mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-12 04:37:51 +02:00
[docs] add JS examples for double texting and human in the loop for cloud (#885)
This commit is contained in:
Isaac Francisco
@@ -65,10 +65,10 @@ There are many occasions where the graph cannot run completely autonomously. For
|
||||
|
||||
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
|
||||
|
||||
|
||||
@@ -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](https://langchain-ai.github.io/langgraph/cloud/concepts/#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:
|
||||
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in sf?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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."}]
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
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.
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in nyc?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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}}"}]
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
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.
|
||||
|
||||
@@ -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](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).
|
||||
|
||||
### 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
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -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](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.
|
||||
|
||||
### 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).
|
||||
@@ -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](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.
|
||||
|
||||
### 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!
|
||||
@@ -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](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.
|
||||
|
||||
### 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}]}}
|
||||
|
||||
@@ -39,10 +39,10 @@ Graph execution can take a while, and sometimes users may change their mind abou
|
||||
|
||||
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](https://langchain-ai.github.io/langgraph/cloud/how-tos/human_in_the_loop_breakpoint/)
|
||||
- [How to wait for user input](https://langchain-ai.github.io/langgraph/cloud/how-tos/human_in_the_loop_user_input/)
|
||||
- [How to edit graph state](https://langchain-ai.github.io/langgraph/cloud/how-tos/human_in_the_loop_edit_state/)
|
||||
- [How to replay and branch from prior states](https://langchain-ai.github.io/langgraph/cloud/how-tos/human_in_the_loop_time_travel/)
|
||||
|
||||
## LangGraph Studio
|
||||
|
||||
|
||||
@@ -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](https://langchain-ai.github.io/langgraph/cloud/concepts/#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:
|
||||
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in sf?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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 ..."}]
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in nyc?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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."}]
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
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'
|
||||
|
||||
@@ -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](https://langchain-ai.github.io/langgraph/cloud/concepts/#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:
|
||||
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in sf?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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."}]
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
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.
|
||||
|
||||
@@ -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](https://langchain-ai.github.io/langgraph/cloud/concepts/#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:
|
||||
|
||||
================================[1m Human Message [0m=================================
|
||||
|
||||
what's the weather in nyc?
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
[{'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
|
||||
=================================[1m Tool Message [0m=================================
|
||||
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}}"}]
|
||||
==================================[1m Ai Message [0m==================================
|
||||
|
||||
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
|
||||
|
||||
@@ -27,7 +27,7 @@ First let's set up our client and thread:
|
||||
```js
|
||||
import { Client } from "@langchain/langgraph-sdk";
|
||||
|
||||
const client = new Client({apiUrl:"whatever-your-deployment-url-is"});
|
||||
const client = new Client({ apiUrl:"whatever-your-deployment-url-is" });
|
||||
// create thread
|
||||
const thread = await client.threads.create();
|
||||
console.log(thread)
|
||||
|
||||
@@ -224,8 +224,8 @@ 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}]}}
|
||||
|
||||
+8
-8
@@ -187,15 +187,15 @@ nav:
|
||||
- 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"
|
||||
|
||||
@@ -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
|
||||
}
|
||||
@@ -1,117 +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",
|
||||
"\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
|
||||
}
|
||||
@@ -1,174 +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",
|
||||
"\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
|
||||
}
|
||||
@@ -1,240 +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",
|
||||
"\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(\n",
|
||||
" thread[\"thread_id\"],\n",
|
||||
" {\"messages\": [last_message]},\n",
|
||||
" checkpoint_id=state_to_replay[\"checkpoint_id\"],\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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
|
||||
}
|
||||
@@ -1,187 +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",
|
||||
"\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 = {\n",
|
||||
" \"messages\": [\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": \"Use the search tool to ask the user where they are, then look up the weather there\",\n",
|
||||
" }\n",
|
||||
" ]\n",
|
||||
"}\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 = [\n",
|
||||
" {\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": \"san francisco\"}\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"await client.threads.update_state(\n",
|
||||
" 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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
@@ -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
|
||||
}
|
||||
Reference in New Issue
Block a user