point(\"model\")\n",
-    "workflow.add_edge(\"model\", END)\n",
-    "\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nopenai_model = ChatOpenAI()\n\nmodels = {\n    \"anthropic\": model,\n    \"openai\": openai_model,\n}\n\n\ndef _call_model(state, config):\n    m = models[config[\"configurable\"].get(\"model\", \"anthropic\")]\n    response = m.invoke(state[\"messages\"])\n    return {\"messages\": [response]}\n\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"model\", _call_model)\nworkflow.add_edge(START, \"model\")\nworkflow.add_edge(\"model\", END)\n\napp = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -150,9 +96,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"
-   ]
+   "source": ["app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"]
   },
   {
    "cell_type": "markdown",
@@ -180,10 +124,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "config = {\"configurable\": {\"model\": \"openai\"}}\n",
-    "app.invoke({\"messages\": [HumanMessage(content=\"hi\")]}, config=config)"
-   ]
+   "source": ["config = {\"configurable\": {\"model\": \"openai\"}}\napp.invoke({\"messages\": [HumanMessage(content=\"hi\")]}, config=config)"]
   },
   {
    "cell_type": "markdown",
@@ -199,29 +140,7 @@
    "id": "f0393a43-9fbe-4056-972f-3e91ea329041",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import SystemMessage\n",
-    "\n",
-    "\n",
-    "def _call_model(state, config):\n",
-    "    m = models[config[\"configurable\"].get(\"model\", \"anthropic\")]\n",
-    "    messages = state[\"messages\"]\n",
-    "    if \"system_message\" in config[\"configurable\"]:\n",
-    "        messages = [\n",
-    "            SystemMessage(content=config[\"configurable\"][\"system_message\"])\n",
-    "        ] + messages\n",
-    "    response = m.invoke(messages)\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"model\", _call_model)\n",
-    "workflow.set_entry_point(\"model\")\n",
-    "workflow.add_edge(\"model\", END)\n",
-    "\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langchain_core.messages import SystemMessage\n\n\ndef _call_model(state, config):\n    m = models[config[\"configurable\"].get(\"model\", \"anthropic\")]\n    messages = state[\"messages\"]\n    if \"system_message\" in config[\"configurable\"]:\n        messages = [\n            SystemMessage(content=config[\"configurable\"][\"system_message\"])\n        ] + messages\n    response = m.invoke(messages)\n    return {\"messages\": [response]}\n\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"model\", _call_model)\nworkflow.add_edge(START, \"model\")\nworkflow.add_edge(\"model\", END)\n\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -241,9 +160,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"
-   ]
+   "source": ["app.invoke({\"messages\": [HumanMessage(content=\"hi\")]})"]
   },
   {
    "cell_type": "code",
@@ -263,10 +180,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "config = {\"configurable\": {\"system_message\": \"respond in italian\"}}\n",
-    "app.invoke({\"messages\": [HumanMessage(content=\"hi\")]}, config=config)"
-   ]
+   "source": ["config = {\"configurable\": {\"system_message\": \"respond in italian\"}}\napp.invoke({\"messages\": [HumanMessage(content=\"hi\")]}, config=config)"]
   },
   {
    "cell_type": "code",
@@ -274,7 +188,7 @@
    "id": "a5c5f7f4-4b0e-4cde-93a6-c1c6329b8591",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/create-react-agent-hitl.ipynb

@@ -113,7 +113,9 @@
     "\n",
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
-    "graph = create_react_agent(model, tools=tools, interrupt_before=[\"tools\"], checkpointer=memory)"
+    "graph = create_react_agent(\n",
+    "    model, tools=tools, interrupt_before=[\"tools\"], checkpointer=memory\n",
+    ")"
    ]
   },
   {

examples/docs/quickstart.ipynb

@@ -12,46 +12,21 @@
    "execution_count": 13,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain-openai"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain-openai"]
   },
   {
    "cell_type": "code",
    "execution_count": 14,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "if not os.environ.get(\"OPENAI_API_KEY\"):\n",
-    "    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nif not os.environ.get(\"OPENAI_API_KEY\"):\n    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"]
   },
   {
    "cell_type": "code",
    "execution_count": 15,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import BaseMessage, HumanMessage\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "from langgraph.graph import END, MessageGraph\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)\n",
-    "\n",
-    "graph = MessageGraph()\n",
-    "\n",
-    "graph.add_node(\"oracle\", model)\n",
-    "graph.add_edge(\"oracle\", END)\n",
-    "\n",
-    "graph.set_entry_point(\"oracle\")\n",
-    "\n",
-    "runnable = graph.compile()"
-   ]
+   "source": ["from langchain_core.messages import BaseMessage, HumanMessage\nfrom langchain_openai import ChatOpenAI\n\nfrom langgraph.graph import END, MessageGraph\n\nmodel = ChatOpenAI(temperature=0)\n\ngraph = MessageGraph()\n\ngraph.add_node(\"oracle\", model)\ngraph.add_edge(\"oracle\", END)\n\ngraph.add_edge(START, \"oracle\")\n\nrunnable = graph.compile()"]
   },
   {
    "cell_type": "code",
@@ -69,15 +44,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(runnable.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(runnable.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "code",
@@ -96,54 +63,14 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "runnable.invoke(HumanMessage(\"What is 1 + 1?\"))"
-   ]
+   "source": ["runnable.invoke(HumanMessage(\"What is 1 + 1?\"))"]
   },
   {
    "cell_type": "code",
    "execution_count": 18,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "from langgraph.graph import END, START\n",
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def multiply(first_number: int, second_number: int):\n",
-    "    \"\"\"Multiplies two numbers together.\"\"\"\n",
-    "    return first_number * second_number\n",
-    "\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)\n",
-    "model_with_tools = model.bind_tools(tools=[multiply])\n",
-    "\n",
-    "graph = MessageGraph()\n",
-    "\n",
-    "graph.add_node(\"oracle\", model_with_tools)\n",
-    "\n",
-    "tool_node = ToolNode([multiply])\n",
-    "graph.add_node(\"multiply\", tool_node)\n",
-    "graph.add_edge(START, \"oracle\")\n",
-    "graph.add_edge(\"multiply\", END)\n",
-    "\n",
-    "\n",
-    "def router(state: list[BaseMessage]) -> Literal[\"multiply\", \"__end__\"]:\n",
-    "    tool_calls = state[-1].additional_kwargs.get(\"tool_calls\", [])\n",
-    "    if len(tool_calls):\n",
-    "        return \"multiply\"\n",
-    "    else:\n",
-    "        return END\n",
-    "\n",
-    "\n",
-    "graph.add_conditional_edges(\"oracle\", router)\n",
-    "runnable = graph.compile()"
-   ]
+   "source": ["from typing import Literal\n\nfrom langchain_core.tools import tool\n\nfrom langgraph.graph import END, START\nfrom langgraph.prebuilt import ToolNode\n\n\n@tool\ndef multiply(first_number: int, second_number: int):\n    \"\"\"Multiplies two numbers together.\"\"\"\n    return first_number * second_number\n\n\nmodel = ChatOpenAI(temperature=0)\nmodel_with_tools = model.bind_tools(tools=[multiply])\n\ngraph = MessageGraph()\n\ngraph.add_node(\"oracle\", model_with_tools)\n\ntool_node = ToolNode([multiply])\ngraph.add_node(\"multiply\", tool_node)\ngraph.add_edge(START, \"oracle\")\ngraph.add_edge(\"multiply\", END)\n\n\ndef router(state: list[BaseMessage]) -> Literal[\"multiply\", \"__end__\"]:\n    tool_calls = state[-1].additional_kwargs.get(\"tool_calls\", [])\n    if len(tool_calls):\n        return \"multiply\"\n    else:\n        return END\n\n\ngraph.add_conditional_edges(\"oracle\", router)\nrunnable = graph.compile()"]
   },
   {
    "cell_type": "code",
@@ -161,13 +88,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "try:\n",
-    "    display(Image(runnable.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["try:\n    display(Image(runnable.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "code",
@@ -187,9 +108,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "runnable.invoke(HumanMessage(\"What is 123 * 456?\"))"
-   ]
+   "source": ["runnable.invoke(HumanMessage(\"What is 123 * 456?\"))"]
   },
   {
    "cell_type": "code",
@@ -208,16 +127,14 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "runnable.invoke(HumanMessage(\"What is your name?\"))"
-   ]
+   "source": ["runnable.invoke(HumanMessage(\"What is your name?\"))"]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/dynamically-returning-directly.ipynb

@@ -28,10 +28,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_community langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -47,19 +44,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")\n",
-    "_set_env(\"TAVILY_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"OPENAI_API_KEY\")\n_set_env(\"TAVILY_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -75,10 +60,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -104,19 +86,7 @@
    "id": "4a1b9990-3b11-4a51-bd51-76117afd38b9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class SearchTool(BaseModel):\n",
-    "    \"\"\"Look up things online, optionally returning directly\"\"\"\n",
-    "\n",
-    "    query: str = Field(description=\"query to look up online\")\n",
-    "    return_direct: bool = Field(\n",
-    "        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n",
-    "        default=False,\n",
-    "    )"
-   ]
+   "source": ["from langchain_core.pydantic_v1 import BaseModel, Field\n\n\nclass SearchTool(BaseModel):\n    \"\"\"Look up things online, optionally returning directly\"\"\"\n\n    query: str = Field(description=\"query to look up online\")\n    return_direct: bool = Field(\n        description=\"Whether or the result of this should be returned directly to the user without you seeing what it is\",\n        default=False,\n    )"]
   },
   {
    "cell_type": "code",
@@ -124,12 +94,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "search_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\n",
-    "tools = [search_tool]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\nsearch_tool = TavilySearchResults(max_results=1, args_schema=SearchTool)\ntools = [search_tool]"]
   },
   {
    "cell_type": "markdown",
@@ -147,11 +112,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -175,11 +136,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -197,9 +154,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -226,14 +181,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, TypedDict\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[list, operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, TypedDict\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[list, operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -268,11 +216,7 @@
    "id": "03308b6b-de72-4cdc-b6c6-47e654df340e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation"]
   },
   {
    "cell_type": "markdown",
@@ -290,22 +234,7 @@
    "id": "55e088b1-f3c8-4798-9ca8-5b0be961b49a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we check if it's suppose to return direct\n",
-    "    else:\n",
-    "        arguments = last_message.tool_calls[0][\"args\"]\n",
-    "        if arguments.get(\"return_direct\", False):\n",
-    "            return \"final\"\n",
-    "        else:\n",
-    "            return \"continue\""
-   ]
+   "source": ["# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we check if it's suppose to return direct\n    else:\n        arguments = last_message.tool_calls[0][\"args\"]\n        if arguments.get(\"return_direct\", False):\n            return \"final\"\n        else:\n            return \"continue\""]
   },
   {
    "cell_type": "code",
@@ -313,14 +242,7 @@
    "id": "2b45da72-1afa-4cd7-9b7f-49a7c99cdb8a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -338,33 +260,7 @@
    "id": "dd876f5d-88d6-4f93-b1d0-f2f0b6f4d991",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    tool_name = tool_call[\"name\"]\n",
-    "    arguments = tool_call[\"args\"]\n",
-    "    if tool_name == \"tavily_search_results_json\":\n",
-    "        if \"return_direct\" in arguments:\n",
-    "            del arguments[\"return_direct\"]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_name,\n",
-    "        tool_input=arguments,\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a ToolMessage\n",
-    "    tool_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [tool_message]}"
-   ]
+   "source": ["# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    tool_name = tool_call[\"name\"]\n    arguments = tool_call[\"args\"]\n    if tool_name == \"tavily_search_results_json\":\n        if \"return_direct\" in arguments:\n            del arguments[\"return_direct\"]\n    action = ToolInvocation(\n        tool=tool_name,\n        tool_input=arguments,\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a ToolMessage\n    tool_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [tool_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -386,56 +282,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "\n",
-    "# Note the \"action\" and \"final\" nodes are identical!\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "workflow.add_node(\"final\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Final call\n",
-    "        \"final\": \"final\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "workflow.add_edge(\"final\", END)\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\n\n# Note the \"action\" and \"final\" nodes are identical!\nworkflow.add_node(\"action\", call_tool)\nworkflow.add_node(\"final\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Final call\n        \"final\": \"final\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\nworkflow.add_edge(\"final\", END)\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -454,11 +301,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph(xray=True).draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph(xray=True).draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -502,18 +345,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -563,22 +395,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\n",
-    "    \"messages\": [\n",
-    "        HumanMessage(\n",
-    "            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n",
-    "        )\n",
-    "    ]\n",
-    "}\n",
-    "for output in app.stream(inputs, stream_mode=\"values\"):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for message in output[\"messages\"]:\n",
-    "        message.pretty_print()\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\n    \"messages\": [\n        HumanMessage(\n            content=\"what is the weather in sf? return this result directly by setting return_direct = True\"\n        )\n    ]\n}\nfor output in app.stream(inputs, stream_mode=\"values\"):\n    # stream() yields dictionaries with output keyed by node name\n    for message in output[\"messages\"]:\n        message.pretty_print()\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -586,7 +403,7 @@
    "id": "49ccc134-4abe-4982-8ecd-d70fc56a4d2d",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/extraction/retries.ipynb

@@ -114,7 +114,7 @@
     ")\n",
     "from typing_extensions import TypedDict\n",
     "\n",
-    "from langgraph.graph import StateGraph\n",
+    "from langgraph.graph import StateGraph, START, END\n",
     "from langgraph.graph.message import add_messages\n",
     "from langgraph.prebuilt import ValidationNode\n",
     "\n",
@@ -273,7 +273,7 @@
     "    builder.add_node(\"finalizer\", Finalizer(retry_strategy.get(\"aggregate_messages\")))\n",
     "\n",
     "    # Define the connectivity\n",
-    "    builder.set_entry_point(\"count_messages\")\n",
+    "    builder.add_edge(START, \"count_messages\")\n",
     "    builder.add_edge(\"count_messages\", \"llm\")\n",
     "\n",
     "    def route_validator(state: State) -> Literal[\"validator\", \"__end__\"]:\n",
@@ -299,7 +299,7 @@
     "\n",
     "    builder.add_conditional_edges(\"validator\", route_validation)\n",
     "\n",
-    "    builder.set_finish_point(\"finalizer\")\n",
+    "    builder.add_edge(\"finalizer\", END)\n",
     "\n",
     "    # These functions let the step be used in a MessageGraph\n",
     "    # or a StateGraph with 'messages' as the key.\n",
@@ -1036,7 +1036,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.1"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

examples/force-calling-a-tool-first.ipynb

@@ -26,10 +26,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain langchain_openai tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain langchain_openai tavily-python"]
   },
   {
    "cell_type": "markdown",
@@ -45,13 +42,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -67,10 +58,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -90,11 +78,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -112,11 +96,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -140,13 +120,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# We will set streaming=True so that we can stream tokens\n",
-    "# See the streaming section for more information on this.\n",
-    "model = ChatOpenAI(temperature=0, streaming=True)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\n# We will set streaming=True so that we can stream tokens\n# See the streaming section for more information on this.\nmodel = ChatOpenAI(temperature=0, streaming=True)"]
   },
   {
    "cell_type": "markdown",
@@ -164,9 +138,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -192,16 +164,7 @@
    "id": "ea793afa-2eab-4901-910d-6eed90cd6564",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import operator\n",
-    "from typing import Annotated, Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import BaseMessage\n",
-    "\n",
-    "\n",
-    "class AgentState(TypedDict):\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]"
-   ]
+   "source": ["import operator\nfrom typing import Annotated, Sequence, TypedDict\n\nfrom langchain_core.messages import BaseMessage\n\n\nclass AgentState(TypedDict):\n    messages: Annotated[Sequence[BaseMessage], operator.add]"]
   },
   {
    "cell_type": "markdown",
@@ -236,66 +199,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation for each tool call\n",
-    "    tool_invocations = []\n",
-    "    for tool_call in last_message.tool_calls:\n",
-    "        action = ToolInvocation(\n",
-    "            tool=tool_call[\"name\"],\n",
-    "            tool_input=tool_call[\"args\"],\n",
-    "        )\n",
-    "        tool_invocations.append(action)\n",
-    "\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n",
-    "    # We use the response to create tool messages\n",
-    "    tool_messages = [\n",
-    "        ToolMessage(\n",
-    "            content=str(response),\n",
-    "            name=tc[\"name\"],\n",
-    "            tool_call_id=tc[\"id\"],\n",
-    "        )\n",
-    "        for tc, response in zip(last_message.tool_calls, responses)\n",
-    "    ]\n",
-    "\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": tool_messages}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation for each tool call\n    tool_invocations = []\n    for tool_call in last_message.tool_calls:\n        action = ToolInvocation(\n            tool=tool_call[\"name\"],\n            tool_input=tool_call[\"args\"],\n        )\n        tool_invocations.append(action)\n\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    responses = tool_executor.batch(tool_invocations, return_exceptions=True)\n    # We use the response to create tool messages\n    tool_messages = [\n        ToolMessage(\n            content=str(response),\n            name=tc[\"name\"],\n            tool_call_id=tc[\"id\"],\n        )\n        for tc, response in zip(last_message.tool_calls, responses)\n    ]\n\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": tool_messages}"]
   },
   {
    "cell_type": "markdown",
@@ -313,30 +217,7 @@
    "id": "1bfd2b22-292a-4f4d-91a0-46bb704f5e38",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# This is the new first - the first call of the model we want to explicitly hard-code some action\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "def first_model(state):\n",
-    "    human_input = state[\"messages\"][-1].content\n",
-    "    return {\n",
-    "        \"messages\": [\n",
-    "            AIMessage(\n",
-    "                content=\"\",\n",
-    "                tool_calls=[\n",
-    "                    {\n",
-    "                        \"name\": \"tavily_search_results_json\",\n",
-    "                        \"args\": {\n",
-    "                            \"query\": human_input,\n",
-    "                        },\n",
-    "                        \"id\": \"tool_abcd123\",\n",
-    "                    }\n",
-    "                ],\n",
-    "            )\n",
-    "        ]\n",
-    "    }"
-   ]
+   "source": ["# This is the new first - the first call of the model we want to explicitly hard-code some action\nfrom langchain_core.messages import AIMessage\n\n\ndef first_model(state):\n    human_input = state[\"messages\"][-1].content\n    return {\n        \"messages\": [\n            AIMessage(\n                content=\"\",\n                tool_calls=[\n                    {\n                        \"name\": \"tavily_search_results_json\",\n                        \"args\": {\n                            \"query\": human_input,\n                        },\n                        \"id\": \"tool_abcd123\",\n                    }\n                ],\n            )\n        ]\n    }"]
   },
   {
    "cell_type": "markdown",
@@ -358,56 +239,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(AgentState)\n",
-    "\n",
-    "# Define the new entrypoint\n",
-    "workflow.add_node(\"first_agent\", first_model)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"first_agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# After we call the first agent, we know we want to go to action\n",
-    "workflow.add_edge(\"first_agent\", \"action\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(AgentState)\n\n# Define the new entrypoint\nworkflow.add_node(\"first_agent\", first_model)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"first_agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# After we call the first agent, we know we want to go to action\nworkflow.add_edge(\"first_agent\", \"action\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -426,15 +258,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "try:\n",
-    "    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\n",
-    "except Exception:\n",
-    "    # This requires some extra dependencies and is optional\n",
-    "    pass"
-   ]
+   "source": ["from IPython.display import Image, display\n\ntry:\n    display(Image(app.get_graph(xray=True).draw_mermaid_png()))\nexcept Exception:\n    # This requires some extra dependencies and is optional\n    pass"]
   },
   {
    "cell_type": "markdown",
@@ -478,18 +302,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
-    "for output in app.stream(inputs):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for key, value in output.items():\n",
-    "        print(f\"Output from node '{key}':\")\n",
-    "        print(\"---\")\n",
-    "        print(value)\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\nfor output in app.stream(inputs):\n    # stream() yields dictionaries with output keyed by node name\n    for key, value in output.items():\n        print(f\"Output from node '{key}':\")\n        print(\"---\")\n        print(value)\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -497,7 +310,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/human-in-the-loop.ipynb

