The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
style: more refs fixes (#33730)
Mason Daugherty123e29dc26ee
diff --git a/libs/core/langchain_core/caches.py b/libs/core/langchain_core/caches.pyindex a2a90eadc6..86139c5d82 100644--- a/libs/core/langchain_core/caches.py+++ b/libs/core/langchain_core/caches.py@@ -2,8 +2,8 @@Distinct from provider-based [prompt caching](https://docs.langchain.com/oss/python/langchain/models#prompt-caching).-!!! warning- This is a beta feature! Please be wary of deploying experimental code to production+!!! warning "Beta feature"+ This is a beta feature. Please be wary of deploying experimental code to productionunless you've taken appropriate precautions.A cache is useful for two reasons:@@ -49,17 +49,18 @@ class BaseCache(ABC):"""Look up based on `prompt` and `llm_string`.A cache implementation is expected to generate a key from the 2-tuple- of prompt and llm_string (e.g., by concatenating them with a delimiter).+ of `prompt` and `llm_string` (e.g., by concatenating them with a delimiter).Args:prompt: A string representation of the prompt.In the case of a chat model, the prompt is a non-trivialserialization of the prompt into the language model.llm_string: A string representation of the LLM configuration.+This is used to capture the invocation parameters of the LLM(e.g., model name, temperature, stop tokens, max tokens, etc.).- These invocation parameters are serialized into a string- representation.++ These invocation parameters are serialized into a string representation.Returns:On a cache miss, return `None`. On a cache hit, return the cached value.@@ -78,8 +79,10 @@ class BaseCache(ABC):In the case of a chat model, the prompt is a non-trivialserialization of the prompt into the language model.llm_string: A string representation of the LLM configuration.+This is used to capture the invocation parameters of the LLM(e.g., model name, temperature, stop tokens, max tokens, etc.).+These invocation parameters are serialized into a stringrepresentation.return_val: The value to be cached. The value is a list of `Generation`@@ -94,15 +97,17 @@ class BaseCache(ABC):"""Async look up based on `prompt` and `llm_string`.A cache implementation is expected to generate a key from the 2-tuple- of prompt and llm_string (e.g., by concatenating them with a delimiter).+ of `prompt` and `llm_string` (e.g., by concatenating them with a delimiter).Args:prompt: A string representation of the prompt.In the case of a chat model, the prompt is a non-trivialserialization of the prompt into the language model.llm_string: A string representation of the LLM configuration.+This is used to capture the invocation parameters of the LLM(e.g., model name, temperature, stop tokens, max tokens, etc.).+These invocation parameters are serialized into a stringrepresentation.@@ -125,8 +130,10 @@ class BaseCache(ABC):In the case of a chat model, the prompt is a non-trivialserialization of the prompt into the language model.llm_string: A string representation of the LLM configuration.+This is used to capture the invocation parameters of the LLM(e.g., model name, temperature, stop tokens, max tokens, etc.).+These invocation parameters are serialized into a stringrepresentation.return_val: The value to be cached. The value is a list of `Generation`diff --git a/libs/core/langchain_core/documents/__init__.py b/libs/core/langchain_core/documents/__init__.pyindex 2bf3f80219..1969f10935 100644--- a/libs/core/langchain_core/documents/__init__.py+++ b/libs/core/langchain_core/documents/__init__.py@@ -1,7 +1,28 @@-"""Documents module.+"""Documents module for data retrieval and processing workflows.-**Document** module is a collection of classes that handle documents-and their transformations.+This module provides core abstractions for handling data in retrieval-augmented+generation (RAG) pipelines, vector stores, and document processing workflows.++!!! warning "Documents vs. message content"+ This module is distinct from `langchain_core.messages.content`, which provides+ multimodal content blocks for **LLM chat I/O** (text, images, audio, etc. within+ messages).++ **Key distinction:**++ - **Documents** (this module): For **data retrieval and processing workflows**+ - Vector stores, retrievers, RAG pipelines+ - Text chunking, embedding, and semantic search+ - Example: Chunks of a PDF stored in a vector database++ - **Content Blocks** (`messages.content`): For **LLM conversational I/O**+ - Multimodal message content sent to/from models+ - Tool calls, reasoning, citations within chat+ - Example: An image sent to a vision model in a chat message (via+ [`ImageContentBlock`][langchain.messages.ImageContentBlock])++ While both can represent similar data types (text, files), they serve different+ architectural purposes in LangChain applications."""from typing import TYPE_CHECKINGdiff --git a/libs/core/langchain_core/documents/base.py b/libs/core/langchain_core/documents/base.pyindex 68eeca0fd3..f049a9897b 100644--- a/libs/core/langchain_core/documents/base.py+++ b/libs/core/langchain_core/documents/base.py@@ -1,4 +1,16 @@-"""Base classes for media and documents."""+"""Base classes for media and documents.++This module contains core abstractions for **data retrieval and processing workflows**:++- `BaseMedia`: Base class providing `id` and `metadata` fields+- `Blob`: Raw data loading (files, binary data) - used by document loaders+- `Document`: Text content for retrieval (RAG, vector stores, semantic search)++!!! note "Not for LLM chat messages"+ These classes are for data processing pipelines, not LLM I/O. For multimodal+ content in chat messages (images, audio in conversations), see+ `langchain.messages` content blocks instead.+"""from __future__ import annotations@@ -19,15 +31,13 @@ PathLike = str | PurePathclass BaseMedia(Serializable):- """Use to represent media content.-- Media objects can be used to represent raw data, such as text or binary data.+ """Base class for content used in retrieval and data processing workflows.- LangChain Media objects allow associating metadata and an optional identifier- with the content.+ Provides common fields for content that needs to be stored, indexed, or searched.- The presence of an ID and metadata make it easier to store, index, and search- over the content in a structured way.+ !!! note+ For multimodal content in **chat messages** (images, audio sent to/from LLMs),+ use `langchain.messages` content blocks instead."""# The ID field is optional at the moment.@@ -45,61 +55,60 @@ class BaseMedia(Serializable):class Blob(BaseMedia):- """Blob represents raw data by either reference or value.+ """Raw data abstraction for document loading and file processing.- Provides an interface to materialize the blob in different representations, and- help to decouple the development of data loaders from the downstream parsing of- the raw data.+ Represents raw bytes or text, either in-memory or by file reference. Used+ primarily by document loaders to decouple data loading from parsing.Inspired by [Mozilla's `Blob`](https://developer.mozilla.org/en-US/docs/Web/API/Blob)- Example: Initialize a blob from in-memory data+ ???+ example "Initialize a blob from in-memory data"- ```python- from langchain_core.documents import Blob+ ```python+ from langchain_core.documents import Blob- blob = Blob.from_data("Hello, world!")+ blob = Blob.from_data("Hello, world!")- # Read the blob as a string- print(blob.as_string())+ # Read the blob as a string+ print(blob.as_string())- # Read the blob as bytes- print(blob.as_bytes())+ # Read the blob as bytes+ print(blob.as_bytes())- # Read the blob as a byte stream- with blob.as_bytes_io() as f:- print(f.read())- ```+ # Read the blob as a byte stream+ with blob.as_bytes_io() as f:+ print(f.read())+ ```- Example: Load from memory and specify mime-type and metadata+ ??? example "Load from memory and specify MIME type and metadata"- ```python- from langchain_core.documents import Blob+ ```python+ from langchain_core.documents import Blob- blob = Blob.from_data(- data="Hello, world!",- mime_type="text/plain",- metadata={"source": "https://example.com"},- )- ```+ blob = Blob.from_data(+ data="Hello, world!",+ mime_type="text/plain",+ metadata={"source": "https://example.com"},+ )+ ```- Example: Load the blob from a file+ ??? example "Load the blob from a file"- ```python- from langchain_core.documents import Blob+ ```python+ from langchain_core.documents import Blob- blob = Blob.from_path("path/to/file.txt")+ blob = Blob.from_path("path/to/file.txt")- # Read the blob as a string- print(blob.as_string())+ # Read the blob as a string+ print(blob.as_string())- # Read the blob as bytes- print(blob.as_bytes())+ # Read the blob as bytes+ print(blob.as_bytes())- # Read the blob as a byte stream- with blob.as_bytes_io() as f:- print(f.read())- ```+ # Read the blob as a byte stream+ with blob.as_bytes_io() as f:+ print(f.read())+ ```"""data: bytes | str | None = None@@ -213,7 +222,7 @@ class Blob(BaseMedia):encoding: Encoding to use if decoding the bytes into a stringmime_type: If provided, will be set as the MIME type of the dataguess_type: If `True`, the MIME type will be guessed from the file- extension, if a mime-type was not provided+ extension, if a MIME type was not providedmetadata: Metadata to associate with the `Blob`Returns:@@ -274,6 +283,10 @@ class Blob(BaseMedia):class Document(BaseMedia):"""Class for storing a piece of text and associated metadata.+ !!! note+ `Document` is for **retrieval workflows**, not chat I/O. For sending text+ to an LLM in a conversation, use message types from `langchain.messages`.+Example:```pythonfrom langchain_core.documents import Documentdiff --git a/libs/core/langchain_core/documents/compressor.py b/libs/core/langchain_core/documents/compressor.pyindex b18728eb9d..c765b378bb 100644--- a/libs/core/langchain_core/documents/compressor.py+++ b/libs/core/langchain_core/documents/compressor.py@@ -21,14 +21,14 @@ class BaseDocumentCompressor(BaseModel, ABC):This abstraction is primarily used for post-processing of retrieved documents.- Documents matching a given query are first retrieved.+ `Document` objects matching a given query are first retrieved.Then the list of documents can be further processed.For example, one could re-rank the retrieved documents using an LLM.!!! note- Users should favor using a RunnableLambda instead of sub-classing from this+ Users should favor using a `RunnableLambda` instead of sub-classing from thisinterface."""@@ -43,9 +43,9 @@ class BaseDocumentCompressor(BaseModel, ABC):"""Compress retrieved documents given the query context.Args:- documents: The retrieved documents.+ documents: The retrieved `Document` objects.query: The query context.- callbacks: Optional callbacks to run during compression.+ callbacks: Optional `Callbacks` to run during compression.Returns:The compressed documents.@@ -61,9 +61,9 @@ class BaseDocumentCompressor(BaseModel, ABC):"""Async compress retrieved documents given the query context.Args:- documents: The retrieved documents.+ documents: The retrieved `Document` objects.query: The query context.- callbacks: Optional callbacks to run during compression.+ callbacks: Optional `Callbacks` to run during compression.Returns:The compressed documents.diff --git a/libs/core/langchain_core/documents/transformers.py b/libs/core/langchain_core/documents/transformers.pyindex 4b815464a6..c05fa29a23 100644--- a/libs/core/langchain_core/documents/transformers.py+++ b/libs/core/langchain_core/documents/transformers.py@@ -16,8 +16,8 @@ if TYPE_CHECKING:class BaseDocumentTransformer(ABC):"""Abstract base class for document transformation.- A document transformation takes a sequence of Documents and returns a- sequence of transformed Documents.