langchain-core 1.0.0a8__py3-none-any.whl → 1.0.0rc2__py3-none-any.whl

langchain_core/indexing/base.py

@@ -61,7 +61,7 @@ class RecordManager(ABC):
         """Initialize the record manager.
 
         Args:
-            namespace (str): The namespace for the record manager.
+            namespace: The namespace for the record manager.
         """
         self.namespace = namespace
 
@@ -244,7 +244,7 @@ class InMemoryRecordManager(RecordManager):
         """Initialize the in-memory record manager.
 
         Args:
-            namespace (str): The namespace for the record manager.
+            namespace: The namespace for the record manager.
         """
         super().__init__(namespace)
         # Each key points to a dictionary
@@ -278,10 +278,10 @@ class InMemoryRecordManager(RecordManager):
         Args:
             keys: A list of record keys to upsert.
             group_ids: A list of group IDs corresponding to the keys.
-                Defaults to None.
+
             time_at_least: Optional timestamp. Implementation can use this
                 to optionally verify that the timestamp IS at least this time
-                in the system that stores. Defaults to None.
+                in the system that stores.
                 E.g., use to validate that the time in the postgres database
                 is equal to or larger than the given timestamp, if not
                 raise an error.
@@ -315,10 +315,10 @@ class InMemoryRecordManager(RecordManager):
         Args:
             keys: A list of record keys to upsert.
             group_ids: A list of group IDs corresponding to the keys.
-                Defaults to None.
+
             time_at_least: Optional timestamp. Implementation can use this
                 to optionally verify that the timestamp IS at least this time
-                in the system that stores. Defaults to None.
+                in the system that stores.
                 E.g., use to validate that the time in the postgres database
                 is equal to or larger than the given timestamp, if not
                 raise an error.
@@ -361,13 +361,13 @@ class InMemoryRecordManager(RecordManager):
 
         Args:
             before: Filter to list records updated before this time.
-                Defaults to None.
+
             after: Filter to list records updated after this time.
-                Defaults to None.
+
             group_ids: Filter to list records with specific group IDs.
-                Defaults to None.
+
             limit: optional limit on the number of records to return.
-                Defaults to None.
+
 
         Returns:
             A list of keys for the matching records.
@@ -397,13 +397,13 @@ class InMemoryRecordManager(RecordManager):
 
         Args:
             before: Filter to list records updated before this time.
-                Defaults to None.
+
             after: Filter to list records updated after this time.
-                Defaults to None.
+
             group_ids: Filter to list records with specific group IDs.
-                Defaults to None.
+
             limit: optional limit on the number of records to return.
-                Defaults to None.
+
 
         Returns:
             A list of keys for the matching records.
@@ -529,7 +529,7 @@ class DocumentIndex(BaseRetriever):
             **kwargs: Additional keyword arguments.
 
         Returns:
-            UpsertResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully added or updated in the vectorstore and the list of IDs that
             failed to be added or updated.
         """
@@ -552,7 +552,7 @@ class DocumentIndex(BaseRetriever):
             **kwargs: Additional keyword arguments.
 
         Returns:
-            UpsertResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully added or updated in the vectorstore and the list of IDs that
             failed to be added or updated.
         """
@@ -571,12 +571,12 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of ids to delete.
-            kwargs: Additional keyword arguments. This is up to the implementation.
+            **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index,
                 or else issue a non-blocking delete etc.
 
         Returns:
-            DeleteResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully deleted and the list of IDs that failed to be deleted.
         """
 
@@ -589,11 +589,11 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of ids to delete.
-            kwargs: Additional keyword arguments. This is up to the implementation.
+            **kwargs: Additional keyword arguments. This is up to the implementation.
                 For example, can include an option to delete the entire index.
 