@@ -39,10 +39,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_openai"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_openai"]
   },
   {
    "cell_type": "markdown",
@@ -58,18 +55,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"OPENAI_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -85,10 +71,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -106,22 +89,7 @@
    "id": "6098e5cb",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# `add_messages`` essentially does this\n",
-    "# (with more robust handling)\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# `add_messages`` essentially does this\n# (with more robust handling)\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -141,22 +109,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder for the actual implementation\n",
-    "    # Don't let the LLM know this though 😊\n",
-    "    return [\n",
-    "        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n",
-    "    ]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder for the actual implementation\n    # Don't let the LLM know this though 😊\n    return [\n        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n    ]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -174,11 +127,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolExecutor\n",
-    "\n",
-    "tool_executor = ToolExecutor(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolExecutor\n\ntool_executor = ToolExecutor(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -199,11 +148,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -221,9 +166,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -258,53 +201,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.messages import ToolMessage\n",
-    "\n",
-    "from langgraph.prebuilt import ToolInvocation\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\"\n",
-    "\n",
-    "\n",
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    response = model.invoke(messages)\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}\n",
-    "\n",
-    "\n",
-    "# Define the function to execute tools\n",
-    "def call_tool(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    # Based on the continue condition\n",
-    "    # we know the last message involves a function call\n",
-    "    last_message = messages[-1]\n",
-    "    # We construct an ToolInvocation from the function_call\n",
-    "    tool_call = last_message.tool_calls[0]\n",
-    "    action = ToolInvocation(\n",
-    "        tool=tool_call[\"name\"],\n",
-    "        tool_input=tool_call[\"args\"],\n",
-    "    )\n",
-    "    # We call the tool_executor and get back a response\n",
-    "    response = tool_executor.invoke(action)\n",
-    "    # We use the response to create a ToolMessage\n",
-    "    tool_message = ToolMessage(\n",
-    "        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n",
-    "    )\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [tool_message]}"
-   ]
+   "source": ["from langchain_core.messages import ToolMessage\n\nfrom langgraph.prebuilt import ToolInvocation\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state):\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\"\n\n\n# Define the function that calls the model\ndef call_model(state):\n    messages = state[\"messages\"]\n    response = model.invoke(messages)\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}\n\n\n# Define the function to execute tools\ndef call_tool(state):\n    messages = state[\"messages\"]\n    # Based on the continue condition\n    # we know the last message involves a function call\n    last_message = messages[-1]\n    # We construct an ToolInvocation from the function_call\n    tool_call = last_message.tool_calls[0]\n    action = ToolInvocation(\n        tool=tool_call[\"name\"],\n        tool_input=tool_call[\"args\"],\n    )\n    # We call the tool_executor and get back a response\n    response = tool_executor.invoke(action)\n    # We use the response to create a ToolMessage\n    tool_message = ToolMessage(\n        content=str(response), name=action.tool, tool_call_id=tool_call[\"id\"]\n    )\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [tool_message]}"]
   },
   {
    "cell_type": "markdown",
@@ -322,45 +219,7 @@
    "id": "812b4e70-4956-4415-8880-db48b3dcbad2",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(State)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(State)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")"]
   },
   {
    "cell_type": "markdown",
@@ -378,11 +237,7 @@
    "id": "6845ed6a-d155-4105-9160-28849877248b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
-    "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")"
-   ]
+   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")"]
   },
   {
    "cell_type": "markdown",
@@ -400,12 +255,7 @@
    "id": "79d29875-8aa8-434c-9f20-1c58346a6249",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"
-   ]
+   "source": ["# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"]
   },
   {
    "cell_type": "markdown",
@@ -432,11 +282,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph().draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph().draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -467,14 +313,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "thread = {\"configurable\": {\"thread_id\": \"2\"}}\n",
-    "inputs = [HumanMessage(content=\"hi! I'm bob\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\nthread = {\"configurable\": {\"thread_id\": \"2\"}}\ninputs = [HumanMessage(content=\"hi! I'm bob\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "code",
@@ -495,11 +334,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = [HumanMessage(content=\"What did I tell you my name was?\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["inputs = [HumanMessage(content=\"What did I tell you my name was?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "code",
@@ -523,11 +358,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = [HumanMessage(content=\"what's the weather in sf now?\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["inputs = [HumanMessage(content=\"what's the weather in sf now?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "markdown",
@@ -561,10 +392,7 @@
      ]
     }
    ],
-   "source": [
-    "for event in app.stream(None, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["for event in app.stream(None, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "markdown",
@@ -599,43 +427,7 @@
    "id": "5454f436-d56e-4499-9381-06192aca1b56",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import json\n",
-    "from typing import Optional\n",
-    "\n",
-    "from langchain_core.messages import AIMessage\n",
-    "\n",
-    "\n",
-    "# Helper function to construct message asking for verification\n",
-    "def generate_verification_message(message: AIMessage) -> None:\n",
-    "    \"\"\"Generate \"verification message\" from message with tool calls.\"\"\"\n",
-    "    serialized_tool_calls = json.dumps(\n",
-    "        message.tool_calls,\n",
-    "        indent=2,\n",
-    "    )\n",
-    "    return AIMessage(\n",
-    "        content=(\n",
-    "            \"I plan to invoke the following tools, do you approve?\\n\\n\"\n",
-    "            \"Type 'y' if you do, anything else to stop.\\n\\n\"\n",
-    "            f\"{serialized_tool_calls}\"\n",
-    "        ),\n",
-    "        id=message.id,\n",
-    "    )\n",
-    "\n",
-    "\n",
-    "# Helper function to stream output from the graph\n",
-    "def stream_app_catch_tool_calls(inputs, thread) -> Optional[AIMessage]:\n",
-    "    \"\"\"Stream app, catching tool calls.\"\"\"\n",
-    "    tool_call_message = None\n",
-    "    for event in app.stream(inputs, thread, stream_mode=\"values\"):\n",
-    "        message = event[\"messages\"][-1]\n",
-    "        if isinstance(message, AIMessage) and message.tool_calls:\n",
-    "            tool_call_message = message\n",
-    "        else:\n",
-    "            message.pretty_print()\n",
-    "\n",
-    "    return tool_call_message"
-   ]
+   "source": ["import json\nfrom typing import Optional\n\nfrom langchain_core.messages import AIMessage\n\n\n# Helper function to construct message asking for verification\ndef generate_verification_message(message: AIMessage) -> None:\n    \"\"\"Generate \"verification message\" from message with tool calls.\"\"\"\n    serialized_tool_calls = json.dumps(\n        message.tool_calls,\n        indent=2,\n    )\n    return AIMessage(\n        content=(\n            \"I plan to invoke the following tools, do you approve?\\n\\n\"\n            \"Type 'y' if you do, anything else to stop.\\n\\n\"\n            f\"{serialized_tool_calls}\"\n        ),\n        id=message.id,\n    )\n\n\n# Helper function to stream output from the graph\ndef stream_app_catch_tool_calls(inputs, thread) -> Optional[AIMessage]:\n    \"\"\"Stream app, catching tool calls.\"\"\"\n    tool_call_message = None\n    for event in app.stream(inputs, thread, stream_mode=\"values\"):\n        message = event[\"messages\"][-1]\n        if isinstance(message, AIMessage) and message.tool_calls:\n            tool_call_message = message\n        else:\n            message.pretty_print()\n\n    return tool_call_message"]
   },
   {
    "cell_type": "code",
@@ -722,43 +514,7 @@
      ]
     }
    ],
-   "source": [
-    "import uuid\n",
-    "\n",
-    "thread = {\"configurable\": {\"thread_id\": \"3\"}}\n",
-    "\n",
-    "tool_call_message = stream_app_catch_tool_calls(\n",
-    "    {\"messages\": [HumanMessage(\"what's the weather in sf now?\")]},\n",
-    "    thread,\n",
-    ")\n",
-    "\n",
-    "while tool_call_message:\n",
-    "    verification_message = generate_verification_message(tool_call_message)\n",
-    "    verification_message.pretty_print()\n",
-    "    input_message = HumanMessage(input())\n",
-    "    if input_message.content == \"exit\":\n",
-    "        break\n",
-    "    input_message.pretty_print()\n",
-    "\n",
-    "    # First we update the state with the verification message and the input message.\n",
-    "    # note that `generate_verification_message` sets the message ID to be the same\n",
-    "    # as the ID from the original tool call message. Updating the state with this\n",
-    "    # message will overwrite the previous tool call.\n",
-    "    snapshot = app.get_state(thread)\n",
-    "    snapshot.values[\"messages\"] += [verification_message, input_message]\n",
-    "\n",
-    "    if input_message.content == \"y\":\n",
-    "        tool_call_message.id = str(uuid.uuid4())\n",
-    "        # If verified, we append the tool call message to the state\n",
-    "        # and resume execution.\n",
-    "        snapshot.values[\"messages\"] += [tool_call_message]\n",
-    "        app.update_state(thread, snapshot.values, as_node=\"agent\")\n",
-    "    else:\n",
-    "        # Otherwise, resume execution from the input message.\n",
-    "        app.update_state(thread, snapshot.values, as_node=\"__start__\")\n",
-    "\n",
-    "    tool_call_message = stream_app_catch_tool_calls(None, thread)"
-   ]
+   "source": ["import uuid\n\nthread = {\"configurable\": {\"thread_id\": \"3\"}}\n\ntool_call_message = stream_app_catch_tool_calls(\n    {\"messages\": [HumanMessage(\"what's the weather in sf now?\")]},\n    thread,\n)\n\nwhile tool_call_message:\n    verification_message = generate_verification_message(tool_call_message)\n    verification_message.pretty_print()\n    input_message = HumanMessage(input())\n    if input_message.content == \"exit\":\n        break\n    input_message.pretty_print()\n\n    # First we update the state with the verification message and the input message.\n    # note that `generate_verification_message` sets the message ID to be the same\n    # as the ID from the original tool call message. Updating the state with this\n    # message will overwrite the previous tool call.\n    snapshot = app.get_state(thread)\n    snapshot.values[\"messages\"] += [verification_message, input_message]\n\n    if input_message.content == \"y\":\n        tool_call_message.id = str(uuid.uuid4())\n        # If verified, we append the tool call message to the state\n        # and resume execution.\n        snapshot.values[\"messages\"] += [tool_call_message]\n        app.update_state(thread, snapshot.values, as_node=\"agent\")\n    else:\n        # Otherwise, resume execution from the input message.\n        app.update_state(thread, snapshot.values, as_node=\"__start__\")\n\n    tool_call_message = stream_app_catch_tool_calls(None, thread)"]
   },
   {
    "cell_type": "markdown",
@@ -779,34 +535,7 @@
    "id": "03232f16-d6fe-46d0-afa0-a6f0d0bf16de",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]\n",
-    "    tool_call_message: Optional[AIMessage]\n",
-    "\n",
-    "\n",
-    "def call_model(state):\n",
-    "    messages = state[\"messages\"]\n",
-    "    if messages[-1].content == \"y\":\n",
-    "        return {\n",
-    "            \"messages\": [state[\"tool_call_message\"]],\n",
-    "            \"tool_call_message\": None,\n",
-    "        }\n",
-    "    else:\n",
-    "        response = model.invoke(messages)\n",
-    "        if response.tool_calls:\n",
-    "            verification_message = generate_verification_message(response)\n",
-    "            response.id = str(uuid.uuid4())\n",
-    "            return {\n",
-    "                \"messages\": [verification_message],\n",
-    "                \"tool_call_message\": response,\n",
-    "            }\n",
-    "        else:\n",
-    "            return {\n",
-    "                \"messages\": [response],\n",
-    "                \"tool_call_message\": None,\n",
-    "            }"
-   ]
+   "source": ["class State(TypedDict):\n    messages: Annotated[list, add_messages]\n    tool_call_message: Optional[AIMessage]\n\n\ndef call_model(state):\n    messages = state[\"messages\"]\n    if messages[-1].content == \"y\":\n        return {\n            \"messages\": [state[\"tool_call_message\"]],\n            \"tool_call_message\": None,\n        }\n    else:\n        response = model.invoke(messages)\n        if response.tool_calls:\n            verification_message = generate_verification_message(response)\n            response.id = str(uuid.uuid4())\n            return {\n                \"messages\": [verification_message],\n                \"tool_call_message\": response,\n            }\n        else:\n            return {\n                \"messages\": [response],\n                \"tool_call_message\": None,\n            }"]
   },
   {
    "cell_type": "markdown",
@@ -822,27 +551,7 @@
    "id": "502dc688-c926-407e-8759-8c9e39eb4257",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "workflow = StateGraph(State)\n",
-    "\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", call_tool)\n",
-    "\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "workflow.add_conditional_edges(\n",
-    "    \"agent\",\n",
-    "    should_continue,\n",
-    "    {\n",
-    "        \"continue\": \"action\",\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "app = workflow.compile(checkpointer=memory)"
-   ]
+   "source": ["workflow = StateGraph(State)\n\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", call_tool)\n\nworkflow.add_edge(START, \"agent\")\n\nworkflow.add_conditional_edges(\n    \"agent\",\n    should_continue,\n    {\n        \"continue\": \"action\",\n        \"end\": END,\n    },\n)\n\nworkflow.add_edge(\"action\", \"agent\")\n\napp = workflow.compile(checkpointer=memory)"]
   },
   {
    "cell_type": "code",
@@ -875,13 +584,7 @@
      ]
     }
    ],
-   "source": [
-    "thread = {\"configurable\": {\"thread_id\": \"4\"}}\n",
-    "\n",
-    "inputs = [HumanMessage(content=\"what's the weather in sf?\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["thread = {\"configurable\": {\"thread_id\": \"4\"}}\n\ninputs = [HumanMessage(content=\"what's the weather in sf?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "code",
@@ -914,11 +617,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = [HumanMessage(content=\"can you specify sf in CA?\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["inputs = [HumanMessage(content=\"can you specify sf in CA?\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   },
   {
    "cell_type": "code",
@@ -949,11 +648,7 @@
      ]
     }
    ],
-   "source": [
-    "inputs = [HumanMessage(content=\"y\")]\n",
-    "for event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
-   ]
+   "source": ["inputs = [HumanMessage(content=\"y\")]\nfor event in app.stream({\"messages\": inputs}, thread, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"]
   }
  ],
  "metadata": {

