langchain-core 0.4.0.dev0__py3-none-any.whl → 1.0.0__py3-none-any.whl

langchain_core/indexing/base.py

@@ -5,7 +5,9 @@ from __future__ import annotations
 import abc
 import time
 from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Any, Optional, TypedDict
+from typing import TYPE_CHECKING, Any, TypedDict
+
+from typing_extensions import override
 
 from langchain_core._api import beta
 from langchain_core.retrievers import BaseRetriever
@@ -59,7 +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
 
@@ -98,8 +100,8 @@ class RecordManager(ABC):
         self,
         keys: Sequence[str],
         *,
-        group_ids: Optional[Sequence[Optional[str]]] = None,
-        time_at_least: Optional[float] = None,
+        group_ids: Sequence[str | None] | None = None,
+        time_at_least: float | None = None,
     ) -> None:
         """Upsert records into the database.
 
@@ -126,8 +128,8 @@ class RecordManager(ABC):
         self,
         keys: Sequence[str],
         *,
-        group_ids: Optional[Sequence[Optional[str]]] = None,
-        time_at_least: Optional[float] = None,
+        group_ids: Sequence[str | None] | None = None,
+        time_at_least: float | None = None,
     ) -> None:
         """Asynchronously upsert records into the database.
 
@@ -175,10 +177,10 @@ class RecordManager(ABC):
     def list_keys(
         self,
         *,
-        before: Optional[float] = None,
-        after: Optional[float] = None,
-        group_ids: Optional[Sequence[str]] = None,
-        limit: Optional[int] = None,
+        before: float | None = None,
+        after: float | None = None,
+        group_ids: Sequence[str] | None = None,
+        limit: int | None = None,
     ) -> list[str]:
         """List records in the database based on the provided filters.
 
@@ -196,10 +198,10 @@ class RecordManager(ABC):
     async def alist_keys(
         self,
         *,
-        before: Optional[float] = None,
-        after: Optional[float] = None,
-        group_ids: Optional[Sequence[str]] = None,
-        limit: Optional[int] = None,
+        before: float | None = None,
+        after: float | None = None,
+        group_ids: Sequence[str] | None = None,
+        limit: int | None = None,
     ) -> list[str]:
         """Asynchronously list records in the database based on the provided filters.
 
@@ -231,7 +233,7 @@ class RecordManager(ABC):
 
 
 class _Record(TypedDict):
-    group_id: Optional[str]
+    group_id: str | None
     updated_at: float
 
 
@@ -242,7 +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
@@ -254,32 +256,32 @@ class InMemoryRecordManager(RecordManager):
         """In-memory schema creation is simply ensuring the structure is initialized."""
 
     async def acreate_schema(self) -> None:
-        """Async in-memory schema creation is simply ensuring the structure is initialized."""  # noqa: E501
+        """In-memory schema creation is simply ensuring the structure is initialized."""
 
+    @override
     def get_time(self) -> float:
-        """Get the current server time as a high resolution timestamp!"""
         return time.time()
 
+    @override
     async def aget_time(self) -> float:
-        """Async get the current server time as a high resolution timestamp!"""
         return self.get_time()
 
     def update(
         self,
         keys: Sequence[str],
         *,
-        group_ids: Optional[Sequence[Optional[str]]] = None,
-        time_at_least: Optional[float] = None,
+        group_ids: Sequence[str | None] | None = None,
+        time_at_least: float | None = None,
     ) -> None:
         """Upsert records into the database.
 
         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.
@@ -305,28 +307,23 @@ class InMemoryRecordManager(RecordManager):
         self,
         keys: Sequence[str],
         *,
-        group_ids: Optional[Sequence[Optional[str]]] = None,
-        time_at_least: Optional[float] = None,
+        group_ids: Sequence[str | None] | None = None,
+        time_at_least: float | None = None,
     ) -> None:
         """Async upsert records into the database.
 
