langchain-core 0.3.73__py3-none-any.whl → 0.3.75__py3-none-any.whl

langchain_core/language_models/base.py

@@ -57,8 +57,8 @@ class LangSmithParams(TypedDict, total=False):
 def get_tokenizer() -> Any:
     """Get a GPT-2 tokenizer instance.
 
-    This function is cached to avoid re-loading the tokenizer
-    every time it is called.
+    This function is cached to avoid re-loading the tokenizer every time it is called.
+
     """
     try:
         from transformers import GPT2TokenizerFast  # type: ignore[import-not-found]
@@ -99,7 +99,8 @@ class BaseLanguageModel(
 ):
     """Abstract base class for interfacing with language models.
 
-    All language model wrappers inherited from BaseLanguageModel.
+    All language model wrappers inherited from ``BaseLanguageModel``.
+
     """
 
     cache: Union[BaseCache, bool, None] = Field(default=None, exclude=True)
@@ -108,9 +109,10 @@ class BaseLanguageModel(
     * If true, will use the global cache.
     * If false, will not use a cache
     * If None, will use the global cache if it's set, otherwise no cache.
-    * If instance of BaseCache, will use the provided cache.
+    * If instance of ``BaseCache``, will use the provided cache.
 
     Caching is not currently supported for streaming methods of models.
+
     """
     verbose: bool = Field(default_factory=_get_verbosity, exclude=True, repr=False)
     """Whether to print out response text."""
@@ -140,6 +142,7 @@ class BaseLanguageModel(
 
         Returns:
             The verbosity setting to use.
+
         """
         if verbose is None:
             return _get_verbosity()
@@ -195,7 +198,8 @@ class BaseLanguageModel(
 
         Returns:
             An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            prompt and additional model provider-specific output.
+
         """
 
     @abstractmethod
@@ -229,8 +233,9 @@ class BaseLanguageModel(
                 to the model provider API call.
 
         Returns:
-            An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            An ``LLMResult``, which contains a list of candidate Generations for each
+            input prompt and additional model provider-specific output.
+
         """
 
     def with_structured_output(
@@ -248,8 +253,8 @@ class BaseLanguageModel(
     ) -> str:
         """Pass a single string input to the model and return a string.
 
-         Use this method when passing in raw text. If you want to pass in specific
-            types of chat messages, use predict_messages.
+        Use this method when passing in raw text. If you want to pass in specific types
+        of chat messages, use predict_messages.
 
         Args:
             text: String input to pass to the model.
@@ -260,6 +265,7 @@ class BaseLanguageModel(
 
         Returns:
             Top model prediction as a string.
+
         """
 
     @deprecated("0.1.7", alternative="invoke", removal="1.0")
@@ -274,7 +280,7 @@ class BaseLanguageModel(
         """Pass a message sequence to the model and return a message.
 
         Use this method when passing in chat messages. If you want to pass in raw text,
-            use predict.
+        use predict.
 
         Args:
             messages: A sequence of chat messages corresponding to a single model input.
@@ -285,6 +291,7 @@ class BaseLanguageModel(
 
         Returns:
             Top model prediction as a message.
+
         """
 
     @deprecated("0.1.7", alternative="ainvoke", removal="1.0")
@@ -295,7 +302,7 @@ class BaseLanguageModel(
         """Asynchronously pass a string to the model and return a string.
 
         Use this method when calling pure text generation models and only the top
-            candidate generation is needed.
+        candidate generation is needed.
 
         Args:
             text: String input to pass to the model.
@@ -306,6 +313,7 @@ class BaseLanguageModel(
 
         Returns:
             Top model prediction as a string.
+
         """
 
     @deprecated("0.1.7", alternative="ainvoke", removal="1.0")
@@ -319,8 +327,8 @@ class BaseLanguageModel(
     ) -> BaseMessage:
         """Asynchronously pass messages to the model and return a message.
 
-        Use this method when calling chat models and only the top
-            candidate generation is needed.
+        Use this method when calling chat models and only the top candidate generation
+        is needed.
 
         Args:
             messages: A sequence of chat messages corresponding to a single model input.
@@ -331,6 +339,7 @@ class BaseLanguageModel(
 
         Returns:
             Top model prediction as a message.
+
         """
 
     @property
@@ -346,7 +355,8 @@ class BaseLanguageModel(
 
         Returns:
             A list of ids corresponding to the tokens in the text, in order they occur
-                in the text.
+            in the text.
+
         """
         if self.custom_get_token_ids is not None:
             return self.custom_get_token_ids(text)
@@ -362,6 +372,7 @@ class BaseLanguageModel(
 
         Returns:
             The integer number of tokens in the text.
+
         """
         return len(self.get_token_ids(text))
 
@@ -374,16 +385,18 @@ class BaseLanguageModel(
 
         Useful for checking if an input fits in a model's context window.
 
