Merge branch 'main' into wfh/docs/memstoreconcept

Merge pull request #2627 from langchain-ai/nc/4dec/state-ensure-config
lib: Call ensure_config in state crud methods
2026-10-09 01:45:13 +02:00 · 2024-12-04 08:58:40 -08:00 · 2024-12-04 11:53:03 -05:00 · 2024-12-04 08:39:53 -08:00 · 2024-12-04 16:38:09 +00:00 · 2024-12-04 08:30:10 -08:00
49 changed files with 1499 additions and 296 deletions
@@ -49,7 +49,7 @@ gain understanding of concepts and how they interact by showing one way to achie

 They should **avoid** giving
 multiple permutations of ways to achieve that goal in-depth. Choice is burdensome. Instead, they should guide a new user through a recommended path to accomplishing a concrete goal. While the end result of a tutorial does not necessarily need to
-be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction.
+be completely production-ready, it should be useful and practically satisfy the goal that you clearly stated in the tutorial's introduction.

 To quote the Diataxis website:

@@ -13,7 +13,7 @@ serve-clean-docs: clean-docs
 	poetry run python -m mkdocs serve -c -f docs/mkdocs.yml --strict -w ./libs/langgraph

 serve-docs: build-typedoc
-	poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph --dirty
+	poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph  -w ./libs/checkpoint --dirty

 clean-docs:
 	find ./docs/docs -name "*.ipynb" -type f -delete
@@ -0,0 +1,123 @@
+# How to add semantic search to your LangGraph deployment
+
+This guide explains how to add semantic search to your LangGraph deployment's cross-thread [store](../../concepts/persistence.md#memory-store), so that your agent can search for memories and other documents by semantic similarity.
+
+## Prerequisites
+
+- A LangGraph deployment (see [how to deploy](setup_pyproject.md))
+- API keys for your embedding provider (in this case, OpenAI)
+- `langchain >= 0.3.8` (if you specify using the string format below)
+
+## Steps
+
+1. Update your `langgraph.json` configuration file to include the store configuration:
+
+```json
+{
+    ...
+    "store": {
+        "index": {
+            "embed": "openai:text-embeddings-3-small",
+            "dims": 1536,
+            "fields": ["$"]
+        }
+    }
+}
+```
+
+This configuration:
+
+- Uses OpenAI's text-embeddings-3-small model for generating embeddings
+- Sets the embedding dimension to 1536 (matching the model's output)
+- Indexes all fields in your stored data (`["$"]` means index everything, or specify specific fields like `["text", "metadata.title"]`)
+
+2. To use the string embedding format above, make sure your dependencies include `langchain >= 0.3.8`:
+
+```toml
+# In pyproject.toml
+[project]
+dependencies = [
+    "langchain>=0.3.8"
+]
+```
+
+Or if using requirements.txt:
+
+```
+langchain>=0.3.8
+```
+
+## Usage
+
+Once configured, you can use semantic search in your LangGraph nodes. The store requires a namespace tuple to organize memories:
+
+```python
+def search_memory(state: State, *, store: BaseStore):
+    # Search the store using semantic similarity
+    # The namespace tuple helps organize different types of memories
+    # e.g., ("user_facts", "preferences") or ("conversation", "summaries")
+    results = store.search(
+        namespace=("memory", "facts"),  # Organize memories by type
+        query="your search query",
+        limit=3  # number of results to return
+    )
+    return results
+```
+
+## Custom Embeddings
+
+If you want to use custom embeddings, you can pass a path to a custom embedding function:
+
+```json
+{
+    ...
+    "store": {
+        "index": {
+            "embed": "path/to/embedding_function.py:embed",
+            "dims": 1536,
+            "fields": ["$"]
+        }
+    }
+}
+```
+
+The deployment will look for the function in the specified path. The function must be async and accept a list of strings:
+
+```python
+# path/to/embedding_function.py
+from openai import AsyncOpenAI
+
+client = AsyncOpenAI()
+
+async def aembed_texts(texts: list[str]) -> list[list[float]]:
+    """Custom embedding function that must:
+    1. Be async
+    2. Accept a list of strings
+    3. Return a list of float arrays (embeddings)
+    """
+    response = await client.embeddings.create(
+        model="text-embedding-3-small",
+        input=texts
+    )
+    return [e.embedding for e in response.data]
+```
+
+## Querying via the API
+
+You can also query the store using the LangGraph SDK. Since the SDK uses async operations:
+
+```python
+from langgraph_sdk import get_client
+
+async def search_store():
+    client = get_client()
+    results = await client.store.search(
+        namespace=("memory", "facts"),
+        query="your search query",
+        limit=3  # number of results to return
+    )
+    return results
+
+# Use in an async context
+results = await search_store()
+```
@@ -83,7 +83,7 @@ We can now call `.get_schemas` to get schemas associated with this graph:
        assistant_id=assistant["assistant_id"]
    )
    # There are multiple types of schemas
-    # We can get the `config_schema` to look at the the configurable parameters
+    # We can get the `config_schema` to look at the configurable parameters
    print(schemas["config_schema"])
    ```

@@ -94,7 +94,7 @@ We can now call `.get_schemas` to get schemas associated with this graph:
      assistant["assistant_id"]
    );
    // There are multiple types of schemas
-    // We can get the `config_schema` to look at the the configurable parameters
+    // We can get the `config_schema` to look at the configurable parameters
    console.log(schemas.config_schema);
    ```

@@ -26,10 +26,11 @@ The LangGraph command line interface includes commands to build and run a LangGr
 The LangGraph CLI requires a JSON configuration file with the following keys:

 | Key                | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-|--------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `dependencies`     | **Required**. Array of dependencies for LangGraph Cloud API server. Dependencies can be one of the following: (1) `"."`, which will look for local Python packages, (2) `pyproject.toml`, `setup.py` or `requirements.txt` in the app directory `"./local_package"`, or (3) a package name.                                                                                                                                                                                                                                                  |
 | `graphs`           | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and creates an instance of `langgraph.graph.state.StateGraph` / `langgraph.graph.state.CompiledStateGraph`.</li></ul> |
 | `env`              | Path to `.env` file or a mapping from environment variable to its value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| `store`            | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, meaningto index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul>                                                                  |
 | `python_version`   | `3.11` or `3.12`. Defaults to `3.11`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
 | `pip_config_file`  | Path to `pip` config file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | `dockerfile_lines` | Array of additional lines to add to Dockerfile following the import from parent image.                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
@@ -41,33 +42,84 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
    </p>
 </div>

-Example:
+### Examples
+
+#### Basic Configuration

 ```json
 {
-  "dependencies": ["langchain_openai", "./your_package"],
+  "dependencies": ["."],
  "graphs": {
-    "my_graph_id": "./your_package/your_file.py:variable"
-  },
-  "env": "./.env"
+    "chat": "./chat/graph.py:graph"
+  }
 }
 ```

-Example with environment variables:
+#### Adding semantic search to the store
+
+All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
+
+The `fields` configuration determines which parts of your documents to embed:
+- If omitted or set to `["$"]`, the entire document will be embedded
+- To embed specific fields, use JSON path notation: `["metadata.title", "content.text"]`
+- Documents missing specified fields will still be stored but won't have embeddings for those fields
+- You can still override which fields to embed on a specific item at `put` time using the `index` parameter

 ```json
 {
-  "python_version": "3.11",
-  "dependencies": ["langchain_openai", "."],
+  "dependencies": ["."],
  "graphs": {
-    "my_graph_id": "./your_package/your_file.py:make_graph"
+    "memory_agent": "./agent/graph.py:graph"
  },
-  "env": {
-    "OPENAI_API_KEY": "secret-key"
+  "store": {
+    "index": {
+      "embed": "openai:text-embedding-3-small",
+      "dims": 1536,
+      "fields": ["$"]
+    }
  }
 }
 ```

+!!! note "Common model dimensions"
+        - openai:text-embedding-3-large: 3072
+        - openai:text-embedding-3-small: 1536
+        - openai:text-embedding-ada-002: 1536
+        - cohere:embed-english-v3.0: 1024
+        - cohere:embed-english-light-v3.0: 384
+        - cohere:embed-multilingual-v3.0: 1024
+        - cohere:embed-multilingual-light-v3.0: 384
+
+#### Semantic search with a custom embedding function
+
+If you want to use semantic search with a custom embedding function, you can pass a path to a custom embedding function:
+
+```json
+{
+  "dependencies": ["."],
+  "graphs": {
+    "memory_agent": "./agent/graph.py:graph"
+  },
+  "store": {
+    "index": {
+      "embed": "./embeddings.py:embed_texts",
+      "dims": 768,
+      "fields": ["text", "summary"]
+    }
+  }
+}
+```
+
+The `embed` field in store configuration can reference a custom function that takes a list of strings and returns a list of embeddings. Example implementation:
+
+```python
+# embeddings.py
+def embed_texts(texts: list[str]) -> list[list[float]]:
+    """Custom embedding function for semantic search."""
+    # Implementation using your preferred embedding model
+    return [[0.1, 0.2, ...] for _ in texts]  # dims-dimensional vectors
+```
+
 ## Commands

 The base command for the LangGraph CLI is `langgraph`.
@@ -98,16 +150,16 @@ langgraph dev [OPTIONS]

 **Options**

-| Option                       | Default          | Description                                                                                |
-|----------------------------|------------------|--------------------------------------------------------------------------------------------|
-| `-c, --config FILE`        | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables       |
-| `--host TEXT`              | `127.0.0.1`      | Host to bind the server to                                                                |
-| `--port INTEGER`           | `2024`           | Port to bind the server to                                                                |
-| `--no-reload`              |                  | Disable auto-reload                                                                        |
-| `--n-jobs-per-worker INTEGER` |               | Number of jobs per worker. Default is 10                                                  |
-| `--no-browser`             |                  | Disable automatic browser opening                                                          |
-| `--debug-port INTEGER`     |                  | Port for debugger to listen on                                                            |
-| `--help`                   |                  | Display command documentation                                                              |
+| Option                        | Default          | Description                                                                         |
+| ----------------------------- | ---------------- | ----------------------------------------------------------------------------------- |
+| `-c, --config FILE`           | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables |
+| `--host TEXT`                 | `127.0.0.1`      | Host to bind the server to                                                          |
+| `--port INTEGER`              | `2024`           | Port to bind the server to                                                          |
+| `--no-reload`                 |                  | Disable auto-reload                                                                 |
+| `--n-jobs-per-worker INTEGER` |                  | Number of jobs per worker. Default is 10                                            |
+| `--no-browser`                |                  | Disable automatic browser opening                                                   |
+| `--debug-port INTEGER`        |                  | Port for debugger to listen on                                                      |
+| `--help`                      |                  | Display command documentation                                                       |

 ### `build`

@@ -122,7 +174,7 @@ langgraph build [OPTIONS]
 **Options**

 | Option               | Default          | Description                                                                                                                  |
-|----------------------|------------------|------------------------------------------------------------------------------------------------------------------------------|
+| -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
 | `--platform TEXT`    |                  | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64`              |
 | `-t, --tag TEXT`     |                  | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image`                                               |
 | `--pull / --no-pull` | `--pull`         | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Cloud API server with locally built images. |
@@ -141,20 +193,20 @@ langgraph up [OPTIONS]

 **Options**

-| Option                       | Default                   | Description                                                                                                           |
-|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------|
-| `--wait`                     |                           | Wait for services to start before returning. Implies --detach                                                         |
-| `--postgres-uri TEXT`        | Local database            | Postgres URI to use for the database.                                                                                 |
-| `--watch`                    |                           | Restart on file changes                                                                                               |
-| `--debugger-base-url TEXT`   | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API.                                                                     |
-| `--debugger-port INTEGER`    |                           | Pull the debugger image locally and serve the UI on specified port                                                    |
-| `--verbose`                  |                           | Show more output from the server logs.                                                                                |
-| `-c, --config FILE`          | `langgraph.json`          | Path to configuration file declaring dependencies, graphs and environment variables.                                  |
-| `-d, --docker-compose FILE`  |                           | Path to docker-compose.yml file with additional services to launch.                                                   |
-| `-p, --port INTEGER`         | `8123`                    | Port to expose. Example: `langgraph up --port 8000`                                                                 |
+| Option                       | Default                   | Description                                                                                                             |
+| ---------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+| `--wait`                     |                           | Wait for services to start before returning. Implies --detach                                                           |
+| `--postgres-uri TEXT`        | Local database            | Postgres URI to use for the database.                                                                                   |
+| `--watch`                    |                           | Restart on file changes                                                                                                 |
+| `--debugger-base-url TEXT`   | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API.                                                                       |
+| `--debugger-port INTEGER`    |                           | Pull the debugger image locally and serve the UI on specified port                                                      |
+| `--verbose`                  |                           | Show more output from the server logs.                                                                                  |
+| `-c, --config FILE`          | `langgraph.json`          | Path to configuration file declaring dependencies, graphs and environment variables.                                    |
+| `-d, --docker-compose FILE`  |                           | Path to docker-compose.yml file with additional services to launch.                                                     |
+| `-p, --port INTEGER`         | `8123`                    | Port to expose. Example: `langgraph up --port 8000`                                                                     |
 | `--pull / --no-pull`         | `pull`                    | Pull latest images. Use `--no-pull` for running the server with locally-built images. Example: `langgraph up --no-pull` |
-| `--recreate / --no-recreate` | `no-recreate`             | Recreate containers even if their configuration and image haven't changed                                             |
-| `--help`                     |                           | Display command documentation.                                                                                        |
+| `--recreate / --no-recreate` | `no-recreate`             | Recreate containers even if their configuration and image haven't changed                                               |
+| `--help`                     |                           | Display command documentation.                                                                                          |