examples/human_in_the_loop/time-travel.ipynb

@@ -40,8 +40,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_anthropic"
+    "%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_anthropic"
    ]
   },
   {
@@ -67,16 +66,7 @@
     }
    ],
    "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"ANTHROPIC_API_KEY\")"
+    "import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"ANTHROPIC_API_KEY\")"
    ]
   },
   {
@@ -94,8 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"
    ]
   },
   {
@@ -118,7 +107,7 @@
     "# Set up the tool\n",
     "from langchain_anthropic import ChatAnthropic\n",
     "from langchain_core.tools import tool\n",
-    "from langgraph.graph import MessagesState\n",
+    "from langgraph.graph import MessagesState, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "from langgraph.graph import END, StateGraph\n",
     "from langgraph.checkpoint.memory import MemorySaver\n",
@@ -133,6 +122,7 @@
     "        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n",
     "    ]\n",
     "\n",
+    "\n",
     "tools = [search]\n",
     "tool_node = ToolNode(tools)\n",
     "\n",
@@ -164,6 +154,7 @@
     "    # We return a list, because this will get added to the existing list\n",
     "    return {\"messages\": [response]}\n",
     "\n",
+    "\n",
     "# Define a new graph\n",
     "workflow = StateGraph(MessagesState)\n",
     "\n",
@@ -173,7 +164,7 @@
     "\n",
     "# Set the entrypoint as `agent`\n",
     "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
+    "workflow.add_edge(START, \"agent\")\n",
     "\n",
     "# We now add a conditional edge\n",
     "workflow.add_conditional_edges(\n",
@@ -265,12 +256,7 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "config = {\"configurable\": {\"thread_id\": \"1\"}}\n",
-    "input_message = HumanMessage(content=\"Use the search tool to look up the weather in SF\")\n",
-    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
-    "    event[\"messages\"][-1].pretty_print()"
+    "from langchain_core.messages import HumanMessage\n\nconfig = {\"configurable\": {\"thread_id\": \"1\"}}\ninput_message = HumanMessage(content=\"Use the search tool to look up the weather in SF\")\nfor event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n    event[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -307,11 +293,7 @@
     }
    ],
    "source": [
-    "all_states = []\n",
-    "for state in app.get_state_history(config):\n",
-    "    print(state)\n",
-    "    all_states.append(state)\n",
-    "    print(\"--\")"
+    "all_states = []\nfor state in app.get_state_history(config):\n    print(state)\n    all_states.append(state)\n    print(\"--\")"
    ]
   },
   {
@@ -401,9 +383,7 @@
     }
    ],
    "source": [
-    "for event in app.stream(None, to_replay.config):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
+    "for event in app.stream(None, to_replay.config):\n    for v in event.values():\n        print(v)"
    ]
   },
   {
@@ -427,13 +407,14 @@
    "source": [
     "# Let's now get the last message in the state\n",
     "# This is the one with the tool calls that we want to update\n",
-    "last_message = to_replay.values['messages'][-1]\n",
+    "last_message = to_replay.values[\"messages\"][-1]\n",
     "\n",
     "# Let's now update the args for that tool call\n",
-    "last_message.tool_calls[0]['args'] = {'query': 'current weather in SF'}\n",
+    "last_message.tool_calls[0][\"args\"] = {\"query\": \"current weather in SF\"}\n",
     "\n",
     "branch_config = app.update_state(\n",
-    "    to_replay.config, {\"messages\": [last_message]},\n",
+    "    to_replay.config,\n",
+    "    {\"messages\": [last_message]},\n",
     ")"
    ]
   },
@@ -461,9 +442,7 @@
     }
    ],
    "source": [
-    "for event in app.stream(None, branch_config):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
+    "for event in app.stream(None, branch_config):\n    for v in event.values():\n        print(v)"
    ]
   },
   {
@@ -485,13 +464,14 @@
     "\n",
     "# Let's now get the last message in the state\n",
     "# This is the one with the tool calls that we want to update\n",
-    "last_message = to_replay.values['messages'][-1]\n",
+    "last_message = to_replay.values[\"messages\"][-1]\n",
     "\n",
     "# Let's now get the ID for the last message, and create a new message with that ID.\n",
     "new_message = AIMessage(content=\"its warm!\", id=last_message.id)\n",
     "\n",
     "branch_config = app.update_state(\n",
-    "    to_replay.config, {\"messages\": [new_message]},\n",
+    "    to_replay.config,\n",
+    "    {\"messages\": [new_message]},\n",
     ")"
    ]
   },
@@ -562,7 +542,9 @@
    "id": "74a7a5ed-0c14-4883-a16b-d70aaf40f7ea",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    ""
+   ]
   }
  ],
  "metadata": {