-        **Note**: the base implementation of get_num_tokens_from_messages ignores
-        tool schemas.
+        .. note::
+            The base implementation of ``get_num_tokens_from_messages`` ignores tool
+            schemas.
 
         Args:
             messages: The message inputs to tokenize.
-            tools: If provided, sequence of dict, BaseModel, function, or BaseTools
-                to be converted to tool schemas.
+            tools: If provided, sequence of dict, ``BaseModel``, function, or
+                ``BaseTools`` to be converted to tool schemas.
 
         Returns:
             The sum of the number of tokens across the messages.
+
         """
         if tools is not None:
             warnings.warn(
@@ -396,6 +409,7 @@ class BaseLanguageModel(
     def _all_required_field_names(cls) -> set:
         """DEPRECATED: Kept for backwards compatibility.
 
-        Use get_pydantic_field_names.
+        Use ``get_pydantic_field_names``.
+
         """
         return get_pydantic_field_names(cls)

langchain_core/language_models/chat_models.py

@@ -78,6 +78,11 @@ def _generate_response_from_error(error: BaseException) -> list[ChatGeneration]:
     if hasattr(error, "response"):
         response = error.response
         metadata: dict = {}
+        if hasattr(response, "json"):
+            try:
+                metadata["body"] = response.json()
+            except Exception:
+                metadata["body"] = getattr(response, "text", None)
         if hasattr(response, "headers"):
             try:
                 metadata["headers"] = dict(response.headers)
@@ -97,17 +102,18 @@ def _generate_response_from_error(error: BaseException) -> list[ChatGeneration]:
 
 
 def _format_for_tracing(messages: list[BaseMessage]) -> list[BaseMessage]:
-    """Format messages for tracing in on_chat_model_start.
+    """Format messages for tracing in ``on_chat_model_start``.
 
     - Update image content blocks to OpenAI Chat Completions format (backward
     compatibility).
-    - Add "type" key to content blocks that have a single key.
+    - Add ``type`` key to content blocks that have a single key.
 
     Args:
         messages: List of messages to format.
 
     Returns:
         List of messages formatted for tracing.
+
     """
     messages_to_trace = []
     for message in messages:
@@ -153,10 +159,11 @@ def generate_from_stream(stream: Iterator[ChatGenerationChunk]) -> ChatResult:
     """Generate from a stream.
 
     Args:
-        stream: Iterator of ChatGenerationChunk.
+        stream: Iterator of ``ChatGenerationChunk``.
 
     Returns:
         ChatResult: Chat result.
+
     """
     generation = next(stream, None)
     if generation:
@@ -180,10 +187,11 @@ async def agenerate_from_stream(
     """Async generate from a stream.
 
     Args:
-        stream: Iterator of ChatGenerationChunk.
+        stream: Iterator of ``ChatGenerationChunk``.
 
     Returns:
         ChatResult: Chat result.
+
     """
     chunks = [chunk async for chunk in stream]
     return await run_in_executor(None, generate_from_stream, iter(chunks))
@@ -311,15 +319,16 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
       provided. This offers the best of both worlds.
     - If False (default), will always use streaming case if available.
 
-    The main reason for this flag is that code might be written using ``.stream()`` and
+    The main reason for this flag is that code might be written using ``stream()`` and
     a user may want to swap out a given model for another model whose the implementation
     does not properly support streaming.
+
     """
 
     @model_validator(mode="before")
     @classmethod
     def raise_deprecation(cls, values: dict) -> Any:
-        """Raise deprecation warning if callback_manager is used.
+        """Raise deprecation warning if ``callback_manager`` is used.
 
         Args:
             values (Dict): Values to validate.
@@ -328,7 +337,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
             Dict: Validated values.
 