 ### `dockerfile`

@@ -169,7 +221,7 @@ langgraph dockerfile [OPTIONS] SAVE_PATH
 **Options**

 | Option              | Default          | Description                                                                                                     |
-|---------------------|------------------|-----------------------------------------------------------------------------------------------------------------|
+| ------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
 | `-c, --config FILE` | `langgraph.json` | Path to the [configuration file](#configuration-file) declaring dependencies, graphs and environment variables. |
 | `--help`            |                  | Show this message and exit.                                                                                     |

@@ -27,8 +27,8 @@ Adding a [breakpoint](./low_level.md#breakpoints) a specific location in the gra
 Here, we compile our graph with a checkpointer and a breakpoint at the node we want to interrupt before, `step_for_human_in_the_loop`. We then perform one of the above interaction patterns, which will create a new checkpoint if a human edits the graph state. The new checkpoint is saved to the `thread` and we can resume the graph execution from there by passing in `None` as the input.

 ```python
-# Compile our graph with a checkpoitner and a breakpoint before "step_for_human_in_the_loop"
-graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["step_for_human_in_the_loop"])
+# Compile our graph with a checkpointer and a breakpoint before "step_for_human_in_the_loop"
+graph = builder.compile(checkpointer=checkpointer, interrupt_before=["step_for_human_in_the_loop"])

 # Run the graph up to the breakpoint
 thread_config = {"configurable": {"thread_id": "1"}}
@@ -98,8 +98,8 @@ With persistence, we can surface the current agent state as well as the next ste
 If approved, the graph resumes execution from the last saved checkpoint, which is saved to the `thread`:

 ```python
-# Compile our graph with a checkpoitner and a breakpoint before the step to approve
-graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["node_2"])
+# Compile our graph with a checkpointer and a breakpoint before the step to approve
+graph = builder.compile(checkpointer=checkpointer, interrupt_before=["node_2"])

 # Run the graph up to the breakpoint
 for event in graph.stream(inputs, thread, stream_mode="values"):
@@ -120,7 +120,7 @@ See [our guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for a detailed h

 Sometimes we want to review and edit the agent's state. 
 
-As with approval, we can interrupt our agent at a [breakpoint](./low_level.md#breakpoints) prior the the step we want to check. 
+As with approval, we can interrupt our agent at a [breakpoint](./low_level.md#breakpoints) prior to the step we want to check. 
 
 We can surface the current state to a user and allow the user to edit the agent state.
 
@@ -131,8 +131,8 @@ We can edit the graph state by forking the current checkpoint, which is saved to
 We can then proceed with the graph from our forked checkpoint as done before. 

 ```python
-# Compile our graph with a checkpoitner and a breakpoint before the step to review
-graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["node_2"])
+# Compile our graph with a checkpointer and a breakpoint before the step to review
+graph = builder.compile(checkpointer=checkpointer, interrupt_before=["node_2"])

 # Run the graph up to the breakpoint
 for event in graph.stream(inputs, thread, stream_mode="values"):
@@ -170,11 +170,11 @@ With editing, the user makes a decision about whether or not to edit the graph s

 With input, we explicitly define a node in our graph for collecting human input!

-The the state update with the human input then runs *as this node*.
+The state update with the human input then runs *as this node*.

 ```python
-# Compile our graph with a checkpoitner and a breakpoint before the step to to collect human input
-graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["human_input"])
+# Compile our graph with a checkpointer and a breakpoint before the step to to collect human input
+graph = builder.compile(checkpointer=checkpointer, interrupt_before=["human_input"])

 # Run the graph up to the breakpoint
 for event in graph.stream(inputs, thread, stream_mode="values"):
@@ -211,8 +211,8 @@ Even if the tool call is correct, we may also want to apply discretion:
 With these points in mind, we can combine the above ideas to create a human-in-the-loop review of a tool call.

 ```python
-# Compile our graph with a checkpoitner and a breakpoint before the step to to review the tool call from the LLM 
-graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["human_review"])
+# Compile our graph with a checkpointer and a breakpoint before the step to to review the tool call from the LLM 
+graph = builder.compile(checkpointer=checkpointer, interrupt_before=["human_review"])

 # Run the graph up to the breakpoint
 for event in graph.stream(inputs, thread, stream_mode="values"):
@@ -319,4 +319,4 @@ for event in graph.stream(None, config, stream_mode="values"):

 See [this additional conceptual guide](https://langchain-ai.github.io/langgraph/concepts/persistence/#update-state) for related context on forking.

-See see [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
+See see [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
@@ -171,7 +171,7 @@ trim_messages(

 ## Long-term memory

-Long-term memory in LangGraph allows systems to retain information across different conversations or sessions. Unlike short-term memory, which is thread-scoped, long-term memory is saved within custom "namespaces."
+Long-term memory in LangGraph allows systems to retain information across different conversations or sessions. Unlike short-term memory, which is **thread-scoped**, long-term memory is saved within custom "namespaces."

 ### Storing memories

@@ -180,16 +180,34 @@ LangGraph stores long-term memories as JSON documents in a [store](persistence.m
 ```python
 from langgraph.store.memory import InMemoryStore

+
+def embed(texts: list[str]) -> list[list[float]]:
+    # Replace with an actual embedding function or LangChain embeddings object
+    return [[1.0, 2.0] * len(texts)]
+
+
 # InMemoryStore saves data to an in-memory dictionary. Use a DB-backed store in production use.
-store = InMemoryStore()
+store = InMemoryStore(index={"embed": embed, "dims": 2})
 user_id = "my-user"
 application_context = "chitchat"
 namespace = (user_id, application_context)
-store.put(namespace, "a-memory", {"rules": ["User likes short, direct language", "User only speaks English & python"], "my-key": "my-value"})
+store.put(
+    namespace,
+    "a-memory",
+    {
+        "rules": [
+            "User likes short, direct language",
+            "User only speaks English & python",
+        ],
+        "my-key": "my-value",
+    },
+)
 # get the "memory" by ID
 item = store.get(namespace, "a-memory")
-# list "memories" within this namespace, filtering on content equivalence
-items = store.search(namespace, filter={"my-key": "my-value"})
+# search for "memories" within this namespace, filtering on content equivalence, sorted by vector similarity
+items = store.search(
+    namespace, filter={"my-key": "my-value"}, query="language preferences"
+)
 ```

 ### Framework for thinking about long-term memory
@@ -232,7 +250,7 @@ Alternatively, memories can be a collection of documents that are continuously u

 However, this shifts some complexity memory updating. The model must now _delete_ or _update_ existing items in the list, which can be tricky. In addition, some models may default to over-inserting and others may default to over-updating. See the [Trustcall](https://github.com/hinthornw/trustcall) package for one way to manage this and consider evaluation (e.g., with a tool like [LangSmith](https://docs.smith.langchain.com/tutorials/Developers/evaluation)) to help you tune the behavior.

-Working with document collections also shifts complexity to memory **search** over the list. The `Store` currently supports [filtering by metadata](https://langchain-ai.github.io/langgraph/reference/store/#storage) and will soon add [semantic search shortly](https://python.langchain.com/docs/concepts/vectorstores/), but selecting the most relevant documents can be tricky as the list grows.
+Working with document collections also shifts complexity to memory **search** over the list. The `Store` currently supports both [semantic search](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.SearchOp.query) and [filtering by content](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.SearchOp.filter).

 Finally, using a collection of memories can make it challenging to provide comprehensive context to the model. While individual memories may follow a specific schema, this structure might not capture the full context or relationships between memories. As a result, when using these memories to generate responses, the model may lack important contextual information that would be more readily available in a unified profile approach.

@@ -218,13 +218,16 @@ The final thing you can optionally specify when calling `update_state` is `as_no

 ## Memory Store

-![Update](img/persistence/shared_state.png)
+![Model of shared state](img/persistence/shared_state.png)

 A [state schema](low_level.md#schema) specifies a set of keys that are populated as a graph is executed. As discussed above, state can be written by a checkpointer to a thread at each graph step, enabling state persistence.

 But, what if we want to retrain some information *across threads*? Consider the case of a chatbot where we want to retain specific information about the user across *all* chat conversations (e.g., threads) with that user!

-With checkpointers alone, we cannot share information across threads. This motivates the need for the `Store` interface. As an illustration, we can define an `InMemoryStore` to store information about a user across threads. We simply compile our graph with a checkpointer, as before, and will our new `in_memory_store`.
+With checkpointers alone, we cannot share information across threads. This motivates the need for the [`Store`](../reference/store.md#langgraph.store.base.BaseStore) interface. As an illustration, we can define an `InMemoryStore` to store information about a user across threads. We simply compile our graph with a checkpointer, as before, and with our new `in_memory_store` variable.
+
+### Basic Usage
+
 First, let's showcase this in isolation without using LangGraph.

 ```python
@@ -239,7 +242,7 @@ user_id = "1"
 namespace_for_memory = (user_id, "memories")
 ```

-We use the `store.put` to save memories to our namespace in the store. When we do this, we specify the namespace, as defined above, and a key-value pair for the memory: the key is simply a unique identifier for the memory (`memory_id`) and the value (a dictionary) is the memory itself.
+We use the `store.put` method to save memories to our namespace in the store. When we do this, we specify the namespace, as defined above, and a key-value pair for the memory: the key is simply a unique identifier for the memory (`memory_id`) and the value (a dictionary) is the memory itself.

 ```python
 memory_id = str(uuid.uuid4())
@@ -247,7 +250,7 @@ memory = {"food_preference" : "I like pizza"}
 in_memory_store.put(namespace_for_memory, memory_id, memory)
 ```

-We can read out memories in our namespace using `store.search`, which will return all memories for a given user as a list. The most recent memory is the last in the list.
+We can read out memories in our namespace using the `store.search` method, which will return all memories for a given user as a list. The most recent memory is the last in the list.

 ```python
 memories = in_memory_store.search(namespace_for_memory)
@@ -259,16 +262,66 @@ memories[-1].dict()
 'updated_at': '2024-10-02T17:22:31.590605+00:00'}
 ```

-Each memory type is a Python class with certain attributes. We can access it as a dictionary by converting via `.dict` as above.
+Each memory type is a Python class ([`Item`](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.Item)) with certain attributes. We can access it as a dictionary by converting via `.dict` as above.
 The attributes it has are:

 - `value`: The value (itself a dictionary) of this memory
- `key`: The UUID for this memory in this namespace
+- `key`: A unique key for this memory in this namespace
 - `namespace`: A list of strings, the namespace of this memory type
 - `created_at`: Timestamp for when this memory was created
 - `updated_at`: Timestamp for when this memory was updated

-With this all in place, we use the `in_memory_store` in LangGraph. The `in_memory_store` works hand-in-hand with the checkpointer: the checkpointer saves state to threads, as discussed above, and the the `in_memory_store` allows us to store arbitrary information for access *across* threads. We compile the graph with both the checkpointer and the `in_memory_store` as follows. 
+### Semantic Search
+
+Beyond simple retrieval, the store also supports semantic search, allowing you to find memories based on meaning rather than exact matches. To enable this, configure the store with an embedding model:
+
+```python
+store = InMemoryStore(
+    index={
+        "embed": "openai:text-embedding-3-small",  # Embedding provider
+        "dims": 1536,                              # Embedding dimensions
+        "fields": ["food_preference", "$"]              # Fields to embed
+    }
+)
+```
+
+Now when searching, you can use natural language queries to find relevant memories:
+
+```python
+# Find memories about food preferences
+memories = store.search(
+    namespace_for_memory,
+    query="What does the user like to eat?",
+    limit=3  # Return top 3 matches
+)
+```
+
+You can control which parts of your memories get embedded by configuring the `fields` parameter or by specifying the `index` parameter when storing memories:
+
+```python
+# Store with specific fields to embed
+store.put(
+    namespace_for_memory,
+    str(uuid.uuid4()),
+    {
+        "food_preference": "I love Italian cuisine",
+        "context": "Discussing dinner plans"
+    },
+    index=["food_preference"]  # Only embed "food_preferences" field
+)
+
+# Store without embedding (still retrievable, but not searchable)
+store.put(
+    namespace_for_memory,
+    str(uuid.uuid4()),
+    {"system_info": "Last updated: 2024-01-01"},
+    index=False
+)
+```
+
+### Using in LangGraph
+
+With this all in place, we use the `in_memory_store` in LangGraph. The `in_memory_store` works hand-in-hand with the checkpointer: the checkpointer saves state to threads, as discussed above, and the `in_memory_store` allows us to store arbitrary information for access *across* threads. We compile the graph with both the checkpointer and the `in_memory_store` as follows. 

 ```python
 from langgraph.checkpoint.memory import MemorySaver
@@ -296,7 +349,7 @@ for update in graph.stream(
    print(update)
 ```

-We can access the `in_memory_store` and the `user_id` in *any node* by passing `store: BaseStore` and `config: RunnableConfig` as node arguments. Just as we saw above, simply use the `put` method to save memories to the store.
+We can access the `in_memory_store` and the `user_id` in *any node* by passing `store: BaseStore` and `config: RunnableConfig` as node arguments. Here's how we might use semantic search in a node to find relevant memories:

 ```python
 def update_memory(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
@@ -317,7 +370,7 @@ def update_memory(state: MessagesState, config: RunnableConfig, *, store: BaseSt

 ```

-As we showed above, we can also access the store in any node and use `search` to get memories. Recall the the memories are returned as a list of objects that can be converted to a dictionary.
+As we showed above, we can also access the store in any node and use the `store.search` method to get memories. Recall the the memories are returned as a list of objects that can be converted to a dictionary.