+ A document transformation takes a sequence of `Document` objects and returns a+ sequence of transformed `Document` objects.Example:```pythondiff --git a/libs/core/langchain_core/embeddings/fake.py b/libs/core/langchain_core/embeddings/fake.pyindex 37260ac711..0a252efc19 100644--- a/libs/core/langchain_core/embeddings/fake.py+++ b/libs/core/langchain_core/embeddings/fake.py@@ -18,7 +18,7 @@ class FakeEmbeddings(Embeddings, BaseModel):This embedding model creates embeddings by sampling from a normal distribution.- !!! warning+ !!! danger "Toy model"Do not use this outside of testing, as it is not a real embedding model.Instantiate:@@ -73,7 +73,7 @@ class DeterministicFakeEmbedding(Embeddings, BaseModel):This embedding model creates embeddings by sampling from a normal distributionwith a seed based on the hash of the text.- !!! warning+ !!! danger "Toy model"Do not use this outside of testing, as it is not a real embedding model.Instantiate:diff --git a/libs/core/langchain_core/language_models/__init__.py b/libs/core/langchain_core/language_models/__init__.pyindex 966b42e122..625543c830 100644--- a/libs/core/langchain_core/language_models/__init__.py+++ b/libs/core/langchain_core/language_models/__init__.py@@ -6,12 +6,13 @@ LangChain has two main classes to work with language models: chat models and**Chat models**Language models that use a sequence of messages as inputs and return chat messages-as outputs (as opposed to using plain text). Chat models support the assignment of-distinct roles to conversation messages, helping to distinguish messages from the AI,-users, and instructions such as system messages.+as outputs (as opposed to using plain text).-The key abstraction for chat models is `BaseChatModel`. Implementations-should inherit from this class.+Chat models support the assignment of distinct roles to conversation messages, helping+to distinguish messages from the AI, users, and instructions such as system messages.++The key abstraction for chat models is `BaseChatModel`. Implementations should inherit+from this class.See existing [chat model integrations](https://docs.langchain.com/oss/python/integrations/chat).diff --git a/libs/core/langchain_core/language_models/fake_chat_models.py b/libs/core/langchain_core/language_models/fake_chat_models.pyindex b619d3eb92..7ffb589601 100644--- a/libs/core/langchain_core/language_models/fake_chat_models.py+++ b/libs/core/langchain_core/language_models/fake_chat_models.py@@ -1,4 +1,4 @@-"""Fake chat model for testing purposes."""+"""Fake chat models for testing purposes."""import asyncioimport rediff --git a/libs/core/langchain_core/language_models/llms.py b/libs/core/langchain_core/language_models/llms.pyindex 645a9ef035..051c2781e1 100644--- a/libs/core/langchain_core/language_models/llms.py+++ b/libs/core/langchain_core/language_models/llms.py@@ -1,4 +1,7 @@-"""Base interface for large language models to expose."""+"""Base interface for traditional large language models (LLMs) to expose.++These are traditionally older models (newer models generally are chat models).+"""from __future__ import annotationsdiff --git a/libs/core/langchain_core/load/serializable.py b/libs/core/langchain_core/load/serializable.pyindex 13898d292d..9c7588c185 100644--- a/libs/core/langchain_core/load/serializable.py+++ b/libs/core/langchain_core/load/serializable.py@@ -97,11 +97,14 @@ class Serializable(BaseModel, ABC):by default. This is to prevent accidental serialization of objects that shouldnot be serialized.- `get_lc_namespace`: Get the namespace of the LangChain object.+During deserialization, this namespace is used to identifythe correct class to instantiate.+Please see the `Reviver` class in `langchain_core.load.load` for more details.During deserialization an additional mapping is handle classes that have movedor been renamed across package versions.+- `lc_secrets`: A map of constructor argument names to secret ids.- `lc_attributes`: List of additional attribute names that should be includedas part of the serialized representation.diff --git a/libs/core/langchain_core/messages/block_translators/google_genai.py b/libs/core/langchain_core/messages/block_translators/google_genai.pyindex 1f4d297bbc..2a82f035c2 100644--- a/libs/core/langchain_core/messages/block_translators/google_genai.py+++ b/libs/core/langchain_core/messages/block_translators/google_genai.py@@ -368,7 +368,7 @@ def _convert_to_v1_from_genai(message: AIMessage) -> list[types.ContentBlock]:else:# Assume it's raw base64 without data URItry:- # Validate base64 and decode for mime type detection+ # Validate base64 and decode for MIME type detectiondecoded_bytes = base64.b64decode(url, validate=True)image_url_b64_block = {@@ -379,7 +379,7 @@ def _convert_to_v1_from_genai(message: AIMessage) -> list[types.ContentBlock]:try:import filetype # type: ignore[import-not-found] # noqa: PLC0415- # Guess mime type based on file bytes+ # Guess MIME type based on file bytesmime_type = Nonekind = filetype.guess(decoded_bytes)if kind:diff --git a/libs/core/langchain_core/messages/content.py b/libs/core/langchain_core/messages/content.pyindex 10e17d6373..4b6a63e95f 100644--- a/libs/core/langchain_core/messages/content.py+++ b/libs/core/langchain_core/messages/content.py@@ -644,7 +644,7 @@ class AudioContentBlock(TypedDict):class PlainTextContentBlock(TypedDict):- """Plaintext data (e.g., from a document).+ """Plaintext data (e.g., from a `.txt` or `.md` document).!!! noteA `PlainTextContentBlock` existed in `langchain-core<1.0.0`. Although the@@ -767,7 +767,7 @@ class FileContentBlock(TypedDict):class NonStandardContentBlock(TypedDict):- """Provider-specific data.+ """Provider-specific content data.This block contains data for which there is not yet a standard type.@@ -802,7 +802,7 @@ class NonStandardContentBlock(TypedDict):"""value: dict[str, Any]- """Provider-specific data."""+ """Provider-specific content data."""index: NotRequired[int | str]"""Index of block in aggregate response. Used during streaming."""@@ -1399,7 +1399,7 @@ def create_non_standard_block("""Create a `NonStandardContentBlock`.Args:- value: Provider-specific data.+ value: Provider-specific content data.id: Content block identifier. Generated automatically if not provided.index: Index of block in aggregate response. Used during streaming.diff --git a/libs/core/langchain_core/messages/utils.py b/libs/core/langchain_core/messages/utils.pyindex 5554aa8abf..16cafce895 100644--- a/libs/core/langchain_core/messages/utils.py+++ b/libs/core/langchain_core/messages/utils.py@@ -86,7 +86,7 @@ AnyMessage = Annotated[| Annotated[ToolMessageChunk, Tag(tag="ToolMessageChunk")],Field(discriminator=Discriminator(_get_type)),]-""""A type representing any defined `Message` or `MessageChunk` type."""+"""A type representing any defined `Message` or `MessageChunk` type."""def get_buffer_string(diff --git a/libs/core/langchain_core/prompt_values.py b/libs/core/langchain_core/prompt_values.pyindex 99b063bc5b..731941514f 100644--- a/libs/core/langchain_core/prompt_values.py+++ b/libs/core/langchain_core/prompt_values.py@@ -37,8 +37,6 @@ class PromptValue(Serializable, ABC):def get_lc_namespace(cls) -> list[str]:"""Get the namespace of the LangChain object.- This is used to determine the namespace of the object when serializing.-Returns:`["langchain", "schema", "prompt"]`"""@@ -64,8 +62,6 @@ class StringPromptValue(PromptValue):def get_lc_namespace(cls) -> list[str]:"""Get the namespace of the LangChain object.- This is used to determine the namespace of the object when serializing.-Returns:`["langchain", "prompts", "base"]`"""@@ -101,8 +97,6 @@ class ChatPromptValue(PromptValue):def get_lc_namespace(cls) -> list[str]:"""Get the namespace of the LangChain object.- This is used to determine the namespace of the object when serializing.-Returns:`["langchain", "prompts", "chat"]`"""diff --git a/libs/core/langchain_core/prompts/base.py b/libs/core/langchain_core/prompts/base.pyindex 941c4ec726..ed322080c9 100644--- a/libs/core/langchain_core/prompts/base.py+++ b/libs/core/langchain_core/prompts/base.py@@ -48,11 +48,13 @@ class BasePromptTemplate("""A list of the names of the variables whose values are required as inputs to theprompt."""optional_variables: list[str] = Field(default=[])- """optional_variables: A list of the names of the variables for placeholder- or MessagePlaceholder that are optional. These variables are auto inferred- from the prompt and user need not provide them."""+ """A list of the names of the variables for placeholder or `MessagePlaceholder` that+ are optional.++ These variables are auto inferred from the prompt and user need not provide them."""input_types: typing.Dict[str, Any] = Field(default_factory=dict, exclude=True) # noqa: UP006"""A dictionary of the types of the variables the prompt template expects.+If not provided, all variables are assumed to be strings."""output_parser: BaseOutputParser | None = None"""How to parse the output of calling an LLM on this formatted prompt."""diff --git a/libs/core/langchain_core/prompts/chat.py b/libs/core/langchain_core/prompts/chat.pyindex 24cd084817..7878761f03 100644--- a/libs/core/langchain_core/prompts/chat.py+++ b/libs/core/langchain_core/prompts/chat.py@@ -776,11 +776,6 @@ class ChatPromptTemplate(BaseChatPromptTemplate):Use to create flexible templated prompts for chat models.- !!! warning "Behavior changed in 0.2.24"- You can pass any Message-like formats supported by- `ChatPromptTemplate.from_messages()` directly to `ChatPromptTemplate()`- init.-```pythonfrom langchain_core.prompts import ChatPromptTemplate@@ -896,25 +891,35 @@ class ChatPromptTemplate(BaseChatPromptTemplate):"""Create a chat prompt template from a variety of message formats.Args:- messages: sequence of message representations.+ messages: Sequence of message representations.+A message can be represented using the following formats:- (1) BaseMessagePromptTemplate, (2) BaseMessage, (3) 2-tuple of- (message type, template); e.g., ("human", "{user_input}"),- (4) 2-tuple of (message class, template), (5) a string which is- shorthand for ("human", template); e.g., "{user_input}".- template_format: format of the template.++ 1. `BaseMessagePromptTemplate`+ 2. `BaseMessage`+ 3. 2-tuple of `(message type, template)`; e.g.,+ `("human", "{user_input}")`+ 4. 2-tuple of `(message class, template)`+ 5. A string which is shorthand for `("human", template)`; e.g.,+ `"{user_input}"`+ template_format: Format of the template.input_variables: A list of the names of the variables whose values arerequired as inputs to the prompt.optional_variables: A list of the names of the variables for placeholderor MessagePlaceholder that are optional.+These variables are auto inferred from the prompt and user need notprovide them.partial_variables: A dictionary of the partial variables the prompt- template carries. Partial variables populate the template so that you- don't need to pass them in every time you call the prompt.+ template carries.++ Partial variables populate the template so that you don't need to pass+ them in every time you call the prompt.validate_template: Whether to validate the template.input_types: A dictionary of the types of the variables the prompt template- expects. If not provided, all variables are assumed to be strings.+ expects.++ If not provided, all variables are assumed to be strings.Examples:Instantiation from a list of message templates:@@ -1119,12 +1124,17 @@ class ChatPromptTemplate(BaseChatPromptTemplate):)```Args:- messages: sequence of message representations.+ messages: Sequence of message representations.+A message can be represented using the following formats:- (1) BaseMessagePromptTemplate, (2) BaseMessage, (3) 2-tuple of- (message type, template); e.g., ("human", "{user_input}"),- (4) 2-tuple of (message class, template), (5) a string which is- shorthand for ("human", template); e.g., "{user_input}".++ 1. `BaseMessagePromptTemplate`+ 2. `BaseMessage`+ 3. 2-tuple of `(message type, template)`; e.g.,+ `("human", "{user_input}")`+ 4. 