         Raises:
-            DeprecationWarning: If callback_manager is used.
+            DeprecationWarning: If ``callback_manager`` is used.
+
         """
         if values.get("callback_manager") is not None:
             warnings.warn(
@@ -528,7 +538,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                     generations = [generations_with_error_metadata]
                 run_manager.on_llm_error(
                     e,
-                    response=LLMResult(generations=generations),  # type: ignore[arg-type]
+                    response=LLMResult(generations=generations),
                 )
                 raise
 
@@ -622,7 +632,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 generations = [generations_with_error_metadata]
             await run_manager.on_llm_error(
                 e,
-                response=LLMResult(generations=generations),  # type: ignore[arg-type]
+                response=LLMResult(generations=generations),
             )
             raise
 
@@ -653,6 +663,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             List of ChatGeneration objects.
+
         """
         converted_generations = []
         for gen in cache_val:
@@ -778,7 +789,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            prompt and additional model provider-specific output.
+
         """
         ls_structured_output_format = kwargs.pop(
             "ls_structured_output_format", None
@@ -835,17 +847,17 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                     run_managers[i].on_llm_error(
                         e,
                         response=LLMResult(
-                            generations=[generations_with_error_metadata]  # type: ignore[list-item]
+                            generations=[generations_with_error_metadata]
                         ),
                     )
                 raise
         flattened_outputs = [
-            LLMResult(generations=[res.generations], llm_output=res.llm_output)  # type: ignore[list-item]
+            LLMResult(generations=[res.generations], llm_output=res.llm_output)
             for res in results
         ]
         llm_output = self._combine_llm_outputs([res.llm_output for res in results])
         generations = [res.generations for res in results]
-        output = LLMResult(generations=generations, llm_output=llm_output)  # type: ignore[arg-type]
+        output = LLMResult(generations=generations, llm_output=llm_output)
         if run_managers:
             run_infos = []
             for manager, flattened_output in zip(run_managers, flattened_outputs):
@@ -892,7 +904,8 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             An LLMResult, which contains a list of candidate Generations for each input
-                prompt and additional model provider-specific output.
+            prompt and additional model provider-specific output.
+
         """
         ls_structured_output_format = kwargs.pop(
             "ls_structured_output_format", None
@@ -954,7 +967,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                     await run_managers[i].on_llm_error(
                         res,
                         response=LLMResult(
-                            generations=[generations_with_error_metadata]  # type: ignore[list-item]
+                            generations=[generations_with_error_metadata]
                         ),
                     )
                 exceptions.append(res)
@@ -964,7 +977,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                     *[
                         run_manager.on_llm_end(
                             LLMResult(
-                                generations=[res.generations],  # type: ignore[list-item, union-attr]
+                                generations=[res.generations],  # type: ignore[union-attr]
                                 llm_output=res.llm_output,  # type: ignore[union-attr]
                             )
                         )
@@ -974,12 +987,12 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
                 )
             raise exceptions[0]
         flattened_outputs = [
-            LLMResult(generations=[res.generations], llm_output=res.llm_output)  # type: ignore[list-item, union-attr]
+            LLMResult(generations=[res.generations], llm_output=res.llm_output)  # type: ignore[union-attr]
             for res in results
         ]
         llm_output = self._combine_llm_outputs([res.llm_output for res in results])  # type: ignore[union-attr]
         generations = [res.generations for res in results]  # type: ignore[union-attr]
-        output = LLMResult(generations=generations, llm_output=llm_output)  # type: ignore[arg-type]
+        output = LLMResult(generations=generations, llm_output=llm_output)
         await asyncio.gather(
             *[
                 run_manager.on_llm_end(flattened_output)
@@ -1248,6 +1261,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             The model output message.
+
         """
         generation = self.generate(
             [messages], stop=stop, callbacks=callbacks, **kwargs
@@ -1288,6 +1302,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             The model output string.
+
         """
         return self.predict(message, stop=stop, **kwargs)
 
@@ -1307,6 +1322,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             The predicted output string.
+
         """
         stop_ = None if stop is None else list(stop)
         result = self([HumanMessage(content=text)], stop=stop_, **kwargs)
@@ -1382,6 +1398,7 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 
         Returns:
             A Runnable that returns a message.
+
         """
         raise NotImplementedError
 
@@ -1544,8 +1561,10 @@ class BaseChatModel(BaseLanguageModel[BaseMessage], ABC):
 class SimpleChatModel(BaseChatModel):
     """Simplified implementation for a chat model to inherit from.
 
-    **Note** This implementation is primarily here for backwards compatibility.
-        For new implementations, please use `BaseChatModel` directly.
+    .. note::
+        This implementation is primarily here for backwards compatibility. For new
+        implementations, please use ``BaseChatModel`` directly.
+
     """
 
     def _generate(

langchain_core/language_models/fake_chat_models.py

@@ -223,11 +223,12 @@ class GenericFakeChatModel(BaseChatModel):
     This can be expanded to accept other types like Callables / dicts / strings
     to make the interface more generic if needed.
 