 ```python
 memories[-1].dict()
@@ -332,12 +385,15 @@ We can access the memories and use them in our model call.

 ```python
 def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
-    
    # Get the user id from the config
    user_id = config["configurable"]["user_id"]
    
-    # Get the memories for the user from the store
-    memories = store.search(("memories", user_id))
+    # Search based on the most recent message
+    memories = store.search(
+        namespace,
+        query=state["messages"][-1].content,
+        limit=3
+    )
    info = "\n".join([d.value["memory"] for d in memories])
    
    # ... Use memories in the model call
@@ -356,7 +412,7 @@ for update in graph.stream(
    print(update)
 ```

-When we use the LangGraph API, either locally (e.g., in LangGraph Studio) or with LangGraph Cloud, the memory store is available to use by default and does not need to be specified during graph compilation.
+When we use the LangGraph API, either locally (e.g., in LangGraph Studio) or with LangGraph Cloud, the base store is available to use by default and does not need to be specified during graph compilation. For cloud deployments, semantic search is automatically configured based on your `langgraph.json` settings. See the [deployment guide](../deployment/semantic_search.md) for more details.

 ## Checkpointer libraries

@@ -405,4 +461,4 @@ Lastly, checkpointing also provides fault-tolerance and error recovery: if one o

 #### Pending writes

-Additionally, when a graph node fails mid-execution at a given superstep, LangGraph stores pending checkpoint writes from any other nodes that completed successfully at that superstep, so that whenever we resume graph execution from that superstep we don't re-run the successful nodes.
+Additionally, when a graph node fails mid-execution at a given superstep, LangGraph stores pending checkpoint writes from any other nodes that completed successfully at that superstep, so that whenever we resume graph execution from that superstep we don't re-run the successful nodes.
@@ -41,6 +41,9 @@
    "    <p>\n",
    "    Support for the <code><a href=\"https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.BaseStore\">Store</a></code> API that is used in this guide was added in LangGraph <code>v0.2.32</code>.\n",
    "    </p>\n",
+    "    <p>\n",
+    "    Support for <b>index</b> and <b>query</b> arguments of the <code><a href=\"https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.BaseStore\">Store</a></code> API that is used in this guide was added in LangGraph <code>v0.2.54</code>.\n",
+    "    </p>\n",
    "</div>\n",
    "\n",
    "## Setup\n",
@@ -114,7 +117,7 @@
    "\n",
    "Importantly, to determine the user, we will be passing `user_id` via the config keyword argument of the node function.\n",
    "\n",
-    "Let's first define an `InMemoryStore` which is already populated with some memories about the users."
+    "Let's first define an `InMemoryStore` already populated with some memories about the users."
   ]
  },
  {
@@ -125,8 +128,14 @@
   "outputs": [],
   "source": [
    "from langgraph.store.memory import InMemoryStore\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
-    "in_memory_store = InMemoryStore()"
+    "in_memory_store = InMemoryStore(\n",
+    "    index={\n",
+    "        \"embed\": OpenAIEmbeddings(model=\"text-embedding-3-small\"),\n",
+    "        \"dims\": 1536,\n",
+    "    }\n",
+    ")"
   ]
  },
  {
@@ -163,7 +172,7 @@
    "def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):\n",
    "    user_id = config[\"configurable\"][\"user_id\"]\n",
    "    namespace = (\"memories\", user_id)\n",
-    "    memories = store.search(namespace)\n",
+    "    memories = store.search(namespace, query=str(state[\"messages\"][-1].content))\n",
    "    info = \"\\n\".join([d.value[\"data\"] for d in memories])\n",
    "    system_msg = f\"You are a helpful assistant talking to the user. User info: {info}\"\n",
    "\n",
@@ -39,6 +39,7 @@ LangGraph makes it easy to manage conversation [memory](../concepts/memory.md) i
 - [How to manage conversation history](memory/manage-conversation-history.ipynb)
 - [How to delete messages](memory/delete-messages.ipynb)
 - [How to add summary conversation memory](memory/add-summary-conversation-history.ipynb)
+- [Add long-term memory (cross-thread)](cross-thread-persistence.ipynb)

 ### Human-in-the-loop

@@ -70,7 +71,7 @@ you to involve humans in the decision-making process of your graph. These how-to

 ### Tool calling

-[Tool calling](https://python.langchain.com/docs/concepts/tool_calling/) is a type of chat model API that accepts tool schemas, along with messages, as input and returns invocations of those tools as part of the output message. 
+[Tool calling](https://python.langchain.com/docs/concepts/tool_calling/) is a type of chat model API that accepts tool schemas, along with messages, as input and returns invocations of those tools as part of the output message.

 These how-to guides show common patterns for tool calling with LangGraph:

@@ -123,7 +124,7 @@ These guides show how to use the prebuilt ReAct agent:

 This section includes how-to guides for LangGraph Platform.

-LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework. 
+LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework.

 The LangGraph Platform offers a few different deployment options described in the [deployment options guide](../concepts/deployment_options.md).

@@ -139,6 +140,7 @@ Learn how to set up your app for deployment to LangGraph Platform:
 - [How to set up app for deployment (requirements.txt)](../cloud/deployment/setup.md)
 - [How to set up app for deployment (pyproject.toml)](../cloud/deployment/setup_pyproject.md)
 - [How to set up app for deployment (JavaScript)](../cloud/deployment/setup_javascript.md)
+- [How to add semantic search](../cloud/deployment/semantic_search.md)
 - [How to customize Dockerfile](../cloud/deployment/custom_docker.md)
 - [How to test locally](../cloud/deployment/test_locally.md)
 - [How to rebuild graph at runtime](../cloud/deployment/graph_rebuild.md)
@@ -150,8 +152,8 @@ LangGraph applications can be deployed using LangGraph Cloud, which provides a r

 - [How to deploy to LangGraph cloud](../cloud/deployment/cloud.md)
 - [How to deploy to a self-hosted environment](./deploy-self-hosted.md)
- [How to interact with the deployment using RemoteGraph](./use-remote-graph.md) 
- 
+- [How to interact with the deployment using RemoteGraph](./use-remote-graph.md)
+
 ### Assistants

 [Assistants](../concepts/assistants.md) is a configured instance of a template.
@@ -196,7 +198,7 @@ When designing complex graphs, relying entirely on the LLM for decision-making c

 ### Double-texting

-Graph execution can take a while, and sometimes users may change their mind about the input they wanted to send before their original input has finished running. For example, a user might notice a typo in their original request and will edit the prompt and resend it. Deciding what to do in these cases is important for ensuring a smooth user experience and preventing your graphs from behaving in unexpected ways. 
+Graph execution can take a while, and sometimes users may change their mind about the input they wanted to send before their original input has finished running. For example, a user might notice a typo in their original request and will edit the prompt and resend it. Deciding what to do in these cases is important for ensuring a smooth user experience and preventing your graphs from behaving in unexpected ways.

 - [How to use the interrupt option](../cloud/how-tos/interrupt_concurrent.md)
 - [How to use the rollback option](../cloud/how-tos/rollback_concurrent.md)
@@ -216,8 +218,9 @@ Graph execution can take a while, and sometimes users may change their mind abou
 LangGraph Studio is a built-in UI for visualizing, testing, and debugging your agents.

 - [How to connect to a LangGraph Cloud deployment](../cloud/how-tos/test_deployment.md)
- [How to connect to a local deployment](../cloud/how-tos/test_local_deployment.md)
- [How to test your graph in LangGraph Studio](../cloud/how-tos/invoke_studio.md)
+- [How to connect to a local dev server](../how-tos/local-studio.md)
+- [How to connect to a local deployment (Docker)](../cloud/how-tos/test_local_deployment.md)
+- [How to test your graph in LangGraph Studio (MacOS only)](../cloud/how-tos/invoke_studio.md)
 - [How to interact with threads in LangGraph Studio](../cloud/how-tos/threads_studio.md)

 ## Troubleshooting
@@ -229,5 +232,3 @@ These are the guides for resolving common errors you may find while building wit
 - [INVALID_GRAPH_NODE_RETURN_VALUE](../troubleshooting/errors/INVALID_GRAPH_NODE_RETURN_VALUE.md)
 - [MULTIPLE_SUBGRAPHS](../troubleshooting/errors/MULTIPLE_SUBGRAPHS.md)
 - [INVALID_CHAT_HISTORY](../troubleshooting/errors/INVALID_CHAT_HISTORY.md)
-
-
@@ -0,0 +1,424 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to add semantic search to your agent's memory\n",
+    "\n",
+    "This guide shows how to enable semantic search in your agent's memory store. This lets search for items in the store by semantic similarity.\n",
+    "\n",
+    "First, install this guide's prerequisites."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture --no-stderr\n",
+    "%pip install -U langgraph langchain-openai langchain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "\n",
+    "def _set_env(var: str):\n",
+    "    if not os.environ.get(var):\n",
+    "        os.environ[var] = getpass.getpass(f\"{var}: \")\n",
+    "\n",
+    "\n",
+    "_set_env(\"OPENAI_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, create the store."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import init_embeddings\n",
+    "from langgraph.store.memory import InMemoryStore\n",
+    "\n",
+    "# Create store with semantic search enabled\n",
+    "embeddings = init_embeddings(\"openai:text-embedding-3-small\")\n",
+    "store = InMemoryStore(\n",
+    "    index={\n",
+    "        \"embed\": embeddings,\n",
+    "        \"dims\": 1536,\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now let's store some memories:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Store some memories\n",
+    "store.put((\"user_123\", \"memories\"), \"1\", {\"text\": \"I love pizza\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"2\", {\"text\": \"I prefer Italian food\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I don't like spicy food\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I am studying econometrics\"})\n",
+    "store.put((\"user_123\", \"memories\"), \"3\", {\"text\": \"I am a plumber\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Search memories using natural language:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Memory: I prefer Italian food (similarity: 0.46482669521168163)\n",
+      "Memory: I love pizza (similarity: 0.35514845174380766)\n",
+      "Memory: I am a plumber (similarity: 0.155698702336571)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Find memories about food preferences\n",
+    "memories = store.search((\"user_123\", \"memories\"), query=\"I like food?\", limit=5)\n",
+    "\n",
+    "for memory in memories:\n",
+    "    print(f'Memory: {memory.value[\"text\"]} (similarity: {memory.score})')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using in your agent\n",
+    "\n",
+    "Add semantic search to any node by injecting the store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import uuid\n",
+    "from typing import Optional\n",
+    "\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "from langchain_core.tools import InjectedToolArg\n",
+    "from langgraph.store.base import BaseStore\n",
+    "from typing_extensions import Annotated\n",
+    "\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "\n",
+    "def add_memories(state, *, store: BaseStore):\n",
+    "    # Search based on user's last message\n",
+    "    items = store.search(\n",
+    "        (\"user_123\", \"memories\"), query=state[\"messages\"][-1].content, limit=2\n",
+    "    )\n",
+    "    memories = \"\\n\".join(item.value[\"text\"] for item in items)\n",
+    "    memories = f\"## Memories of user\\n{memories}\" if memories else \"\"\n",
+    "    return [\n",
+    "        {\"role\": \"system\", \"content\": f\"You are a helpful assistant.\\n{memories}\"}\n",
+    "    ] + state[\"messages\"]\n",
+    "\n",
+    "\n",
+    "def upsert_memory(\n",
+    "    content: str,\n",
+    "    *,\n",
+    "    memory_id: Optional[uuid.UUID] = None,\n",
+    "    store: Annotated[BaseStore, InjectedToolArg],\n",
+    "):\n",
+    "    \"\"\"Upsert a memory in the database.\"\"\"\n",
+    "    mem_id = memory_id or uuid.uuid4()\n",
+    "    store.put(\n",
+    "        (\"user_123\", \"memories\"),\n",
+    "        key=str(mem_id),\n",
+    "        value={\"text\": content},\n",
+    "    )\n",
+    "    return f\"Stored memory {mem_id}\"\n",
+    "\n",
+    "\n",
+    "agent = create_react_agent(\n",
+    "    init_chat_model(\"openai:gpt-4o-mini\"),\n",
+    "    tools=[upsert_memory],\n",
+    "    state_modifier=add_memories,\n",
+    "    store=store,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "What are you in the mood for? Since you love Italian food and pizza, would you like some recommendations for a delicious pizza or a different Italian dish?"
+     ]
+    }
+   ],
+   "source": [
+    "async for message, metadata in agent.astream(\n",
+    "    input={\"messages\": [{\"role\": \"user\", \"content\": \"I'm hungry\"}]},\n",
+    "    stream_mode=\"messages\",\n",
+    "):\n",
+    "    print(message.content, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Advanced Usage\n",
+    "\n",
+    "#### Multi-vector indexing\n",
+    "\n",
+    "Store and search different aspects of memories separately to improve recall or omit certain fields from being indexed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configure store to embed both memory content and emotional context\n",
+    "store = InMemoryStore(\n",
+    "    index={\"embed\": embeddings, \"dims\": 1536, \"fields\": [\"memory\", \"emotional_context\"]}\n",
+    ")\n",
+    "# Store memories with different content/emotion pairs\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\n",
+    "        \"memory\": \"Had pizza with friends at Mario's\",\n",
+    "        \"emotional_context\": \"felt happy and connected\",\n",
+    "        \"this_isnt_indexed\": \"I prefer ravioli though\",\n",
+    "    },\n",
+    ")\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\n",
+    "        \"memory\": \"Ate alone at home\",\n",
+    "        \"emotional_context\": \"felt a bit lonely\",\n",
+    "        \"this_isnt_indexed\": \"I like pie\",\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "# Search focusing on emotional state - matches mem2\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"times they felt isolated\", limit=1\n",
+    ")\n",
+    "print(\"Expect mem 2\")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")\n",
+    "\n",
+    "# Search focusing on social eating - matches mem1\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"fun pizza\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")\n",
+    "\n",
+    "print(\"Expect random lower score (ravioli not indexed)\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"ravioli\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Emotion: {r.value['emotional_context']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Override fields at storage time\n",
+    "You can override which fields to embed when storing a specific memory using `put(..., index=[...fields])`, regardless of the store's default configuration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Expect mem1\n",
+      "Item: mem1; Score (0.3374698138722726)\n",
+      "Memory: I love spicy food\n",
+      "Context: At a Thai restaurant\n",
+      "\n",
+      "Expect mem2\n",
+      "Item: mem2; Score (0.3679447999059255)\n",
+      "Memory: The restaurant was too loud\n",
+      "Context: Dinner at an Italian place\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = init_embeddings(\"openai:text-embedding-3-small\")\n",
+    "store = InMemoryStore(\n",
+    "    index={\n",
+    "        \"embed\": embeddings,\n",
+    "        \"dims\": 1536,\n",
+    "        \"fields\": [\"memory\"],\n",
+    "    }  # Default to embed memory field\n",
+    ")\n",
+    "\n",
+    "# Store one memory with default indexing\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\"memory\": \"I love spicy food\", \"context\": \"At a Thai restaurant\"},\n",
+    ")\n",
+    "\n",
+    "# Store another overriding which fields to embed\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\"memory\": \"The restaurant was too loud\", \"context\": \"Dinner at an Italian place\"},\n",
+    "    index=[\"context\"],  # Override: only embed the context\n",
+    ")\n",
+    "\n",
+    "# Search about food - matches mem1 (using default field)\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"what food do they like\", limit=1\n",
+    ")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Context: {r.value['context']}\\n\")\n",
+    "\n",
+    "# Search about restaurant atmosphere - matches mem2 (using overridden field)\n",
+    "print(\"Expect mem2\")\n",
+    "results = store.search(\n",
+    "    (\"user_123\", \"memories\"), query=\"restaurant environment\", limit=1\n",
+    ")\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Context: {r.value['context']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Disable Indexing for Specific Memories\n",
+    "\n",
+    "Some memories shouldn't be searchable by content. You can disable indexing for these while still storing them using \n",
+    "`put(..., index=False)`. Example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "store = InMemoryStore(index={\"embed\": embeddings, \"dims\": 1536, \"fields\": [\"memory\"]})\n",
+    "\n",
+    "# Store a normal indexed memory\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem1\",\n",
+    "    {\"memory\": \"I love chocolate ice cream\", \"type\": \"preference\"},\n",
+    ")\n",
+    "\n",
+    "# Store a system memory without indexing\n",
+    "store.put(\n",
+    "    (\"user_123\", \"memories\"),\n",
+    "    \"mem2\",\n",
+    "    {\"memory\": \"User completed onboarding\", \"type\": \"system\"},\n",
+    "    index=False,  # Disable indexing entirely\n",
+    ")\n",
+    "\n",
+    "# Search about food preferences - finds mem1\n",
+    "print(\"Expect mem1\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"what food preferences\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Type: {r.value['type']}\\n\")\n",
+    "\n",
+    "# Search about onboarding - won't find mem2 (not indexed)\n",
+    "print(\"Expect low score (mem2 not indexed)\")\n",
+    "results = store.search((\"user_123\", \"memories\"), query=\"onboarding status\", limit=1)\n",
+    "for r in results:\n",
+    "    print(f\"Item: {r.key}; Score ({r.score})\")\n",
+    "    print(f\"Memory: {r.value['memory']}\")\n",
+    "    print(f\"Type: {r.value['type']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
@@ -164,6 +164,7 @@ nav:
            - how-tos/memory/manage-conversation-history.ipynb
            - how-tos/memory/delete-messages.ipynb
            - how-tos/memory/add-summary-conversation-history.ipynb
+            - how-tos/memory/semantic-search.ipynb
        - Human-in-the-loop:
            - Human-in-the-loop: how-tos#human-in-the-loop
            - how-tos/human_in_the_loop/breakpoints.ipynb
@@ -225,6 +226,7 @@ nav:
              - cloud/deployment/setup.md
              - cloud/deployment/setup_pyproject.md
              - cloud/deployment/setup_javascript.md
+              - cloud/deployment/semantic_search.md
              - cloud/deployment/custom_docker.md
              - cloud/deployment/test_locally.md
              - cloud/deployment/graph_rebuild.md
@@ -42,7 +42,7 @@ class DuckDBSaver(BaseDuckDBSaver):
            DuckDBSaver: A new DuckDBSaver instance.
        """
        with duckdb.connect(conn_string) as conn:
-            yield DuckDBSaver(conn)
+            yield cls(conn)