2-tuple of `(message class, template)`+ 5. A string which is shorthand for `("human", template)`; e.g.,+ `"{user_input}"`template_format: format of the template.Returns:@@ -1236,7 +1246,7 @@ class ChatPromptTemplate(BaseChatPromptTemplate):"""Extend the chat template with a sequence of messages.Args:- messages: sequence of message representations to append.+ messages: Sequence of message representations to append."""self.messages.extend([_convert_to_message_template(message) for message in messages]diff --git a/libs/core/langchain_core/prompts/structured.py b/libs/core/langchain_core/prompts/structured.pyindex 7ae138cf05..33888691f7 100644--- a/libs/core/langchain_core/prompts/structured.py+++ b/libs/core/langchain_core/prompts/structured.py@@ -104,19 +104,23 @@ class StructuredPrompt(ChatPromptTemplate):)```Args:- messages: sequence of message representations.+ messages: Sequence of message representations.+A message can be represented using the following formats:- (1) BaseMessagePromptTemplate, (2) BaseMessage, (3) 2-tuple of- (message type, template); e.g., ("human", "{user_input}"),- (4) 2-tuple of (message class, template), (5) a string which is- shorthand for ("human", template); e.g., "{user_input}"- schema: a dictionary representation of function call, or a Pydantic model.++ 1. `BaseMessagePromptTemplate`+ 2. `BaseMessage`+ 3. 2-tuple of `(message type, template)`; e.g.,+ `("human", "{user_input}")`+ 4. 2-tuple of `(message class, template)`+ 5. A string which is shorthand for `("human", template)`; e.g.,+ `"{user_input}"`+ schema: A dictionary representation of function call, or a Pydantic model.**kwargs: Any additional kwargs to pass through to`ChatModel.with_structured_output(schema, **kwargs)`.Returns:- a structured prompt template-+ A structured prompt template"""return cls(messages, schema, **kwargs)diff --git a/libs/core/langchain_core/retrievers.py b/libs/core/langchain_core/retrievers.pyindex bb50d2985e..7be6df9a72 100644--- a/libs/core/langchain_core/retrievers.py+++ b/libs/core/langchain_core/retrievers.py@@ -50,65 +50,65 @@ class LangSmithRetrieverParams(TypedDict, total=False):class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):- """Abstract base class for a Document retrieval system.+ """Abstract base class for a document retrieval system.A retrieval system is defined as something that can take string queries and return- the most 'relevant' Documents from some source.+ the most 'relevant' documents from some source.Usage:- A retriever follows the standard Runnable interface, and should be used- via the standard Runnable methods of `invoke`, `ainvoke`, `batch`, `abatch`.+ A retriever follows the standard `Runnable` interface, and should be used via the+ standard `Runnable` methods of `invoke`, `ainvoke`, `batch`, `abatch`.Implementation:- When implementing a custom retriever, the class should implement- the `_get_relevant_documents` method to define the logic for retrieving documents.+ When implementing a custom retriever, the class should implement the+ `_get_relevant_documents` method to define the logic for retrieving documents.Optionally, an async native implementations can be provided by overriding the`_aget_relevant_documents` method.- Example: A retriever that returns the first 5 documents from a list of documents+ !!! example "Retriever that returns the first 5 documents from a list of documents"- ```python- from langchain_core.documents import Document- from langchain_core.retrievers import BaseRetriever+ ```python+ from langchain_core.documents import Document+ from langchain_core.retrievers import BaseRetriever- class SimpleRetriever(BaseRetriever):- docs: list[Document]- k: int = 5+ class SimpleRetriever(BaseRetriever):+ docs: list[Document]+ k: int = 5- def _get_relevant_documents(self, query: str) -> list[Document]:- \"\"\"Return the first k documents from the list of documents\"\"\"- return self.docs[:self.k]+ def _get_relevant_documents(self, query: str) -> list[Document]:+ \"\"\"Return the first k documents from the list of documents\"\"\"+ return self.docs[:self.k]- async def _aget_relevant_documents(self, query: str) -> list[Document]:- \"\"\"(Optional) async native implementation.\"\"\"- return self.docs[:self.k]- ```+ async def _aget_relevant_documents(self, query: str) -> list[Document]:+ \"\"\"(Optional) async native implementation.\"\"\"+ return self.docs[:self.k]+ ```- Example: A simple retriever based on a scikit-learn vectorizer+ !!! example "Simple retriever based on a scikit-learn vectorizer"- ```python- from sklearn.metrics.pairwise import cosine_similarity+ ```python+ from sklearn.metrics.pairwise import cosine_similarity- class TFIDFRetriever(BaseRetriever, BaseModel):- vectorizer: Any- docs: list[Document]- tfidf_array: Any- k: int = 4+ class TFIDFRetriever(BaseRetriever, BaseModel):+ vectorizer: Any+ docs: list[Document]+ tfidf_array: Any+ k: int = 4- class Config:- arbitrary_types_allowed = True+ class Config:+ arbitrary_types_allowed = True- def _get_relevant_documents(self, query: str) -> list[Document]:- # Ip -- (n_docs,x), Op -- (n_docs,n_Feats)- query_vec = self.vectorizer.transform([query])- # Op -- (n_docs,1) -- Cosine Sim with each doc- results = cosine_similarity(self.tfidf_array, query_vec).reshape((-1,))- return [self.docs[i] for i in results.argsort()[-self.k :][::-1]]- ```+ def _get_relevant_documents(self, query: str) -> list[Document]:+ # Ip -- (n_docs,x), Op -- (n_docs,n_Feats)+ query_vec = self.vectorizer.transform([query])+ # Op -- (n_docs,1) -- Cosine Sim with each doc+ results = cosine_similarity(self.tfidf_array, query_vec).reshape((-1,))+ return [self.docs[i] for i in results.argsort()[-self.k :][::-1]]+ ```"""model_config = ConfigDict(@@ -119,15 +119,19 @@ class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):_expects_other_args: bool = Falsetags: list[str] | None = None"""Optional list of tags associated with the retriever.+These tags will be associated with each call to this retriever,and passed as arguments to the handlers defined in `callbacks`.+You can use these to eg identify a specific instance of a retriever with itsuse case."""metadata: dict[str, Any] | None = None"""Optional metadata associated with the retriever.+This metadata will be associated with each call to this retriever,and passed as arguments to the handlers defined in `callbacks`.+You can use these to eg identify a specific instance of a retriever with itsuse case."""diff --git a/libs/core/langchain_core/tools/convert.py b/libs/core/langchain_core/tools/convert.pyindex cf16aef45a..ee51e30840 100644--- a/libs/core/langchain_core/tools/convert.py+++ b/libs/core/langchain_core/tools/convert.py@@ -89,6 +89,7 @@ def tool(runnable: Optional runnable to convert to a tool. Must be provided as apositional argument.description: Optional description for the tool.+Precedence for the tool description value is as follows:- `description` argument@@ -105,11 +106,13 @@ def tool(infer_schema: Whether to infer the schema of the arguments fromthe function's signature. This also makes the resultant toolaccept a dictionary input to its `run()` function.- response_format: The tool response format. If `"content"` then the output of- the tool is interpreted as the contents of a `ToolMessage`. If- `"content_and_artifact"` then the output is expected to be a two-tuple- corresponding to the `(content, artifact)` of a `ToolMessage`.- parse_docstring: if `infer_schema` and `parse_docstring`, will attempt to+ response_format: The tool response format.++ If `"content"` then the output of the tool is interpreted as the contents of+ a `ToolMessage`. If `"content_and_artifact"` then the output is expected to+ be a two-tuple corresponding to the `(content, artifact)` of a+ `ToolMessage`.+ parse_docstring: If `infer_schema` and `parse_docstring`, will attempt toparse parameter descriptions from Google Style function docstrings.error_on_invalid_docstring: if `parse_docstring` is provided, configurewhether to raise `ValueError` on invalid Google Style docstrings.diff --git a/libs/core/langchain_core/tools/retriever.py b/libs/core/langchain_core/tools/retriever.pyindex 298ae6dd93..5677e97bd7 100644--- a/libs/core/langchain_core/tools/retriever.py+++ b/libs/core/langchain_core/tools/retriever.py@@ -83,11 +83,12 @@ def create_retriever_tool(model, so should be descriptive.document_prompt: The prompt to use for the document.document_separator: The separator to use between documents.- response_format: The tool response format. If `"content"` then the output of- the tool is interpreted as the contents of a `ToolMessage`. If- `"content_and_artifact"` then the output is expected to be a two-tuple- corresponding to the `(content, artifact)` of a `ToolMessage` (artifact- being a list of documents in this case).+ response_format: The tool response format.++ If `"content"` then the output of the tool is interpreted as the contents of+ a `ToolMessage`. If `"content_and_artifact"` then the output is expected to+ be a two-tuple corresponding to the `(content, artifact)` of a `ToolMessage`+ (artifact being a list of documents in this case).Returns:Tool class to pass to an agent.diff --git a/libs/core/langchain_core/tools/structured.py b/libs/core/langchain_core/tools/structured.pyindex 632c450c3b..43e981570a 100644--- a/libs/core/langchain_core/tools/structured.py+++ b/libs/core/langchain_core/tools/structured.py@@ -151,11 +151,13 @@ class StructuredTool(BaseTool):return_direct: Whether to return the result directly or as a callback.args_schema: The schema of the tool's input arguments.infer_schema: Whether to infer the schema from the function's signature.- response_format: The tool response format. If `"content"` then the output of- the tool is interpreted as the contents of a `ToolMessage`. If- `"content_and_artifact"` then the output is expected to be a two-tuple- corresponding to the `(content, artifact)` of a `ToolMessage`.- parse_docstring: if `infer_schema` and `parse_docstring`, will attempt+ response_format: The tool response format.++ If `"content"` then the output of the tool is interpreted as the+ contents of a `ToolMessage`. If `"content_and_artifact"` then the output+ is expected to be a two-tuple corresponding to the `(content, artifact)`+ of a `ToolMessage`.+ parse_docstring: If `infer_schema` and `parse_docstring`, will attemptto parse parameter descriptions from Google Style function docstrings.error_on_invalid_docstring: if `parse_docstring` is provided, configurewhether to raise `ValueError` on invalid Google Style docstrings.diff --git a/libs/core/tests/unit_tests/runnables/test_runnable.py b/libs/core/tests/unit_tests/runnables/test_runnable.pyindex e04bf4e75b..22300f4188 100644--- a/libs/core/tests/unit_tests/runnables/test_runnable.py+++ b/libs/core/tests/unit_tests/runnables/test_runnable.py@@ -313,6 +313,12 @@ def test_schemas(snapshot: SnapshotAssertion) -> None:"description": "Class for storing a piece of text and ""associated metadata.\n""\n"+ "!!! note\n"+ " `Document` is for **retrieval workflows**, not chat I/O. For "+ "sending text\n"+ " to an LLM in a conversation, use message types from "+ "`langchain.messages`.\n"+ "\n""Example:\n"" ```python\n"" from langchain_core.documents import Document\n"diff --git a/libs/langchain/langchain_classic/chat_models/base.py b/libs/langchain/langchain_classic/chat_models/base.pyindex 248e0dd0b0..1ac5d4bdc0 100644--- a/libs/langchain/langchain_classic/chat_models/base.py+++ b/libs/langchain/langchain_classic/chat_models/base.py@@ -76,26 +76,35 @@ def init_chat_model(config_prefix: str | None = None,**kwargs: Any,) -> BaseChatModel | _ConfigurableModel:- """Initialize a chat model in a single line using the model's name and provider.+ """Initialize a chat model from any supported provider using a unified interface.++ **Two main use cases:**++ 1. **Fixed model** – specify the model upfront and get back a ready-to-use chat+ model.+ 2. **Configurable model** – choose to specify parameters (including model name) at+ runtime via `config`. Makes it easy to switch between models/providers without+ changing your code!!! note- Requires the integration package for your model provider to be installed.