-    Note: if you want to pass a list, you can use `iter` to convert it to an iterator.
+    .. note::
+        if you want to pass a list, you can use ``iter`` to convert it to an iterator.
 
-    Please note that 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.
+    .. 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

langchain_core/load/dump.py

@@ -73,10 +73,9 @@ def dumps(obj: Any, *, pretty: bool = False, **kwargs: Any) -> str:
 def dumpd(obj: Any) -> Any:
     """Return a dict representation of an object.
 
-    Note:
-        Unfortunately this function is not as efficient as it could be
-        because it first dumps the object to a json string and then loads it
-        back into a dictionary.
+    .. note::
+        Unfortunately this function is not as efficient as it could be because it first
+        dumps the object to a json string and then loads it back into a dictionary.
 
     Args:
         obj: The object to dump.

langchain_core/messages/ai.py

@@ -358,7 +358,10 @@ class AIMessageChunk(AIMessage, BaseMessageChunk):
 
         for chunk in self.tool_call_chunks:
             try:
-                args_ = parse_partial_json(chunk["args"]) if chunk["args"] != "" else {}  # type: ignore[arg-type]
+                if chunk["args"] is not None and chunk["args"] != "":
+                    args_ = parse_partial_json(chunk["args"])
+                else:
+                    args_ = {}
                 if isinstance(args_, dict):
                     tool_calls.append(
                         create_tool_call(

langchain_core/messages/modifier.py

@@ -13,7 +13,7 @@ class RemoveMessage(BaseMessage):
 
     def __init__(
         self,
-        id: str,  # noqa: A002
+        id: str,
         **kwargs: Any,
     ) -> None:
         """Create a RemoveMessage.

langchain_core/messages/tool.py

@@ -212,7 +212,7 @@ def tool_call(
     *,
     name: str,
     args: dict[str, Any],
-    id: Optional[str],  # noqa: A002
+    id: Optional[str],
 ) -> ToolCall:
     """Create a tool call.
 
@@ -260,7 +260,7 @@ def tool_call_chunk(
     *,
     name: Optional[str] = None,
     args: Optional[str] = None,
-    id: Optional[str] = None,  # noqa: A002
+    id: Optional[str] = None,
     index: Optional[int] = None,
 ) -> ToolCallChunk:
     """Create a tool call chunk.
@@ -298,7 +298,7 @@ def invalid_tool_call(
     *,
     name: Optional[str] = None,
     args: Optional[str] = None,
-    id: Optional[str] = None,  # noqa: A002
+    id: Optional[str] = None,
     error: Optional[str] = None,
 ) -> InvalidToolCall:
     """Create an invalid tool call.

langchain_core/messages/utils.py

@@ -213,7 +213,7 @@ def _create_message_from_message_type(
     name: Optional[str] = None,
     tool_call_id: Optional[str] = None,
     tool_calls: Optional[list[dict[str, Any]]] = None,
-    id: Optional[str] = None,  # noqa: A002
+    id: Optional[str] = None,
     **additional_kwargs: Any,
 ) -> BaseMessage:
     """Create a message from a message type and content string.
@@ -656,22 +656,23 @@ def trim_messages(
     properties:
 
     1. The resulting chat history should be valid. Most chat models expect that chat
-       history starts with either (1) a `HumanMessage` or (2) a `SystemMessage` followed
-       by a `HumanMessage`. To achieve this, set `start_on="human"`.
-       In addition, generally a `ToolMessage` can only appear after an `AIMessage`
+       history starts with either (1) a ``HumanMessage`` or (2) a ``SystemMessage`` followed
+       by a ``HumanMessage``. To achieve this, set ``start_on="human"``.
+       In addition, generally a ``ToolMessage`` can only appear after an ``AIMessage``
        that involved a tool call.
        Please see the following link for more information about messages:
        https://python.langchain.com/docs/concepts/#messages
     2. It includes recent messages and drops old messages in the chat history.
-       To achieve this set the `strategy="last"`.
-    3. Usually, the new chat history should include the `SystemMessage` if it
-       was present in the original chat history since the `SystemMessage` includes
-       special instructions to the chat model. The `SystemMessage` is almost always
+       To achieve this set the ``strategy="last"``.
+    3. Usually, the new chat history should include the ``SystemMessage`` if it
+       was present in the original chat history since the ``SystemMessage`` includes
+       special instructions to the chat model. The ``SystemMessage`` is almost always
        the first message in the history if present. To achieve this set the
-       `include_system=True`.
+       ``include_system=True``.
 