    def setup(self) -> None:
        """Set up the checkpoint database asynchronously.
@@ -45,7 +45,7 @@ class AsyncDuckDBSaver(BaseDuckDBSaver):
            AsyncDuckDBSaver: A new AsyncDuckDBSaver instance.
        """
        with duckdb.connect(conn_string) as conn:
-            yield AsyncDuckDBSaver(conn)
+            yield cls(conn)

    async def setup(self) -> None:
        """Set up the checkpoint database asynchronously.
@@ -156,7 +156,7 @@ class AsyncDuckDBStore(AsyncBatchedBaseStore, BaseDuckDBStore):
            AsyncDuckDBStore: A new AsyncDuckDBStore instance.
        """
        with duckdb.connect(conn_string) as conn:
-            yield AsyncDuckDBStore(conn)
+            yield cls(conn)

    async def setup(self) -> None:
        """Set up the store database asynchronously.
@@ -54,7 +54,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
        pipeline: bool = False,
        serde: Optional[SerializerProtocol] = None,
    ) -> AsyncIterator["AsyncPostgresSaver"]:
-        """Create a new PostgresSaver instance from a connection string.
+        """Create a new AsyncPostgresSaver instance from a connection string.

        Args:
            conn_string (str): The Postgres connection info string.
@@ -37,6 +37,70 @@ logger = logging.getLogger(__name__)


 class AsyncPostgresStore(AsyncBatchedBaseStore, BasePostgresStore[_ainternal.Conn]):
+    """Asynchronous Postgres-backed store with optional vector search using pgvector.
+
+    !!! example "Examples"
+        Basic setup and key-value storage:
+        ```python
+        from langgraph.store.postgres import AsyncPostgresStore
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname"
+        ) as store:
+            await store.setup()
+
+            # Store and retrieve data
+            await store.aput(("users", "123"), "prefs", {"theme": "dark"})
+            item = await store.aget(("users", "123"), "prefs")
+        ```
+
+        Vector search using LangChain embeddings:
+        ```python
+        from langchain.embeddings import init_embeddings
+        from langgraph.store.postgres import AsyncPostgresStore
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname",
+            index={
+                "dims": 1536,
+                "embed": init_embeddings("openai:text-embedding-3-small"),
+                "fields": ["text"]  # specify which fields to embed. Default is the whole serialized value
+            }
+        ) as store:
+            await store.setup()  # Do this once to run migrations
+
+            # Store documents
+            await store.aput(("docs",), "doc1", {"text": "Python tutorial"})
+            await store.aput(("docs",), "doc2", {"text": "TypeScript guide"})
+            # Don't index the following
+            await store.aput(("docs",), "doc3", {"text": "Other guide"}, index=False)
+
+            # Search by similarity
+            results = await store.asearch(("docs",), query="python programming")
+        ```
+
+        Using connection pooling for better performance:
+        ```python
+        from langgraph.store.postgres import AsyncPostgresStore, PoolConfig
+
+        async with AsyncPostgresStore.from_conn_string(
+            "postgresql://user:pass@localhost:5432/dbname",
+            pool_config=PoolConfig(
+                min_size=5,
+                max_size=20
+            )
+        ) as store:
+            await store.setup()
+            # Use store with connection pooling...
+        ```
+
+    Warning:
+        Make sure to:
+        1. Call `setup()` before first use to create necessary tables and indexes
+        2. Have the pgvector extension available to use vector search
+        3. Use Python 3.10+ for async functionality
+    """
+
    __slots__ = (
        "_deserializer",
        "pipe",
@@ -534,6 +534,53 @@ class BasePostgresStore(Generic[C]):


 class PostgresStore(BaseStore, BasePostgresStore[_pg_internal.Conn]):
+    """Postgres-backed store with optional vector search using pgvector.
+
+    !!! example "Examples"
+        Basic setup and key-value storage:
+        ```python
+        from langgraph.store.postgres import PostgresStore
+
+        store = PostgresStore(
+            connection_string="postgresql://user:pass@localhost:5432/dbname"
+        )
+        store.setup()
+
+        # Store and retrieve data
+        store.put(("users", "123"), "prefs", {"theme": "dark"})
+        item = store.get(("users", "123"), "prefs")
+        ```
+
+        Vector search using LangChain embeddings:
+        ```python
+        from langchain.embeddings import init_embeddings
+        from langgraph.store.postgres import PostgresStore
+
+        store = PostgresStore(
+            connection_string="postgresql://user:pass@localhost:5432/dbname",
+            index={
+                "dims": 1536,
+                "embed": init_embeddings("openai:text-embedding-3-small"),
+                "fields": ["text"]  # specify which fields to embed. Default is the whole serialized value
+            }
+        )
+        store.setup() # Do this once to run migrations
+
+        # Store documents
+        store.put(("docs",), "doc1", {"text": "Python tutorial"})
+        store.put(("docs",), "doc2", {"text": "TypeScript guide"})
+        store.put(("docs",), "doc2", {"text": "Other guide"}, index=False) # don't index
+
+        # Search by similarity
+        results = store.search(("docs",), query="python programming")
+        ```
+
+    Warning:
+        Make sure to call `setup()` before first use to create necessary tables and indexes.
+        The pgvector extension must be available to use vector search.
+
+    """
+
    __slots__ = (
        "_deserializer",
        "pipe",
@@ -110,7 +110,7 @@ class SqliteSaver(BaseCheckpointSaver[str]):
                check_same_thread=False,
            )
        ) as conn:
-            yield SqliteSaver(conn)
+            yield cls(conn)

    def setup(self) -> None:
        """Set up the checkpoint database.
@@ -137,7 +137,7 @@ class AsyncSqliteSaver(BaseCheckpointSaver[str]):
            AsyncSqliteSaver: A new AsyncSqliteSaver instance.
        """
        async with aiosqlite.connect(conn_string) as conn:
-            yield AsyncSqliteSaver(conn)
+            yield cls(conn)

    def get_tuple(self, config: RunnableConfig) -> Optional[CheckpointTuple]:
        """Get a checkpoint tuple from the database.
@@ -4,9 +4,9 @@ Stores provide long-term memory that persists across threads and conversations.
 Supports hierarchical namespaces, key-value storage, and optional vector search.

 Core types:
- BaseStore: Store interface with sync/async operations
- Item: Stored key-value pairs with metadata
- Op: Get/Put/Search/List operations
+    - BaseStore: Store interface with sync/async operations
+    - Item: Stored key-value pairs with metadata
+    - Op: Get/Put/Search/List operations
 """

 from abc import ABC, abstractmethod
@@ -89,7 +89,7 @@ class Item:


 class SearchItem(Item):
-    """Represents a result item with additional response metadata."""
+    """Represents an item returned from a search operation with additional metadata."""

    __slots__ = ("score",)

@@ -133,7 +133,7 @@ class GetOp(NamedTuple):
    This operation allows precise retrieval of stored items using their full path
    (namespace) and unique identifier (key) combination.

-    ??? example "Examples"
+    ???+ example "Examples"

        Basic item retrieval:
        ```python
@@ -145,7 +145,7 @@ class GetOp(NamedTuple):
    namespace: tuple[str, ...]
    """Hierarchical path that uniquely identifies the item's location.

-    ??? example "Examples"
+    ???+ example "Examples"

        ```python
        ("users",)  # Root level users namespace
@@ -156,7 +156,7 @@ class GetOp(NamedTuple):
    key: str
    """Unique identifier for the item within its specific namespace.

-    ??? example "Examples"
+    ???+ example "Examples"

        ```python
        "user123"  # For a user profile
@@ -175,7 +175,7 @@ class SearchOp(NamedTuple):
    Note:
        Natural language search support depends on your store implementation.

-    ??? example "Examples"
+    ???+ example "Examples"
        Search with filters and pagination:
        ```python
        SearchOp(
@@ -199,7 +199,7 @@ class SearchOp(NamedTuple):
    namespace_prefix: tuple[str, ...]
    """Hierarchical path prefix defining the search scope.

-    ??? example "Examples"
+    ???+ example "Examples"

        ```python
        ()  # Search entire store
@@ -221,8 +221,7 @@ class SearchOp(NamedTuple):
        - $lt: Less than
        - $lte: Less than or equal to

-    ??? example "Examples"
-
+    ???+ example "Examples"
        Simple exact match:

        ```python
@@ -243,9 +242,6 @@ class SearchOp(NamedTuple):
            "color": "red"
        }
        ```
-
-    Note:
-        Comparison operator support depends on your store implementation.
    """

    limit: int = 10
@@ -257,7 +253,7 @@ class SearchOp(NamedTuple):
    query: Optional[str] = None
    """Natural language search query for semantic search capabilities.

-    ??? example "Examples"
+    ???+ example "Examples"
        - "technical documentation about REST APIs"
        - "machine learning papers from 2023"
    """
@@ -267,10 +263,12 @@ class SearchOp(NamedTuple):
 NamespacePath = tuple[Union[str, Literal["*"]], ...]
 """A tuple representing a namespace path that can include wildcards.

-Examples:
+???+ example "Examples"
+    ```python
    ("users",)  # Exact users namespace
    ("documents", "*")  # Any sub-namespace under documents
    ("cache", "*", "v1")  # Any cache category with v1 version
+    ```
 """

 # Type for specifying how to match namespaces
@@ -290,7 +288,7 @@ class MatchCondition(NamedTuple):
    pattern that can include wildcards to flexibly match different namespace
    hierarchies.