+ Requires the integration package for the chosen model provider to be installed.See the `model_provider` parameter below for specific package names(e.g., `pip install langchain-openai`).Refer to the [provider integration's API reference](https://docs.langchain.com/oss/python/integrations/providers)- for supported model parameters.+ for supported model parameters to use as `**kwargs`.Args:model: The name of the model, e.g. `'o3-mini'`, `'claude-sonnet-4-5'`.- You can also specify model and model provider in a single argument using:-+ You can also specify model and model provider in a single argument using`'{model_provider}:{model}'` format, e.g. `'openai:o1'`.model_provider: The model provider if not specified as part of the model arg- (see above). Supported `model_provider` values and the corresponding- integration package are:+ (see above).++ Supported `model_provider` values and the corresponding integration package+ are:- `openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai)- `anthropic` -> [`langchain-anthropic`](https://docs.langchain.com/oss/python/integrations/providers/anthropic)@@ -132,80 +141,95 @@ def init_chat_model(- `deepseek...` -> `deepseek`- `grok...` -> `xai`- `sonar...` -> `perplexity`- configurable_fields: Which model parameters are configurable:+ configurable_fields: Which model parameters are configurable at runtime:- - `None`: No configurable fields.+ - `None`: No configurable fields (i.e., a fixed model).- `'any'`: All fields are configurable. **See security note below.**- `list[str] | Tuple[str, ...]`: Specified fields are configurable.- Fields are assumed to have `config_prefix` stripped if there is a- `config_prefix`. If model is specified, then defaults to `None`. If model is- not specified, then defaults to `("model", "model_provider")`.+ Fields are assumed to have `config_prefix` stripped if a `config_prefix` is+ specified.++ If `model` is specified, then defaults to `None`.++ If `model` is not specified, then defaults to `("model", "model_provider")`.!!! warning "Security note"Setting `configurable_fields="any"` means fields like `api_key`,- `base_url`, etc. can be altered at runtime, potentially redirecting- model requests to a different service/user. Make sure that if you're- accepting untrusted configurations that you enumerate the- `configurable_fields=(...)` explicitly.-- config_prefix: If `'config_prefix'` is a non-empty string then model will be- configurable at runtime via the- `config["configurable"]["{config_prefix}_{param}"]` keys. If- `'config_prefix'` is an empty string then model will be configurable via+ `base_url`, etc., can be altered at runtime, potentially redirecting+ model requests to a different service/user.++ Make sure that if you're accepting untrusted configurations that you+ enumerate the `configurable_fields=(...)` explicitly.++ config_prefix: Optional prefix for configuration keys.++ Useful when you have multiple configurable models in the same application.++ If `'config_prefix'` is a non-empty string then `model` will be configurable+ at runtime via the `config["configurable"]["{config_prefix}_{param}"]` keys.+ See examples below.++ If `'config_prefix'` is an empty string then model will be configurable via`config["configurable"]["{param}"]`.- temperature: Model temperature.- max_tokens: Max output tokens.- timeout: The maximum time (in seconds) to wait for a response from the model- before canceling the request.- max_retries: The maximum number of attempts the system will make to resend a- request if it fails due to issues like network timeouts or rate limits.- base_url: The URL of the API endpoint where requests are sent.- rate_limiter: A `BaseRateLimiter` to space out requests to avoid exceeding- rate limits.- kwargs: Additional model-specific keyword args to pass to- `<<selected chat model>>.__init__(model=model_name, **kwargs)`.+ **kwargs: Additional model-specific keyword args to pass to the underlying+ chat model's `__init__` method. Common parameters include:++ - `temperature`: Model temperature for controlling randomness.+ - `max_tokens`: Maximum number of output tokens.+ - `timeout`: Maximum time (in seconds) to wait for a response.+ - `max_retries`: Maximum number of retry attempts for failed requests.+ - `base_url`: Custom API endpoint URL.+ - `rate_limiter`: A+ [`BaseRateLimiter`][langchain_core.rate_limiters.BaseRateLimiter]+ instance to control request rate.++ Refer to the specific model provider's+ [integration reference](https://reference.langchain.com/python/integrations/)+ for all available parameters.Returns:- A `BaseChatModel` corresponding to the `model_name` and `model_provider`- specified if configurability is inferred to be `False`. If configurable, a- chat model emulator that initializes the underlying model at runtime once a- config is passed in.+ A [`BaseChatModel`][langchain_core.language_models.BaseChatModel] corresponding+ to the `model_name` and `model_provider` specified if configurability is+ inferred to be `False`. If configurable, a chat model emulator that+ initializes the underlying model at runtime once a config is passed in.Raises:ValueError: If `model_provider` cannot be inferred or isn't supported.ImportError: If the model provider integration package is not installed.- ???+ note "Initialize a non-configurable model"+ ???+ example "Initialize a non-configurable model"```python# pip install langchain langchain-openai langchain-anthropic langchain-google-vertexai+from langchain_classic.chat_models import init_chat_modelo3_mini = init_chat_model("openai:o3-mini", temperature=0)claude_sonnet = init_chat_model("anthropic:claude-sonnet-4-5", temperature=0)- gemini_2_flash = init_chat_model(+ gemini_2-5_flash = init_chat_model("google_vertexai:gemini-2.5-flash", temperature=0)o3_mini.invoke("what's your name")claude_sonnet.invoke("what's your name")- gemini_2_flash.invoke("what's your name")+ gemini_2-5_flash.invoke("what's your name")```- ??? note "Partially configurable model with no default"+ ??? example "Partially configurable model with no default"```python# pip install langchain langchain-openai langchain-anthropic+from langchain_classic.chat_models import init_chat_model- # We don't need to specify configurable=True if a model isn't specified.+ # (We don't need to specify configurable=True if a model isn't specified.)configurable_model = init_chat_model(temperature=0)configurable_model.invoke("what's your name", config={"configurable": {"model": "gpt-4o"}})- # GPT-4o response+ # Use GPT-4o to generate the responseconfigurable_model.invoke("what's your name",@@ -213,10 +237,11 @@ def init_chat_model()```- ??? note "Fully configurable model with a default"+ ??? example "Fully configurable model with a default"```python# pip install langchain langchain-openai langchain-anthropic+from langchain_classic.chat_models import init_chat_modelconfigurable_model_with_default = init_chat_model(@@ -227,7 +252,7 @@ def init_chat_model()configurable_model_with_default.invoke("what's your name")- # GPT-4o response with temperature 0+ # GPT-4o response with temperature 0 (as set in default)configurable_model_with_default.invoke("what's your name",@@ -238,15 +263,17 @@ def init_chat_model(}},)+ # Override default to use Sonnet 4.5 with temperature 0.6 to generate response```- ??? note "Bind tools to a configurable model"+ ??? example "Bind tools to a configurable model"You can call any chat model declarative methods on a configurable model in thesame way that you would with a normal model:```python# pip install langchain langchain-openai langchain-anthropic+from langchain_classic.chat_models import init_chat_modelfrom pydantic import BaseModel, Field@@ -280,11 +307,13 @@ def init_chat_model(configurable_model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")+ # Use GPT-4oconfigurable_model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?",config={"configurable": {"model": "claude-sonnet-4-5"}},)+ # Use Sonnet 4.5```!!! warning "Behavior changed in 0.2.8"diff --git a/libs/langchain/langchain_classic/evaluation/embedding_distance/base.py b/libs/langchain/langchain_classic/evaluation/embedding_distance/base.pyindex e2af7665ea..c7c0e320db 100644--- a/libs/langchain/langchain_classic/evaluation/embedding_distance/base.py+++ b/libs/langchain/langchain_classic/evaluation/embedding_distance/base.py@@ -48,7 +48,7 @@ def _check_numpy() -> bool:def _embedding_factory() -> Embeddings:- """Create an Embeddings object.+ """Create an `Embeddings` object.Returns:The created `Embeddings` object.diff --git a/libs/langchain/pyproject.toml b/libs/langchain/pyproject.tomlindex 1a791d4481..6316b97ab1 100644--- a/libs/langchain/pyproject.toml+++ b/libs/langchain/pyproject.toml@@ -153,6 +153,7 @@ ignore = ["TC003", # Doesn't play well with Pydantic"TD002", # Missing author in TODO"TD003", # Missing issue link in TODO+ "RUF002", # Em-dash in docstring# TODO rules"ANN401", # No type Anydiff --git a/libs/langchain_v1/langchain/agents/factory.py b/libs/langchain_v1/langchain/agents/factory.pyindex e22f851bd8..3094261bd2 100644--- a/libs/langchain_v1/langchain/agents/factory.py+++ b/libs/langchain_v1/langchain/agents/factory.py@@ -530,44 +530,65 @@ def create_agent( # noqa: PLR0915Args:model: The language model for the agent. Can be a string identifier- (e.g., `"openai:gpt-4"`) or a chat model instance (e.g., `ChatOpenAI()`).+ (e.g., `"openai:gpt-4"`) or a direct chat model instance (e.g.,+ [`ChatOpenAI`][langchain_openai.ChatOpenAI] or other another+ [chat model](https://docs.langchain.com/oss/python/integrations/chat)).+For a full list of supported model strings, see[`init_chat_model`][langchain.chat_models.init_chat_model(model_provider)].- tools: A list of tools, `dicts`, or `Callable`. If `None` or an empty list,- the agent will consist of a model node without a tool calling loop.- system_prompt: An optional system prompt for the LLM. Prompts are converted to a- `SystemMessage` and added to the beginning of the message list.+ tools: A list of tools, `dicts`, or `Callable`.++ If `None` or an empty list, the agent will consist of a model node without a+ tool calling loop.+ system_prompt: An optional system prompt for the LLM.++ Prompts are converted to a+ [`SystemMessage`][langchain.messages.SystemMessage] and added to the+ beginning of the message list.middleware: A sequence of middleware instances to apply to the agent.- Middleware can intercept and modify agent behavior at various stages.++ Middleware can intercept and modify agent behavior at various stages. See+ the [full guide](https://docs.langchain.com/oss/python/langchain/middleware).response_format: An optional configuration for structured responses.+Can be a `ToolStrategy`, `ProviderStrategy`, or a Pydantic model class.+If provided, the agent will handle structured output during theconversation flow. Raw schemas will be wrapped in an appropriate strategybased on model capabilities.state_schema: An optional `TypedDict` schema that extends `AgentState`.+When provided, this schema is used instead of `AgentState` as the baseschema for merging with middleware state schemas. This allows users toadd custom state fields without needing to create custom middleware.- Generally, it's recommended to use state_schema extensions via middleware+ Generally, it's recommended to use `state_schema` extensions via middlewareto keep relevant extensions scoped to corresponding hooks / tools.+The schema must be a subclass of `AgentState[ResponseT]`.context_schema: An optional schema for runtime context.- checkpointer: An optional checkpoint saver object. This is used for persisting- the state of the graph (e.g., as chat memory) for a single thread- (e.g., a single conversation).- store: An optional store object. This is used for persisting data- across multiple threads (e.g., multiple conversations / users).