-    **Note** The examples below show how to configure `trim_messages` to achieve
-        a behavior consistent with the above properties.
+    .. note::
+        The examples below show how to configure ``trim_messages`` to achieve a behavior
+        consistent with the above properties.
 
     Args:
         messages: Sequence of Message-like objects to trim.
@@ -1580,26 +1581,26 @@ def count_tokens_approximately(
         chars_per_token: Number of characters per token to use for the approximation.
             Default is 4 (one token corresponds to ~4 chars for common English text).
             You can also specify float values for more fine-grained control.
-            See more here: https://platform.openai.com/tokenizer
+            `See more here. <https://platform.openai.com/tokenizer>`__
         extra_tokens_per_message: Number of extra tokens to add per message.
             Default is 3 (special tokens, including beginning/end of message).
             You can also specify float values for more fine-grained control.
-            See more here:
-            https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+            `See more here. <https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb>`__
         count_name: Whether to include message names in the count.
             Enabled by default.
 
     Returns:
         Approximate number of tokens in the messages.
 
-    Note:
-        This is a simple approximation that may not match the exact token count
-        used by specific models. For accurate counts, use model-specific tokenizers.
+    .. note::
+        This is a simple approximation that may not match the exact token count used by
+        specific models. For accurate counts, use model-specific tokenizers.
 
     Warning:
         This function does not currently support counting image tokens.
 
     .. versionadded:: 0.3.46
+
     """
     token_count = 0.0
     for message in convert_to_messages(messages):

langchain_core/output_parsers/openai_tools.py

@@ -246,6 +246,8 @@ class JsonOutputKeyToolsParser(JsonOutputToolsParser):
                     _ = tool_call.pop("id")
         else:
             try:
+                # This exists purely for backward compatibility / cached messages
+                # All new messages should use `message.tool_calls`
                 raw_tool_calls = copy.deepcopy(message.additional_kwargs["tool_calls"])
             except KeyError:
                 if self.first_tool_only:

langchain_core/output_parsers/transform.py

@@ -32,7 +32,7 @@ class BaseTransformOutputParser(BaseOutputParser[T]):
 
     def _transform(
         self,
-        input: Iterator[Union[str, BaseMessage]],  # noqa: A002
+        input: Iterator[Union[str, BaseMessage]],
     ) -> Iterator[T]:
         for chunk in input:
             if isinstance(chunk, BaseMessage):
@@ -42,7 +42,7 @@ class BaseTransformOutputParser(BaseOutputParser[T]):
 
     async def _atransform(
         self,
-        input: AsyncIterator[Union[str, BaseMessage]],  # noqa: A002
+        input: AsyncIterator[Union[str, BaseMessage]],
     ) -> AsyncIterator[T]:
         async for chunk in input:
             if isinstance(chunk, BaseMessage):

langchain_core/output_parsers/xml.py

@@ -105,10 +105,11 @@ class _StreamingParser:
         self.buffer = ""
         # yield all events
         try:
-            for event, elem in self.pull_parser.read_events():
+            events = self.pull_parser.read_events()
+            for event, elem in events:  # type: ignore[misc]
                 if event == "start":
                     # update current path
-                    self.current_path.append(elem.tag)
+                    self.current_path.append(elem.tag)  # type: ignore[union-attr]
                     self.current_path_has_children = False
                 elif event == "end":
                     # remove last element from current path
@@ -116,7 +117,7 @@ class _StreamingParser:
                     self.current_path.pop()
                     # yield element
                     if not self.current_path_has_children:
-                        yield nested_element(self.current_path, elem)
+                        yield nested_element(self.current_path, elem)  # type: ignore[arg-type]
                     # prevent yielding of parent element
                     if self.current_path:
                         self.current_path_has_children = True

langchain_core/prompts/chat.py

@@ -155,9 +155,7 @@ class MessagesPlaceholder(BaseMessagePromptTemplate):
         """
         # mypy can't detect the init which is defined in the parent class
         # b/c these are BaseModel classes.
-        super().__init__(  # type: ignore[call-arg]
-            variable_name=variable_name, optional=optional, **kwargs
-        )
+        super().__init__(variable_name=variable_name, optional=optional, **kwargs)
 
     def format_messages(self, **kwargs: Any) -> list[BaseMessage]:
         """Format messages from kwargs.