         Returns:
-            DeleteResponse: A response object that contains the list of IDs that were
+            A response object that contains the list of IDs that were
             successfully deleted and the list of IDs that failed to be deleted.
         """
         return await run_in_executor(
@@ -624,10 +624,10 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of IDs to get.
-            kwargs: Additional keyword arguments. These are up to the implementation.
+            **kwargs: Additional keyword arguments. These are up to the implementation.
 
         Returns:
-            list[Document]: List of documents that were found.
+            List of documents that were found.
         """
 
     async def aget(
@@ -650,10 +650,10 @@ class DocumentIndex(BaseRetriever):
 
         Args:
             ids: List of IDs to get.
-            kwargs: Additional keyword arguments. These are up to the implementation.
+            **kwargs: Additional keyword arguments. These are up to the implementation.
 
         Returns:
-            list[Document]: List of documents that were found.
+            List of documents that were found.
         """
         return await run_in_executor(
             None,

langchain_core/language_models/__init__.py

@@ -1,45 +1,29 @@
 """Language models.
 
-**Language Model** is a type of model that can generate text or complete
-text prompts.
+LangChain has two main classes to work with language models: chat models and
+"old-fashioned" LLMs.
 
-LangChain has two main classes to work with language models: **Chat Models**
-and "old-fashioned" **LLMs**.
-
-**Chat Models**
+**Chat models**
 
 Language models that use a sequence of messages as inputs and return chat messages
-as outputs (as opposed to using plain text). These are traditionally newer models (
-older models are generally LLMs, see below). Chat models support the assignment of
+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.
 
 The key abstraction for chat models is `BaseChatModel`. Implementations
-should inherit from this class. Please see LangChain how-to guides with more
-information on how to implement a custom chat model.
-
-To implement a custom Chat Model, inherit from `BaseChatModel`. See
-the following guide for more information on how to implement a custom Chat Model:
+should inherit from this class.
 
-https://python.langchain.com/docs/how_to/custom_chat_model/
+See existing [chat model integrations](https://docs.langchain.com/oss/python/integrations/chat).
 
 **LLMs**
 
 Language models that takes a string as input and returns a string.
-These are traditionally older models (newer models generally are Chat Models,
-see below).
-
-Although the underlying models are string in, string out, the LangChain wrappers
-also allow these models to take messages as input. This gives them the same interface
-as Chat Models. When messages are passed in as input, they will be formatted into a
-string under the hood before being passed to the underlying model.
-
-To implement a custom LLM, inherit from `BaseLLM` or `LLM`.
-Please see the following guide for more information on how to implement a custom LLM:
-
-https://python.langchain.com/docs/how_to/custom_llm/
-
+These are traditionally older models (newer models generally are chat models).
 
+Although the underlying models are string in, string out, the LangChain wrappers also
+allow these models to take messages as input. This gives them the same interface as
+chat models. When messages are passed in as input, they will be formatted into a string
+under the hood before being passed to the underlying model.
 """
 
 from typing import TYPE_CHECKING

langchain_core/language_models/_utils.py

@@ -19,7 +19,7 @@ def is_openai_data_block(
 ) -> bool:
     """Check whether a block contains multimodal data in OpenAI Chat Completions format.
 
-    Supports both data and ID-style blocks (e.g. ``'file_data'`` and ``'file_id'``)
+    Supports both data and ID-style blocks (e.g. `'file_data'` and `'file_id'`)
 
     If additional keys are present, they are ignored / will not affect outcome as long
     as the required keys are present and valid.
@@ -30,12 +30,12 @@ def is_openai_data_block(
             - "image": Only match image_url blocks
             - "audio": Only match input_audio blocks
             - "file": Only match file blocks
-            If None, match any valid OpenAI data block type. Note that this means that
+            If `None`, match any valid OpenAI data block type. Note that this means that
             if the block has a valid OpenAI data type but the filter_ is set to a
             different type, this function will return False.
 
     Returns:
-        True if the block is a valid OpenAI data block and matches the filter_
+        `True` if the block is a valid OpenAI data block and matches the filter_
         (if provided).
 