+ checkpointer: An optional checkpoint saver object.++ Used for persisting the state of the graph (e.g., as chat memory) for a+ single thread (e.g., a single conversation).+ store: An optional store object.++ Used for persisting data across multiple threads (e.g., multiple+ conversations / users).interrupt_before: An optional list of node names to interrupt before.+Useful if you want to add a user confirmation or other interruptbefore taking an action.interrupt_after: An optional list of node names to interrupt after.+Useful if you want to return directly or run additional processingon an output.- debug: Whether to enable verbose logging for graph execution. When enabled,- prints detailed information about each node execution, state updates,- and transitions during agent runtime. Useful for debugging middleware- behavior and understanding agent execution flow.+ debug: Whether to enable verbose logging for graph execution.++ When enabled, prints detailed information about each node execution, state+ updates, and transitions during agent runtime. Useful for debugging+ middleware behavior and understanding agent execution flow.name: An optional name for the `CompiledStateGraph`.+This name will be automatically used when adding the agent graph toanother graph as a subgraph node - particularly useful for buildingmulti-agent systems.@@ -577,11 +598,12 @@ def create_agent( # noqa: PLR0915A compiled `StateGraph` that can be used for chat interactions.The agent node calls the language model with the messages list (after applying- the system prompt). If the resulting `AIMessage` contains `tool_calls`, the graph- will then call the tools. The tools node executes the tools and adds the responses- to the messages list as `ToolMessage` objects. The agent node then calls the- language model again. The process repeats until no more `tool_calls` are- present in the response. The agent then returns the full list of messages.+ the system prompt). If the resulting [`AIMessage`][langchain.messages.AIMessage]+ contains `tool_calls`, the graph will then call the tools. The tools node executes+ the tools and adds the responses to the messages list as+ [`ToolMessage`][langchain.messages.ToolMessage] objects. The agent node then calls+ the language model again. The process repeats until no more `tool_calls` are present+ in the response. The agent then returns the full list of messages.Example:```pythondiff --git a/libs/langchain_v1/langchain/agents/middleware/context_editing.py b/libs/langchain_v1/langchain/agents/middleware/context_editing.pyindex 1f0978ed77..3623d1872c 100644--- a/libs/langchain_v1/langchain/agents/middleware/context_editing.py+++ b/libs/langchain_v1/langchain/agents/middleware/context_editing.py@@ -182,7 +182,7 @@ class ClearToolUsesEdit(ContextEdit):class ContextEditingMiddleware(AgentMiddleware):- """Middleware that automatically prunes tool results to manage context size.+ """Automatically prunes tool results to manage context size.The middleware applies a sequence of edits when the total input token countexceeds configured thresholds. Currently the `ClearToolUsesEdit` strategy isdiff --git a/libs/langchain_v1/langchain/agents/middleware/model_call_limit.py b/libs/langchain_v1/langchain/agents/middleware/model_call_limit.pyindex 412cd16b8e..90dba99dfa 100644--- a/libs/langchain_v1/langchain/agents/middleware/model_call_limit.py+++ b/libs/langchain_v1/langchain/agents/middleware/model_call_limit.py@@ -87,7 +87,7 @@ class ModelCallLimitExceededError(Exception):class ModelCallLimitMiddleware(AgentMiddleware[ModelCallLimitState, Any]):- """Middleware that tracks model call counts and enforces limits.+ """Tracks model call counts and enforces limits.This middleware monitors the number of model calls made during agent executionand can terminate the agent when specified limits are reached. It supportsdiff --git a/libs/langchain_v1/langchain/agents/middleware/summarization.py b/libs/langchain_v1/langchain/agents/middleware/summarization.pyindex de59095be1..6ba6221206 100644--- a/libs/langchain_v1/langchain/agents/middleware/summarization.py+++ b/libs/langchain_v1/langchain/agents/middleware/summarization.py@@ -60,7 +60,7 @@ _SEARCH_RANGE_FOR_TOOL_PAIRS = 5class SummarizationMiddleware(AgentMiddleware):- """Middleware that summarizes conversation history when token limits are approached.+ """Summarizes conversation history when token limits are approached.This middleware monitors message token counts and automatically summarizes oldermessages when a threshold is reached, preserving recent messages and maintainingdiff --git a/libs/langchain_v1/langchain/agents/middleware/tool_call_limit.py b/libs/langchain_v1/langchain/agents/middleware/tool_call_limit.pyindex df97f5da23..dca66e9682 100644--- a/libs/langchain_v1/langchain/agents/middleware/tool_call_limit.py+++ b/libs/langchain_v1/langchain/agents/middleware/tool_call_limit.py@@ -146,7 +146,7 @@ class ToolCallLimitExceededError(Exception):class ToolCallLimitMiddleware(AgentMiddleware[ToolCallLimitState, Any]):- """Middleware that tracks tool call counts and enforces limits.+ """Tracks tool call counts and enforces limits.This middleware monitors the number of tool calls made during agent executionand can terminate the agent when specified limits are reached. It supportsdiff --git a/libs/langchain_v1/langchain/agents/middleware/tool_emulator.py b/libs/langchain_v1/langchain/agents/middleware/tool_emulator.pyindex 019045c577..74e814ed1f 100644--- a/libs/langchain_v1/langchain/agents/middleware/tool_emulator.py+++ b/libs/langchain_v1/langchain/agents/middleware/tool_emulator.py@@ -20,7 +20,7 @@ if TYPE_CHECKING:class LLMToolEmulator(AgentMiddleware):- """Middleware that emulates specified tools using an LLM instead of executing them.+ """Emulates specified tools using an LLM instead of executing them.This middleware allows selective emulation of tools for testing purposes.By default (when tools=None), all tools are emulated. You can specify whichdiff --git a/libs/langchain_v1/langchain/chat_models/base.py b/libs/langchain_v1/langchain/chat_models/base.pyindex e546c3ad84..43a6d38619 100644--- a/libs/langchain_v1/langchain/chat_models/base.py+++ b/libs/langchain_v1/langchain/chat_models/base.py@@ -64,26 +64,34 @@ def init_chat_model(config_prefix: str | None = None,**kwargs: Any,) -> BaseChatModel | _ConfigurableModel:- """Initialize a chat model in a single line using the model's name and provider.+ """Initialize a chat model from any supported provider using a unified interface.++ **Two main use cases:**++ 1. **Fixed model** – specify the model upfront and get a ready-to-use chat model.+ 2. **Configurable model** – choose to specify parameters (including model name) at+ runtime via `config`. Makes it easy to switch between models/providers without+ changing your code!!! note- Requires the integration package for your model provider to be installed.+ Requires the integration package for the chosen model provider to be installed.See the `model_provider` parameter below for specific package names(e.g., `pip install langchain-openai`).Refer to the [provider integration's API reference](https://docs.langchain.com/oss/python/integrations/providers)- for supported model parameters.+ for supported model parameters to use as `**kwargs`.Args:model: The name of the model, e.g. `'o3-mini'`, `'claude-sonnet-4-5'`.- You can also specify model and model provider in a single argument using:-+ You can also specify model and model provider in a single argument using`'{model_provider}:{model}'` format, e.g. `'openai:o1'`.model_provider: The model provider if not specified as part of the model arg- (see above). Supported `model_provider` values and the corresponding- integration package are:+ (see above).++ Supported `model_provider` values and the corresponding integration package+ are:- `openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai)- `anthropic` -> [`langchain-anthropic`](https://docs.langchain.com/oss/python/integrations/providers/anthropic)@@ -120,27 +128,36 @@ def init_chat_model(- `deepseek...` -> `deepseek`- `grok...` -> `xai`- `sonar...` -> `perplexity`- configurable_fields: Which model parameters are configurable:+ configurable_fields: Which model parameters are configurable at runtime:- - `None`: No configurable fields.+ - `None`: No configurable fields (i.e., a fixed model).- `'any'`: All fields are configurable. **See security note below.**- `list[str] | Tuple[str, ...]`: Specified fields are configurable.- Fields are assumed to have `config_prefix` stripped if there is a- `config_prefix`. If model is specified, then defaults to `None`. If model is- not specified, then defaults to `("model", "model_provider")`.+ Fields are assumed to have `config_prefix` stripped if a `config_prefix` is+ specified.++ If `model` is specified, then defaults to `None`.++ If `model` is not specified, then defaults to `("model", "model_provider")`.!!! warning "Security note"Setting `configurable_fields="any"` means fields like `api_key`,- `base_url`, etc. can be altered at runtime, potentially redirecting- model requests to a different service/user. Make sure that if you're- accepting untrusted configurations that you enumerate the- `configurable_fields=(...)` explicitly.-- config_prefix: If `'config_prefix'` is a non-empty string then model will be- configurable at runtime via the- `config["configurable"]["{config_prefix}_{param}"]` keys. If- `'config_prefix'` is an empty string then model will be configurable via+ `base_url`, etc., can be altered at runtime, potentially redirecting+ model requests to a different service/user.++ Make sure that if you're accepting untrusted configurations that you+ enumerate the `configurable_fields=(...)` explicitly.++ config_prefix: Optional prefix for configuration keys.++ Useful when you have multiple configurable models in the same application.++ If `'config_prefix'` is a non-empty string then `model` will be configurable+ at runtime via the `config["configurable"]["{config_prefix}_{param}"]` keys.+ See examples below.++ If `'config_prefix'` is an empty string then model will be configurable via`config["configurable"]["{param}"]`.**kwargs: Additional model-specific keyword args to pass to the underlyingchat model's `__init__` method. Common parameters include:@@ -150,10 +167,13 @@ def init_chat_model(- `timeout`: Maximum time (in seconds) to wait for a response.- `max_retries`: Maximum number of retry attempts for failed requests.- `base_url`: Custom API endpoint URL.- - `rate_limiter`: A `BaseRateLimiter` instance to control request rate.+ - `rate_limiter`: A+ [`BaseRateLimiter`][langchain_core.rate_limiters.BaseRateLimiter]+ instance to control request rate.- Refer to the specific model provider's documentation for all available- parameters.+ Refer to the specific model provider's+ [integration reference](https://reference.langchain.com/python/integrations/)+ for all available parameters.Returns:A `BaseChatModel` corresponding to the `model_name` and `model_provider`@@ -165,32 +185,34 @@ def init_chat_model(ValueError: If `model_provider` cannot be inferred or isn't supported.ImportError: If the model provider integration package is not installed.- ???+ note "Initialize a non-configurable model"+ ???+ example "Initialize a non-configurable model"```python# pip install langchain langchain-openai langchain-anthropic langchain-google-vertexai+from langchain.chat_models import init_chat_modelo3_mini = init_chat_model("openai:o3-mini", temperature=0)claude_sonnet = init_chat_model("anthropic:claude-sonnet-4-5", temperature=0)- gemini_2_flash = init_chat_model("google_vertexai:gemini-2.5-flash", temperature=0)+ gemini_2-5_flash = init_chat_model("google_vertexai:gemini-2.5-flash", temperature=0)o3_mini.invoke("what's your name")claude_sonnet.invoke("what's your name")- gemini_2_flash.invoke("what's your name")+ gemini_2-5_flash.invoke("what's your name")```- ??? note "Partially configurable model with no default"+ ??? example "Partially configurable model with no default"```python# pip install langchain langchain-openai langchain-anthropic+from langchain.chat_models import init_chat_model- # We don't need to specify configurable=True if a model isn't specified.