style(core): typo/docs lint pass (#33093)

Author: mdrxy

docs/docs/how_to/index.mdx

@@ -72,7 +72,7 @@ See [supported integrations](/docs/integrations/chat/) for details on getting st
 
 ### Example selectors
 
-[Example Selectors](/docs/concepts/example_selectors) are responsible for selecting the correct few shot examples to pass to the prompt.
+[Example Selectors](/docs/concepts/example_selectors) are responsible for selecting the correct few-shot examples to pass to the prompt.
 
 - [How to: use example selectors](/docs/how_to/example_selectors)
 - [How to: select examples by length](/docs/how_to/example_selectors_length_based)
@@ -168,7 +168,7 @@ See [supported integrations](/docs/integrations/vectorstores/) for details on ge
 
 Indexing is the process of keeping your vectorstore in-sync with the underlying data source.
 
-- [How to: reindex data to keep your vectorstore in sync with the underlying data source](/docs/how_to/indexing)
+- [How to: reindex data to keep your vectorstore in-sync with the underlying data source](/docs/how_to/indexing)
 
 ### Tools
 

libs/core/langchain_core/language_models/chat_models.py

@@ -471,7 +471,7 @@ def stream(
         **kwargs: Any,
     ) -> Iterator[BaseMessageChunk]:
         if not self._should_stream(async_api=False, **{**kwargs, "stream": True}):
-            # model doesn't implement streaming, so use default implementation
+            # Model doesn't implement streaming, so use default implementation
             yield cast(
                 "BaseMessageChunk",
                 self.invoke(input, config=config, stop=stop, **kwargs),

libs/core/langchain_core/language_models/fake_chat_models.py

@@ -19,7 +19,7 @@
 
 
 class FakeMessagesListChatModel(BaseChatModel):
-    """Fake ChatModel for testing purposes."""
+    """Fake ``ChatModel`` for testing purposes."""
 
     responses: list[BaseMessage]
     """List of responses to **cycle** through in order."""
@@ -212,10 +212,11 @@ class GenericFakeChatModel(BaseChatModel):
     """Generic fake chat model that can be used to test the chat model interface.
 
     * Chat model should be usable in both sync and async tests
-    * Invokes on_llm_new_token to allow for testing of callback related code for new
+    * Invokes ``on_llm_new_token`` to allow for testing of callback related code for new
       tokens.
     * Includes logic to break messages into message chunk to facilitate testing of
       streaming.
+
     """
 
     messages: Iterator[Union[AIMessage, str]]
@@ -230,6 +231,7 @@ class GenericFakeChatModel(BaseChatModel):
     .. warning::
         Streaming is not implemented yet. We should try to implement it in the future by
         delegating to invoke and then breaking the resulting output into message chunks.
+
     """
 
     @override
@@ -351,6 +353,7 @@ class ParrotFakeChatModel(BaseChatModel):
     """Generic fake chat model that can be used to test the chat model interface.
 
     * Chat model should be usable in both sync and async tests
+
     """
 
     @override

libs/core/langchain_core/messages/ai.py

@@ -45,7 +45,6 @@ class InputTokenDetails(TypedDict, total=False):
     Does *not* need to sum to full input token count. Does *not* need to have all keys.
 
     Example:
-
         .. code-block:: python
 
             {
@@ -72,6 +71,7 @@ class InputTokenDetails(TypedDict, total=False):
 
     Since there was a cache hit, the tokens were read from the cache. More precisely,
     the model state given these tokens was read from the cache.
+
     """
 
 
@@ -81,7 +81,6 @@ class OutputTokenDetails(TypedDict, total=False):
     Does *not* need to sum to full output token count. Does *not* need to have all keys.
 
     Example:
-
         .. code-block:: python
 
             {
@@ -100,6 +99,7 @@ class OutputTokenDetails(TypedDict, total=False):
 
     Tokens generated by the model in a chain of thought process (i.e. by OpenAI's o1
     models) that are not returned as part of model output.
+
     """
 
 
@@ -109,7 +109,6 @@ class UsageMetadata(TypedDict):
     This is a standard representation of token usage that is consistent across models.
 
     Example:
-
         .. code-block:: python
 
             {
@@ -148,6 +147,7 @@ class UsageMetadata(TypedDict):
     """Breakdown of output token counts.
 
     Does *not* need to sum to full output token count. Does *not* need to have all keys.
+
     """
 
 
@@ -159,12 +159,14 @@ class AIMessage(BaseMessage):
     This message represents the output of the model and consists of both
     the raw output as returned by the model together standardized fields
     (e.g., tool calls, usage metadata) added by the LangChain framework.
+
     """
 
     example: bool = False
     """Use to denote that a message is part of an example conversation.
 