-    ??? example "Examples"
+    ???+ example "Examples"
        Prefix matching:
        ```python
        MatchCondition(match_type="prefix", path=("users", "profiles"))
@@ -320,7 +318,7 @@ class ListNamespacesOp(NamedTuple):
    This operation allows exploring the organization of data, finding specific
    collections, and navigating the namespace hierarchy.

-    ??? example "Examples"
+    ???+ example "Examples"

        List all namespaces under the "documents" path:
        ```python
@@ -343,7 +341,7 @@ class ListNamespacesOp(NamedTuple):
    match_conditions: Optional[tuple[MatchCondition, ...]] = None
    """Optional conditions for filtering namespaces.

-    ??? example "Examples"
+    ???+ example "Examples"
        All user namespaces:
        ```python
        (MatchCondition(match_type="prefix", path=("users",)),)
@@ -385,7 +383,7 @@ class PutOp(NamedTuple):
    The namespace acts as a folder-like structure to organize items.
    Each element in the tuple represents one level in the hierarchy.

-    ??? example "Examples"
+    ???+ example "Examples"
        Root level documents
        ```python
        ("documents",)
@@ -431,9 +429,9 @@ class PutOp(NamedTuple):
    """Controls how the item's fields are indexed for search operations.

    Indexing configuration determines how the item can be found through search:
-    - None (default): Uses the store's default indexing configuration (if provided)
-    - False: Disables indexing for this item
-    - list[str]: Specifies which json path fields to index for search
+        - None (default): Uses the store's default indexing configuration (if provided)
+        - False: Disables indexing for this item
+        - list[str]: Specifies which json path fields to index for search

    The item remains accessible through direct get() operations regardless of indexing.
    When indexed, fields can be searched using natural language queries through
@@ -447,15 +445,14 @@ class PutOp(NamedTuple):
          - Last element: "array[-1]"
          - All elements (each individually): "array[*]"

-    ??? example "Examples"
-        - None - Use store defaults
-        - False - Don't index this item
+    ???+ example "Examples"
+        - None - Use store defaults (whole item)
        - list[str] - List of fields to index
        
        ```python
        [
            "metadata.title",                    # Nested field access
-            "chapters[*].content",               # Index content from all chapters as separate vectors
+            "context[*].content",                # Index content from all context as separate vectors
            "authors[0].name",                   # First author's name
            "revisions[-1].changes",             # Most recent revision's changes
            "sections[*].paragraphs[*].text",    # All text from all paragraphs in all sections
@@ -480,22 +477,116 @@ class IndexConfig(TypedDict, total=False):
    """Number of dimensions in the embedding vectors.
    
    Common embedding models have the following dimensions:
-        - OpenAI text-embedding-3-large: 256, 1024, or 3072
-        - OpenAI text-embedding-3-small: 512 or 1536
-        - OpenAI text-embedding-ada-002: 1536
-        - Cohere embed-english-v3.0: 1024
-        - Cohere embed-english-light-v3.0: 384
-        - Cohere embed-multilingual-v3.0: 1024
-        - Cohere embed-multilingual-light-v3.0: 384
+        - openai:text-embedding-3-large: 3072
+        - openai:text-embedding-3-small: 1536
+        - openai:text-embedding-ada-002: 1536
+        - cohere:embed-english-v3.0: 1024
+        - cohere:embed-english-light-v3.0: 384
+        - cohere:embed-multilingual-v3.0: 1024
+        - cohere:embed-multilingual-light-v3.0: 384
    """

    embed: Union[Embeddings, EmbeddingsFunc, AEmbeddingsFunc]
-    """Optional function to generate embeddings from text."""
+    """Optional function to generate embeddings from text.
+    
+    Can be specified in three ways:
+        1. A LangChain Embeddings instance
+        2. A synchronous embedding function (EmbeddingsFunc)
+        3. An asynchronous embedding function (AEmbeddingsFunc)
+    
+    ???+ example "Examples"
+        Using LangChain's initialization with InMemoryStore:
+        ```python
+        from langchain.embeddings import init_embeddings
+        from langgraph.store.memory import InMemoryStore
+        
+        store = InMemoryStore(
+            index={
+                "dims": 1536,
+                "embed": init_embeddings("openai:text-embedding-3-small")
+            }
+        )
+        ```
+        
+        Using a custom embedding function with InMemoryStore:
+        ```python
+        from openai import OpenAI
+        from langgraph.store.memory import InMemoryStore
+        
+        client = OpenAI()
+        
+        def embed_texts(texts: list[str]) -> list[list[float]]:
+            response = client.embeddings.create(
+                model="text-embedding-3-small",
+                input=texts
+            )
+            return [e.embedding for e in response.data]
+            
+        store = InMemoryStore(
+            index={
+                "dims": 1536,
+                "embed": embed_texts
+            }
+        )
+        ```
+        
+        Using an asynchronous embedding function with InMemoryStore:
+        ```python
+        from openai import AsyncOpenAI
+        from langgraph.store.memory import InMemoryStore
+        
+        client = AsyncOpenAI()
+        
+        async def aembed_texts(texts: list[str]) -> list[list[float]]:
+            response = await client.embeddings.create(
+                model="text-embedding-3-small",
+                input=texts
+            )
+            return [e.embedding for e in response.data]
+            
+        store = InMemoryStore(
+            index={
+                "dims": 1536,
+                "embed": aembed_texts
+            }
+        )
+        ```
+    """

    fields: Optional[list[str]]
    """Fields to extract text from for embedding generation.
    
-    Defaults to the root ["$"], which embeds the json object as a whole.
+    Controls which parts of stored items are embedded for semantic search. Follows JSON path syntax:
+
+        - ["$"]: Embeds the entire JSON object as one vector  (default)
+        - ["field1", "field2"]: Embeds specific top-level fields
+        - ["parent.child"]: Embeds nested fields using dot notation
+        - ["array[*].field"]: Embeds field from each array element separately
+    
+    Note:
+        You can always override this behavior when storing an item using the
+        `index` parameter in the `put` or `aput` operations.
+    
+    ???+ example "Examples"
+        ```python
+        # Embed entire document (default)
+        fields=["$"]
+        
+        # Embed specific fields
+        fields=["text", "summary"]
+        
+        # Embed nested fields
+        fields=["metadata.title", "content.body"]
+        
+        # Embed from arrays
+        fields=["messages[*].content"]  # Each message content separately
+        fields=["context[0].text"]      # First context item's text
+        ```
+    
+    Note:
+        - Fields missing from a document are skipped
+        - Array notation creates separate embeddings for each element
+        - Complex nested paths are supported (e.g., "a.b[*].c.d")
    """


@@ -565,6 +656,39 @@ class BaseStore(ABC):

        Returns:
            List of items matching the search criteria.
+
+        ???+ example "Examples"
+            Basic filtering:
+            ```python
+            # Search for documents with specific metadata
+            results = store.search(
+                ("docs",),
+                filter={"type": "article", "status": "published"}
+            )
+            ```
+
+            Natural language search (requires vector store implementation):
+            ```python
+            # Initialize store with embedding configuration
+            store = YourStore( # e.g., InMemoryStore, AsyncPostgresStore
+                index={
+                    "dims": 1536,  # embedding dimensions
+                    "embed": your_embedding_function,  # function to create embeddings
+                    "fields": ["text"]  # fields to embed. Defaults to ["$"]
+                }
+            )
+
+            # Search for semantically similar documents
+            results = store.search(
+                ("docs",),
+                query="machine learning applications in healthcare",
+                filter={"type": "research_paper"},
+                limit=5
+            )
+            ```
+
+            Note: Natural language search support depends on your store implementation
+            and requires proper embedding configuration.
        """
        return self.batch([SearchOp(namespace_prefix, filter, limit, offset, query)])[0]

@@ -585,7 +709,10 @@ class BaseStore(ABC):
            value: Dictionary containing the item's data. Must contain string keys
                and JSON-serializable values.
            index: Controls how the item's fields are indexed for search:
-                - None (default): Use store's default indexing configuration
+
+                - None (default): Use `fields` you configured when creating the store (if any)
+                    If you do not initialize the store with indexing capabilities,
+                    the `index` parameter will be ignored
                - False: Disable indexing for this item
                - list[str]: List of field paths to index, supporting:
                    - Nested fields: "metadata.title"
@@ -593,23 +720,25 @@ class BaseStore(ABC):
                    - Specific indices: "authors[0].name"

        Note:
-            Indexing capabilities depend on your store implementation.
-            Some implementations may support only a subset of indexing features.
+            Indexing support depends on your store implementation.
+            If you do not initialize the store with indexing capabilities,
+            the `index` parameter will be ignored.

-        ??? example "Examples"
-            Simple storage without special indexing (respects store defaults)
+        ???+ example "Examples"
+            Store item. Indexing depends on how you configure the store.
            ```python
-            store.put(("docs",), "report", {"title": "Annual Report"})
+            store.put(("docs",), "report", {"memory": "Will likes ai"})
            ```

-            Index specific fields for search
+            Do not index item for semantic search. Still accessible through get()
+            and search() operations but won't have a vector representation.
            ```python
-            store.put(("docs",), "report", {"title": "Annual Report"}, index=["title"])
+            store.put(("docs",), "report", {"memory": "Will likes ai"}, index=False)
            ```

-            Do not index for semantic search
+            Index specific fields for search.
            ```python
-            store.put(("docs",), "report", {"title": "Annual Report"}, index=False)
+            store.put(("docs",), "report", {"memory": "Will likes ai"}, index=["memory"])
            ```
        """
        _validate_namespace(namespace)
@@ -650,7 +779,7 @@ class BaseStore(ABC):
            List[Tuple[str, ...]]: A list of namespace tuples that match the criteria.
            Each tuple represents a full namespace path up to `max_depth`.

-        ??? example "Examples":
+        ???+ example "Examples":
            Setting max_depth=3. Given the namespaces:
            ```python
            # Example if you have the following namespaces:
@@ -710,6 +839,39 @@ class BaseStore(ABC):

        Returns:
            List of items matching the search criteria.
+
+        ???+ example "Examples"
+            Basic filtering:
+            ```python
+            # Search for documents with specific metadata
+            results = await store.asearch(
+                ("docs",),
+                filter={"type": "article", "status": "published"}
+            )
+            ```
+
+            Natural language search (requires vector store implementation):
+            ```python
+            # Initialize store with embedding configuration
+            store = YourStore( # e.g., InMemoryStore, AsyncPostgresStore
+                index={
+                    "dims": 1536,  # embedding dimensions
+                    "embed": your_embedding_function,  # function to create embeddings
+                    "fields": ["text"]  # fields to embed
+                }
+            )
+
+            # Search for semantically similar documents
+            results = await store.asearch(
+                ("docs",),
+                query="machine learning applications in healthcare",
+                filter={"type": "research_paper"},
+                limit=5
+            )
+            ```
+
+            Note: Natural language search support depends on your store implementation
+            and requires proper embedding configuration.
        """
        return (
            await self.abatch(
@@ -734,7 +896,10 @@ class BaseStore(ABC):
            value: Dictionary containing the item's data. Must contain string keys
                and JSON-serializable values.
            index: Controls how the item's fields are indexed for search:
-                - None (default): Use store's default indexing configuration
+
+                - None (default): Use `fields` you configured when creating the store (if any)
+                    If you do not initialize the store with indexing capabilities,
+                    the `index` parameter will be ignored
                - False: Disable indexing for this item
                - list[str]: List of field paths to index, supporting:
                    - Nested fields: "metadata.title"
@@ -742,25 +907,32 @@ class BaseStore(ABC):
                    - Specific indices: "authors[0].name"

        Note:
-            Indexing capabilities depend on your store implementation.
-            Some implementations may support only a subset of indexing features.
+            Indexing support depends on your store implementation.
+            If you do not initialize the store with indexing capabilities,
+            the `index` parameter will be ignored.

-        ??? example "Examples"
-            Simple storage without special indexing:
+        ???+ example "Examples"
+            Store item. Indexing depends on how you configure the store.
            ```python
-            await store.aput(("docs",), "report", {"title": "Annual Report"})
+            await store.aput(("docs",), "report", {"memory": "Will likes ai"})
            ```

-            Index specific fields for search:
+            Do not index item for semantic search. Still accessible through get()
+            and search() operations but won't have a vector representation.
+            ```python
+            await store.aput(("docs",), "report", {"memory": "Will likes ai"}, index=False)
+            ```
+
+            Index specific fields for search (if store configured to index items):
            ```python
            await store.aput(
                ("docs",),
                "report",
                {
-                    "title": "Q4 Report",
-                    "chapters": [{"content": "..."}, {"content": "..."}]
+                    "memory": "Will likes ai",
+                    "context": [{"content": "..."}, {"content": "..."}]
                },
-                index=["title", "chapters[*].content"]
+                index=["memory", "context[*].content"]
            )
            ```
        """
@@ -802,7 +974,7 @@ class BaseStore(ABC):
            List[Tuple[str, ...]]: A list of namespace tuples that match the criteria.
            Each tuple represents a full namespace path up to `max_depth`.

-        ??? example "Examples"
+        ???+ example "Examples"
            Setting max_depth=3 with existing namespaces:
            ```python
            # Given the following namespaces:
@@ -1,31 +1,102 @@
-"""In-memory key-value store.
+"""In-memory dictionary-backed store with optional vector search.