+ # (We don't need to specify configurable=True if a model isn't specified.)configurable_model = init_chat_model(temperature=0)configurable_model.invoke("what's your name", config={"configurable": {"model": "gpt-4o"}})- # GPT-4o response+ # Use GPT-4o to generate the responseconfigurable_model.invoke("what's your name",@@ -198,10 +220,11 @@ def init_chat_model()```- ??? note "Fully configurable model with a default"+ ??? example "Fully configurable model with a default"```python# pip install langchain langchain-openai langchain-anthropic+from langchain.chat_models import init_chat_modelconfigurable_model_with_default = init_chat_model(@@ -212,7 +235,7 @@ def init_chat_model()configurable_model_with_default.invoke("what's your name")- # GPT-4o response with temperature 0+ # GPT-4o response with temperature 0 (as set in default)configurable_model_with_default.invoke("what's your name",@@ -223,15 +246,17 @@ def init_chat_model(}},)+ # Override default to use Sonnet 4.5 with temperature 0.6 to generate response```- ??? note "Bind tools to a configurable model"+ ??? example "Bind tools to a configurable model"You can call any chat model declarative methods on a configurable model in thesame way that you would with a normal model:```python# pip install langchain langchain-openai langchain-anthropic+from langchain.chat_models import init_chat_modelfrom pydantic import BaseModel, Field@@ -261,11 +286,13 @@ def init_chat_model(configurable_model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?")+ # Use GPT-4oconfigurable_model_with_tools.invoke("Which city is hotter today and which is bigger: LA or NY?",config={"configurable": {"model": "claude-sonnet-4-5"}},)+ # Use Sonnet 4.5```""" # noqa: E501diff --git a/libs/langchain_v1/langchain/embeddings/__init__.py b/libs/langchain_v1/langchain/embeddings/__init__.pyindex 90a7644e0d..6943b1cd7c 100644--- a/libs/langchain_v1/langchain/embeddings/__init__.py+++ b/libs/langchain_v1/langchain/embeddings/__init__.py@@ -1,4 +1,4 @@-"""Embeddings.+"""Embeddings models.!!! warning "Reference docs"This page contains **reference documentation** for Embeddings. Seediff --git a/libs/langchain_v1/langchain/embeddings/base.py b/libs/langchain_v1/langchain/embeddings/base.pyindex 2793c02df7..708ac6a41a 100644--- a/libs/langchain_v1/langchain/embeddings/base.py+++ b/libs/langchain_v1/langchain/embeddings/base.py@@ -126,26 +126,27 @@ def init_embeddings(provider: str | None = None,**kwargs: Any,) -> Embeddings:- """Initialize an embeddings model from a model name and optional provider.+ """Initialize an embedding model from a model name and optional provider.!!! note- Must have the integration package corresponding to the model provider- installed.+ Requires the integration package for the chosen model provider to be installed.- Args:- model: Name of the model to use.+ See the `model_provider` parameter below for specific package names+ (e.g., `pip install langchain-openai`).- Can be either:+ Refer to the [provider integration's API reference](https://docs.langchain.com/oss/python/integrations/providers)+ for supported model parameters to use as `**kwargs`.- - A model string like `"openai:text-embedding-3-small"`- - Just the model name if the provider is specified separately or can be- inferred.+ Args:+ model: The name of the model, e.g. `'openai:text-embedding-3-small'`.- See supported providers under the `provider` arg description.- provider: Optional explicit provider name. If not specified, will attempt to- parse from the model string in the `model` arg.+ You can also specify model and model provider in a single argument using+ `'{model_provider}:{model}'` format, e.g. `'openai:text-embedding-3-small'`.+ provider: The model provider if not specified as part of the model arg+ (see above).- Supported providers:+ Supported `provider` values and the corresponding integration package+ are:- `openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai)- `azure_openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai)@@ -157,7 +158,10 @@ def init_embeddings(- `ollama` -> [`langchain-ollama`](https://docs.langchain.com/oss/python/integrations/providers/ollama)**kwargs: Additional model-specific parameters passed to the embedding model.- These vary by provider, see the provider-specific documentation for details.++ These vary by provider. Refer to the specific model provider's+ [integration reference](https://reference.langchain.com/python/integrations/)+ for all available parameters.Returns:An `Embeddings` instance that can generate embeddings for text.@@ -166,9 +170,11 @@ def init_embeddings(ValueError: If the model provider is not supported or cannot be determinedImportError: If the required provider package is not installed- ???+ note "Example Usage"+ ???+ example```python+ # pip install langchain langchain-openai+# Using a model stringmodel = init_embeddings("openai:text-embedding-3-small")model.embed_query("Hello, world!")diff --git a/libs/langchain_v1/langchain/messages/__init__.py b/libs/langchain_v1/langchain/messages/__init__.pyindex 9ebe98c81f..b757afd1f4 100644--- a/libs/langchain_v1/langchain/messages/__init__.py+++ b/libs/langchain_v1/langchain/messages/__init__.py@@ -1,4 +1,4 @@-"""Message types.+"""Message and message content types.Includes message types for different roles (e.g., human, AI, system), as well as typesfor message content blocks (e.g., text, image, audio) and tool calls.diff --git a/libs/langchain_v1/pyproject.toml b/libs/langchain_v1/pyproject.tomlindex 7c76e4e417..9289bec806 100644--- a/libs/langchain_v1/pyproject.toml+++ b/libs/langchain_v1/pyproject.toml@@ -115,6 +115,7 @@ ignore = ["PLC0415", # Imports should be at the top. Not always desirable"PLR0913", # Too many arguments in function definition"PLC0414", # Inconsistent with how type checkers expect to be notified of intentional re-exports+ "RUF002", # Em-dash in docstring]unfixable = ["B028"] # People should intentionally tune the stackleveldiff --git a/libs/partners/anthropic/langchain_anthropic/chat_models.py b/libs/partners/anthropic/langchain_anthropic/chat_models.pyindex 6d55ce3faf..f25bdccfe2 100644--- a/libs/partners/anthropic/langchain_anthropic/chat_models.py+++ b/libs/partners/anthropic/langchain_anthropic/chat_models.py@@ -1535,7 +1535,11 @@ class ChatAnthropic(BaseChatModel):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "chat_models", "anthropic"]`+ """return ["langchain", "chat_models", "anthropic"]@propertydiff --git a/libs/partners/fireworks/langchain_fireworks/chat_models.py b/libs/partners/fireworks/langchain_fireworks/chat_models.pyindex 38343c188e..53af609a42 100644--- a/libs/partners/fireworks/langchain_fireworks/chat_models.py+++ b/libs/partners/fireworks/langchain_fireworks/chat_models.py@@ -286,7 +286,11 @@ class ChatFireworks(BaseChatModel):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "chat_models", "fireworks"]`+ """return ["langchain", "chat_models", "fireworks"]@propertydiff --git a/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.py b/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.pyindex 6d8dbd73e5..8c55348cee 100644--- a/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.py+++ b/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface.py@@ -12,8 +12,6 @@ from langchain_huggingface.utils.import_utils import (is_optimum_intel_version,)-DEFAULT_MODEL_NAME = "sentence-transformers/all-mpnet-base-v2"-_MIN_OPTIMUM_VERSION = "1.22"@@ -37,7 +35,9 @@ class HuggingFaceEmbeddings(BaseModel, Embeddings):```"""- model_name: str = Field(default=DEFAULT_MODEL_NAME, alias="model")+ model_name: str = Field(+ default="sentence-transformers/all-mpnet-base-v2", alias="model"+ )"""Model name to use."""cache_folder: str | None = None"""Path to store models.diff --git a/libs/partners/mistralai/langchain_mistralai/chat_models.py b/libs/partners/mistralai/langchain_mistralai/chat_models.pyindex d36f0511b3..39c7c80d91 100644--- a/libs/partners/mistralai/langchain_mistralai/chat_models.py+++ b/libs/partners/mistralai/langchain_mistralai/chat_models.py@@ -1138,7 +1138,11 @@ class ChatMistralAI(BaseChatModel):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "chat_models", "mistralai"]`+ """return ["langchain", "chat_models", "mistralai"]diff --git a/libs/partners/openai/langchain_openai/chat_models/azure.py b/libs/partners/openai/langchain_openai/chat_models/azure.pyindex 429d599af9..ce4440b3e1 100644--- a/libs/partners/openai/langchain_openai/chat_models/azure.py+++ b/libs/partners/openai/langchain_openai/chat_models/azure.py@@ -572,7 +572,11 @@ class AzureChatOpenAI(BaseChatOpenAI):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "chat_models", "azure_openai"]`+ """return ["langchain", "chat_models", "azure_openai"]@propertydiff --git a/libs/partners/openai/langchain_openai/chat_models/base.py b/libs/partners/openai/langchain_openai/chat_models/base.pyindex 35beb08ec5..7b11cd2921 100644--- a/libs/partners/openai/langchain_openai/chat_models/base.py+++ b/libs/partners/openai/langchain_openai/chat_models/base.py@@ -2839,7 +2839,11 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "chat_models", "openai"]`+ """return ["langchain", "chat_models", "openai"]@propertydiff --git a/libs/partners/openai/langchain_openai/llms/azure.py b/libs/partners/openai/langchain_openai/llms/azure.pyindex cad149c506..e86e911386 100644--- a/libs/partners/openai/langchain_openai/llms/azure.py+++ b/libs/partners/openai/langchain_openai/llms/azure.py@@ -97,7 +97,11 @@ class AzureOpenAI(BaseOpenAI):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "llms", "openai"]`+ """return ["langchain", "llms", "openai"]@propertydiff --git a/libs/partners/openai/langchain_openai/llms/base.py b/libs/partners/openai/langchain_openai/llms/base.pyindex f983f39823..08f4dc458f 100644--- a/libs/partners/openai/langchain_openai/llms/base.py+++ b/libs/partners/openai/langchain_openai/llms/base.py@@ -799,7 +799,11 @@ class OpenAI(BaseOpenAI):@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain", "llms", "openai"]`+ """return ["langchain", "llms", "openai"]@classmethoddiff --git a/libs/partners/openai/uv.lock b/libs/partners/openai/uv.lockindex 16616fa8bf..352ff9f6e2 100644--- a/libs/partners/openai/uv.lock+++ b/libs/partners/openai/uv.lock@@ -1,5 +1,5 @@version = 1-revision = 2+revision = 3requires-python = ">=3.10.0, <4.0.0"resolution-markers = ["python_full_version >= '3.13' and platform_python_implementation == 'PyPy'",@@ -544,7 +544,7 @@ wheels = [[[package]]name = "langchain"-version = "1.0.1"+version = "1.0.2"source = { editable = "../../langchain_v1" }dependencies = [{ name = "langchain-core" },@@ -570,7 +570,7 @@ requires-dist = [{ name = "langchain-perplexity", marker = "extra == 'perplexity'" },{ name = "langchain-together", marker = "extra == 'together'" },{ name = "langchain-xai", marker = "extra == 'xai'" },- { name = "langgraph", specifier = ">=1.0.0,<1.1.0" },+ { name = "langgraph", specifier = ">=1.0.2,<1.1.0" },{ name = "pydantic", specifier = ">=2.7.4,<3.0.0" },]provides-extras = ["community", "anthropic", "openai", "google-vertexai", "google-genai", "fireworks", "ollama", "together", "mistralai", "huggingface", "groq", "aws", "deepseek", "xai", "perplexity"]@@ -606,7 +606,7 @@ typing = [[[package]]name = "langchain-core"-version = "1.0.0"+version = "1.0.1"source = { editable = "../../core" }dependencies = [{ name = "jsonpatch" },@@ -796,7 +796,7 @@ typing = [[[package]]name = "langgraph"-version = "1.0.1"+version = "1.0.2"source = { registry = "https://pypi.org/simple" }dependencies = [{ name = "langchain-core" },@@ -806,9 +806,9 @@ dependencies = [{ name = "pydantic" },{ name = "xxhash" },]-sdist = { url = "https://files.pythonhosted.org/packages/20/7c/a0f4211f751b8b37aae2d88c6243ceb14027ca9ebf00ac8f3b210657af6a/langgraph-1.0.1.tar.gz", hash = "sha256:4985b32ceabb046a802621660836355dfcf2402c5876675dc353db684aa8f563", size = 480245, upload-time = "2025-10-20T18:51:59.839Z" }+sdist = { url = "https://files.pythonhosted.org/packages/0e/25/18e6e056ee1a8af64fcab441b4a3f2e158399935b08f148c7718fc42ecdb/langgraph-1.0.2.tar.gz", hash = "sha256:dae1af08d6025cb1fcaed68f502c01af7d634d9044787c853a46c791cfc52f67", size = 482660, upload-time = "2025-10-29T18:38:28.374Z" }wheels = [- { url = "https://files.pythonhosted.org/packages/b1/3c/acc0956a0da96b25a2c5c1a85168eacf1253639a04ed391d7a7bcaae5d6c/langgraph-1.0.1-py3-none-any.whl", hash = "sha256:892f04f64f4889abc80140265cc6bd57823dd8e327a5eef4968875f2cd9013bd", size = 155415, upload-time = "2025-10-20T18:51:58.321Z" },+ { url = "https://files.pythonhosted.org/packages/d7/b1/9f4912e13d4ed691f2685c8a4b764b5a9237a30cca0c5782bc213d9f0a9a/langgraph-1.0.2-py3-none-any.whl", hash = "sha256:b3d56b8c01de857b5fb1da107e8eab6e30512a377685eeedb4f76456724c9729", size = 156751, upload-time = "2025-10-29T18:38:26.577Z" },][[package]]@@ -826,15 +826,15 @@ wheels = [[[package]]name = "langgraph-prebuilt"-version = "1.0.1"+version = "1.0.2"source = { registry = "https://pypi.org/simple" }dependencies = [{ name = "langchain-core" },{ name = "langgraph-checkpoint" },]-sdist = { url = "https://files.pythonhosted.org/packages/b2/b6/2bcb992acf67713a3557e51c1955854672ec6c1abe6ba51173a87eb8d825/langgraph_prebuilt-1.0.1.tar.gz", hash = "sha256:ecbfb9024d9d7ed9652dde24eef894650aaab96bf79228e862c503e2a060b469", size = 119918, upload-time = "2025-10-20T18:49:55.991Z" }+sdist = { url = "https://files.pythonhosted.org/packages/33/2f/b940590436e07b3450fe6d791aad5e581363ad536c4f1771e3ba46530268/langgraph_prebuilt-1.0.2.tar.gz", hash = "sha256:9896dbabf04f086eb59df4294f54ab5bdb21cd78e27e0a10e695dffd1cc6097d", size = 142075, upload-time = "2025-10-29T18:29:00.401Z" }wheels = [- { url = "https://files.pythonhosted.org/packages/68/47/9ffd10882403020ea866e381de7f8e504a78f606a914af7f8244456c7783/langgraph_prebuilt-1.0.1-py3-none-any.whl", hash = "sha256:8c02e023538f7ef6ad5ed76219ba1ab4f6de0e31b749e4d278f57a8a95eec9f7", size = 28458, upload-time = "2025-10-20T18:49:54.723Z" },+ { url = "https://files.pythonhosted.org/packages/27/2f/9a7d00d4afa036e65294059c7c912002fb72ba5dbbd5c2a871ca06360278/langgraph_prebuilt-1.0.2-py3-none-any.whl", hash = "sha256:d9499f7c449fb637ee7b87e3f6a3b74095f4202053c74d33894bd839ea4c57c7", size = 34286, upload-time = "2025-10-29T18:28:59.26Z" },][[package]]diff --git a/libs/partners/xai/langchain_xai/chat_models.py b/libs/partners/xai/langchain_xai/chat_models.pyindex d2de07c20f..d717e7bf45 100644--- a/libs/partners/xai/langchain_xai/chat_models.py+++ b/libs/partners/xai/langchain_xai/chat_models.py@@ -428,7 +428,11 @@ class ChatXAI(BaseChatOpenAI): # type: ignore[override]@classmethoddef get_lc_namespace(cls) -> list[str]:- """Get the namespace of the LangChain object."""+ """Get the namespace of the LangChain object.++ Returns:+ `["langchain_xai", "chat_models"]`+ """return ["langchain_xai", "chat_models"]@propertydiff --git a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py b/libs/standard-tests/langchain_tests/integration_tests/chat_models.pyindex 6b1131fad5..6f80704d1a 100644--- a/libs/standard-tests/langchain_tests/integration_tests/chat_models.py+++ b/libs/standard-tests/langchain_tests/integration_tests/chat_models.py@@ -202,7 +202,7 @@ class ChatModelIntegrationTests(ChatModelTests):calling or multi-modality) by selectively overriding the following properties.Expand to see details:- ??? note "`has_tool_calling`"+ ??? info "`has_tool_calling`"Boolean property indicating whether the chat model supports tool calling.@@ -217,7 +217,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`tool_choice_value`"+ ??? info "`tool_choice_value`"Value to use for tool choice when used in tests.@@ -235,7 +235,7 @@ class ChatModelIntegrationTests(ChatModelTests):return "any"```- ??? note "`has_tool_choice`"+ ??? info "`has_tool_choice`"Boolean property indicating whether the chat model supports forcing toolcalling via a `tool_choice` parameter.@@ -255,7 +255,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "`has_structured_output`"+ ??? info "`has_structured_output`"Boolean property indicating whether the chat model supports structuredoutput.@@ -272,7 +272,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`structured_output_kwargs`"+ ??? info "`structured_output_kwargs`"Dict property that can be used to specify additional kwargs for`with_structured_output`. Useful for testing different models.@@ -283,7 +283,7 @@ class ChatModelIntegrationTests(ChatModelTests):return {"method": "function_calling"}```- ??? note "`supports_json_mode`"+ ??? info "`supports_json_mode`"Boolean property indicating whether the chat model supports JSON mode in`with_structured_output`.@@ -296,7 +296,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`supports_image_inputs`"+ ??? info "`supports_image_inputs`"Boolean property indicating whether the chat model supports image inputs.@@ -309,7 +309,7 @@ class ChatModelIntegrationTests(ChatModelTests):{"type": "image","base64": "<base64 image data>",- "mime_type": "image/jpeg", # or appropriate mime-type+ "mime_type": "image/jpeg", # or appropriate MIME type}```@@ -330,7 +330,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`supports_image_urls`"+ ??? info "`supports_image_urls`"Boolean property indicating whether the chat model supports image inputs fromURLs.@@ -355,7 +355,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`supports_pdf_inputs`"+ ??? info "`supports_pdf_inputs`"Boolean property indicating whether the chat model supports PDF inputs.@@ -380,7 +380,7 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`supports_audio_inputs`"+ ??? info "`supports_audio_inputs`"Boolean property indicating whether the chat model supports audio inputs.@@ -393,7 +393,7 @@ class ChatModelIntegrationTests(ChatModelTests):{"type": "audio","base64": "<base64 audio data>",- "mime_type": "audio/wav", # or appropriate mime-type+ "mime_type": "audio/wav", # or appropriate MIME type}```@@ -405,13 +405,13 @@ class ChatModelIntegrationTests(ChatModelTests):return True```- ??? note "`supports_video_inputs`"+ ??? info "`supports_video_inputs`"Boolean property indicating whether the chat model supports image inputs.Defaults to `False`. No current tests are written for this feature.- ??? note "`returns_usage_metadata`"+ ??? info "`returns_usage_metadata`"Boolean property indicating whether the chat model returns usage metadataon invoke and streaming responses.@@ -431,7 +431,7 @@ class ChatModelIntegrationTests(ChatModelTests):Models supporting `usage_metadata` should also return the name of theunderlying model in the `response_metadata` of the `AIMessage`.- ??? note "`supports_anthropic_inputs`"+ ??? info "`supports_anthropic_inputs`"Boolean property indicating whether the chat model supports Anthropic-styleinputs.@@ -459,7 +459,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "`supports_image_tool_message`"+ ??? info "`supports_image_tool_message`"Boolean property indicating whether the chat model supports a `ToolMessage`that includes image content, e.g. in the OpenAI Chat Completions format:@@ -502,7 +502,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "`supports_pdf_tool_message`"+ ??? info "`supports_pdf_tool_message`"Boolean property indicating whether the chat model supports a `ToolMessagethat include PDF content using the LangChain `FileContentBlock` format:@@ -530,7 +530,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "`supported_usage_metadata_details`"+ ??? info "`supported_usage_metadata_details`"Property controlling what usage metadata details are emitted in both invokeand stream.@@ -545,7 +545,7 @@ class ChatModelIntegrationTests(ChatModelTests):Only needs to be overridden if these details are supplied.- ??? note "`enable_vcr_tests`"+ ??? info "`enable_vcr_tests`"Property controlling whether to enable select tests that rely on[VCR](https://vcrpy.readthedocs.io/en/latest/) caching of HTTP calls, such@@ -706,7 +706,7 @@ class ChatModelIntegrationTests(ChatModelTests):This should pass for all integrations.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, you should make sure your `_generate` methoddoes not raise any exceptions, and that it returns a valid@@ -732,7 +732,7 @@ class ChatModelIntegrationTests(ChatModelTests):a "natively async" implementation, but rather that the model can be usedin an async context.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`.@@ -763,7 +763,7 @@ class ChatModelIntegrationTests(ChatModelTests):a "streaming" implementation, but rather that the model can be used in astreaming context.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`.@@ -801,7 +801,7 @@ class ChatModelIntegrationTests(ChatModelTests):a "natively async" or "streaming" implementation, but rather that the model canbe used in an async streaming context.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_stream`.@@ -840,7 +840,7 @@ class ChatModelIntegrationTests(ChatModelTests):This should pass for all integrations. Tests the model's ability to processmultiple prompts in a single batch.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`@@ -868,7 +868,7 @@ class ChatModelIntegrationTests(ChatModelTests):This should pass for all integrations. Tests the model's ability to processmultiple prompts in a single batch asynchronously.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_batch`@@ -899,7 +899,7 @@ class ChatModelIntegrationTests(ChatModelTests):a sequence of alternating human and AI messages as context for generatingthe next response.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`@@ -930,7 +930,7 @@ class ChatModelIntegrationTests(ChatModelTests):a sequence of double-system, double-human, and double-ai messages as contextfor generating the next response.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"First, debug`langchain_tests.integration_tests.chat_models.ChatModelIntegrationTests.test_invoke`@@ -1013,11 +1013,11 @@ class ChatModelIntegrationTests(ChatModelTests):}```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, first verify that your model returns`langchain_core.messages.ai.UsageMetadata` dicts- attached to the returned AIMessage object in `_generate`:+ attached to the returned `AIMessage` object in `_generate`:```pythonreturn ChatResult(@@ -1185,11 +1185,11 @@ class ChatModelIntegrationTests(ChatModelTests):}```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, first verify that your model yields`langchain_core.messages.ai.UsageMetadata` dicts- attached to the returned AIMessage object in `_stream`+ attached to the returned `AIMessage` object in `_stream`that sum up to the total usage metadata.Note that `input_tokens` should only be included on one of the chunks@@ -1307,7 +1307,7 @@ class ChatModelIntegrationTests(ChatModelTests):This should pass for all integrations.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the function signature for `_generate`(as well as `_stream` and async variants) accepts the `stop` parameter:@@ -1357,7 +1357,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that `bind_tools` is implemented to correctlytranslate LangChain tool objects into the appropriate schema for your@@ -1419,7 +1419,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that `bind_tools` is implemented to correctlytranslate LangChain tool objects into the appropriate schema for your@@ -1482,7 +1482,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that `bind_tools` is implemented to correctlytranslate LangChain tool objects into the appropriate schema for your@@ -1552,7 +1552,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that:@@ -1641,7 +1641,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that:@@ -1721,7 +1721,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check whether the `test_tool_calling` test is passing.If it is not, refer to the troubleshooting steps in that test first.