     """
@@ -89,21 +89,20 @@ class ParsedDataUri(TypedDict):
 def _parse_data_uri(uri: str) -> ParsedDataUri | None:
     """Parse a data URI into its components.
 
-    If parsing fails, return None. If either MIME type or data is missing, return None.
+    If parsing fails, return `None`. If either MIME type or data is missing, return
+    `None`.
 
     Example:
-
-        .. code-block:: python
-
-            data_uri = "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
-            parsed = _parse_data_uri(data_uri)
-
-            assert parsed == {
-                "source_type": "base64",
-                "mime_type": "image/jpeg",
-                "data": "/9j/4AAQSkZJRg...",
-            }
-
+        ```python
+        data_uri = "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
+        parsed = _parse_data_uri(data_uri)
+
+        assert parsed == {
+            "source_type": "base64",
+            "mime_type": "image/jpeg",
+            "data": "/9j/4AAQSkZJRg...",
+        }
+        ```
     """
     regex = r"^data:(?P<mime_type>[^;]+);base64,(?P<data>.+)$"
     match = re.match(regex, uri)
@@ -133,8 +132,8 @@ def _normalize_messages(
     - LangChain v1 standard content blocks
 
     This function extends support to:
-    - `Audio <https://platform.openai.com/docs/api-reference/chat/create>`__ and
-        `file <https://platform.openai.com/docs/api-reference/files>`__ data in OpenAI
+    - `[Audio](https://platform.openai.com/docs/api-reference/chat/create) and
+        `[file](https://platform.openai.com/docs/api-reference/files) data in OpenAI
         Chat Completions format
         - Images are technically supported but we expect chat models to handle them
             directly; this may change in the future
@@ -148,50 +147,50 @@ def _normalize_messages(
 
     ??? note "v0 Content Block Schemas"
 
-        ``URLContentBlock``:
+        `URLContentBlock`:
 
-        .. codeblock::
-
-            {
-                mime_type: NotRequired[str]
-                type: Literal['image', 'audio', 'file'],
-                source_type: Literal['url'],
-                url: str,
-            }
-
-        ``Base64ContentBlock``:
+        ```python
+        {
+            mime_type: NotRequired[str]
+            type: Literal['image', 'audio', 'file'],
+            source_type: Literal['url'],
+            url: str,
+        }
+        ```
 
-        .. codeblock::
+        `Base64ContentBlock`:
 
-            {
-                mime_type: NotRequired[str]
-                type: Literal['image', 'audio', 'file'],
-                source_type: Literal['base64'],
-                data: str,
-            }
+        ```python
+        {
+            mime_type: NotRequired[str]
+            type: Literal['image', 'audio', 'file'],
+            source_type: Literal['base64'],
+            data: str,
+        }
+        ```
 
-        ``IDContentBlock``:
+        `IDContentBlock`:
 
         (In practice, this was never used)
 
-        .. codeblock::
-
-            {
-                type: Literal['image', 'audio', 'file'],
-                source_type: Literal['id'],
-                id: str,
-            }
-
-        ``PlainTextContentBlock``:
+        ```python
+        {
+            type: Literal["image", "audio", "file"],
+            source_type: Literal["id"],
+            id: str,
+        }
+        ```
 
-        .. codeblock::
+        `PlainTextContentBlock`:
 
-            {
-                mime_type: NotRequired[str]
-                type: Literal['file'],
-                source_type: Literal['text'],
-                url: str,
-            }
+        ```python
+        {
+            mime_type: NotRequired[str]
+            type: Literal['file'],
+            source_type: Literal['text'],
+            url: str,
+        }
+        ```
 