-A lightweight store implementation using Python dictionaries. Supports basic
-key-value operations and vector search when configured with embeddings.
-
-Examples:
+!!! example "Examples"
    Basic key-value storage:
-        store = InMemoryStore()
-        store.put(("users", "123"), "prefs", {"theme": "dark"})
-        item = store.get(("users", "123"), "prefs")
+    ```python
+    from langgraph.store.memory import InMemoryStore

-    Vector search with embeddings:
-        from langchain_openai import OpenAIEmbeddings
-        store = InMemoryStore(index={
+    store = InMemoryStore()
+    store.put(("users", "123"), "prefs", {"theme": "dark"})
+    item = store.get(("users", "123"), "prefs")
+    ```
+
+    Vector search using LangChain embeddings:
+    ```python
+    from langchain.embeddings import init_embeddings
+    from langgraph.store.memory import InMemoryStore
+
+    store = InMemoryStore(
+        index={
            "dims": 1536,
-            "embed": OpenAIEmbeddings(model="text-embedding-3-small"),
-        })
+            "embed": init_embeddings("openai:text-embedding-3-small")
+        }
+    )

-        # Store documents
-        store.put(("docs",), "doc1", {"text": "Python tutorial"})
-        store.put(("docs",), "doc2", {"text": "TypeScript guide"})
+    # Store documents
+    store.put(("docs",), "doc1", {"text": "Python tutorial"})
+    store.put(("docs",), "doc2", {"text": "TypeScript guide"})

-        # Search by similarity
-        results = store.search(("docs",), query="python programming")
+    # Search by similarity
+    results = store.search(("docs",), query="python programming")
+    ```

+    Vector search using OpenAI SDK directly:
+    ```python
+    from openai import OpenAI
+    from langgraph.store.memory import InMemoryStore

-Note:
-    For production use cases requiring persistence, use a database-backed store instead.
+    client = OpenAI()
+
+    def embed_texts(texts: list[str]) -> list[list[float]]:
+        response = client.embeddings.create(
+            model="text-embedding-3-small",
+            input=texts
+        )
+        return [e.embedding for e in response.data]
+
+    store = InMemoryStore(
+        index={
+            "dims": 1536,
+            "embed": embed_texts
+        }
+    )
+
+    # Store documents
+    store.put(("docs",), "doc1", {"text": "Python tutorial"})
+    store.put(("docs",), "doc2", {"text": "TypeScript guide"})
+
+    # Search by similarity
+    results = store.search(("docs",), query="python programming")
+    ```
+
+    Async vector search using OpenAI SDK:
+    ```python
+    from openai import AsyncOpenAI
+    from langgraph.store.memory import InMemoryStore
+
+    client = AsyncOpenAI()
+
+    async def aembed_texts(texts: list[str]) -> list[list[float]]:
+        response = await client.embeddings.create(
+            model="text-embedding-3-small",
+            input=texts
+        )
+        return [e.embedding for e in response.data]
+
+    store = InMemoryStore(
+        index={
+            "dims": 1536,
+            "embed": aembed_texts
+        }
+    )
+
+    # Store documents
+    await store.aput(("docs",), "doc1", {"text": "Python tutorial"})
+    await store.aput(("docs",), "doc2", {"text": "TypeScript guide"})
+
+    # Search by similarity
+    results = await store.asearch(("docs",), query="python programming")
+    ```
+
+Warning:
+    This store keeps all data in memory. Data is lost when the process exits.
+    For persistence, use a database-backed store like PostgresStore.
+
+Tip:
+    For vector search, install numpy for better performance:
+    ```bash
+    pip install numpy
+    ```
 """

 import asyncio
@@ -62,17 +133,18 @@ logger = logging.getLogger(__name__)
 class InMemoryStore(BaseStore):
    """In-memory dictionary-backed store with optional vector search.

-    Examples:
+    !!! example "Examples"
        Basic key-value storage:
            store = InMemoryStore()
            store.put(("users", "123"), "prefs", {"theme": "dark"})
            item = store.get(("users", "123"), "prefs")

        Vector search with embeddings:
-            from langchain_openai import OpenAIEmbeddings
+            from langchain.embeddings import init_embeddings
            store = InMemoryStore(index={
                "dims": 1536,
-                "embed": OpenAIEmbeddings(model="text-embedding-3-small"),
+                "embed": init_embeddings("openai:text-embedding-3-small"),
+                "fields": ["text"],
            })

            # Store documents
@@ -413,6 +485,8 @@ def _cosine_similarity(X: list[float], Y: list[list[float]]) -> list[float]:
    Compute cosine similarity between a vector X and a matrix Y.
    Lazy import numpy for efficiency.
    """
+    if not Y:
+        return []
    if _check_numpy():
        import numpy as np  # type: ignore

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-checkpoint"
-version = "2.0.7"
+version = "2.0.8"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 authors = []
 license = "MIT"
@@ -17,13 +17,13 @@ class IndexConfig(TypedDict, total=False):
    """Number of dimensions in the embedding vectors.
    
    Common embedding models have the following dimensions:
-        - OpenAI text-embedding-3-large: 256, 1024, or 3072
-        - OpenAI text-embedding-3-small: 512 or 1536
-        - OpenAI text-embedding-ada-002: 1536
-        - Cohere embed-english-v3.0: 1024
-        - Cohere embed-english-light-v3.0: 384
-        - Cohere embed-multilingual-v3.0: 1024
-        - Cohere embed-multilingual-light-v3.0: 384
+        - openai:text-embedding-3-large: 3072
+        - openai:text-embedding-3-small: 1536
+        - openai:text-embedding-ada-002: 1536
+        - cohere:embed-english-v3.0: 1024
+        - cohere:embed-english-light-v3.0: 384
+        - cohere:embed-multilingual-v3.0: 1024
+        - cohere:embed-multilingual-light-v3.0: 384
    """

    embed: str
@@ -829,15 +829,16 @@ def _coerce_state(schema: Type[Any], input: dict[str, Any]) -> dict[str, Any]:
 def _control_branch(value: Any) -> Sequence[Union[str, Send]]:
    if isinstance(value, Send):
        return [value]
-    if not isinstance(value, GraphCommand):
+    if not isinstance(value, Command):
        return EMPTY_SEQ
    if value.graph == Command.PARENT:
        raise ParentCommand(value)
    rtn: list[Union[str, Send]] = []
-    if isinstance(value.goto, str):
-        rtn.append(value.goto)
-    else:
-        rtn.extend(value.goto)
+    if isinstance(value, GraphCommand):
+        if isinstance(value.goto, str):
+            rtn.append(value.goto)
+        else:
+            rtn.extend(value.goto)
    if isinstance(value.send, Send):
        rtn.append(value.send)
    else:
@@ -848,15 +849,16 @@ def _control_branch(value: Any) -> Sequence[Union[str, Send]]:
 async def _acontrol_branch(value: Any) -> Sequence[Union[str, Send]]:
    if isinstance(value, Send):
        return [value]
-    if not isinstance(value, GraphCommand):
+    if not isinstance(value, Command):
        return EMPTY_SEQ
    if value.graph == Command.PARENT:
        raise ParentCommand(value)
    rtn: list[Union[str, Send]] = []
-    if isinstance(value.goto, str):
-        rtn.append(value.goto)
-    else:
-        rtn.extend(value.goto)
+    if isinstance(value, GraphCommand):
+        if isinstance(value.goto, str):
+            rtn.append(value.goto)
+        else:
+            rtn.extend(value.goto)
    if isinstance(value.send, Send):
        rtn.append(value.send)
    else:
@@ -933,12 +935,12 @@ def _is_field_binop(typ: Type[Any]) -> Optional[BinaryOperatorAggregate]:
    if hasattr(typ, "__metadata__"):
        meta = typ.__metadata__
        if len(meta) >= 1 and callable(meta[-1]):
-            sig = signature(meta[0])
+            sig = signature(meta[-1])
            params = list(sig.parameters.values())
            if len(params) == 2 and all(
                p.kind in (p.POSITIONAL_ONLY, p.POSITIONAL_OR_KEYWORD) for p in params
            ):
-                return BinaryOperatorAggregate(typ, meta[0])
+                return BinaryOperatorAggregate(typ, meta[-1])
            else:
                raise ValueError(
                    f"Invalid reducer signature. Expected (a, b) -> c. Got {sig}"
@@ -673,7 +673,7 @@ class Pregel(PregelProtocol):
        self, config: RunnableConfig, *, subgraphs: bool = False
    ) -> StateSnapshot:
        """Get the current state of the graph."""
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -710,7 +710,7 @@ class Pregel(PregelProtocol):
        self, config: RunnableConfig, *, subgraphs: bool = False
    ) -> StateSnapshot:
        """Get the current state of the graph."""
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -751,8 +751,9 @@ class Pregel(PregelProtocol):
        before: Optional[RunnableConfig] = None,
        limit: Optional[int] = None,
    ) -> Iterator[StateSnapshot]:
+        config = ensure_config(config)
        """Get the history of the state of the graph."""
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -800,8 +801,9 @@ class Pregel(PregelProtocol):
        before: Optional[RunnableConfig] = None,
        limit: Optional[int] = None,
    ) -> AsyncIterator[StateSnapshot]:
+        config = ensure_config(config)
        """Get the history of the state of the graph."""
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -855,7 +857,7 @@ class Pregel(PregelProtocol):
        node `as_node`. If `as_node` is not provided, it will be set to the last node
        that updated the state, if not ambiguous.
        """
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -1130,7 +1132,7 @@ class Pregel(PregelProtocol):
        values: dict[str, Any] | Any,
        as_node: Optional[str] = None,
    ) -> RunnableConfig:
-        checkpointer: Optional[BaseCheckpointSaver] = config[CONF].get(
+        checkpointer: Optional[BaseCheckpointSaver] = ensure_config(config)[CONF].get(
            CONFIG_KEY_CHECKPOINTER, self.checkpointer
        )
        if not checkpointer:
@@ -575,6 +575,7 @@ class RemoteGraph(PregelProtocol):
        interrupt_before: Optional[Union[All, Sequence[str]]] = None,
        interrupt_after: Optional[Union[All, Sequence[str]]] = None,
        subgraphs: bool = False,
+        **kwargs: Any,
    ) -> Iterator[Union[dict[str, Any], Any]]:
        """Create a run and stream the results.

@@ -589,6 +590,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
            subgraphs: Stream from subgraphs.
+            **kwargs: Additional params to pass to client.runs.stream.

        Yields:
            The output of the graph.
@@ -616,6 +618,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_after=interrupt_after,
            stream_subgraphs=subgraphs or stream is not None,
            if_not_exists="create",
+            **kwargs,
        ):
            # split mode and ns
            if NS_SEP in chunk.event:
@@ -664,6 +667,7 @@ class RemoteGraph(PregelProtocol):
        interrupt_before: Optional[Union[All, Sequence[str]]] = None,
        interrupt_after: Optional[Union[All, Sequence[str]]] = None,
        subgraphs: bool = False,
+        **kwargs: Any,
    ) -> AsyncIterator[Union[dict[str, Any], Any]]:
        """Create a run and stream the results.

@@ -678,6 +682,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
            subgraphs: Stream from subgraphs.
+            **kwargs: Additional params to pass to client.runs.stream.

        Yields:
            The output of the graph.
@@ -705,6 +710,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_after=interrupt_after,
            stream_subgraphs=subgraphs or stream is not None,
            if_not_exists="create",
+            **kwargs,
        ):
            # split mode and ns
            if NS_SEP in chunk.event:
@@ -767,18 +773,16 @@ class RemoteGraph(PregelProtocol):
        *,
        interrupt_before: Optional[Union[All, Sequence[str]]] = None,
        interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        **kwargs: Any,
    ) -> Union[dict[str, Any], Any]:
        """Create a run, wait until it finishes and return the final state.

-        This method calls `POST /threads/{thread_id}/runs/wait` if a `thread_id`
-        is speciffed in the `configurable` field of the config or
-        `POST /runs/wait` otherwise.
-
        Args:
            input: Input to the graph.
            config: A `RunnableConfig` for graph invocation.
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
+            **kwargs: Additional params to pass to RemoteGraph.stream.

        Returns:
            The output of the graph.
@@ -789,6 +793,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
            stream_mode="values",
+            **kwargs,
        ):
            pass
        try:
@@ -803,18 +808,16 @@ class RemoteGraph(PregelProtocol):
        *,
        interrupt_before: Optional[Union[All, Sequence[str]]] = None,
        interrupt_after: Optional[Union[All, Sequence[str]]] = None,
+        **kwargs: Any,
    ) -> Union[dict[str, Any], Any]:
        """Create a run, wait until it finishes and return the final state.

-        This method calls `POST /threads/{thread_id}/runs/wait` if a `thread_id`
-        is speciffed in the `configurable` field of the config or
-        `POST /runs/wait` otherwise.
-
        Args:
            input: Input to the graph.
            config: A `RunnableConfig` for graph invocation.
            interrupt_before: Interrupt the graph before these nodes.
            interrupt_after: Interrupt the graph after these nodes.
+            **kwargs: Additional params to pass to RemoteGraph.astream.