     At the moment, this is ignored by most models. Usage is discouraged.
+
     """
 
     tool_calls: list[ToolCall] = []
@@ -175,15 +177,18 @@ class AIMessage(BaseMessage):
     """If provided, usage metadata for a message, such as token counts.
 
     This is a standard representation of token usage that is consistent across models.
+
     """
 
     type: Literal["ai"] = "ai"
-    """The type of the message (used for deserialization). Defaults to "ai"."""
+    """The type of the message (used for deserialization). Defaults to ``'ai'``."""
 
     def __init__(
-        self, content: Union[str, list[Union[str, dict]]], **kwargs: Any
+        self,
+        content: Union[str, list[Union[str, dict]]],
+        **kwargs: Any,
     ) -> None:
-        """Pass in content as positional arg.
+        """Initialize ``AIMessage``.
 
         Args:
             content: The content of the message.
@@ -254,6 +259,7 @@ def pretty_repr(self, html: bool = False) -> str:
 
         Returns:
             A pretty representation of the message.
+
         """
         base = super().pretty_repr(html=html)
         lines = []
@@ -293,7 +299,10 @@ class AIMessageChunk(AIMessage, BaseMessageChunk):
     # non-chunk variant.
     type: Literal["AIMessageChunk"] = "AIMessageChunk"  # type: ignore[assignment]
     """The type of the message (used for deserialization).
-    Defaults to "AIMessageChunk"."""
+
+    Defaults to ``AIMessageChunk``.
+
+    """
 
     tool_call_chunks: list[ToolCallChunk] = []
     """If provided, tool call chunks associated with the message."""
@@ -311,7 +320,10 @@ def init_tool_calls(self) -> Self:
         """Initialize tool calls from tool call chunks.
 
         Returns:
-            This ``AIMessageChunk``.
+            The values with tool calls initialized.
+
+        Raises:
+            ValueError: If the tool call chunks are malformed.
         """
         if not self.tool_call_chunks:
             if self.tool_calls:
@@ -522,9 +534,9 @@ def add_usage(
 def subtract_usage(
     left: Optional[UsageMetadata], right: Optional[UsageMetadata]
 ) -> UsageMetadata:
-    """Recursively subtract two UsageMetadata objects.
+    """Recursively subtract two ``UsageMetadata`` objects.
 
-    Token counts cannot be negative so the actual operation is max(left - right, 0).
+    Token counts cannot be negative so the actual operation is ``max(left - right, 0)``.
 
     Example:
         .. code-block:: python

libs/core/langchain_core/messages/base.py

@@ -20,7 +20,7 @@
 class BaseMessage(Serializable):
     """Base abstract message class.
 
-    Messages are the inputs and outputs of ChatModels.
+    Messages are the inputs and outputs of ``ChatModel``s.
     """
 
     content: Union[str, list[Union[str, dict]]]
@@ -31,17 +31,18 @@ class BaseMessage(Serializable):
 
     For example, for a message from an AI, this could include tool calls as
     encoded by the model provider.
+
     """
 
     response_metadata: dict = Field(default_factory=dict)
-    """Response metadata. For example: response headers, logprobs, token counts, model
-    name."""
+    """Examples: response headers, logprobs, token counts, model name."""
 
     type: str
     """The type of the message. Must be a string that is unique to the message type.
 
     The purpose of this field is to allow for easy identification of the message type
     when deserializing messages.
+
     """
 
     name: Optional[str] = None
@@ -51,20 +52,26 @@ class BaseMessage(Serializable):
 
     Usage of this field is optional, and whether it's used or not is up to the
     model implementation.
+
     """
 
     id: Optional[str] = Field(default=None, coerce_numbers_to_str=True)
-    """An optional unique identifier for the message. This should ideally be
-    provided by the provider/model which created the message."""
+    """An optional unique identifier for the message.
+
+    This should ideally be provided by the provider/model which created the message.
+
+    """
 
     model_config = ConfigDict(
         extra="allow",
     )
 
     def __init__(
-        self, content: Union[str, list[Union[str, dict]]], **kwargs: Any
+        self,
+        content: Union[str, list[Union[str, dict]]],
+        **kwargs: Any,
     ) -> None:
-        """Pass in content as positional arg.
+        """Initialize ``BaseMessage``.
 
         Args:
             content: The string contents of the message.
@@ -73,7 +80,7 @@ def __init__(
 
     @classmethod
     def is_lc_serializable(cls) -> bool:
-        """BaseMessage is serializable.
+        """``BaseMessage`` is serializable.
 
         Returns:
             True
@@ -90,10 +97,11 @@ def get_lc_namespace(cls) -> list[str]:
         return ["langchain", "schema", "messages"]
 
     def text(self) -> str:
-        """Get the text content of the message.
+        """Get the text ``content`` of the message.
 