@@ -1773,7 +1773,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that `bind_tools` is implemented to correctlytranslate LangChain tool objects into the appropriate schema for your@@ -1846,7 +1846,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the `status` field on `ToolMessage`objects is either ignored or passed to the model appropriately.@@ -1907,7 +1907,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"This test uses [a utility function](https://python.langchain.com/api_reference/core/utils/langchain_core.utils.function_calling.tool_example_to_messages.html).in `langchain_core` to generate a sequence of messages representing@@ -1971,7 +1971,7 @@ class ChatModelIntegrationTests(ChatModelTests):By default, `has_structured_output` is True if a model overrides the`with_structured_output` or `bind_tools` methods.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles both JSON Schema and Pydantic V2 models.@@ -2054,7 +2054,7 @@ class ChatModelIntegrationTests(ChatModelTests):By default, `has_structured_output` is True if a model overrides the`with_structured_output` or `bind_tools` methods.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles both JSON Schema and Pydantic V2 models.@@ -2136,7 +2136,7 @@ class ChatModelIntegrationTests(ChatModelTests):By default, `has_structured_output` is True if a model overrides the`with_structured_output` or `bind_tools` methods.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles both JSON Schema and Pydantic V1 models.@@ -2202,7 +2202,7 @@ class ChatModelIntegrationTests(ChatModelTests):By default, `has_structured_output` is True if a model overrides the`with_structured_output` or `bind_tools` methods.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles Pydantic V2 models with optional parameters.@@ -2271,7 +2271,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"See example implementation of `with_structured_output` here: https://python.langchain.com/api_reference/_modules/langchain_openai/chat_models/base.html#BaseChatOpenAI.with_structured_output@@ -2355,7 +2355,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model can correctly handle messageswith pdf content blocks, including base64-encoded files. Otherwise, set@@ -2412,7 +2412,7 @@ class ChatModelIntegrationTests(ChatModelTests):{"type": "audio","base64": "<base64 audio data>",- "mime_type": "audio/wav", # or appropriate mime-type+ "mime_type": "audio/wav", # or appropriate MIME type}```@@ -2441,7 +2441,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model can correctly handle messageswith audio content blocks, specifically base64-encoded files. Otherwise,@@ -2495,7 +2495,7 @@ class ChatModelIntegrationTests(ChatModelTests):{"type": "image","base64": "<base64 image data>",- "mime_type": "image/jpeg", # or appropriate mime-type+ "mime_type": "image/jpeg", # or appropriate MIME type}```@@ -2541,7 +2541,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model can correctly handle messageswith image content blocks, including base64-encoded images. Otherwise, set@@ -2643,7 +2643,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model can correctly handle messageswith image content blocks in `ToolMessage` objects, including base64-encoded@@ -2742,7 +2742,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model can correctly handle messageswith PDF content blocks in `ToolMessage` objects, specifically@@ -2848,7 +2848,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that:@@ -2984,7 +2984,7 @@ class ChatModelIntegrationTests(ChatModelTests):If possible, the `name` field should be parsed and passed appropriatelyto the model. Otherwise, it should be ignored.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the `name` field on `HumanMessage`objects is either ignored or passed to the model appropriately.@@ -3018,7 +3018,7 @@ class ChatModelIntegrationTests(ChatModelTests):return False```- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that `bind_tools` is implemented to correctlytranslate LangChain tool objects into the appropriate schema for yourdiff --git a/libs/standard-tests/langchain_tests/unit_tests/chat_models.py b/libs/standard-tests/langchain_tests/unit_tests/chat_models.pyindex ff536f5d96..e54c70ccac 100644--- a/libs/standard-tests/langchain_tests/unit_tests/chat_models.py+++ b/libs/standard-tests/langchain_tests/unit_tests/chat_models.py@@ -310,7 +310,7 @@ class ChatModelUnitTests(ChatModelTests):calling or multi-modality) by selectively overriding the following properties.Expand to see details:- ??? note "`has_tool_calling`"+ ??? info "`has_tool_calling`"Boolean property indicating whether the chat model supports tool calling.@@ -325,7 +325,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`tool_choice_value`"+ ??? info "`tool_choice_value`"Value to use for tool choice when used in tests.@@ -342,7 +342,7 @@ class ChatModelUnitTests(ChatModelTests):return "any"```- ??? note "`has_tool_choice`"+ ??? info "`has_tool_choice`"Boolean property indicating whether the chat model supports forcing toolcalling via a `tool_choice` parameter.@@ -362,7 +362,7 @@ class ChatModelUnitTests(ChatModelTests):return False```- ??? note "`has_structured_output`"+ ??? info "`has_structured_output`"Boolean property indicating whether the chat model supports structuredoutput.@@ -379,7 +379,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`structured_output_kwargs`"+ ??? info "`structured_output_kwargs`"Dict property that can be used to specify additional kwargs for`with_structured_output`. Useful for testing different models.@@ -390,7 +390,7 @@ class ChatModelUnitTests(ChatModelTests):return {"method": "function_calling"}```- ??? note "`supports_json_mode`"+ ??? info "`supports_json_mode`"Boolean property indicating whether the chat model supports JSON mode in`with_structured_output`.@@ -403,7 +403,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`supports_image_inputs`"+ ??? info "`supports_image_inputs`"Boolean property indicating whether the chat model supports image inputs.@@ -416,7 +416,7 @@ class ChatModelUnitTests(ChatModelTests):{"type": "image","base64": "<base64 image data>",- "mime_type": "image/jpeg", # or appropriate mime-type+ "mime_type": "image/jpeg", # or appropriate MIME type}```@@ -438,7 +438,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`supports_image_urls`"+ ??? info "`supports_image_urls`"Boolean property indicating whether the chat model supports image inputs fromURLs.@@ -464,7 +464,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`supports_pdf_inputs`"+ ??? info "`supports_pdf_inputs`"Boolean property indicating whether the chat model supports PDF inputs.@@ -490,7 +490,7 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`supports_audio_inputs`"+ ??? info "`supports_audio_inputs`"Boolean property indicating whether the chat model supports audio inputs.@@ -503,7 +503,7 @@ class ChatModelUnitTests(ChatModelTests):{"type": "audio","base64": "<base64 audio data>",- "mime_type": "audio/wav", # or appropriate mime-type+ "mime_type": "audio/wav", # or appropriate MIME type}```@@ -515,13 +515,13 @@ class ChatModelUnitTests(ChatModelTests):return True```- ??? note "`supports_video_inputs`"+ ??? info "`supports_video_inputs`"Boolean property indicating whether the chat model supports image inputs.Defaults to `False`. No current tests are written for this feature.- ??? note "`returns_usage_metadata`"+ ??? info "`returns_usage_metadata`"Boolean property indicating whether the chat model returns usage metadataon invoke and streaming responses.@@ -541,7 +541,7 @@ class ChatModelUnitTests(ChatModelTests):Models supporting `usage_metadata` should also return the name of theunderlying model in the `response_metadata` of the `AIMessage`.- ??? note "`supports_anthropic_inputs`"+ ??? info "`supports_anthropic_inputs`"Boolean property indicating whether the chat model supports Anthropic-styleinputs.@@ -569,7 +569,7 @@ class ChatModelUnitTests(ChatModelTests):return False```- ??? note "`supports_image_tool_message`"+ ??? info "`supports_image_tool_message`"Boolean property indicating whether the chat model supports `ToolMessage`objects that include image content, e.g.,@@ -615,7 +615,7 @@ class ChatModelUnitTests(ChatModelTests):return False```- ??? note "`supports_pdf_tool_message`"+ ??? info "`supports_pdf_tool_message`"Boolean property indicating whether the chat model supports `ToolMessage`objects that include PDF content, i.e.,@@ -645,7 +645,7 @@ class ChatModelUnitTests(ChatModelTests):return False```- ??? note "`supported_usage_metadata_details`"+ ??? info "`supported_usage_metadata_details`"Property controlling what usage metadata details are emitted in both `invoke`and `stream`.@@ -660,7 +660,7 @@ class ChatModelUnitTests(ChatModelTests):Only needs to be overridden if these details are supplied.- ??? note "`enable_vcr_tests`"+ ??? info "`enable_vcr_tests`"Property controlling whether to enable select tests that rely on[VCR](https://vcrpy.readthedocs.io/en/latest/) caching of HTTP calls, such@@ -815,7 +815,7 @@ class ChatModelUnitTests(ChatModelTests):These tests can be enabled by overriding the `init_from_env_params`property (see below).- ??? note "`init_from_env_params`"+ ??? info "`init_from_env_params`"This property is used in unit tests to test initialization fromenvironment variables. It should return a tuple of three dictionaries@@ -862,7 +862,7 @@ class ChatModelUnitTests(ChatModelTests):def test_init(self) -> None:"""Test model initialization. This should pass for all integrations.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that:@@ -886,7 +886,7 @@ class ChatModelUnitTests(ChatModelTests):Relies on the `init_from_env_params` property. Test is skipped if thatproperty is not set.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that `init_from_env_params` is specifiedcorrectly and that model parameters are properly set from environment@@ -913,7 +913,7 @@ class ChatModelUnitTests(ChatModelTests):This is for backward-compatibility purposes.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model can be initialized with aboolean `streaming` parameter.@@ -939,7 +939,7 @@ class ChatModelUnitTests(ChatModelTests):into `bind_tools`. Test is skipped if the `has_tool_calling` propertyon the test class is False.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles Pydantic V2 models. `langchain_core` implements@@ -981,7 +981,7 @@ class ChatModelUnitTests(ChatModelTests):Test is skipped if the `has_structured_output` property on the test class isFalse.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, ensure that the model's `bind_tools` methodproperly handles Pydantic V2 models. `langchain_core` implements@@ -1006,7 +1006,7 @@ class ChatModelUnitTests(ChatModelTests):These are used for tracing purposes.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the model accommodates [standard parameters](https://python.langchain.com/docs/concepts/chat_models/#standard-parameters).@@ -1046,7 +1046,7 @@ class ChatModelUnitTests(ChatModelTests):Test is skipped if the `is_lc_serializable` property on the chat model classis not overwritten to return `True`.- ??? note "Troubleshooting"+ ??? question "Troubleshooting"If this test fails, check that the `init_from_env_params` property iscorrectly set on the test class.diff --git a/libs/text-splitters/langchain_text_splitters/__init__.py b/libs/text-splitters/langchain_text_splitters/__init__.pyindex e6c88699ba..623582f8d9 100644--- a/libs/text-splitters/langchain_text_splitters/__init__.py+++ b/libs/text-splitters/langchain_text_splitters/__init__.py@@ -1,4 +1,4 @@-"""**Text Splitters** are classes for splitting text.+"""Text Splitters are classes for splitting text.!!! note`MarkdownHeaderTextSplitter` and `HTMLHeaderTextSplitter` do not derive from