        Returns:
            The output of the graph.
@@ -825,6 +828,7 @@ class RemoteGraph(PregelProtocol):
            interrupt_before=interrupt_before,
            interrupt_after=interrupt_after,
            stream_mode="values",
+            **kwargs,
        ):
            pass
        try:
@@ -791,17 +791,6 @@ cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]

-[[package]]
-name = "httpx-sse"
-version = "0.4.0"
-description = "Consume Server-Sent Event (SSE) messages with HTTPX."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "httpx-sse-0.4.0.tar.gz", hash = "sha256:1e81a3a3070ce322add1d3529ed42eb5f70817f45ed6ec915ab753f961139721"},
-    {file = "httpx_sse-0.4.0-py3-none-any.whl", hash = "sha256:f329af6eae57eaa2bdfd962b42524764af68075ea87370a2de920af5341e318f"},
-]
-
 [[package]]
 name = "idna"
 version = "3.10"
@@ -1359,7 +1348,7 @@ typing-extensions = ">=4.7"

 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.4"
+version = "2.0.8"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -1393,7 +1382,7 @@ url = "../checkpoint-duckdb"

 [[package]]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.2"
+version = "2.0.7"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -1401,10 +1390,10 @@ files = []
 develop = true

 [package.dependencies]
-langgraph-checkpoint = "^2.0.2"
+langgraph-checkpoint = "^2.0.7"
 orjson = ">=3.10.1"
-psycopg = "^3.0.0"
-psycopg-pool = "^3.0.0"
+psycopg = "^3.2.0"
+psycopg-pool = "^3.2.0"

 [package.source]
 type = "directory"
@@ -1429,7 +1418,7 @@ url = "../checkpoint-sqlite"

 [[package]]
 name = "langgraph-sdk"
-version = "0.1.36"
+version = "0.1.42"
 description = "SDK for interacting with LangGraph API"
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -1438,7 +1427,6 @@ develop = true

 [package.dependencies]
 httpx = ">=0.25.2"
-httpx-sse = ">=0.4.0"
 orjson = ">=3.10.1"

 [package.source]
@@ -3425,4 +3413,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9.0,<4.0"
-content-hash = "9bf5668d3f70f3b77457906732404a6401583a5966f70a72ef10a68f2a5b27ad"
+content-hash = "2df4d5d5e61917bdfff0ba430067a17662666eedee2858d841fa02e594cf69d0"
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph"
-version = "0.2.53"
+version = "0.2.54"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 license = "MIT"
@@ -11,7 +11,7 @@ repository = "https://www.github.com/langchain-ai/langgraph"
 python = ">=3.9.0,<4.0"
 langchain-core = ">=0.2.43,<0.4.0,!=0.3.0,!=0.3.1,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14"
 langgraph-checkpoint = "^2.0.4"
-langgraph-sdk = "^0.1.32"
+langgraph-sdk = "^0.1.42"

 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.2"
@@ -1925,7 +1925,7 @@ def test_send_sequences() -> None:

    def send_for_fun(state):
        return [
-            Send("2", GraphCommand(send=Send("2", 3))),
+            Send("2", Command(send=Send("2", 3))),
            Send("2", GraphCommand(send=Send("2", 4))),
            "3.1",
        ]
@@ -2573,14 +2573,14 @@ async def test_send_sequences(checkpointer_name: str) -> None:
                if isinstance(state, list)  # or isinstance(state, Control)
                else ["|".join((self.name, str(state)))]
            )
-            if isinstance(state, GraphCommand):
+            if isinstance(state, Command):
                return replace(state, update=update)
            else:
                return update

    async def send_for_fun(state):
        return [
-            Send("2", GraphCommand(send=Send("2", 3))),
+            Send("2", Command(send=Send("2", 3))),
            Send("2", GraphCommand(send=Send("2", 4))),
            "3.1",
        ]
@@ -1,6 +1,6 @@
 {
  "name": "@langchain/langgraph-sdk",
-  "version": "0.0.30",
+  "version": "0.0.31",
  "description": "Client library for interacting with the LangGraph API",
  "type": "module",
  "packageManager": "yarn@1.22.19",
@@ -1206,6 +1206,7 @@ export class StoreClient extends BaseClient {
   * @param options.filter Optional dictionary of key-value pairs to filter results.
   * @param options.limit Maximum number of items to return (default is 10).
   * @param options.offset Number of items to skip before returning results (default is 0).
+   * @param options.query Optional search query.
   * @returns Promise<SearchItemsResponse>
   */
  async searchItems(
@@ -1214,6 +1215,7 @@ export class StoreClient extends BaseClient {
      filter?: Record<string, any>;
      limit?: number;
      offset?: number;
+      query?: string;
    },
  ): Promise<SearchItemsResponse> {
    const payload = {
@@ -1221,6 +1223,7 @@ export class StoreClient extends BaseClient {
      filter: options?.filter,
      limit: options?.limit ?? 10,
      offset: options?.offset ?? 0,
+      query: options?.query,
    };

    const response = await this.fetch<APISearchItemsResponse>(
@@ -264,11 +264,6 @@ export interface Checkpoint {
 export interface ListNamespaceResponse {
  namespaces: string[][];
 }
-
-export interface SearchItemsResponse {
-  items: Item[];
-}
-
 export interface Item {
  namespace: string[];
  key: string;
@@ -276,3 +271,10 @@ export interface Item {
  createdAt: string;
  updatedAt: string;
 }
+
+export interface SearchItem extends Item {
+  score?: number;
+}
+export interface SearchItemsResponse {
+  items: SearchItem[];
+}
@@ -26,7 +26,6 @@ from typing import (
 )

 import httpx
-import httpx_sse
 import orjson
 from httpx._types import QueryParamTypes

@@ -61,6 +60,7 @@ from langgraph_sdk.schema import (
    ThreadStatus,
    ThreadUpdateStateResponse,
 )
+from langgraph_sdk.sse import SSEDecoder, aiter_lines_raw, iter_lines_raw

 logger = logging.getLogger(__name__)

@@ -190,7 +190,7 @@ class LangGraphClient:


 class HttpClient:
-    """Hancle async requests to the LangGraph API.
+    """Handle async requests to the LangGraph API.

    Adds additional error messaging & content handling above the
    provided httpx client.
@@ -282,22 +282,35 @@ class HttpClient:
    ) -> AsyncIterator[StreamPart]:
        """Stream results using SSE."""
        headers, content = await aencode_json(json)
-        async with httpx_sse.aconnect_sse(
-            self.client, method, path, headers=headers, content=content
-        ) as sse:
+        headers["Accept"] = "text/event-stream"
+        headers["Cache-Control"] = "no-store"
+
+        async with self.client.stream(
+            method, path, headers=headers, content=content
+        ) as res:
+            # check status
            try:
-                sse.response.raise_for_status()
+                res.raise_for_status()
            except httpx.HTTPStatusError as e:
-                body = (await sse.response.aread()).decode()
+                body = (await res.aread()).decode()
                if sys.version_info >= (3, 11):
                    e.add_note(body)
                else:
                    logger.error(f"Error from langgraph-api: {body}", exc_info=e)
                raise e
-            async for event in sse.aiter_sse():
-                yield StreamPart(
-                    event.event, orjson.loads(event.data) if event.data else None
+            # check content type
+            content_type = res.headers.get("content-type", "").partition(";")[0]
+            if "text/event-stream" not in content_type:
+                raise httpx.TransportError(
+                    "Expected response header Content-Type to contain 'text/event-stream', "
+                    f"got {content_type!r}"
                )
+            # parse SSE
+            decoder = SSEDecoder()
+            async for line in aiter_lines_raw(res):
+                sse = decoder.decode(line=line.rstrip(b"\n"))
+                if sse is not None:
+                    yield sse


 async def aencode_json(json: Any) -> tuple[dict[str, str], bytes]:
@@ -2438,22 +2451,30 @@ class SyncHttpClient:
    ) -> Iterator[StreamPart]:
        """Stream the results of a request using SSE."""
        headers, content = encode_json(json)
-        with httpx_sse.connect_sse(
-            self.client, method, path, headers=headers, content=content
-        ) as sse:
+        with self.client.stream(method, path, headers=headers, content=content) as res:
+            # check status
            try:
-                sse.response.raise_for_status()
+                res.raise_for_status()
            except httpx.HTTPStatusError as e:
-                body = sse.response.read().decode()
+                body = (res.read()).decode()
                if sys.version_info >= (3, 11):
                    e.add_note(body)
                else:
                    logger.error(f"Error from langgraph-api: {body}", exc_info=e)
                raise e
-            for event in sse.iter_sse():
-                yield StreamPart(
-                    event.event, orjson.loads(event.data) if event.data else None
+            # check content type
+            content_type = res.headers.get("content-type", "").partition(";")[0]
+            if "text/event-stream" not in content_type:
+                raise httpx.TransportError(
+                    "Expected response header Content-Type to contain 'text/event-stream', "
+                    f"got {content_type!r}"
                )
+            # parse SSE
+            decoder = SSEDecoder()
+            for line in iter_lines_raw(res):
+                sse = decoder.decode(line.rstrip(b"\n"))
+                if sse is not None:
+                    yield sse


 def encode_json(json: Any) -> tuple[dict[str, str], bytes]:
@@ -0,0 +1,148 @@
+"""Adapted from httpx_sse to split lines on \n, \r, \r\n per the SSE spec."""
+
+from typing import AsyncIterator, Iterator, Optional, Union
+
+import httpx
+import orjson
+
+from langgraph_sdk.schema import StreamPart
+
+BytesLike = Union[bytes, bytearray, memoryview]
+
+
+class BytesLineDecoder:
+    """
+    Handles incrementally reading lines from text.
+
+    Has the same behaviour as the stdllib bytes splitlines,
+    but handling the input iteratively.
+    """
+
+    def __init__(self) -> None:
+        self.buffer = bytearray()
+        self.trailing_cr: bool = False
+
+    def decode(self, text: bytes) -> list[BytesLike]:
+        # See https://docs.python.org/3/glossary.html#term-universal-newlines
+        NEWLINE_CHARS = b"\n\r"
+
+        # We always push a trailing `\r` into the next decode iteration.
+        if self.trailing_cr:
+            text = b"\r" + text
+            self.trailing_cr = False
+        if text.endswith(b"\r"):
+            self.trailing_cr = True
+            text = text[:-1]
+
+        if not text:
+            # NOTE: the edge case input of empty text doesn't occur in practice,
+            # because other httpx internals filter out this value
+            return []  # pragma: no cover
+
+        trailing_newline = text[-1] in NEWLINE_CHARS
+        lines = text.splitlines()
+
+        if len(lines) == 1 and not trailing_newline:
+            # No new lines, buffer the input and continue.
+            self.buffer.extend(lines[0])
+            return []
+
+        if self.buffer:
+            # Include any existing buffer in the first portion of the
+            # splitlines result.
+            self.buffer.extend(lines[0])
+            lines = [self.buffer] + lines[1:]
+            self.buffer = bytearray()
+
+        if not trailing_newline:
+            # If the last segment of splitlines is not newline terminated,
+            # then drop it from our output and start a new buffer.
+            self.buffer.extend(lines.pop())
+
+        return lines
+
+    def flush(self) -> list[BytesLike]:
+        if not self.buffer and not self.trailing_cr:
+            return []
+
+        lines = [self.buffer]
+        self.buffer = bytearray()
+        self.trailing_cr = False
+        return lines
+
+
+class SSEDecoder:
+    def __init__(self) -> None:
+        self._event = ""
+        self._data = bytearray()
+        self._last_event_id = ""
+        self._retry: Optional[int] = None
+
+    def decode(self, line: bytes) -> Optional[StreamPart]:
+        # See: https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation  # noqa: E501
+
+        if not line:
+            if (
+                not self._event
+                and not self._data
+                and not self._last_event_id
+                and self._retry is None
+            ):
+                return None
+
+            sse = StreamPart(
+                event=self._event,
+                data=orjson.loads(self._data) if self._data else None,
+            )
+
+            # NOTE: as per the SSE spec, do not reset last_event_id.
+            self._event = ""
+            self._data = bytearray()
+            self._retry = None
+
+            return sse
+
+        if line.startswith(b":"):
+            return None
+
+        fieldname, _, value = line.partition(b":")
+
+        if value.startswith(b" "):
+            value = value[1:]
+
+        if fieldname == b"event":
+            self._event = value.decode()
+        elif fieldname == b"data":
+            self._data.extend(value)
+        elif fieldname == b"id":
+            if b"\0" in value:
+                pass
+            else:
+                self._last_event_id = value.decode()
+        elif fieldname == b"retry":
+            try:
+                self._retry = int(value)
+            except (TypeError, ValueError):
+                pass
+        else:
+            pass  # Field is ignored.
+
+        return None
+
+
+async def aiter_lines_raw(response: httpx.Response) -> AsyncIterator[BytesLike]:
+    decoder = BytesLineDecoder()
+    async for chunk in response.aiter_bytes():
+        for line in decoder.decode(chunk):
+            yield line
+    for line in decoder.flush():
+        yield line
+
+
+def iter_lines_raw(response: httpx.Response) -> Iterator[BytesLike]:
+    decoder = BytesLineDecoder()
+    for chunk in response.iter_bytes():
+        for line in decoder.decode(chunk):
+            yield line
+    for line in decoder.flush():
+        yield line
@@ -141,17 +141,6 @@ cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
 http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]

-[[package]]
-name = "httpx-sse"
-version = "0.4.0"
-description = "Consume Server-Sent Event (SSE) messages with HTTPX."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "httpx-sse-0.4.0.tar.gz", hash = "sha256:1e81a3a3070ce322add1d3529ed42eb5f70817f45ed6ec915ab753f961139721"},
-    {file = "httpx_sse-0.4.0-py3-none-any.whl", hash = "sha256:f329af6eae57eaa2bdfd962b42524764af68075ea87370a2de920af5341e318f"},
-]
-
 [[package]]
 name = "idna"
 version = "3.7"
@@ -490,4 +479,4 @@ watchmedo = ["PyYAML (>=3.10)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9.0,<4.0"
-content-hash = "832acea0ad21ce71ae74edef225a1ad6f8fb166f6bf1531d876fe80fac7495f0"
+content-hash = "1262a6148df18cc44ade00466b6e0f8305897a460eea370c8de649d8d20cd7a2"
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langgraph-sdk"
-version = "0.1.41"
+version = "0.1.42"
 description = "SDK for interacting with LangGraph API"
 authors = []
 license = "MIT"
@@ -11,7 +11,6 @@ packages = [{ include = "langgraph_sdk" }]
 [tool.poetry.dependencies]
 python = "^3.9.0,<4.0"
 httpx = ">=0.25.2"
-httpx-sse = ">=0.4.0"
 orjson = ">=3.10.1"

 [tool.poetry.group.dev.dependencies]
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.