examples/lats/lats.ipynb

@@ -37,11 +37,7 @@
    "id": "dcc9159b-cc8c-426d-9670-3e8ada06723f",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install -U --quiet langchain langgraph langchain_openai\n",
-    "%pip install -U --quiet tavily-python"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install -U --quiet langchain langgraph langchain_openai\n%pip install -U --quiet tavily-python"]
   },
   {
    "cell_type": "code",
@@ -49,27 +45,7 @@
    "id": "a177ecc9-0c96-460f-9b39-9c1ce54754f1",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from __future__ import annotations  # noqa: F404\n",
-    "\n",
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_if_undefined(var: str) -> None:\n",
-    "    if os.environ.get(var):\n",
-    "        return\n",
-    "    os.environ[var] = getpass.getpass(var)\n",
-    "\n",
-    "\n",
-    "# Optional: Configure tracing to visualize and debug the agent\n",
-    "_set_if_undefined(\"LANGCHAIN_API_KEY\")\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"LATS\"\n",
-    "\n",
-    "_set_if_undefined(\"OPENAI_API_KEY\")\n",
-    "_set_if_undefined(\"TAVILY_API_KEY\")"
-   ]
+   "source": ["from __future__ import annotations  # noqa: F404\n\nimport getpass\nimport os\n\n\ndef _set_if_undefined(var: str) -> None:\n    if os.environ.get(var):\n        return\n    os.environ[var] = getpass.getpass(var)\n\n\n# Optional: Configure tracing to visualize and debug the agent\n_set_if_undefined(\"LANGCHAIN_API_KEY\")\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_PROJECT\"] = \"LATS\"\n\n_set_if_undefined(\"OPENAI_API_KEY\")\n_set_if_undefined(\"TAVILY_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -93,134 +69,7 @@
    "id": "54c6f319-3966-4f66-aa7b-50e249189111",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import math\n",
-    "from collections import deque\n",
-    "from typing import Optional\n",
-    "\n",
-    "from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n",
-    "\n",
-    "\n",
-    "class Node:\n",
-    "    def __init__(\n",
-    "        self,\n",
-    "        messages: list[BaseMessage],\n",
-    "        reflection: Reflection,\n",
-    "        parent: Optional[Node] = None,\n",
-    "    ):\n",
-    "        self.messages = messages\n",
-    "        self.parent = parent\n",
-    "        self.children = []\n",
-    "        self.value = 0\n",
-    "        self.visits = 0\n",
-    "        self.reflection = reflection\n",
-    "        self.depth = parent.depth + 1 if parent is not None else 1\n",
-    "        self._is_solved = reflection.found_solution if reflection else False\n",
-    "        if self._is_solved:\n",
-    "            self._mark_tree_as_solved()\n",
-    "        self.backpropagate(reflection.normalized_score)\n",
-    "\n",
-    "    def __repr__(self) -> str:\n",
-    "        return (\n",
-    "            f\"<Node value={self.value}, visits={self.visits},\"\n",
-    "            f\" solution={self.messages} reflection={self.reflection}/>\"\n",
-    "        )\n",
-    "\n",
-    "    @property\n",
-    "    def is_solved(self):\n",
-    "        \"\"\"If any solutions exist, we can end the search.\"\"\"\n",
-    "        return self._is_solved\n",
-    "\n",
-    "    @property\n",
-    "    def is_terminal(self):\n",
-    "        return not self.children\n",
-    "\n",
-    "    @property\n",
-    "    def best_child(self):\n",
-    "        \"\"\"Select the child with the highest UCT to search next.\"\"\"\n",
-    "        if not self.children:\n",
-    "            return None\n",
-    "        all_nodes = self._get_all_children()\n",
-    "        return max(all_nodes, key=lambda child: child.upper_confidence_bound())\n",
-    "\n",
-    "    @property\n",
-    "    def best_child_score(self):\n",
-    "        \"\"\"Return the child with the highest value.\"\"\"\n",
-    "        if not self.children:\n",
-    "            return None\n",
-    "        return max(self.children, key=lambda child: int(child.is_solved) * child.value)\n",
-    "\n",
-    "    @property\n",
-    "    def height(self) -> int:\n",
-    "        \"\"\"Check for how far we've rolled out the tree.\"\"\"\n",
-    "        if self.children:\n",
-    "            return 1 + max([child.height for child in self.children])\n",
-    "        return 1\n",
-    "\n",
-    "    def upper_confidence_bound(self, exploration_weight=1.0):\n",
-    "        \"\"\"Return the UCT score. This helps balance exploration vs. exploitation of a branch.\"\"\"\n",
-    "        if self.parent is None:\n",
-    "            raise ValueError(\"Cannot obtain UCT from root node\")\n",
-    "        if self.visits == 0:\n",
-    "            return self.value\n",
-    "        # Encourages exploitation of high-value trajectories\n",
-    "        average_reward = self.value / self.visits\n",
-    "        # Encourages exploration of less-visited trajectories\n",
-    "        exploration_term = math.sqrt(math.log(self.parent.visits) / self.visits)\n",
-    "        return average_reward + exploration_weight * exploration_term\n",
-    "\n",
-    "    def backpropagate(self, reward: float):\n",
-    "        \"\"\"Update the score of this node and its parents.\"\"\"\n",
-    "        node = self\n",
-    "        while node:\n",
-    "            node.visits += 1\n",
-    "            node.value = (node.value * (node.visits - 1) + reward) / node.visits\n",
-    "            node = node.parent\n",
-    "\n",
-    "    def get_messages(self, include_reflections: bool = True):\n",
-    "        if include_reflections:\n",
-    "            return self.messages + [self.reflection.as_message()]\n",
-    "        return self.messages\n",
-    "\n",
-    "    def get_trajectory(self, include_reflections: bool = True) -> list[BaseMessage]:\n",
-    "        \"\"\"Get messages representing this search branch.\"\"\"\n",
-    "        messages = []\n",
-    "        node = self\n",
-    "        while node:\n",
-    "            messages.extend(\n",
-    "                node.get_messages(include_reflections=include_reflections)[::-1]\n",
-    "            )\n",
-    "            node = node.parent\n",
-    "        # Reverse the final back-tracked trajectory to return in the correct order\n",
-    "        return messages[::-1]  # root solution, reflection, child 1, ...\n",
-    "\n",
-    "    def _get_all_children(self):\n",
-    "        all_nodes = []\n",
-    "        nodes = deque()\n",
-    "        nodes.append(self)\n",
-    "        while nodes:\n",
-    "            node = nodes.popleft()\n",
-    "            all_nodes.extend(node.children)\n",
-    "            for n in node.children:\n",
-    "                nodes.append(n)\n",
-    "        return all_nodes\n",
-    "\n",
-    "    def get_best_solution(self):\n",
-    "        \"\"\"Return the best solution from within the current sub-tree.\"\"\"\n",
-    "        all_nodes = [self] + self._get_all_children()\n",
-    "        best_node = max(\n",
-    "            all_nodes,\n",
-    "            # We filter out all non-terminal, non-solution trajectories\n",
-    "            key=lambda node: int(node.is_terminal and node.is_solved) * node.value,\n",
-    "        )\n",
-    "        return best_node\n",
-    "\n",
-    "    def _mark_tree_as_solved(self):\n",
-    "        parent = self.parent\n",
-    "        while parent:\n",
-    "            parent._is_solved = True\n",
-    "            parent = parent.parent"
-   ]
+   "source": ["import math\nfrom collections import deque\nfrom typing import Optional\n\nfrom langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n\n\nclass Node:\n    def __init__(\n        self,\n        messages: list[BaseMessage],\n        reflection: Reflection,\n        parent: Optional[Node] = None,\n    ):\n        self.messages = messages\n        self.parent = parent\n        self.children = []\n        self.value = 0\n        self.visits = 0\n        self.reflection = reflection\n        self.depth = parent.depth + 1 if parent is not None else 1\n        self._is_solved = reflection.found_solution if reflection else False\n        if self._is_solved:\n            self._mark_tree_as_solved()\n        self.backpropagate(reflection.normalized_score)\n\n    def __repr__(self) -> str:\n        return (\n            f\"<Node value={self.value}, visits={self.visits},\"\n            f\" solution={self.messages} reflection={self.reflection}/>\"\n        )\n\n    @property\n    def is_solved(self):\n        \"\"\"If any solutions exist, we can end the search.\"\"\"\n        return self._is_solved\n\n    @property\n    def is_terminal(self):\n        return not self.children\n\n    @property\n    def best_child(self):\n        \"\"\"Select the child with the highest UCT to search next.\"\"\"\n        if not self.children:\n            return None\n        all_nodes = self._get_all_children()\n        return max(all_nodes, key=lambda child: child.upper_confidence_bound())\n\n    @property\n    def best_child_score(self):\n        \"\"\"Return the child with the highest value.\"\"\"\n        if not self.children:\n            return None\n        return max(self.children, key=lambda child: int(child.is_solved) * child.value)\n\n    @property\n    def height(self) -> int:\n        \"\"\"Check for how far we've rolled out the tree.\"\"\"\n        if self.children:\n            return 1 + max([child.height for child in self.children])\n        return 1\n\n    def upper_confidence_bound(self, exploration_weight=1.0):\n        \"\"\"Return the UCT score. This helps balance exploration vs. exploitation of a branch.\"\"\"\n        if self.parent is None:\n            raise ValueError(\"Cannot obtain UCT from root node\")\n        if self.visits == 0:\n            return self.value\n        # Encourages exploitation of high-value trajectories\n        average_reward = self.value / self.visits\n        # Encourages exploration of less-visited trajectories\n        exploration_term = math.sqrt(math.log(self.parent.visits) / self.visits)\n        return average_reward + exploration_weight * exploration_term\n\n    def backpropagate(self, reward: float):\n        \"\"\"Update the score of this node and its parents.\"\"\"\n        node = self\n        while node:\n            node.visits += 1\n            node.value = (node.value * (node.visits - 1) + reward) / node.visits\n            node = node.parent\n\n    def get_messages(self, include_reflections: bool = True):\n        if include_reflections:\n            return self.messages + [self.reflection.as_message()]\n        return self.messages\n\n    def get_trajectory(self, include_reflections: bool = True) -> list[BaseMessage]:\n        \"\"\"Get messages representing this search branch.\"\"\"\n        messages = []\n        node = self\n        while node:\n            messages.extend(\n                node.get_messages(include_reflections=include_reflections)[::-1]\n            )\n            node = node.parent\n        # Reverse the final back-tracked trajectory to return in the correct order\n        return messages[::-1]  # root solution, reflection, child 1, ...\n\n    def _get_all_children(self):\n        all_nodes = []\n        nodes = deque()\n        nodes.append(self)\n        while nodes:\n            node = nodes.popleft()\n            all_nodes.extend(node.children)\n            for n in node.children:\n                nodes.append(n)\n        return all_nodes\n\n    def get_best_solution(self):\n        \"\"\"Return the best solution from within the current sub-tree.\"\"\"\n        all_nodes = [self] + self._get_all_children()\n        best_node = max(\n            all_nodes,\n            # We filter out all non-terminal, non-solution trajectories\n            key=lambda node: int(node.is_terminal and node.is_solved) * node.value,\n        )\n        return best_node\n\n    def _mark_tree_as_solved(self):\n        parent = self.parent\n        while parent:\n            parent._is_solved = True\n            parent = parent.parent"]
   },
   {
    "cell_type": "markdown",
@@ -238,16 +87,7 @@
    "id": "e10c94ba-9daa-4899-97ce-4f28428c2c38",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "\n",
-    "class TreeState(TypedDict):\n",
-    "    # The full tree\n",
-    "    root: Node\n",
-    "    # The original input\n",
-    "    input: str"
-   ]
+   "source": ["from typing_extensions import TypedDict\n\n\nclass TreeState(TypedDict):\n    # The full tree\n    root: Node\n    # The original input\n    input: str"]
   },
   {
    "cell_type": "markdown",
@@ -270,11 +110,7 @@
    "id": "48738896-42ac-47eb-b482-0d4d4dd86c87",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-4o\")"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nllm = ChatOpenAI(model=\"gpt-4o\")"]
   },
   {
    "cell_type": "markdown",
@@ -292,17 +128,7 @@
    "id": "55c2aff3-f454-43da-8f45-1a3d46523cd5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper\n",
-    "\n",
-    "from langgraph.prebuilt.tool_executor import ToolExecutor, ToolInvocation\n",
-    "\n",
-    "search = TavilySearchAPIWrapper()\n",
-    "tavily_tool = TavilySearchResults(api_wrapper=search, max_results=5)\n",
-    "tools = [tavily_tool]\n",
-    "tool_executor = ToolExecutor(tools=tools)"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_community.utilities.tavily_search import TavilySearchAPIWrapper\n\nfrom langgraph.prebuilt.tool_executor import ToolExecutor, ToolInvocation\n\nsearch = TavilySearchAPIWrapper()\ntavily_tool = TavilySearchResults(api_wrapper=search, max_results=5)\ntools = [tavily_tool]\ntool_executor = ToolExecutor(tools=tools)"]
   },
   {
    "cell_type": "markdown",
@@ -321,68 +147,7 @@
    "id": "ddfd1750-c265-4b29-b505-83b1c5e2d30e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers.openai_tools import (\n",
-    "    JsonOutputToolsParser,\n",
-    "    PydanticToolsParser,\n",
-    ")\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "from langchain_core.runnables import chain as as_runnable\n",
-    "\n",
-    "\n",
-    "class Reflection(BaseModel):\n",
-    "    reflections: str = Field(\n",
-    "        description=\"The critique and reflections on the sufficiency, superfluency,\"\n",
-    "        \" and general quality of the response\"\n",
-    "    )\n",
-    "    score: int = Field(\n",
-    "        description=\"Score from 0-10 on the quality of the candidate response.\",\n",
-    "        gte=0,\n",
-    "        lte=10,\n",
-    "    )\n",
-    "    found_solution: bool = Field(\n",
-    "        description=\"Whether the response has fully solved the question or task.\"\n",
-    "    )\n",
-    "\n",
-    "    def as_message(self):\n",
-    "        return HumanMessage(\n",
-    "            content=f\"Reasoning: {self.reflections}\\nScore: {self.score}\"\n",
-    "        )\n",
-    "\n",
-    "    @property\n",
-    "    def normalized_score(self) -> float:\n",
-    "        return self.score / 10.0\n",
-    "\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"Reflect and grade the assistant response to the user question below.\",\n",
-    "        ),\n",
-    "        (\"user\", \"{input}\"),\n",
-    "        MessagesPlaceholder(variable_name=\"candidate\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "reflection_llm_chain = (\n",
-    "    prompt\n",
-    "    | llm.bind_tools(tools=[Reflection], tool_choice=\"Reflection\").with_config(\n",
-    "        run_name=\"Reflection\"\n",
-    "    )\n",
-    "    | PydanticToolsParser(tools=[Reflection])\n",
-    ")\n",
-    "\n",
-    "\n",
-    "@as_runnable\n",
-    "def reflection_chain(inputs) -> Reflection:\n",
-    "    tool_choices = reflection_llm_chain.invoke(inputs)\n",
-    "    reflection = tool_choices[0]\n",
-    "    if not isinstance(inputs[\"candidate\"][-1], AIMessage):\n",
-    "        reflection.found_solution = False\n",
-    "    return reflection"
-   ]
+   "source": ["from langchain_core.output_parsers.openai_tools import (\n    JsonOutputToolsParser,\n    PydanticToolsParser,\n)\nfrom langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\nfrom langchain_core.pydantic_v1 import BaseModel, Field\nfrom langchain_core.runnables import chain as as_runnable\n\n\nclass Reflection(BaseModel):\n    reflections: str = Field(\n        description=\"The critique and reflections on the sufficiency, superfluency,\"\n        \" and general quality of the response\"\n    )\n    score: int = Field(\n        description=\"Score from 0-10 on the quality of the candidate response.\",\n        gte=0,\n        lte=10,\n    )\n    found_solution: bool = Field(\n        description=\"Whether the response has fully solved the question or task.\"\n    )\n\n    def as_message(self):\n        return HumanMessage(\n            content=f\"Reasoning: {self.reflections}\\nScore: {self.score}\"\n        )\n\n    @property\n    def normalized_score(self) -> float:\n        return self.score / 10.0\n\n\nprompt = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"Reflect and grade the assistant response to the user question below.\",\n        ),\n        (\"user\", \"{input}\"),\n        MessagesPlaceholder(variable_name=\"candidate\"),\n    ]\n)\n\nreflection_llm_chain = (\n    prompt\n    | llm.bind_tools(tools=[Reflection], tool_choice=\"Reflection\").with_config(\n        run_name=\"Reflection\"\n    )\n    | PydanticToolsParser(tools=[Reflection])\n)\n\n\n@as_runnable\ndef reflection_chain(inputs) -> Reflection:\n    tool_choices = reflection_llm_chain.invoke(inputs)\n    reflection = tool_choices[0]\n    if not isinstance(inputs[\"candidate\"][-1], AIMessage):\n        reflection.found_solution = False\n    return reflection"]
   },
   {
    "cell_type": "markdown",
@@ -400,29 +165,7 @@
    "id": "72fc5363-f0f3-4362-8499-14eb583bd75b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.prompt_values import ChatPromptValue\n",
-    "from langchain_core.runnables import RunnableConfig\n",
-    "\n",
-    "prompt_template = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are an AI assistant.\",\n",
-    "        ),\n",
-    "        (\"user\", \"{input}\"),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\", optional=True),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "\n",
-    "initial_answer_chain = prompt_template | llm.bind_tools(tools=tools).with_config(\n",
-    "    run_name=\"GenerateInitialCandidate\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "parser = JsonOutputToolsParser(return_id=True)"
-   ]
+   "source": ["from langchain_core.prompt_values import ChatPromptValue\nfrom langchain_core.runnables import RunnableConfig\n\nprompt_template = ChatPromptTemplate.from_messages(\n    [\n        (\n            \"system\",\n            \"You are an AI assistant.\",\n        ),\n        (\"user\", \"{input}\"),\n        MessagesPlaceholder(variable_name=\"messages\", optional=True),\n    ]\n)\n\n\ninitial_answer_chain = prompt_template | llm.bind_tools(tools=tools).with_config(\n    run_name=\"GenerateInitialCandidate\"\n)\n\n\nparser = JsonOutputToolsParser(return_id=True)"]
   },
   {
    "cell_type": "code",
@@ -441,12 +184,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "initial_response = initial_answer_chain.invoke(\n",
-    "    {\"input\": \"Write a research report on lithium pollution.\"}\n",
-    ")\n",
-    "initial_response"
-   ]
+   "source": ["initial_response = initial_answer_chain.invoke(\n    {\"input\": \"Write a research report on lithium pollution.\"}\n)\ninitial_response"]
   },
   {
    "cell_type": "markdown",
@@ -464,31 +202,7 @@
    "id": "5b6b173c-78f5-4ae1-80b3-28c80e68f5c5",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import json\n",
-    "\n",
-    "\n",
-    "# Define the node we will add to the graph\n",
-    "def generate_initial_response(state: TreeState) -> dict:\n",
-    "    \"\"\"Generate the initial candidate response.\"\"\"\n",
-    "    res = initial_answer_chain.invoke({\"input\": state[\"input\"]})\n",
-    "    parsed = parser.invoke(res)\n",
-    "    tool_responses = tool_executor.batch(\n",
-    "        [ToolInvocation(tool=r[\"type\"], tool_input=r[\"args\"]) for r in parsed]\n",
-    "    )\n",
-    "    output_messages = [res] + [\n",
-    "        ToolMessage(content=json.dumps(resp), tool_call_id=tool_call[\"id\"])\n",
-    "        for resp, tool_call in zip(tool_responses, parsed)\n",
-    "    ]\n",
-    "    reflection = reflection_chain.invoke(\n",
-    "        {\"input\": state[\"input\"], \"candidate\": output_messages}\n",
-    "    )\n",
-    "    root = Node(output_messages, reflection=reflection)\n",
-    "    return {\n",
-    "        **state,\n",
-    "        \"root\": root,\n",
-    "    }"
-   ]
+   "source": ["import json\n\n\n# Define the node we will add to the graph\ndef generate_initial_response(state: TreeState) -> dict:\n    \"\"\"Generate the initial candidate response.\"\"\"\n    res = initial_answer_chain.invoke({\"input\": state[\"input\"]})\n    parsed = parser.invoke(res)\n    tool_responses = tool_executor.batch(\n        [ToolInvocation(tool=r[\"type\"], tool_input=r[\"args\"]) for r in parsed]\n    )\n    output_messages = [res] + [\n        ToolMessage(content=json.dumps(resp), tool_call_id=tool_call[\"id\"])\n        for resp, tool_call in zip(tool_responses, parsed)\n    ]\n    reflection = reflection_chain.invoke(\n        {\"input\": state[\"input\"], \"candidate\": output_messages}\n    )\n    root = Node(output_messages, reflection=reflection)\n    return {\n        **state,\n        \"root\": root,\n    }"]
   },
   {
    "cell_type": "markdown",
@@ -506,26 +220,7 @@
    "id": "550bff9a-86aa-43ad-ad98-506e97c122d2",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# This generates N candidate values\n",
-    "# for a single input to sample actions from the environment\n",
-    "\n",
-    "\n",
-    "def generate_candidates(messages: ChatPromptValue, config: RunnableConfig):\n",
-    "    n = config[\"configurable\"].get(\"N\", 5)\n",
-    "    bound_kwargs = llm.bind_tools(tools=tools).kwargs\n",
-    "    chat_result = llm.generate(\n",
-    "        [messages.to_messages()],\n",
-    "        n=n,\n",
-    "        callbacks=config[\"callbacks\"],\n",
-    "        run_name=\"GenerateCandidates\",\n",
-    "        **bound_kwargs,\n",
-    "    )\n",
-    "    return [gen.message for gen in chat_result.generations[0]]\n",
-    "\n",
-    "\n",
-    "expansion_chain = prompt_template | generate_candidates"
-   ]
+   "source": ["# This generates N candidate values\n# for a single input to sample actions from the environment\n\n\ndef generate_candidates(messages: ChatPromptValue, config: RunnableConfig):\n    n = config[\"configurable\"].get(\"N\", 5)\n    bound_kwargs = llm.bind_tools(tools=tools).kwargs\n    chat_result = llm.generate(\n        [messages.to_messages()],\n        n=n,\n        callbacks=config[\"callbacks\"],\n        run_name=\"GenerateCandidates\",\n        **bound_kwargs,\n    )\n    return [gen.message for gen in chat_result.generations[0]]\n\n\nexpansion_chain = prompt_template | generate_candidates"]
   },
   {
    "cell_type": "code",
@@ -548,10 +243,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "res = expansion_chain.invoke({\"input\": \"Write a research report on lithium pollution.\"})\n",
-    "res"
-   ]
+   "source": ["res = expansion_chain.invoke({\"input\": \"Write a research report on lithium pollution.\"})\nres"]
   },
   {
    "cell_type": "markdown",
@@ -570,55 +262,7 @@
    "id": "d32af859-53e8-46be-8182-7d522be31f54",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from collections import defaultdict\n",
-    "\n",
-    "\n",
-    "def expand(state: TreeState, config: RunnableConfig) -> dict:\n",
-    "    \"\"\"Starting from the \"best\" node in the tree, generate N candidates for the next step.\"\"\"\n",
-    "    root = state[\"root\"]\n",
-    "    best_candidate: Node = root.best_child if root.children else root\n",
-    "    messages = best_candidate.get_trajectory()\n",
-    "    # Generate N candidates from the single child candidate\n",
-    "    new_candidates = expansion_chain.invoke(\n",
-    "        {\"input\": state[\"input\"], \"messages\": messages}, config\n",
-    "    )\n",
-    "    parsed = parser.batch(new_candidates)\n",
-    "    flattened = [\n",
-    "        (i, tool_call)\n",
-    "        for i, tool_calls in enumerate(parsed)\n",
-    "        for tool_call in tool_calls\n",
-    "    ]\n",
-    "    tool_responses = tool_executor.batch(\n",
-    "        [\n",
-    "            ToolInvocation(tool=tool_call[\"type\"], tool_input=tool_call[\"args\"])\n",
-    "            for _, tool_call in flattened\n",
-    "        ]\n",
-    "    )\n",
-    "    collected_responses = defaultdict(list)\n",
-    "    for (i, tool_call), resp in zip(flattened, tool_responses):\n",
-    "        collected_responses[i].append(\n",
-    "            ToolMessage(content=json.dumps(resp), tool_call_id=tool_call[\"id\"])\n",
-    "        )\n",
-    "    output_messages = []\n",
-    "    for i, candidate in enumerate(new_candidates):\n",
-    "        output_messages.append([candidate] + collected_responses[i])\n",
-    "\n",
-    "    # Reflect on each candidate\n",
-    "    # For tasks with external validation, you'd add that here.\n",
-    "    reflections = reflection_chain.batch(\n",
-    "        [{\"input\": state[\"input\"], \"candidate\": msges} for msges in output_messages],\n",
-    "        config,\n",
-    "    )\n",
-    "    # Grow tree\n",
-    "    child_nodes = [\n",
-    "        Node(cand, parent=best_candidate, reflection=reflection)\n",
-    "        for cand, reflection in zip(output_messages, reflections)\n",
-    "    ]\n",
-    "    best_candidate.children.extend(child_nodes)\n",
-    "    # We have already extended the tree directly, so we just return the state\n",
-    "    return state"
-   ]
+   "source": ["from collections import defaultdict\n\n\ndef expand(state: TreeState, config: RunnableConfig) -> dict:\n    \"\"\"Starting from the \"best\" node in the tree, generate N candidates for the next step.\"\"\"\n    root = state[\"root\"]\n    best_candidate: Node = root.best_child if root.children else root\n    messages = best_candidate.get_trajectory()\n    # Generate N candidates from the single child candidate\n    new_candidates = expansion_chain.invoke(\n        {\"input\": state[\"input\"], \"messages\": messages}, config\n    )\n    parsed = parser.batch(new_candidates)\n    flattened = [\n        (i, tool_call)\n        for i, tool_calls in enumerate(parsed)\n        for tool_call in tool_calls\n    ]\n    tool_responses = tool_executor.batch(\n        [\n            ToolInvocation(tool=tool_call[\"type\"], tool_input=tool_call[\"args\"])\n            for _, tool_call in flattened\n        ]\n    )\n    collected_responses = defaultdict(list)\n    for (i, tool_call), resp in zip(flattened, tool_responses):\n        collected_responses[i].append(\n            ToolMessage(content=json.dumps(resp), tool_call_id=tool_call[\"id\"])\n        )\n    output_messages = []\n    for i, candidate in enumerate(new_candidates):\n        output_messages.append([candidate] + collected_responses[i])\n\n    # Reflect on each candidate\n    # For tasks with external validation, you'd add that here.\n    reflections = reflection_chain.batch(\n        [{\"input\": state[\"input\"], \"candidate\": msges} for msges in output_messages],\n        config,\n    )\n    # Grow tree\n    child_nodes = [\n        Node(cand, parent=best_candidate, reflection=reflection)\n        for cand, reflection in zip(output_messages, reflections)\n    ]\n    best_candidate.children.extend(child_nodes)\n    # We have already extended the tree directly, so we just return the state\n    return state"]
   },
   {
    "cell_type": "markdown",
@@ -636,41 +280,7 @@
    "id": "8aec0f20-f978-4df0-8900-e3a1f0544f6d",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "\n",
-    "def should_loop(state: TreeState) -> Literal[\"expand\", \"__end__\"]:\n",
-    "    \"\"\"Determine whether to continue the tree search.\"\"\"\n",
-    "    root = state[\"root\"]\n",
-    "    if root.is_solved:\n",
-    "        return END\n",
-    "    if root.height > 5:\n",
-    "        return END\n",
-    "    return \"expand\"\n",
-    "\n",
-    "\n",
-    "builder = StateGraph(TreeState)\n",
-    "builder.add_node(\"start\", generate_initial_response)\n",
-    "builder.add_node(\"expand\", expand)\n",
-    "builder.set_entry_point(\"start\")\n",
-    "\n",
-    "\n",
-    "builder.add_conditional_edges(\n",
-    "    \"start\",\n",
-    "    # Either expand/rollout or finish\n",
-    "    should_loop,\n",
-    ")\n",
-    "builder.add_conditional_edges(\n",
-    "    \"expand\",\n",
-    "    # Either continue to rollout or finish\n",
-    "    should_loop,\n",
-    ")\n",
-    "\n",
-    "graph = builder.compile()"
-   ]
+   "source": ["from typing import Literal\n\nfrom langgraph.graph import END, StateGraph, START\n\n\ndef should_loop(state: TreeState) -> Literal[\"expand\", \"__end__\"]:\n    \"\"\"Determine whether to continue the tree search.\"\"\"\n    root = state[\"root\"]\n    if root.is_solved:\n        return END\n    if root.height > 5:\n        return END\n    return \"expand\"\n\n\nbuilder = StateGraph(TreeState)\nbuilder.add_node(\"start\", generate_initial_response)\nbuilder.add_node(\"expand\", expand)\nbuilder.add_edge(START, \"start\")\n\n\nbuilder.add_conditional_edges(\n    \"start\",\n    # Either expand/rollout or finish\n    should_loop,\n)\nbuilder.add_conditional_edges(\n    \"expand\",\n    # Either continue to rollout or finish\n    should_loop,\n)\n\ngraph = builder.compile()"]
   },
   {
    "cell_type": "code",
@@ -690,11 +300,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from IPython.display import Image\n",
-    "\n",
-    "Image(graph.get_graph().draw_mermaid_png())"
-   ]
+   "source": ["from IPython.display import Image\n\nImage(graph.get_graph().draw_mermaid_png())"]
   },
   {
    "cell_type": "markdown",
@@ -723,16 +329,7 @@
      ]
     }
    ],
-   "source": [
-    "question = \"Generate a table with the average size and weight, as well as the oldest recorded instance for each of the top 5 most common birds.\"\n",
-    "last_step = None\n",
-    "for step in graph.stream({\"input\": question}):\n",
-    "    last_step = step\n",
-    "    step_name, step_state = next(iter(step.items()))\n",
-    "    print(step_name)\n",
-    "    print(\"rolled out: \", step_state[\"root\"].height)\n",
-    "    print(\"---\")"
-   ]
+   "source": ["question = \"Generate a table with the average size and weight, as well as the oldest recorded instance for each of the top 5 most common birds.\"\nlast_step = None\nfor step in graph.stream({\"input\": question}):\n    last_step = step\n    step_name, step_state = next(iter(step.items()))\n    print(step_name)\n    print(\"rolled out: \", step_state[\"root\"].height)\n    print(\"---\")"]
   },
   {
    "cell_type": "code",
@@ -786,11 +383,7 @@
      ]
     }
    ],
-   "source": [
-    "solution_node = last_step[\"expand\"][\"root\"].get_best_solution()\n",
-    "best_trajectory = solution_node.get_trajectory(include_reflections=False)\n",
-    "print(best_trajectory[-1].content)"
-   ]
+   "source": ["solution_node = last_step[\"expand\"][\"root\"].get_best_solution()\nbest_trajectory = solution_node.get_trajectory(include_reflections=False)\nprint(best_trajectory[-1].content)"]
   },
   {
    "cell_type": "code",
@@ -814,16 +407,7 @@
      ]
     }
    ],
-   "source": [
-    "question = \"Write out magnus carlson series of moves in his game against Alireza Firouzja and propose an alternate strategy\"\n",
-    "last_step = None\n",
-    "for step in graph.stream({\"input\": question}):\n",
-    "    last_step = step\n",
-    "    step_name, step_state = next(iter(step.items()))\n",
-    "    print(step_name)\n",
-    "    print(\"rolled out: \", step_state[\"root\"].height)\n",
-    "    print(\"---\")"
-   ]
+   "source": ["question = \"Write out magnus carlson series of moves in his game against Alireza Firouzja and propose an alternate strategy\"\nlast_step = None\nfor step in graph.stream({\"input\": question}):\n    last_step = step\n    step_name, step_state = next(iter(step.items()))\n    print(step_name)\n    print(\"rolled out: \", step_state[\"root\"].height)\n    print(\"---\")"]
   },
   {
    "cell_type": "code",
@@ -886,11 +470,7 @@
      ]
     }
    ],
-   "source": [
-    "solution_node = last_step[\"expand\"][\"root\"].get_best_solution()\n",
-    "best_trajectory = solution_node.get_trajectory(include_reflections=False)\n",
-    "print(best_trajectory[-1].content)"
-   ]
+   "source": ["solution_node = last_step[\"expand\"][\"root\"].get_best_solution()\nbest_trajectory = solution_node.get_trajectory(include_reflections=False)\nprint(best_trajectory[-1].content)"]
   },
   {
    "cell_type": "markdown",