     If a v1 message is passed in, it will be returned as-is, meaning it is safe to
     always pass in v1 messages to this function for assurance.
@@ -222,7 +221,7 @@ def _normalize_messages(
         "type": Literal['file'],
         "file": Union[
             {
-                "filename": Optional[str] = "$FILENAME",
+                "filename": str | None = "$FILENAME",
                 "file_data": str = "$BASE64_ENCODED_FILE",
             },
             {

langchain_core/language_models/base.py

@@ -96,9 +96,16 @@ def _get_token_ids_default_method(text: str) -> list[int]:
 
 
 LanguageModelInput = PromptValue | str | Sequence[MessageLikeRepresentation]
+"""Input to a language model."""
+
 LanguageModelOutput = BaseMessage | str
+"""Output from a language model."""
+
 LanguageModelLike = Runnable[LanguageModelInput, LanguageModelOutput]
+"""Input/output interface for a language model."""
+
 LanguageModelOutputVar = TypeVar("LanguageModelOutputVar", AIMessage, str)
+"""Type variable for the output of a language model."""
 
 
 def _get_verbosity() -> bool:
@@ -110,20 +117,19 @@ 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: BaseCache | bool | None = Field(default=None, exclude=True)
     """Whether to cache the response.
 
-    * 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 `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.
 
     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."""
@@ -144,9 +150,9 @@ class BaseLanguageModel(
 
     @field_validator("verbose", mode="before")
     def set_verbose(cls, verbose: bool | None) -> bool:  # noqa: FBT001
-        """If verbose is None, set it.
+        """If verbose is `None`, set it.
 
-        This allows users to pass in None as verbose to access the global setting.
+        This allows users to pass in `None` as verbose to access the global setting.
 
         Args:
             verbose: The verbosity setting to use.
@@ -162,7 +168,7 @@ class BaseLanguageModel(
     @property
     @override
     def InputType(self) -> TypeAlias:
-        """Get the input type for this runnable."""
+        """Get the input type for this `Runnable`."""
         # This is a version of LanguageModelInput which replaces the abstract
         # base class BaseMessage with a union of its subclasses, which makes
         # for a much better schema.
@@ -186,12 +192,12 @@ class BaseLanguageModel(
         1. Take advantage of batched calls,
         2. Need more output from the model than just the top generated value,
         3. Are building chains that are agnostic to the underlying language model
-           type (e.g., pure text completion models vs chat models).
+            type (e.g., pure text completion models vs chat models).
 
         Args:
-            prompts: List of PromptValues. A PromptValue is an object that can be
-                converted to match the format of any language model (string for pure
-                text generation models and BaseMessages for chat models).
+            prompts: List of `PromptValue` objects. A `PromptValue` is an object that
+                can be converted to match the format of any language model (string for
+                pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
             callbacks: Callbacks to pass through. Used for executing additional
@@ -200,8 +206,8 @@ 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 `Generation` objects for
+            each input prompt and additional model provider-specific output.
 
         """
 
@@ -223,12 +229,12 @@ class BaseLanguageModel(
         1. Take advantage of batched calls,
         2. Need more output from the model than just the top generated value,
         3. Are building chains that are agnostic to the underlying language model
-           type (e.g., pure text completion models vs chat models).
+            type (e.g., pure text completion models vs chat models).
 
         Args:
-            prompts: List of PromptValues. A PromptValue is an object that can be
-                converted to match the format of any language model (string for pure
-                text generation models and BaseMessages for chat models).
+            prompts: List of `PromptValue` objects. A `PromptValue` is an object that
+                can be converted to match the format of any language model (string for
+                pure text generation models and `BaseMessage` objects for chat models).
             stop: Stop words to use when generating. Model output is cut off at the
                 first occurrence of any of these substrings.
             callbacks: Callbacks to pass through. Used for executing additional
@@ -237,8 +243,8 @@ 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 `Generation` objects for
+            each input prompt and additional model provider-specific output.
 
         """
 
@@ -294,13 +300,13 @@ 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
+            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
+                `BaseTool` objects to be converted to tool schemas.
 
         Returns:
             The sum of the number of tokens across the messages.