 [[package]]
 name = "aiohappyeyeballs"
@@ -2862,30 +2862,30 @@ adal = ["adal (>=1.0.2)"]

 [[package]]
 name = "langchain"
-version = "0.3.1"
+version = "0.3.9"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain-0.3.1-py3-none-any.whl", hash = "sha256:94e5ee7464d4366e4b158aa5704953c39701ea237b9ed4b200096d49e83bb3ae"},
-    {file = "langchain-0.3.1.tar.gz", hash = "sha256:54d6e3abda2ec056875a231a418a4130ba7576e629e899067e499bfc847b7586"},
+    {file = "langchain-0.3.9-py3-none-any.whl", hash = "sha256:ade5a1fee2f94f2e976a6c387f97d62cc7f0b9f26cfe0132a41d2bda761e1045"},
+    {file = "langchain-0.3.9.tar.gz", hash = "sha256:4950c4ad627d0aa95ce6bda7de453e22059b7e7836b562a8f781fb0b05d7294c"},
 ]

 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
-langchain-core = ">=0.3.6,<0.4.0"
+langchain-core = ">=0.3.21,<0.4.0"
 langchain-text-splitters = ">=0.3.0,<0.4.0"
 langsmith = ">=0.1.17,<0.2.0"
 numpy = [
-    {version = ">=1,<2", markers = "python_version < \"3.12\""},
-    {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.22.4,<2", markers = "python_version < \"3.12\""},
+    {version = ">=1.26.2,<3", markers = "python_version >= \"3.12\""},
 ]
 pydantic = ">=2.7.4,<3.0.0"
 PyYAML = ">=5.3"
 requests = ">=2,<3"
 SQLAlchemy = ">=1.4,<3"
-tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10"

 [[package]]
 name = "langchain-anthropic"
@@ -2933,13 +2933,13 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"

 [[package]]
 name = "langchain-core"
-version = "0.3.15"
+version = "0.3.21"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "langchain_core-0.3.15-py3-none-any.whl", hash = "sha256:3d4ca6dbb8ed396a6ee061063832a2451b0ce8c345570f7b086ffa7288e4fa29"},
-    {file = "langchain_core-0.3.15.tar.gz", hash = "sha256:b1a29787a4ffb7ec2103b4e97d435287201da7809b369740dd1e32f176325aba"},
+    {file = "langchain_core-0.3.21-py3-none-any.whl", hash = "sha256:7e723dff80946a1198976c6876fea8326dc82566ef9bcb5f8d9188f738733665"},
+    {file = "langchain_core-0.3.21.tar.gz", hash = "sha256:561b52b258ffa50a9fb11d7a1940ebfd915654d1ec95b35e81dfd5ee84143411"},
 ]

 [package.dependencies]
@@ -3035,7 +3035,7 @@ langchain-core = ">=0.3.0,<0.4.0"

 [[package]]
 name = "langgraph"
-version = "0.2.52"
+version = "0.2.54"
 description = "Building stateful, multi-actor applications with LLMs"
 optional = false
 python-versions = ">=3.9.0,<4.0"
@@ -3045,7 +3045,7 @@ develop = true
 [package.dependencies]
 langchain-core = ">=0.2.43,<0.4.0,!=0.3.0,!=0.3.1,!=0.3.2,!=0.3.3,!=0.3.4,!=0.3.5,!=0.3.6,!=0.3.7,!=0.3.8,!=0.3.9,!=0.3.10,!=0.3.11,!=0.3.12,!=0.3.13,!=0.3.14"
 langgraph-checkpoint = "^2.0.4"
-langgraph-sdk = "^0.1.32"
+langgraph-sdk = "^0.1.42"

 [package.source]
 type = "directory"
@@ -3053,7 +3053,7 @@ url = "libs/langgraph"

 [[package]]
 name = "langgraph-checkpoint"
-version = "2.0.5"
+version = "2.0.8"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3070,7 +3070,7 @@ url = "libs/checkpoint"

 [[package]]
 name = "langgraph-checkpoint-postgres"
-version = "2.0.3"
+version = "2.0.7"
 description = "Library with a Postgres implementation of LangGraph checkpoint saver."
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3078,10 +3078,10 @@ files = []
 develop = true

 [package.dependencies]
-langgraph-checkpoint = "^2.0.2"
+langgraph-checkpoint = "^2.0.7"
 orjson = ">=3.10.1"
-psycopg = "^3.0.0"
-psycopg-pool = "^3.0.0"
+psycopg = "^3.2.0"
+psycopg-pool = "^3.2.0"

 [package.source]
 type = "directory"
@@ -3106,7 +3106,7 @@ url = "libs/checkpoint-sqlite"

 [[package]]
 name = "langgraph-sdk"
-version = "0.1.36"
+version = "0.1.42"
 description = "SDK for interacting with LangGraph API"
 optional = false
 python-versions = "^3.9.0,<4.0"
@@ -3115,7 +3115,6 @@ develop = true

 [package.dependencies]
 httpx = ">=0.25.2"
-httpx-sse = ">=0.4.0"
 orjson = ">=3.10.1"

 [package.source]
@@ -3586,7 +3585,6 @@ optional = false
 python-versions = ">=3.6"
 files = [
    {file = "mkdocs-redirects-1.2.1.tar.gz", hash = "sha256:9420066d70e2a6bb357adf86e67023dcdca1857f97f07c7fe450f8f1fb42f861"},
-    {file = "mkdocs_redirects-1.2.1-py3-none-any.whl", hash = "sha256:497089f9e0219e7389304cffefccdfa1cac5ff9509f2cb706f4c9b221726dffb"},
 ]

 [package.dependencies]
@@ -6964,7 +6962,6 @@ description = "Automatically mock your HTTP interactions to simplify and speed u
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "vcrpy-6.0.1-py2.py3-none-any.whl", hash = "sha256:621c3fb2d6bd8aa9f87532c688e4575bcbbde0c0afeb5ebdb7e14cac409edfdd"},
    {file = "vcrpy-6.0.1.tar.gz", hash = "sha256:9e023fee7f892baa0bbda2f7da7c8ac51165c1c6e38ff8688683a12a4bde9278"},
 ]

@@ -7476,4 +7473,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "776ee42630769f08e3896338f18ec81830166695d32d2208dc31dedb22d3b22d"
+content-hash = "cf18eed5e183fc4f7786d095540b6c9261e130750f2d1fcc427e08b78d522c61"
@@ -34,7 +34,7 @@ ruff = "^0.6.8"
 jupyter = "^1.1.1"

 [tool.poetry.group.test.dependencies]
-langchain = "^0.3.1"
+langchain = "^0.3.8"
 langchain-openai = "^0.2.0"
 langchain-anthropic = "^0.2.1"
 langchain-nomic = "^0.1.3"
Author	SHA1	Message	Date
William Fu-Hinthorn	78e5bf4511	Merge branch 'main' into wfh/docs/memstoreconcept	2024-12-04 08:58:40 -08:00
Nuno CamposandGitHub	9ab5fbc0f8	Merge pull request #2627 from langchain-ai/nc/4dec/state-ensure-config lib: Call ensure_config in state crud methods	2024-12-04 11:53:03 -05:00
William FHandGitHub	c141f0fdf0	Add memory how-to (#2629 )	2024-12-04 08:39:53 -08:00
William FHandGitHub	830557d6b7	Clarify behavior in docstring (#2628 )	2024-12-04 16:38:09 +00:00
Nuno Campos	e5b00cdd1e	Fix	2024-12-04 08:30:10 -08:00
Nuno Campos	8eea7ac401	lib: Call ensure_config in state crud methods - this ensures that config from context vars is merged in	2024-12-04 08:15:01 -08:00
William FHandGitHub	c322f7ffa6	Add Memory Store conceptual doc section (#2624 ) On semantic search	2024-12-04 15:19:49 +00:00
William Fu-Hinthorn	2709c7e786	Relative	2024-12-04 07:06:12 -08:00
William FHandGitHub	e6c83abecd	Fix ref doc formatting (#2623 )	2024-12-04 06:55:15 -08:00
William Fu-Hinthorn	62dafd2f2f	Update the common dims table	2024-12-04 06:53:55 -08:00
William Fu-Hinthorn	c5904135cc	Merge remote-tracking branch 'origin/main' into wfh/docs/memstoreconcept	2024-12-04 06:49:29 -08:00
William Fu-Hinthorn	fb188c4c5c	Add Memory Store conceptual doc section On semantic search	2024-12-04 06:45:23 -08:00
ACMCMCandGitHub	a8db511e24	Fix typo (#2620 )	2024-12-04 06:30:05 -08:00
湛露先生andGitHub	84d33f9621	Fix typos in langgraph_sdk client. (#2621 ) Fix typos in langgraph_sdk client. Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>	2024-12-04 06:29:28 -08:00
William FHandGitHub	9220049b35	Add store langgraph.json config ref (#2622 )	2024-12-04 06:28:54 -08:00
William FHandGitHub	879df6b52c	[JS] Update SDK version (#2619 )	2024-12-03 23:01:19 -08:00
William FHandGitHub	9b8bf70d9e	Add link to local studio testing (#2617 )	2024-12-04 04:36:59 +00:00
Phoenix LoganandGitHub	aca67107c1	fix: make database saver classes inheritance-friendly (#2615 ) Replace hardcoded database saver class names with `cls` in `from_conn_string` factory methods to improve subclassing support ## Changes * Replaced direct class instantiations with `cls(conn)` in `from_conn_string` classmethods across all database implementations * Updated both synchronous and asynchronous variants for DuckDB, PostgreSQL, and SQLite savers ## Why This refactor makes the database saver classes more extensible by following Python's convention of using `cls` in class methods. This enables proper inheritance patterns where subclasses can reuse the factory methods without needing to override them. Previously, the hardcoded class names would always instantiate the parent class, even when called from a subclass. ## Testing The change is backward compatible and doesn't alter existing functionality. All existing tests should continue to pass as this is purely a structural refactoring that preserves the current behavior while improving extensibility. ## Notes This PR addresses follow up on comments from #2518 - AsyncPostgresSaver didn't need to be fixed but many of the other DB saver classes did.	2024-12-03 20:26:06 -08:00
William FHandGitHub	5fa196ab38	Update docstrings for store classes (#2616 )	2024-12-03 19:51:25 -08:00
Nuno CamposandGitHub	584d9271ce	Merge pull request #2614 from langchain-ai/nc/3dec/handle-command Handle Command returned from node (in addition to GraphCommand)	2024-12-03 19:05:05 -05:00
Nuno Campos	1bee33db3a	Fix	2024-12-03 15:52:41 -08:00
Nuno Campos	a203ddecf7	Handle Command returned from node (in addition to GraphCommand)	2024-12-03 15:48:59 -08:00
Vadym BardaandGitHub	5e3c326424	langgraph: bump sdk, release 0.2.54 (#2613 )	2024-12-03 16:38:59 -05:00
Nuno CamposandGitHub	86407aa6e8	Merge pull request #2071 from langchain-ai/brace/doc-nits fix(docs): Small nits & typo fixes	2024-12-03 16:38:36 -05:00
Vadym BardaandGitHub	7a80d6cb87	sdk-py: release 0.1.42 (#2612 )	2024-12-03 16:34:08 -05:00
Nuno Campos	70f323779e	Update persistence.md	2024-12-03 16:26:36 -05:00
Brace Sproul Nuno Campos Vadym Barda	23d5162945	Update human_in_the_loop.md Co-authored-by: Vadym Barda <vadym@langchain.dev>	2024-12-03 16:26:36 -05:00
bracesproulandNuno Campos	9d755f54e4	fix(docs): Small nits & typo fixes	2024-12-03 16:26:36 -05:00
Nuno CamposandGitHub	75cccc4fc4	Merge pull request #2589 from stneng/main fix: get correct reducer when type has multiple metadata.	2024-12-03 16:23:33 -05:00
Nuno CamposandGitHub	dd010e9230	Merge pull request #2593 from langchain-ai/nc/2dec/sdk-sse sdk-py: Fix SSE parsing to split lines only \n \r , remove httpx-sse, fix missing decoder flush	2024-12-03 16:23:11 -05:00
Nuno CamposandGitHub	2d87195b59	Merge pull request #2611 from langchain-ai/vb/remote-graph-kwargs langgraph: allow passing kwargs to SDK methods in RemoteGraph's invoke/stream	2024-12-03 16:21:09 -05:00
vbarda	515242d0ba	langgraph: allow passing kwargs to SDK methods in RemoteGraph's invoke/stream	2024-12-03 15:40:18 -05:00
Nuno Campos	3bf92d0b03	Fix	2024-12-03 11:04:28 -08:00
William FHandGitHub	36b6cd1493	fix: Handle empty store similarity (numpy) (#2602 )	2024-12-02 18:20:19 -08:00
Nuno CamposandGitHub	b80933c5fb	Merge branch 'main' into main	2024-12-02 20:50:44 -05:00
Nuno Campos	3cee1d5087	Remove httpx_sse, fix missing flush of sse decoder	2024-12-02 12:03:31 -08:00
Nuno Campos	2ce2021c39	Revert "Revert "sdk-py: Fix SSE parsing to split lines only \n \r \r\n per SSE spec"" This reverts commit `53ec7c41b2`.	2024-12-02 11:29:06 -08:00
stneng	363c6e2e4c	fix	2024-12-01 16:07:15 -08:00