examples/learning.ipynb

@@ -38,9 +38,7 @@
      ]
     }
    ],
-   "source": [
-    "!%pip install --quiet -U langgraph langchain langchain_openai tavily-pythonvily-python"
-   ]
+   "source": ["!%pip install --quiet -U langgraph langchain langchain_openai tavily-pythonvily-python"]
   },
   {
    "cell_type": "markdown",
@@ -65,13 +63,7 @@
      ]
     }
    ],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
-   ]
+   "source": ["import getpass\nimport os\n\nos.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\nos.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -87,10 +79,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"]
   },
   {
    "cell_type": "markdown",
@@ -110,11 +99,7 @@
    "id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "\n",
-    "tools = [TavilySearchResults(max_results=1)]"
-   ]
+   "source": ["from langchain_community.tools.tavily_search import TavilySearchResults\n\ntools = [TavilySearchResults(max_results=1)]"]
   },
   {
    "cell_type": "markdown",
@@ -131,11 +116,7 @@
    "id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -159,11 +140,7 @@
    "id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -180,9 +157,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -217,17 +192,7 @@
    "id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state):\n",
-    "    last_message = state[\"messages\"][-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["# Define the function that determines whether to continue or not\ndef should_continue(state):\n    last_message = state[\"messages\"][-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -245,107 +210,7 @@
    "id": "812b4e70-4956-4415-8880-db48b3dcbad2",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated, TypedDict\n",
-    "\n",
-    "from langchain_core.messages import (\n",
-    "    AIMessage,\n",
-    "    AnyMessage,\n",
-    "    HumanMessage,\n",
-    "    SystemMessage,\n",
-    "    ToolMessage,\n",
-    ")\n",
-    "\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "from langgraph.graph.message import add_messages\n",
-    "from langgraph.managed.few_shot import FewShotExamples\n",
-    "\n",
-    "\n",
-    "class BaseState(TypedDict):\n",
-    "    messages: Annotated[list[AnyMessage], add_messages]\n",
-    "    examples: Annotated[list, FewShotExamples]\n",
-    "\n",
-    "\n",
-    "def _render_message(m):\n",
-    "    if isinstance(m, HumanMessage):\n",
-    "        return \"Human: \" + m.content\n",
-    "    elif isinstance(m, AIMessage):\n",
-    "        _m = \"AI: \" + m.content\n",
-    "        if len(m.tool_calls) > 0:\n",
-    "            _m += f\" Tools: {m.tool_calls}\"\n",
-    "        return _m\n",
-    "    elif isinstance(m, ToolMessage):\n",
-    "        return \"Tool Result: ...\"\n",
-    "    else:\n",
-    "        raise ValueError\n",
-    "\n",
-    "\n",
-    "def _render_messages(ms):\n",
-    "    m_string = [_render_message(m) for m in ms]\n",
-    "    return \"\\n\".join(m_string)\n",
-    "\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(BaseState)\n",
-    "\n",
-    "\n",
-    "def _agent(state: BaseState):\n",
-    "    if len(state[\"examples\"]) > 0:\n",
-    "        _examples = \"\\n\\n\".join(\n",
-    "            [\n",
-    "                f\"Example {i}: \" + _render_messages(e[\"messages\"])\n",
-    "                for i, e in enumerate(state[\"examples\"])\n",
-    "            ]\n",
-    "        )\n",
-    "        system_message = \"\"\"You are a helpful assistant. Below are some examples of interactions you had with users. \\\n",
-    "These were good interactions where the final result they got was the desired one. As much as possible, you should learn from these interactions and mimic them in the future. \\\n",
-    "Pay particularly close attention to when tools are called, and what the inputs are.!\n",
-    "\n",
-    "{examples}\n",
-    "\n",
-    "Assist the user as they require!\"\"\".format(\n",
-    "            examples=_examples\n",
-    "        )\n",
-    "\n",
-    "    else:\n",
-    "        system_message = \"\"\"You are a helpful assistant\"\"\"\n",
-    "    output = model.invoke([SystemMessage(content=system_message)] + state[\"messages\"])\n",
-    "    return {\"messages\": [output]}\n",
-    "\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", _agent)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")"
-   ]
+   "source": ["from typing import Annotated, TypedDict\n\nfrom langchain_core.messages import (\n    AIMessage,\n    AnyMessage,\n    HumanMessage,\n    SystemMessage,\n    ToolMessage,\n)\n\nfrom langgraph.graph import END, StateGraph, START\nfrom langgraph.graph.message import add_messages\nfrom langgraph.managed.few_shot import FewShotExamples\n\n\nclass BaseState(TypedDict):\n    messages: Annotated[list[AnyMessage], add_messages]\n    examples: Annotated[list, FewShotExamples]\n\n\ndef _render_message(m):\n    if isinstance(m, HumanMessage):\n        return \"Human: \" + m.content\n    elif isinstance(m, AIMessage):\n        _m = \"AI: \" + m.content\n        if len(m.tool_calls) > 0:\n            _m += f\" Tools: {m.tool_calls}\"\n        return _m\n    elif isinstance(m, ToolMessage):\n        return \"Tool Result: ...\"\n    else:\n        raise ValueError\n\n\ndef _render_messages(ms):\n    m_string = [_render_message(m) for m in ms]\n    return \"\\n\".join(m_string)\n\n\n# Define a new graph\nworkflow = StateGraph(BaseState)\n\n\ndef _agent(state: BaseState):\n    if len(state[\"examples\"]) > 0:\n        _examples = \"\\n\\n\".join(\n            [\n                f\"Example {i}: \" + _render_messages(e[\"messages\"])\n                for i, e in enumerate(state[\"examples\"])\n            ]\n        )\n        system_message = \"\"\"You are a helpful assistant. Below are some examples of interactions you had with users. \\\nThese were good interactions where the final result they got was the desired one. As much as possible, you should learn from these interactions and mimic them in the future. \\\nPay particularly close attention to when tools are called, and what the inputs are.!\n\n{examples}\n\nAssist the user as they require!\"\"\".format(\n            examples=_examples\n        )\n\n    else:\n        system_message = \"\"\"You are a helpful assistant\"\"\"\n    output = model.invoke([SystemMessage(content=system_message)] + state[\"messages\"])\n    return {\"messages\": [output]}\n\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", _agent)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")"]
   },
   {
    "cell_type": "markdown",
@@ -363,11 +228,7 @@
    "id": "6845ed6a-d155-4105-9160-28849877248b",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
-    "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")"
-   ]
+   "source": ["from langgraph.checkpoint.sqlite import SqliteSaver\n\nmemory = SqliteSaver.from_conn_string(\":memory:\")"]
   },
   {
    "cell_type": "code",
@@ -375,12 +236,7 @@
    "id": "79d29875-8aa8-434c-9f20-1c58346a6249",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"
-   ]
+   "source": ["# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile(checkpointer=memory, interrupt_before=[\"action\"])"]
   },
   {
    "cell_type": "markdown",
@@ -408,11 +264,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "from IPython.display import Image\n",
-    "\n",
-    "Image(app.get_graph().draw_png())"
-   ]
+   "source": ["from IPython.display import Image\n\nImage(app.get_graph().draw_png())"]
   },
   {
    "cell_type": "markdown",
@@ -438,14 +290,7 @@
      ]
     }
    ],
-   "source": [
-    "thread = {\"configurable\": {\"thread_id\": \"1\"}}\n",
-    "for event in app.stream(\n",
-    "    {\"messages\": [HumanMessage(content=\"what's the weather in sf?\")]}, thread\n",
-    "):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
-   ]
+   "source": ["thread = {\"configurable\": {\"thread_id\": \"1\"}}\nfor event in app.stream(\n    {\"messages\": [HumanMessage(content=\"what's the weather in sf?\")]}, thread\n):\n    for v in event.values():\n        print(v)"]
   },
   {
    "cell_type": "code",
@@ -465,10 +310,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "current_values = app.get_state(thread)\n",
-    "current_values.values"
-   ]
+   "source": ["current_values = app.get_state(thread)\ncurrent_values.values"]
   },
   {
    "cell_type": "code",
@@ -476,11 +318,7 @@
    "id": "1a0cdb78-40c6-4550-8c27-8f1b02d9e678",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "current_values.values[\"messages\"][-1].tool_calls[0][\"args\"][\n",
-    "    \"query\"\n",
-    "] = \"weather in San Francisco, Accuweather\""
-   ]
+   "source": ["current_values.values[\"messages\"][-1].tool_calls[0][\"args\"][\n    \"query\"\n] = \"weather in San Francisco, Accuweather\""]
   },
   {
    "cell_type": "code",
@@ -500,9 +338,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "app.update_state(thread, current_values.values)"
-   ]
+   "source": ["app.update_state(thread, current_values.values)"]
   },
   {
    "cell_type": "code",
@@ -521,9 +357,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "app.get_state(thread)"
-   ]
+   "source": ["app.get_state(thread)"]
   },
   {
    "cell_type": "code",
@@ -540,11 +374,7 @@
      ]
     }
    ],
-   "source": [
-    "for event in app.stream(None, thread):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
-   ]
+   "source": ["for event in app.stream(None, thread):\n    for v in event.values():\n        print(v)"]
   },
   {
    "cell_type": "code",
@@ -552,16 +382,7 @@
    "id": "84748206-975e-4a33-a178-d43df683298c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "chkpnt_tuple = memory.get_tuple({\"configurable\": {\"thread_id\": \"1\"}})\n",
-    "config = chkpnt_tuple.config\n",
-    "checkpoint = chkpnt_tuple.checkpoint\n",
-    "metadata = chkpnt_tuple.metadata\n",
-    "\n",
-    "# mark as \"good\"\n",
-    "metadata[\"score\"] = 1\n",
-    "memory.put(config, checkpoint, metadata)"
-   ]
+   "source": ["chkpnt_tuple = memory.get_tuple({\"configurable\": {\"thread_id\": \"1\"}})\nconfig = chkpnt_tuple.config\ncheckpoint = chkpnt_tuple.checkpoint\nmetadata = chkpnt_tuple.metadata\n\n# mark as \"good\"\nmetadata[\"score\"] = 1\nmemory.put(config, checkpoint, metadata)"]
   },
   {
    "cell_type": "code",
@@ -569,9 +390,7 @@
    "id": "ce7fa228-8c37-4001-afd4-0001b268e1db",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "examples = list(memory.search({\"score\": 1}))"
-   ]
+   "source": ["examples = list(memory.search({\"score\": 1}))"]
   },
   {
    "cell_type": "code",
@@ -590,9 +409,7 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "examples"
-   ]
+   "source": ["examples"]
   },
   {
    "cell_type": "code",
@@ -608,14 +425,7 @@
      ]
     }
    ],
-   "source": [
-    "thread = {\"configurable\": {\"thread_id\": \"7\"}}\n",
-    "for event in app.stream(\n",
-    "    {\"messages\": [HumanMessage(content=\"what's the weather in la?\")]}, thread\n",
-    "):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
-   ]
+   "source": ["thread = {\"configurable\": {\"thread_id\": \"7\"}}\nfor event in app.stream(\n    {\"messages\": [HumanMessage(content=\"what's the weather in la?\")]}, thread\n):\n    for v in event.values():\n        print(v)"]
   },
   {
    "cell_type": "code",
@@ -632,11 +442,7 @@
      ]
     }
    ],
-   "source": [
-    "for event in app.stream(None, thread):\n",
-    "    for v in event.values():\n",
-    "        print(v)"
-   ]
+   "source": ["for event in app.stream(None, thread):\n    for v in event.values():\n        print(v)"]
   },
   {
    "cell_type": "code",
@@ -644,7 +450,7 @@
    "id": "9ab115de-9b11-4e8b-8ace-c23e1369300b",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/managing-agent-steps.ipynb