         Returns:
             The text content of the message.
+
         """
         if isinstance(self.content, str):
             return self.content
@@ -136,6 +144,7 @@ def pretty_repr(
 
         Returns:
             A pretty representation of the message.
+
         """
         title = get_msg_title_repr(self.type.title() + " Message", bold=html)
         # TODO: handle non-string content.
@@ -155,11 +164,12 @@ def merge_content(
     """Merge multiple message contents.
 
     Args:
-        first_content: The first content. Can be a string or a list.
-        contents: The other contents. Can be a string or a list.
+        first_content: The first ``content``. Can be a string or a list.
+        contents: The other ``content``s. Can be a string or a list.
 
     Returns:
         The merged content.
+
     """
     merged = first_content
     for content in contents:
@@ -207,9 +217,10 @@ def __add__(self, other: Any) -> BaseMessageChunk:  # type: ignore[override]
 
         For example,
 
-        `AIMessageChunk(content="Hello") + AIMessageChunk(content=" World")`
+        ``AIMessageChunk(content="Hello") + AIMessageChunk(content=" World")``
+
+        will give ``AIMessageChunk(content="Hello World")``
 
-        will give `AIMessageChunk(content="Hello World")`
         """
         if isinstance(other, BaseMessageChunk):
             # If both are (subclasses of) BaseMessageChunk,
@@ -257,8 +268,9 @@ def message_to_dict(message: BaseMessage) -> dict:
         message: Message to convert.
 
     Returns:
-        Message as a dict. The dict will have a "type" key with the message type
-        and a "data" key with the message data as a dict.
+        Message as a dict. The dict will have a ``type`` key with the message type
+        and a ``data`` key with the message data as a dict.
+
     """
     return {"type": message.type, "data": message.model_dump()}
 
@@ -267,10 +279,11 @@ def messages_to_dict(messages: Sequence[BaseMessage]) -> list[dict]:
     """Convert a sequence of Messages to a list of dictionaries.
 
     Args:
-        messages: Sequence of messages (as BaseMessages) to convert.
+        messages: Sequence of messages (as ``BaseMessage``s) to convert.
 
     Returns:
         List of messages as dicts.
+
     """
     return [message_to_dict(m) for m in messages]
 
@@ -284,6 +297,7 @@ def get_msg_title_repr(title: str, *, bold: bool = False) -> str:
 
     Returns:
         The title representation.
+
     """
     padded = " " + title + " "
     sep_len = (80 - len(padded)) // 2

libs/core/langchain_core/messages/chat.py

@@ -30,7 +30,10 @@ class ChatMessageChunk(ChatMessage, BaseMessageChunk):
     # non-chunk variant.
     type: Literal["ChatMessageChunk"] = "ChatMessageChunk"  # type: ignore[assignment]
     """The type of the message (used during serialization).
-    Defaults to "ChatMessageChunk"."""
+
+    Defaults to ``'ChatMessageChunk'``.
+
+    """
 
     @override
     def __add__(self, other: Any) -> BaseMessageChunk:  # type: ignore[override]

libs/core/langchain_core/messages/function.py

@@ -15,19 +15,20 @@
 class FunctionMessage(BaseMessage):
     """Message for passing the result of executing a tool back to a model.
 
-    FunctionMessage are an older version of the ToolMessage schema, and
-    do not contain the tool_call_id field.
+    ``FunctionMessage`` are an older version of the ``ToolMessage`` schema, and
+    do not contain the ``tool_call_id`` field.
 
-    The tool_call_id field is used to associate the tool call request with the
+    The ``tool_call_id`` field is used to associate the tool call request with the
     tool call response. This is useful in situations where a chat model is able
     to request multiple tool calls in parallel.
+
     """
 
     name: str
     """The name of the function that was executed."""
 
     type: Literal["function"] = "function"
-    """The type of the message (used for serialization). Defaults to "function"."""
+    """The type of the message (used for serialization). Defaults to ``'function'``."""
 
 
 class FunctionMessageChunk(FunctionMessage, BaseMessageChunk):
@@ -38,7 +39,10 @@ class FunctionMessageChunk(FunctionMessage, BaseMessageChunk):
     # non-chunk variant.
     type: Literal["FunctionMessageChunk"] = "FunctionMessageChunk"  # type: ignore[assignment]
     """The type of the message (used for serialization).
-    Defaults to "FunctionMessageChunk"."""
+
+    Defaults to ``'FunctionMessageChunk'``.
+
+    """
 
     @override
     def __add__(self, other: Any) -> BaseMessageChunk:  # type: ignore[override]