@@ -28,10 +28,7 @@
    "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install --quiet -U langgraph langchain_openai"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install --quiet -U langgraph langchain_openai"]
   },
   {
    "cell_type": "markdown",
@@ -47,18 +44,7 @@
    "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_env(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
-    "\n",
-    "\n",
-    "_set_env(\"OPENAI_API_KEY\")"
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_env(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"{var}: \")\n\n\n_set_env(\"OPENAI_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -74,10 +60,7 @@
    "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "_set_env(\"LANGCHAIN_API_KEY\")"
-   ]
+   "source": ["os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n_set_env(\"LANGCHAIN_API_KEY\")"]
   },
   {
    "cell_type": "markdown",
@@ -103,22 +86,7 @@
    "id": "5f374964",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from typing_extensions import TypedDict\n",
-    "\n",
-    "from langgraph.graph.message import add_messages\n",
-    "\n",
-    "# Add messages essentially does this with more\n",
-    "# robust handling\n",
-    "# def add_messages(left: list, right: list):\n",
-    "#     return left + right\n",
-    "\n",
-    "\n",
-    "class State(TypedDict):\n",
-    "    messages: Annotated[list, add_messages]"
-   ]
+   "source": ["from typing import Annotated\n\nfrom typing_extensions import TypedDict\n\nfrom langgraph.graph.message import add_messages\n\n# Add messages essentially does this with more\n# robust handling\n# def add_messages(left: list, right: list):\n#     return left + right\n\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]"]
   },
   {
    "cell_type": "markdown",
@@ -138,21 +106,7 @@
    "id": "692cffb0",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.tools import tool\n",
-    "\n",
-    "\n",
-    "@tool\n",
-    "def search(query: str):\n",
-    "    \"\"\"Call to surf the web.\"\"\"\n",
-    "    # This is a placeholder, but don't tell the LLM that...\n",
-    "    return [\n",
-    "        \"Try again in a few seconds! Checking with the weathermen... Call be again next.\"\n",
-    "    ]\n",
-    "\n",
-    "\n",
-    "tools = [search]"
-   ]
+   "source": ["from langchain_core.tools import tool\n\n\n@tool\ndef search(query: str):\n    \"\"\"Call to surf the web.\"\"\"\n    # This is a placeholder, but don't tell the LLM that...\n    return [\n        \"Try again in a few seconds! Checking with the weathermen... Call be again next.\"\n    ]\n\n\ntools = [search]"]
   },
   {
    "cell_type": "markdown",
@@ -169,11 +123,7 @@
    "id": "ae7abc20",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.prebuilt import ToolNode\n",
-    "\n",
-    "tool_node = ToolNode(tools)"
-   ]
+   "source": ["from langgraph.prebuilt import ToolNode\n\ntool_node = ToolNode(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -197,11 +147,7 @@
    "id": "4ad247ff",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"
-   ]
+   "source": ["from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)"]
   },
   {
    "cell_type": "markdown",
@@ -219,9 +165,7 @@
    "id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "model = model.bind_tools(tools)"
-   ]
+   "source": ["model = model.bind_tools(tools)"]
   },
   {
    "cell_type": "markdown",
@@ -256,21 +200,7 @@
    "id": "e718a9c5-6596-457f-ac25-a25d8cb8c259",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Literal\n",
-    "\n",
-    "\n",
-    "# Define the function that determines whether to continue or not\n",
-    "def should_continue(state: State) -> Literal[\"__end__\", \"action\"]:\n",
-    "    messages = state[\"messages\"]\n",
-    "    last_message = messages[-1]\n",
-    "    # If there is no function call, then we finish\n",
-    "    if not last_message.tool_calls:\n",
-    "        return \"end\"\n",
-    "    # Otherwise if there is, we continue\n",
-    "    else:\n",
-    "        return \"continue\""
-   ]
+   "source": ["from typing import Literal\n\n\n# Define the function that determines whether to continue or not\ndef should_continue(state: State) -> Literal[\"__end__\", \"action\"]:\n    messages = state[\"messages\"]\n    last_message = messages[-1]\n    # If there is no function call, then we finish\n    if not last_message.tool_calls:\n        return \"end\"\n    # Otherwise if there is, we continue\n    else:\n        return \"continue\""]
   },
   {
    "cell_type": "markdown",
@@ -288,19 +218,7 @@
    "id": "714e4135-7cb5-4f17-b2ae-46f7e98bde61",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Define the function that calls the model\n",
-    "def call_model(state):\n",
-    "    messages = []\n",
-    "    for m in state[\"messages\"][::-1]:\n",
-    "        messages.append(m)\n",
-    "        if len(messages) >= 5:\n",
-    "            if messages[-1].type != \"tool\":\n",
-    "                break\n",
-    "    response = model.invoke(messages[::-1])\n",
-    "    # We return a list, because this will get added to the existing list\n",
-    "    return {\"messages\": [response]}"
-   ]
+   "source": ["# Define the function that calls the model\ndef call_model(state):\n    messages = []\n    for m in state[\"messages\"][::-1]:\n        messages.append(m)\n        if len(messages) >= 5:\n            if messages[-1].type != \"tool\":\n                break\n    response = model.invoke(messages[::-1])\n    # We return a list, because this will get added to the existing list\n    return {\"messages\": [response]}"]
   },
   {
    "cell_type": "markdown",
@@ -318,50 +236,7 @@
    "id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "# Define a new graph\n",
-    "workflow = StateGraph(State)\n",
-    "\n",
-    "# Define the two nodes we will cycle between\n",
-    "workflow.add_node(\"agent\", call_model)\n",
-    "workflow.add_node(\"action\", tool_node)\n",
-    "\n",
-    "# Set the entrypoint as `agent`\n",
-    "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
-    "\n",
-    "# We now add a conditional edge\n",
-    "workflow.add_conditional_edges(\n",
-    "    # First, we define the start node. We use `agent`.\n",
-    "    # This means these are the edges taken after the `agent` node is called.\n",
-    "    \"agent\",\n",
-    "    # Next, we pass in the function that will determine which node is called next.\n",
-    "    should_continue,\n",
-    "    # Finally we pass in a mapping.\n",
-    "    # The keys are strings, and the values are other nodes.\n",
-    "    # END is a special node marking that the graph should finish.\n",
-    "    # What will happen is we will call `should_continue`, and then the output of that\n",
-    "    # will be matched against the keys in this mapping.\n",
-    "    # Based on which one it matches, that node will then be called.\n",
-    "    {\n",
-    "        # If `tools`, then we call the tool node.\n",
-    "        \"continue\": \"action\",\n",
-    "        # Otherwise we finish.\n",
-    "        \"end\": END,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "# We now add a normal edge from `tools` to `agent`.\n",
-    "# This means that after `tools` is called, `agent` node is called next.\n",
-    "workflow.add_edge(\"action\", \"agent\")\n",
-    "\n",
-    "# Finally, we compile it!\n",
-    "# This compiles it into a LangChain Runnable,\n",
-    "# meaning you can use it as you would any other runnable\n",
-    "app = workflow.compile()"
-   ]
+   "source": ["from langgraph.graph import END, StateGraph, START\n\n# Define a new graph\nworkflow = StateGraph(State)\n\n# Define the two nodes we will cycle between\nworkflow.add_node(\"agent\", call_model)\nworkflow.add_node(\"action\", tool_node)\n\n# Set the entrypoint as `agent`\n# This means that this node is the first one called\nworkflow.add_edge(START, \"agent\")\n\n# We now add a conditional edge\nworkflow.add_conditional_edges(\n    # First, we define the start node. We use `agent`.\n    # This means these are the edges taken after the `agent` node is called.\n    \"agent\",\n    # Next, we pass in the function that will determine which node is called next.\n    should_continue,\n    # Finally we pass in a mapping.\n    # The keys are strings, and the values are other nodes.\n    # END is a special node marking that the graph should finish.\n    # What will happen is we will call `should_continue`, and then the output of that\n    # will be matched against the keys in this mapping.\n    # Based on which one it matches, that node will then be called.\n    {\n        # If `tools`, then we call the tool node.\n        \"continue\": \"action\",\n        # Otherwise we finish.\n        \"end\": END,\n    },\n)\n\n# We now add a normal edge from `tools` to `agent`.\n# This means that after `tools` is called, `agent` node is called next.\nworkflow.add_edge(\"action\", \"agent\")\n\n# Finally, we compile it!\n# This compiles it into a LangChain Runnable,\n# meaning you can use it as you would any other runnable\napp = workflow.compile()"]
   },
   {
    "cell_type": "code",
@@ -380,11 +255,7 @@
      "output_type": "display_data"
     }
    ],
-   "source": [
-    "from IPython.display import Image, display\n",
-    "\n",
-    "display(Image(app.get_graph(xray=True).draw_mermaid_png()))"
-   ]
+   "source": ["from IPython.display import Image, display\n\ndisplay(Image(app.get_graph(xray=True).draw_mermaid_png()))"]
   },
   {
    "cell_type": "markdown",
@@ -635,22 +506,7 @@
      ]
     }
    ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "inputs = {\n",
-    "    \"messages\": [\n",
-    "        HumanMessage(\n",
-    "            content=\"what is the weather in sf? Don't give up! Keep using your tools.\"\n",
-    "        )\n",
-    "    ]\n",
-    "}\n",
-    "for event in app.stream(inputs, stream_mode=\"values\"):\n",
-    "    # stream() yields dictionaries with output keyed by node name\n",
-    "    for message in event[\"messages\"]:\n",
-    "        message.pretty_print()\n",
-    "    print(\"\\n---\\n\")"
-   ]
+   "source": ["from langchain_core.messages import HumanMessage\n\ninputs = {\n    \"messages\": [\n        HumanMessage(\n            content=\"what is the weather in sf? Don't give up! Keep using your tools.\"\n        )\n    ]\n}\nfor event in app.stream(inputs, stream_mode=\"values\"):\n    # stream() yields dictionaries with output keyed by node name\n    for message in event[\"messages\"]:\n        message.pretty_print()\n    print(\"\\n---\\n\")"]
   },
   {
    "cell_type": "code",
@@ -658,7 +514,7 @@
    "id": "08ae8246-11d5-40e1-8567-361e5bef8917",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {

examples/memory/add-summary-conversation-history.ipynb

@@ -0,0 +1,543 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
+   "metadata": {},
+   "source": [
+    "# How to add summary of the conversation history\n",
+    "\n",
+    "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. One way to work around that is to create a summary of the conversation to date, and use that with the past N messages. This guide will go through an example of how to do that.\n",
+    "\n",
+    "This will involve a few steps:\n",
+    "- Check if the conversation is too long (can be done by checking number of messages or length of messages)\n",
+    "- If yes, the create summary (will need a prompt for this)\n",
+    "- Then remove all except the last N messages\n",
+    "\n",
+    "A big part of this is deleting old messages. For an in depth guide on how to do that, see [this guide](./delete-messages.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7cbd446a-808f-4394-be92-d45ab818953c",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "First, let's set up the packages we're going to want to use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install --quiet -U langgraph langchain_anthropic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0abe11f4-62ed-4dc4-8875-3db21e260d1d",
+   "metadata": {},
+   "source": [
+    "Next, we need to set API keys for Anthropic (the LLM we will use)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "\n",
+    "def _set_env(var: str):\n",
+    "    if not os.environ.get(var):\n",
+    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
+    "\n",
+    "\n",
+    "_set_env(\"ANTHROPIC_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0ed46a8-effe-4596-b0e1-a6a29ee16f5c",
+   "metadata": {},
+   "source": [
+    "Optionally, we can set API key for [LangSmith tracing](https://smith.langchain.com/), which will give us best-in-class observability."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "_set_env(\"LANGCHAIN_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84835fdb-a5f3-4c90-85f3-0e6257650aba",
+   "metadata": {},
+   "source": [
+    "## Build the chatbot\n",
+    "\n",
+    "Let's now build the chatbot."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "378899a9-3b9a-4748-95b6-eb00e0828677",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Literal\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "from langchain_core.messages import SystemMessage, RemoveMessage\n",
+    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.graph import MessagesState, StateGraph, START, END\n",
+    "\n",
+    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "\n",
+    "# We will add a `summary` attribute (in addition to `messages` key,\n",
+    "# which MessagesState already has)\n",
+    "class State(MessagesState):\n",
+    "    summary: str\n",
+    "\n",
+    "# We will use this model for both the conversation and the summarization\n",
+    "model = ChatAnthropic(model_name=\"claude-3-haiku-20240307\")\n",
+    "\n",
+    "# Define the logic to call the model\n",
+    "def call_model(state: State):\n",
+    "    # If a summary exists, we add this in as a system message\n",
+    "    summary = state.get('summary', '')\n",
+    "    if summary:\n",
+    "        system_message = f\"Summary of conversation earlier: {summary}\"\n",
+    "        messages = [SystemMessage(content=system_message)] + state['messages']\n",
+    "    else:\n",
+    "        messages = state['messages']\n",
+    "    response = model.invoke(messages)\n",
+    "    # We return a list, because this will get added to the existing list\n",
+    "    return {\"messages\": [response]}\n",
+    "\n",
+    "\n",
+    "# We now define the logic for determining whether to end or summarize the conversation\n",
+    "def should_continue(state: State) -> Literal[\"summarize_conversation\", END]:\n",
+    "    \"\"\"Return the next node to execute.\"\"\"\n",
+    "    messages = state[\"messages\"]\n",
+    "    # If there are more than six messages, then we summarize the conversation\n",
+    "    if len(messages) > 6:\n",
+    "        return \"summarize_conversation\"\n",
+    "    # Otherwise we can just end\n",
+    "    return END\n",
+    "\n",
+    "\n",
+    "def summarize_conversation(state: State):\n",
+    "    # First, we summarize the conversation\n",
+    "    summary = state.get('summary', '')\n",
+    "    if summary:\n",
+    "        # If a summary already exists, we use a different system prompt\n",
+    "        # to summarize it than if one didn't\n",
+    "        summary_message = (\n",
+    "            f\"This is summary of the conversation to date: {summary}\\n\\n\"\n",
+    "            \"Extend the summary by taking into account the new messages above:\"\n",
+    "        )\n",
+    "    else:\n",
+    "        summary_message = \"Create a summary of the conversation above:\"\n",
+    "        \n",
+    "    messages = state['messages'] + [HumanMessage(content=summary_message)]\n",
+    "    response = model.invoke(messages)\n",
+    "    # We now need to delete messages that we no longer want to show up\n",
+    "    # I will delete all but the last two messages, but you can change this\n",
+    "    delete_messages = [RemoveMessage(id=m.id) for m in state['messages'][:-2]]\n",
+    "    return {\n",
+    "        \"summary\": response.content,\n",
+    "        \"messages\": delete_messages\n",
+    "    }\n",
+    "    \n",
+    "\n",
+    "\n",
+    "# Define a new graph\n",
+    "workflow = StateGraph(State)\n",
+    "\n",
+    "# Define the conversation node and the summarize node\n",
+    "workflow.add_node(\"conversation\", call_model)\n",
+    "workflow.add_node(summarize_conversation)\n",
+    "\n",
+    "# Set the entrypoint as conversation\n",
+    "workflow.add_edge(START, \"conversation\")\n",
+    "\n",
+    "# We now add a conditional edge\n",
+    "workflow.add_conditional_edges(\n",
+    "    # First, we define the start node. We use `conversation`.\n",
+    "    # This means these are the edges taken after the `conversation` node is called.\n",
+    "    \"conversation\",\n",
+    "    # Next, we pass in the function that will determine which node is called next.\n",
+    "    should_continue,\n",
+    ")\n",
+    "\n",
+    "# We now add a normal edge from `summarize_conversation` to END.\n",
+    "# This means that after `summarize_conversation` is called, we end.\n",
+    "workflow.add_edge(\"summarize_conversation\", END)\n",
+    "\n",
+    "# Finally, we compile it!\n",
+    "app = workflow.compile(checkpointer=memory)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "41c2872e-04b3-4c44-9e03-9e84a5230adf",
+   "metadata": {},
+   "source": [
+    "## Using the graph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "dc697132-8fa1-4bf5-9722-56a9859331ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def print_update(update):\n",
+    "    for k, v in update.items():\n",
+    "        for m in v['messages']:\n",
+    "            m.pretty_print()\n",
+    "        if 'summary' in v:\n",
+    "            print(v['summary'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "57b27553-21be-43e5-ac48-d1d0a3aa0dca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "hi! I'm bob\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "It's nice to meet you, Bob! I'm an AI assistant created by Anthropic. How can I help you today?\n",
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "what's my name?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "Your name is Bob, as you told me at the beginning of our conversation.\n",
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "i like the celtics!\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "That's great, the Celtics are a fun team to follow! Basketball is an exciting sport. Do you have a favorite Celtics player or a favorite moment from a Celtics game you've watched? I'd be happy to discuss the team and the sport with you.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "config = {\"configurable\": {\"thread_id\": \"4\"}}\n",
+    "input_message = HumanMessage(content=\"hi! I'm bob\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)\n",
+    "\n",
+    "input_message = HumanMessage(content=\"what's my name?\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)\n",
+    "\n",
+    "input_message = HumanMessage(content=\"i like the celtics!\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9760e219-a7fc-4d81-b4e8-1334c5afc510",
+   "metadata": {},
+   "source": [
+    "We can see that so far no summarization has happened - this is because there are only six messages in the list."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "935265a0-d511-475a-8a0d-b3c3cc5e42a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content=\"hi! I'm bob\", id='6534853d-b8a7-44b9-837b-eb7abaf7ebf7'),\n",
+       "  AIMessage(content=\"It's nice to meet you, Bob! I'm an AI assistant created by Anthropic. How can I help you today?\", response_metadata={'id': 'msg_015wCFew2vwMQJcpUh2VZ5ah', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 12, 'output_tokens': 30}}, id='run-0d33008b-1094-4f5e-94ce-293283fc3024-0'),\n",
+       "  HumanMessage(content=\"what's my name?\", id='0a4f203a-b95a-42a9-b1c5-bb20f68b3251'),\n",
+       "  AIMessage(content='Your name is Bob, as you told me at the beginning of our conversation.', response_metadata={'id': 'msg_01PLp8wg2xDsJbNR9uCtxcGz', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 50, 'output_tokens': 19}}, id='run-3815dd4d-ee0c-4fc2-9889-f6dd40325961-0'),\n",
+       "  HumanMessage(content='i like the celtics!', id='ac128172-42d1-4390-b7cc-7bcb2d22ee48'),\n",
+       "  AIMessage(content=\"That's great, the Celtics are a fun team to follow! Basketball is an exciting sport. Do you have a favorite Celtics player or a favorite moment from a Celtics game you've watched? I'd be happy to discuss the team and the sport with you.\", response_metadata={'id': 'msg_01CSg5avZEx6CKcZsSvSVXpr', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 78, 'output_tokens': 61}}, id='run-698faa28-0f72-495f-8ebe-e948664d2200-0')]}"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "values = app.get_state(config).values\n",
+    "values"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb40eddb-9a31-4410-a4c0-9762e2d89e56",
+   "metadata": {},
+   "source": [
+    "Now let's send another message in"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "048805a4-3d97-4e76-ac45-8d80d4364c46",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "i like how much they win\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "That's understandable, the Celtics have been one of the more successful NBA franchises over the years. Their history of winning championships is very impressive. It's always fun to follow a team that regularly competes for titles. What do you think has been the key to the Celtics' sustained success? Is there a particular era or team that stands out as your favorite?\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "Here is a summary of our conversation so far:\n",
+      "\n",
+      "- You introduced yourself as Bob and said you like the Boston Celtics basketball team.\n",
+      "- I acknowledged that it's nice to meet you, Bob, and noted that you had shared your name earlier in the conversation.\n",
+      "- You expressed that you like how much the Celtics win, and I agreed that their history of sustained success and championship pedigree is impressive.\n",
+      "- I asked if you have a favorite Celtics player or moment that stands out to you, and invited further discussion about the team and the sport of basketball.\n",
+      "- The overall tone has been friendly and conversational, with me trying to engage with your interest in the Celtics by asking follow-up questions.\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_message = HumanMessage(content=\"i like how much they win\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b196367-6151-4982-9430-3db7373de06e",
+   "metadata": {},
+   "source": [
+    "If we check the state now, we can see that we have a summary of the conversation, as well as the last two messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "09ebb693-4738-4474-a095-6491def5c5f9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content='i like how much they win', id='bb916ce7-534c-4d48-9f92-e269f9dc4859'),\n",
+       "  AIMessage(content=\"That's understandable, the Celtics have been one of the more successful NBA franchises over the years. Their history of winning championships is very impressive. It's always fun to follow a team that regularly competes for titles. What do you think has been the key to the Celtics' sustained success? Is there a particular era or team that stands out as your favorite?\", response_metadata={'id': 'msg_01B7TMagaM8xBnYXLSMwUDAG', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 148, 'output_tokens': 82}}, id='run-c5aa9a8f-7983-4a7f-9c1e-0c0055334ac1-0')],\n",
+       " 'summary': \"Here is a summary of our conversation so far:\\n\\n- You introduced yourself as Bob and said you like the Boston Celtics basketball team.\\n- I acknowledged that it's nice to meet you, Bob, and noted that you had shared your name earlier in the conversation.\\n- You expressed that you like how much the Celtics win, and I agreed that their history of sustained success and championship pedigree is impressive.\\n- I asked if you have a favorite Celtics player or moment that stands out to you, and invited further discussion about the team and the sport of basketball.\\n- The overall tone has been friendly and conversational, with me trying to engage with your interest in the Celtics by asking follow-up questions.\"}"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "values = app.get_state(config).values\n",
+    "values"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "966e4177-c0fc-4fd0-a494-dd03f7f2fddb",
+   "metadata": {},
+   "source": [
+    "We can now resume having a conversation! Note that even though we only have the last two messages, we can still ask it questions about things mentioned earlier in the conversation (because we summarized those)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "7094c5ab-66f8-42ff-b1c3-90c8a9468e62",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "what's my name?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "In our conversation so far, you introduced yourself as Bob. I acknowledged that earlier when you had shared your name.\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_message = HumanMessage(content=\"what's my name?\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "40e5db8e-9db9-4ac7-9d76-a99fd4034bf3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "what NFL team do you think I like?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "I don't actually have any information about what NFL team you might like. In our conversation so far, you've only mentioned that you're a fan of the Boston Celtics basketball team. I don't have any prior knowledge about your preferences for NFL teams. Unless you provide me with that information, I don't have a basis to guess which NFL team you might be a fan of.\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_message = HumanMessage(content=\"what NFL team do you think I like?\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "0a1a0fda-5309-45f0-9465-9f3dff604d74",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "i like the patriots!\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "Okay, got it! Thanks for sharing that you're also a fan of the New England Patriots in the NFL. That makes sense, given your interest in other Boston sports teams like the Celtics. The Patriots have also had a very successful run over the past couple of decades, winning multiple Super Bowls. It's fun to follow winning franchises like the Celtics and Patriots. Do you have a favorite Patriots player or moment that stands out to you?\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "================================\u001b[1m Remove Message \u001b[0m================================\n",
+      "\n",
+      "\n",
+      "Okay, extending the summary with the new information:\n",
+      "\n",
+      "- You initially introduced yourself as Bob and said you like the Boston Celtics basketball team. \n",
+      "- I acknowledged that and we discussed your appreciation for the Celtics' history of winning.\n",
+      "- You then asked what your name was, and I reminded you that you had introduced yourself as Bob earlier in the conversation.\n",
+      "- You followed up by asking what NFL team I thought you might like, and I explained that I didn't have any prior information about your NFL team preferences.\n",
+      "- You then revealed that you are also a fan of the New England Patriots, which made sense given your Celtics fandom.\n",
+      "- I responded positively to this new information, noting the Patriots' own impressive success and dynasty over the past couple of decades.\n",
+      "- I then asked if you have a particular favorite Patriots player or moment that stands out to you, continuing the friendly, conversational tone.\n",
+      "\n",
+      "Overall, the discussion has focused on your sports team preferences, with you sharing that you are a fan of both the Celtics and the Patriots. I've tried to engage with your interests and ask follow-up questions to keep the dialogue flowing.\n"
+     ]
+    }
+   ],
+   "source": [
+    "input_message = HumanMessage(content=\"i like the patriots!\")\n",
+    "input_message.pretty_print()\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"updates\"):\n",
+    "    print_update(event)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "67d26013-1362-4cee-b135-ab5c3c4eb3d0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/memory/delete-messages.ipynb

@@ -0,0 +1,495 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
+   "metadata": {},
+   "source": [
+    "# How to delete messages\n",
+    "\n",
+    "One of the common states for a graph is a list of messages. Usually you only add messages to that state. However, sometimes you may want to remove messages (either by directly modifying the state or as part of the graph). To do that, you can use the `RemoveMessage` modifier. In this guide, we will cover how to do that.\n",
+    "\n",
+    "The key idea is that each state key has a `reducer` key. This key specifies how to combine updates to the state. The default `MessagesState` has a messages key, and the reducer for that key accepts these `RemoveMessage` modifiers. That reducer then uses these `RemoveMessage` to delete messages from the key.\n",
+    "\n",
+    "So note that just because your graph state has a key that is a list of messages, it doesn't mean that that this `RemoveMessage` modifier will work. You also have to have a `reducer` defined that knows how to work with this.\n",
+    "\n",
+    "**NOTE**: Many models expect certain rules around lists of messages. For example, some expect them to start with a `user` message, others expect all messages with tool calls to be followed by a tool message. **When deleting messages, you will want to make sure you don't violate these rules.**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7cbd446a-808f-4394-be92-d45ab818953c",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "First, let's build a simple graph that uses messages. Note that it's using the `MessagesState` which has the required `reducer`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install --quiet -U langgraph langchain_anthropic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0abe11f4-62ed-4dc4-8875-3db21e260d1d",
+   "metadata": {},
+   "source": [
+    "Next, we need to set API keys for Anthropic (the LLM we will use)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "ANTHROPIC_API_KEY:  ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "\n",
+    "def _set_env(var: str):\n",
+    "    if not os.environ.get(var):\n",
+    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
+    "\n",
+    "\n",
+    "_set_env(\"ANTHROPIC_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0ed46a8-effe-4596-b0e1-a6a29ee16f5c",
+   "metadata": {},
+   "source": [
+    "Optionally, we can set API key for [LangSmith tracing](https://smith.langchain.com/), which will give us best-in-class observability."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "_set_env(\"LANGCHAIN_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4767ef1c-a7cf-41f8-a301-558988cb7ac5",
+   "metadata": {},
+   "source": [
+    "## Build the agent\n",
+    "Let's now build a simple ReAct style agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "378899a9-3b9a-4748-95b6-eb00e0828677",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Literal\n",
+    "\n",
+    "from langchain_anthropic import ChatAnthropic\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.graph import MessagesState, StateGraph, START\n",
+    "from langgraph.prebuilt import ToolNode\n",
+    "\n",
+    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def search(query: str):\n",
+    "    \"\"\"Call to surf the web.\"\"\"\n",
+    "    # This is a placeholder for the actual implementation\n",
+    "    # Don't let the LLM know this though 😊\n",
+    "    return [\n",
+    "        \"It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\"\n",
+    "    ]\n",
+    "\n",
+    "\n",
+    "tools = [search]\n",
+    "tool_node = ToolNode(tools)\n",
+    "model = ChatAnthropic(model_name=\"claude-3-haiku-20240307\")\n",
+    "bound_model = model.bind_tools(tools)\n",
+    "\n",
+    "\n",
+    "def should_continue(state: MessagesState) -> Literal[\"action\", \"__end__\"]:\n",
+    "    \"\"\"Return the next node to execute.\"\"\"\n",
+    "    last_message = state[\"messages\"][-1]\n",
+    "    # If there is no function call, then we finish\n",
+    "    if not last_message.tool_calls:\n",
+    "        return \"__end__\"\n",
+    "    # Otherwise if there is, we continue\n",
+    "    return \"action\"\n",
+    "\n",
+    "\n",
+    "# Define the function that calls the model\n",
+    "def call_model(state: MessagesState):\n",
+    "    response = model.invoke(state[\"messages\"])\n",
+    "    # We return a list, because this will get added to the existing list\n",
+    "    return {\"messages\": response}\n",
+    "\n",
+    "\n",
+    "# Define a new graph\n",
+    "workflow = StateGraph(MessagesState)\n",
+    "\n",
+    "# Define the two nodes we will cycle between\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", tool_node)\n",
+    "\n",
+    "# Set the entrypoint as `agent`\n",
+    "# This means that this node is the first one called\n",
+    "workflow.add_edge(START, \"agent\")\n",
+    "\n",
+    "# We now add a conditional edge\n",
+    "workflow.add_conditional_edges(\n",
+    "    # First, we define the start node. We use `agent`.\n",
+    "    # This means these are the edges taken after the `agent` node is called.\n",
+    "    \"agent\",\n",
+    "    # Next, we pass in the function that will determine which node is called next.\n",
+    "    should_continue,\n",
+    ")\n",
+    "\n",
+    "# We now add a normal edge from `tools` to `agent`.\n",
+    "# This means that after `tools` is called, `agent` node is called next.\n",
+    "workflow.add_edge(\"action\", \"agent\")\n",
+    "\n",
+    "# Finally, we compile it!\n",
+    "# This compiles it into a LangChain Runnable,\n",
+    "# meaning you can use it as you would any other runnable\n",
+    "app = workflow.compile(checkpointer=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "57b27553-21be-43e5-ac48-d1d0a3aa0dca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "hi! I'm bob\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "It's nice to meet you, Bob! I'm Claude, an AI assistant created by Anthropic. How can I assist you today?\n",
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "what's my name?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "Your name is Bob, as you introduced yourself at the beginning of our conversation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "config = {\"configurable\": {\"thread_id\": \"2\"}}\n",
+    "input_message = HumanMessage(content=\"hi! I'm bob\")\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()\n",
+    "\n",
+    "\n",
+    "input_message = HumanMessage(content=\"what's my name?\")\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2fb0de5b-30ec-42d4-813a-7ad63fe1c367",
+   "metadata": {},
+   "source": [
+    "## Manually deleting messages\n",
+    "\n",
+    "First, we will cover how to manually delete messages. Let's take a look at the current state of the thread:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8a850529-d038-48f7-b5a2-8d4d2923f83a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content=\"hi! I'm bob\", id='bc1c6dd2-3bb9-4aa9-b7af-3c6af7e173ea'),\n",
+       " AIMessage(content=\"It's nice to meet you, Bob! I'm Claude, an AI assistant created by Anthropic. How can I assist you today?\", response_metadata={'id': 'msg_01XPSAenmSqK8rX2WgPZHfz7', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 12, 'output_tokens': 32}}, id='run-1c69af09-adb1-412d-9010-2456e5a555fb-0', usage_metadata={'input_tokens': 12, 'output_tokens': 32, 'total_tokens': 44}),\n",
+       " HumanMessage(content=\"what's my name?\", id='f3c71afe-8ce2-4ed0-991e-65021f03b0a5'),\n",
+       " AIMessage(content='Your name is Bob, as you introduced yourself at the beginning of our conversation.', response_metadata={'id': 'msg_01BPZdwsjuMAbC1YAkqawXaF', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 52, 'output_tokens': 19}}, id='run-b2eb9137-2f4e-446f-95f5-3d5f621a2cf8-0', usage_metadata={'input_tokens': 52, 'output_tokens': 19, 'total_tokens': 71})]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = app.get_state(config).values['messages']\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81be8a0a-1e94-4302-bd84-d1b72e3c501c",
+   "metadata": {},
+   "source": [
+    "We can call `update_state` and pass in the id of the first message. This will delete that message."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "df1a0970-7e64-4170-beef-2855d10eef42",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/vadymbarda/.virtualenvs/langgraph/lib/python3.11/site-packages/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: The class `RemoveMessage` is in beta. It is actively being worked on, so the API may change.\n",
+      "  warn_beta(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'configurable': {'thread_id': '2',\n",
+       "  'thread_ts': '1ef42d00-d9ad-6f24-8005-feb089654def'}}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import RemoveMessage\n",
+    "app.update_state(config, {\"messages\": RemoveMessage(id=messages[0].id)})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c9127ae-0d42-42b8-957f-ea69a5da555f",
+   "metadata": {},
+   "source": [
+    "If we now look at the messages, we can verify that the first one was deleted."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "8bfe4ffa-e170-43bc-aec4-6e36ac620931",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content=\"It's nice to meet you, Bob! I'm Claude, an AI assistant created by Anthropic. How can I assist you today?\", response_metadata={'id': 'msg_01XPSAenmSqK8rX2WgPZHfz7', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 12, 'output_tokens': 32}}, id='run-1c69af09-adb1-412d-9010-2456e5a555fb-0', usage_metadata={'input_tokens': 12, 'output_tokens': 32, 'total_tokens': 44}),\n",
+       " HumanMessage(content=\"what's my name?\", id='f3c71afe-8ce2-4ed0-991e-65021f03b0a5'),\n",
+       " AIMessage(content='Your name is Bob, as you introduced yourself at the beginning of our conversation.', response_metadata={'id': 'msg_01BPZdwsjuMAbC1YAkqawXaF', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 52, 'output_tokens': 19}}, id='run-b2eb9137-2f4e-446f-95f5-3d5f621a2cf8-0', usage_metadata={'input_tokens': 52, 'output_tokens': 19, 'total_tokens': 71})]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = app.get_state(config).values['messages']\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef129a75-4cad-44d7-b532-eb37b0553c0c",
+   "metadata": {},
+   "source": [
+    "## Programmatically deleting messages\n",
+    "\n",
+    "We can also delete messages programmatically from inside the graph. Here we'll modify the graph to delete any old messages (longer than 3 messages ago) at the end of a graph run."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "bb22ede0-e153-4fd0-a4c0-f9af2f7663b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import RemoveMessage\n",
+    "from langgraph.graph import END\n",
+    "\n",
+    "\n",
+    "def delete_messages(state):\n",
+    "    messages = state['messages']\n",
+    "    if len(messages) > 3:\n",
+    "        return {\"messages\": [RemoveMessage(id=m.id) for m in messages[:-3]]}\n",
+    "\n",
+    "# We need to modify the logic to call delete_messages rather than end right away\n",
+    "def should_continue(state: MessagesState) -> Literal[\"action\", \"delete_messages\"]:\n",
+    "    \"\"\"Return the next node to execute.\"\"\"\n",
+    "    last_message = state[\"messages\"][-1]\n",
+    "    # If there is no function call, then we call our delete_messages function\n",
+    "    if not last_message.tool_calls:\n",
+    "        return \"delete_messages\"\n",
+    "    # Otherwise if there is, we continue\n",
+    "    return \"action\"\n",
+    "\n",
+    "\n",
+    "# Define a new graph\n",
+    "workflow = StateGraph(MessagesState)\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", tool_node)\n",
+    "\n",
+    "# This is our new node we're defining\n",
+    "workflow.add_node(delete_messages)\n",
+    "\n",
+    "\n",
+    "workflow.add_edge(START, \"agent\")\n",
+    "workflow.add_conditional_edges(\"agent\", should_continue,)\n",
+    "workflow.add_edge(\"action\", \"agent\")\n",
+    "\n",
+    "# This is the new edge we're adding: after we delete messages, we finish\n",
+    "workflow.add_edge(\"delete_messages\", END)\n",
+    "app = workflow.compile(checkpointer=memory)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52cbdef6-7db7-45a2-8194-de4f8929bd1f",
+   "metadata": {},
+   "source": [
+    "We can now try this out. We can call the graph twice and then check the state"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "3975f34c-c243-40ea-b9d2-424d50a48dc9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[('human', \"hi! I'm bob\")]\n",
+      "[('human', \"hi! I'm bob\"), ('ai', \"Hello Bob! It's nice to meet you. I'm an AI assistant created by Anthropic. I'm here to help with any questions or tasks you might have. Please let me know how I can assist you.\")]\n",
+      "[('human', \"hi! I'm bob\"), ('ai', \"Hello Bob! It's nice to meet you. I'm an AI assistant created by Anthropic. I'm here to help with any questions or tasks you might have. Please let me know how I can assist you.\"), ('human', \"what's my name?\")]\n",
+      "[('human', \"hi! I'm bob\"), ('ai', \"Hello Bob! It's nice to meet you. I'm an AI assistant created by Anthropic. I'm here to help with any questions or tasks you might have. Please let me know how I can assist you.\"), ('human', \"what's my name?\"), ('ai', 'You said your name is Bob, so that is the name I have for you.')]\n",
+      "[('ai', \"Hello Bob! It's nice to meet you. I'm an AI assistant created by Anthropic. I'm here to help with any questions or tasks you might have. Please let me know how I can assist you.\"), ('human', \"what's my name?\"), ('ai', 'You said your name is Bob, so that is the name I have for you.')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "config = {\"configurable\": {\"thread_id\": \"3\"}}\n",
+    "input_message = HumanMessage(content=\"hi! I'm bob\")\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
+    "    print([(message.type, message.content) for message in event[\"messages\"]])\n",
+    "\n",
+    "\n",
+    "input_message = HumanMessage(content=\"what's my name?\")\n",
+    "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
+    "    print([(message.type, message.content) for message in event[\"messages\"]])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "67b2fd2a-14a1-4c47-8632-f8cbb0ba1d35",
+   "metadata": {},
+   "source": [
+    "If we now check the state, we should see that it is only three messages long. This is because we just deleted the earlier messages - otherwise it would be four!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "a3e15abb-81d8-4072-9f10-61ae0fd61dac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[AIMessage(content=\"Hello Bob! It's nice to meet you. I'm an AI assistant created by Anthropic. I'm here to help with any questions or tasks you might have. Please let me know how I can assist you.\", response_metadata={'id': 'msg_01XPEgPPbcnz5BbGWUDWTmzG', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 12, 'output_tokens': 48}}, id='run-eded3820-b6a9-4d66-9210-03ca41787ce6-0', usage_metadata={'input_tokens': 12, 'output_tokens': 48, 'total_tokens': 60}),\n",
+       " HumanMessage(content=\"what's my name?\", id='a0ea2097-3280-402b-92e1-67177b807ae8'),\n",
+       " AIMessage(content='You said your name is Bob, so that is the name I have for you.', response_metadata={'id': 'msg_01JGT62pxhrhN4SykZ57CSjW', 'model': 'claude-3-haiku-20240307', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 68, 'output_tokens': 20}}, id='run-ace3519c-81f8-45fe-a777-91f42d48b3a3-0', usage_metadata={'input_tokens': 68, 'output_tokens': 20, 'total_tokens': 88})]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = app.get_state(config).values['messages']\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "359cfeae-d43a-46ee-9069-a1cab9a5720a",
+   "metadata": {},
+   "source": [
+    "Remember, when deleting messages you will want to make sure that the remaining message list is still valid. This message list **may actually not be** - this is because it currently starts with an AI message, which some models do not allow."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d7222cd-5767-42f0-bc69-10615127eba5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langgraph",
+   "language": "python",
+   "name": "langgraph"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/memory/manage-conversation-history.ipynb

@@ -7,7 +7,12 @@
    "source": [
     "# How to manage conversation history\n",
     "\n",
-    "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. In this notebook we will discuss a few strategies for how to deal with this."
+    "One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation history can build up and take up more and more of the context window. This can often be undesirable as it leads to more expensive and longer calls to the LLM, and potentially ones that error. In order to prevent this from happening, you need to probably manage the conversation history.\n",
+    "\n",
+    "Note: this guide focuses on how to do this in LangGraph, where you can fully customize how this is done. If you want a more off-the-shelf solution, you can look into functionality provided in LangChain:\n",
+    "\n",
+    "- [How to filter messages](https://python.langchain.com/v0.2/docs/how_to/filter_messages/)\n",
+    "- [How to trim messages](https://python.langchain.com/v0.2/docs/how_to/trim_messages/)"
    ]
   },
   {
@@ -82,6 +87,7 @@
    "id": "4767ef1c-a7cf-41f8-a301-558988cb7ac5",
    "metadata": {},
    "source": [
+    "## Build the agent\n",
     "Let's now build a simple ReAct style agent."
    ]
   },
@@ -98,7 +104,7 @@
     "from langchain_core.tools import tool\n",
     "\n",
     "from langgraph.checkpoint.sqlite import SqliteSaver\n",
-    "from langgraph.graph import MessagesState, StateGraph\n",
+    "from langgraph.graph import MessagesState, StateGraph, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "\n",
     "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
@@ -146,7 +152,7 @@
     "\n",
     "# Set the entrypoint as `agent`\n",
     "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
+    "workflow.add_edge(START, \"agent\")\n",
     "\n",
     "# We now add a conditional edge\n",
     "workflow.add_conditional_edges(\n",
@@ -229,7 +235,7 @@
     "from langchain_core.tools import tool\n",
     "\n",
     "from langgraph.checkpoint.sqlite import SqliteSaver\n",
-    "from langgraph.graph import MessagesState, StateGraph\n",
+    "from langgraph.graph import MessagesState, StateGraph, START\n",
     "from langgraph.prebuilt import ToolNode\n",
     "\n",
     "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
@@ -283,7 +289,7 @@
     "\n",
     "# Set the entrypoint as `agent`\n",
     "# This means that this node is the first one called\n",
-    "workflow.set_entry_point(\"agent\")\n",
+    "workflow.add_edge(START, \"agent\")\n",
     "\n",
     "# We now add a conditional edge\n",
     "workflow.add_conditional_edges(\n",
@@ -343,6 +349,25 @@
     "for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
     "    event[\"messages\"][-1].pretty_print()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "454102b6-7112-4710-aa08-ba675e8be14c",
+   "metadata": {},
+   "source": [
+    "In the above example we defined the `filter_messages` function ourselves. We also provide off-the-shelf ways to trim and filter messages in LangChain. \n",
+    "\n",
+    "- [How to filter messages](https://python.langchain.com/v0.2/docs/how_to/filter_messages/)\n",
+    "- [How to trim messages](https://python.langchain.com/v0.2/docs/how_to/trim_messages/)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "686861bb-ec32-46f3-b7b3-fdac106f22f6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

examples/multi_agent/agent_supervisor.ipynb

@@ -26,10 +26,7 @@
    "id": "0d30b6f7-3bec-4d9f-af50-43dfdc81ae6c",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%%capture --no-stderr\n",
-    "%pip install -U langgraph langchain langchain_openai langchain_experimental langsmith pandas"
-   ]
+   "source": ["%%capture --no-stderr\n%pip install -U langgraph langchain langchain_openai langchain_experimental langsmith pandas"]
   },
   {
    "cell_type": "code",
@@ -37,24 +34,7 @@
    "id": "30c2f3de-c730-4aec-85a6-af2c2f058803",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "\n",
-    "def _set_if_undefined(var: str):\n",
-    "    if not os.environ.get(var):\n",
-    "        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n",
-    "\n",
-    "\n",
-    "_set_if_undefined(\"OPENAI_API_KEY\")\n",
-    "_set_if_undefined(\"LANGCHAIN_API_KEY\")\n",
-    "_set_if_undefined(\"TAVILY_API_KEY\")\n",
-    "\n",
-    "# Optional, add tracing in LangSmith\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"Multi-agent Collaboration\""
-   ]
+   "source": ["import getpass\nimport os\n\n\ndef _set_if_undefined(var: str):\n    if not os.environ.get(var):\n        os.environ[var] = getpass.getpass(f\"Please provide your {var}\")\n\n\n_set_if_undefined(\"OPENAI_API_KEY\")\n_set_if_undefined(\"LANGCHAIN_API_KEY\")\n_set_if_undefined(\"TAVILY_API_KEY\")\n\n# Optional, add tracing in LangSmith\nos.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\nos.environ[\"LANGCHAIN_PROJECT\"] = \"Multi-agent Collaboration\""]
   },
   {
    "cell_type": "markdown",
@@ -72,17 +52,7 @@
    "id": "f04c6778-403b-4b49-9b93-678e910d5cec",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from typing import Annotated\n",
-    "\n",
-    "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_experimental.tools import PythonREPLTool\n",
-    "\n",
-    "tavily_tool = TavilySearchResults(max_results=5)\n",
-    "\n",
-    "# This executes code locally, which can be unsafe\n",
-    "python_repl_tool = PythonREPLTool()"
-   ]
+   "source": ["from typing import Annotated\n\nfrom langchain_community.tools.tavily_search import TavilySearchResults\nfrom langchain_experimental.tools import PythonREPLTool\n\ntavily_tool = TavilySearchResults(max_results=5)\n\n# This executes code locally, which can be unsafe\npython_repl_tool = PythonREPLTool()"]
   },
   {
    "cell_type": "markdown",
@@ -100,28 +70,7 @@
    "id": "c4823dd9-26bd-4e1a-8117-b97b2860211a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
-    "from langchain_core.messages import BaseMessage, HumanMessage\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "\n",
-    "def create_agent(llm: ChatOpenAI, tools: list, system_prompt: str):\n",
-    "    # Each worker node will be given a name and some tools.\n",
-    "    prompt = ChatPromptTemplate.from_messages(\n",
-    "        [\n",
-    "            (\n",
-    "                \"system\",\n",
-    "                system_prompt,\n",
-    "            ),\n",
-    "            MessagesPlaceholder(variable_name=\"messages\"),\n",
-    "            MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
-    "        ]\n",
-    "    )\n",
-    "    agent = create_openai_tools_agent(llm, tools, prompt)\n",
-    "    executor = AgentExecutor(agent=agent, tools=tools)\n",
-    "    return executor"
-   ]
+   "source": ["from langchain.agents import AgentExecutor, create_openai_tools_agent\nfrom langchain_core.messages import BaseMessage, HumanMessage\nfrom langchain_openai import ChatOpenAI\n\n\ndef create_agent(llm: ChatOpenAI, tools: list, system_prompt: str):\n    # Each worker node will be given a name and some tools.\n    prompt = ChatPromptTemplate.from_messages(\n        [\n            (\n                \"system\",\n                system_prompt,\n            ),\n            MessagesPlaceholder(variable_name=\"messages\"),\n            MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n        ]\n    )\n    agent = create_openai_tools_agent(llm, tools, prompt)\n    executor = AgentExecutor(agent=agent, tools=tools)\n    return executor"]
   },
   {
    "cell_type": "markdown",
@@ -137,11 +86,7 @@
    "id": "80862241-a1a7-4726-bce5-f867b233832e",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def agent_node(state, agent, name):\n",
-    "    result = agent.invoke(state)\n",
-    "    return {\"messages\": [HumanMessage(content=result[\"output\"], name=name)]}"
-   ]
+   "source": ["def agent_node(state, agent, name):\n    result = agent.invoke(state)\n    return {\"messages\": [HumanMessage(content=result[\"output\"], name=name)]}"]
   },
   {
    "cell_type": "markdown",
@@ -159,59 +104,7 @@
    "id": "311f0a58-b425-4496-adac-dc4cd8ffb912",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "\n",
-    "members = [\"Researcher\", \"Coder\"]\n",
-    "system_prompt = (\n",
-    "    \"You are a supervisor tasked with managing a conversation between the\"\n",
-    "    \" following workers:  {members}. Given the following user request,\"\n",
-    "    \" respond with the worker to act next. Each worker will perform a\"\n",
-    "    \" task and respond with their results and status. When finished,\"\n",
-    "    \" respond with FINISH.\"\n",
-    ")\n",
-    "# Our team supervisor is an LLM node. It just picks the next agent to process\n",
-    "# and decides when the work is completed\n",
-    "options = [\"FINISH\"] + members\n",
-    "# Using openai function calling can make output parsing easier for us\n",
-    "function_def = {\n",
-    "    \"name\": \"route\",\n",
-    "    \"description\": \"Select the next role.\",\n",
-    "    \"parameters\": {\n",
-    "        \"title\": \"routeSchema\",\n",
-    "        \"type\": \"object\",\n",
-    "        \"properties\": {\n",
-    "            \"next\": {\n",
-    "                \"title\": \"Next\",\n",
-    "                \"anyOf\": [\n",
-    "                    {\"enum\": options},\n",
-    "                ],\n",
-    "            }\n",
-    "        },\n",
-    "        \"required\": [\"next\"],\n",
-    "    },\n",
-    "}\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"messages\"),\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"Given the conversation above, who should act next?\"\n",
-    "            \" Or should we FINISH? Select one of: {options}\",\n",
-    "        ),\n",
-    "    ]\n",
-    ").partial(options=str(options), members=\", \".join(members))\n",
-    "\n",
-    "llm = ChatOpenAI(model=\"gpt-4-1106-preview\")\n",
-    "\n",
-    "supervisor_chain = (\n",
-    "    prompt\n",
-    "    | llm.bind_functions(functions=[function_def], function_call=\"route\")\n",
-    "    | JsonOutputFunctionsParser()\n",
-    ")"
-   ]
+   "source": ["from langchain_core.output_parsers.openai_functions import JsonOutputFunctionsParser\nfrom langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n\nmembers = [\"Researcher\", \"Coder\"]\nsystem_prompt = (\n    \"You are a supervisor tasked with managing a conversation between the\"\n    \" following workers:  {members}. Given the following user request,\"\n    \" respond with the worker to act next. Each worker will perform a\"\n    \" task and respond with their results and status. When finished,\"\n    \" respond with FINISH.\"\n)\n# Our team supervisor is an LLM node. It just picks the next agent to process\n# and decides when the work is completed\noptions = [\"FINISH\"] + members\n# Using openai function calling can make output parsing easier for us\nfunction_def = {\n    \"name\": \"route\",\n    \"description\": \"Select the next role.\",\n    \"parameters\": {\n        \"title\": \"routeSchema\",\n        \"type\": \"object\",\n        \"properties\": {\n            \"next\": {\n                \"title\": \"Next\",\n                \"anyOf\": [\n                    {\"enum\": options},\n                ],\n            }\n        },\n        \"required\": [\"next\"],\n    },\n}\nprompt = ChatPromptTemplate.from_messages(\n    [\n        (\"system\", system_prompt),\n        MessagesPlaceholder(variable_name=\"messages\"),\n        (\n            \"system\",\n            \"Given the conversation above, who should act next?\"\n            \" Or should we FINISH? Select one of: {options}\",\n        ),\n    ]\n).partial(options=str(options), members=\", \".join(members))\n\nllm = ChatOpenAI(model=\"gpt-4-1106-preview\")\n\nsupervisor_chain = (\n    prompt\n    | llm.bind_functions(functions=[function_def], function_call=\"route\")\n    | JsonOutputFunctionsParser()\n)"]
   },
   {
    "cell_type": "markdown",
@@ -229,41 +122,7 @@
    "id": "6a430af7-8fce-4e66-ba9e-d940c1bc48e8",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import functools\n",
-    "import operator\n",
-    "from typing import Sequence, TypedDict\n",
-    "\n",
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
-    "\n",
-    "from langgraph.graph import END, StateGraph\n",
-    "\n",
-    "\n",
-    "# The agent state is the input to each node in the graph\n",
-    "class AgentState(TypedDict):\n",
-    "    # The annotation tells the graph that new messages will always\n",
-    "    # be added to the current states\n",
-    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
-    "    # The 'next' field indicates where to route to next\n",
-    "    next: str\n",
-    "\n",
-    "\n",
-    "research_agent = create_agent(llm, [tavily_tool], \"You are a web researcher.\")\n",
-    "research_node = functools.partial(agent_node, agent=research_agent, name=\"Researcher\")\n",
-    "\n",
-    "# NOTE: THIS PERFORMS ARBITRARY CODE EXECUTION. PROCEED WITH CAUTION\n",
-    "code_agent = create_agent(\n",
-    "    llm,\n",
-    "    [python_repl_tool],\n",
-    "    \"You may generate safe python code to analyze data and generate charts using matplotlib.\",\n",
-    ")\n",
-    "code_node = functools.partial(agent_node, agent=code_agent, name=\"Coder\")\n",
-    "\n",
-    "workflow = StateGraph(AgentState)\n",
-    "workflow.add_node(\"Researcher\", research_node)\n",
-    "workflow.add_node(\"Coder\", code_node)\n",
-    "workflow.add_node(\"supervisor\", supervisor_chain)"
-   ]
+   "source": ["import functools\nimport operator\nfrom typing import Sequence, TypedDict\n\nfrom langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n\nfrom langgraph.graph import END, StateGraph, START\n\n\n# The agent state is the input to each node in the graph\nclass AgentState(TypedDict):\n    # The annotation tells the graph that new messages will always\n    # be added to the current states\n    messages: Annotated[Sequence[BaseMessage], operator.add]\n    # The 'next' field indicates where to route to next\n    next: str\n\n\nresearch_agent = create_agent(llm, [tavily_tool], \"You are a web researcher.\")\nresearch_node = functools.partial(agent_node, agent=research_agent, name=\"Researcher\")\n\n# NOTE: THIS PERFORMS ARBITRARY CODE EXECUTION. PROCEED WITH CAUTION\ncode_agent = create_agent(\n    llm,\n    [python_repl_tool],\n    \"You may generate safe python code to analyze data and generate charts using matplotlib.\",\n)\ncode_node = functools.partial(agent_node, agent=code_agent, name=\"Coder\")\n\nworkflow = StateGraph(AgentState)\nworkflow.add_node(\"Researcher\", research_node)\nworkflow.add_node(\"Coder\", code_node)\nworkflow.add_node(\"supervisor\", supervisor_chain)"]
   },
   {
    "cell_type": "markdown",
@@ -279,20 +138,7 @@
    "id": "14778e86-077b-4e6a-893c-400e59b0cdbf",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "for member in members:\n",
-    "    # We want our workers to ALWAYS \"report back\" to the supervisor when done\n",
-    "    workflow.add_edge(member, \"supervisor\")\n",
-    "# The supervisor populates the \"next\" field in the graph state\n",
-    "# which routes to a node or finishes\n",
-    "conditional_map = {k: k for k in members}\n",
-    "conditional_map[\"FINISH\"] = END\n",
-    "workflow.add_conditional_edges(\"supervisor\", lambda x: x[\"next\"], conditional_map)\n",
-    "# Finally, add entrypoint\n",
-    "workflow.set_entry_point(\"supervisor\")\n",
-    "\n",
-    "graph = workflow.compile()"
-   ]
+   "source": ["for member in members:\n    # We want our workers to ALWAYS \"report back\" to the supervisor when done\n    workflow.add_edge(member, \"supervisor\")\n# The supervisor populates the \"next\" field in the graph state\n# which routes to a node or finishes\nconditional_map = {k: k for k in members}\nconditional_map[\"FINISH\"] = END\nworkflow.add_conditional_edges(\"supervisor\", lambda x: x[\"next\"], conditional_map)\n# Finally, add entrypoint\nworkflow.add_edge(START, \"supervisor\")\n\ngraph = workflow.compile()"]
   },
   {
    "cell_type": "markdown",
@@ -336,18 +182,7 @@
      ]
     }
    ],
-   "source": [
-    "for s in graph.stream(\n",
-    "    {\n",
-    "        \"messages\": [\n",
-    "            HumanMessage(content=\"Code hello world and print it to the terminal\")\n",
-    "        ]\n",
-    "    }\n",
-    "):\n",
-    "    if \"__end__\" not in s:\n",
-    "        print(s)\n",
-    "        print(\"----\")"
-   ]
+   "source": ["for s in graph.stream(\n    {\n        \"messages\": [\n            HumanMessage(content=\"Code hello world and print it to the terminal\")\n        ]\n    }\n):\n    if \"__end__\" not in s:\n        print(s)\n        print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -368,15 +203,7 @@
      ]
     }
    ],
-   "source": [
-    "for s in graph.stream(\n",
-    "    {\"messages\": [HumanMessage(content=\"Write a brief research report on pikas.\")]},\n",
-    "    {\"recursion_limit\": 100},\n",
-    "):\n",
-    "    if \"__end__\" not in s:\n",
-    "        print(s)\n",
-    "        print(\"----\")"
-   ]
+   "source": ["for s in graph.stream(\n    {\"messages\": [HumanMessage(content=\"Write a brief research report on pikas.\")]},\n    {\"recursion_limit\": 100},\n):\n    if \"__end__\" not in s:\n        print(s)\n        print(\"----\")"]
   },
   {
    "cell_type": "code",
@@ -384,7 +211,7 @@
    "id": "1d363d2c-e0da-4cce-ba47-ad2aa9df0fef",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [""]
   }
  ],
  "metadata": {