         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.
                 This is meant to help prevent time-drift issues since
                 time may not be monotonically increasing!
-
-        Raises:
-            ValueError: If the length of keys doesn't match the length of group
-                ids.
-            ValueError: If time_at_least is in the future.
         """
         self.update(keys, group_ids=group_ids, time_at_least=time_at_least)
 
@@ -355,22 +352,22 @@ class InMemoryRecordManager(RecordManager):
     def list_keys(
         self,
         *,
-        before: Optional[float] = None,
-        after: Optional[float] = None,
-        group_ids: Optional[Sequence[str]] = None,
-        limit: Optional[int] = None,
+        before: float | None = None,
+        after: float | None = None,
+        group_ids: Sequence[str] | None = None,
+        limit: int | None = None,
     ) -> list[str]:
         """List records in the database based on the provided filters.
 
         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.
@@ -391,22 +388,22 @@ class InMemoryRecordManager(RecordManager):
     async def alist_keys(
         self,
         *,
-        before: Optional[float] = None,
-        after: Optional[float] = None,
-        group_ids: Optional[Sequence[str]] = None,
-        limit: Optional[int] = None,
+        before: float | None = None,
+        after: float | None = None,
+        group_ids: Sequence[str] | None = None,
+        limit: int | None = None,
     ) -> list[str]:
         """Async list records in the database based on the provided filters.
 
         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.
@@ -488,8 +485,8 @@ class DeleteResponse(TypedDict, total=False):
     failed: Sequence[str]
     """The IDs that failed to be deleted.
 
-    Please note that deleting an ID that
-    does not exist is **NOT** considered a failure.
+    !!! warning
+        Deleting an ID that does not exist is **NOT** considered a failure.
     """
 
     num_failed: int
@@ -512,7 +509,7 @@ class DocumentIndex(BaseRetriever):
     2. Fetching document by ID.
     3. Searching for document using a query.
 
-    .. versionadded:: 0.2.29
+    !!! version-added "Added in version 0.2.29"
     """
 
     @abc.abstractmethod
@@ -525,14 +522,14 @@ class DocumentIndex(BaseRetriever):
 
         When an ID is specified and the content already exists in the vectorstore,
         the upsert method should update the content with the new data. If the content
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **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.
         """
@@ -548,14 +545,14 @@ class DocumentIndex(BaseRetriever):
 
         When an ID is specified and the item already exists in the vectorstore,
         the upsert method should update the item with the new data. If the item
-        does not exist, the upsert method should add the item to the vectorstore.
+        does not exist, the upsert method should add the item to the `VectorStore`.
 
         Args:
-            items: Sequence of documents to add to the vectorstore.
+            items: Sequence of documents to add to the `VectorStore`.
             **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.
         """
@@ -567,24 +564,24 @@ class DocumentIndex(BaseRetriever):
         )
 
     @abc.abstractmethod
-    def delete(self, ids: Optional[list[str]] = None, **kwargs: Any) -> DeleteResponse:
+    def delete(self, ids: list[str] | None = None, **kwargs: Any) -> DeleteResponse:
         """Delete by IDs or other criteria.
 
         Calling delete without any input parameters should raise a ValueError!
 
         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.
         """
 
     async def adelete(
-        self, ids: Optional[list[str]] = None, **kwargs: Any
+        self, ids: list[str] | None = None, **kwargs: Any
     ) -> DeleteResponse:
         """Delete by IDs or other criteria. Async variant.
 
@@ -592,11 +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(
@@ -627,10 +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(
@@ -653,10 +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/indexing/in_memory.py

@@ -3,7 +3,7 @@
 import operator
 import uuid
 from collections.abc import Sequence
-from typing import Any, Optional, cast
+from typing import Any, cast
 
 from pydantic import Field
 from typing_extensions import override
@@ -24,7 +24,7 @@ class InMemoryDocumentIndex(DocumentIndex):
     It provides a simple search API that returns documents by the number of
     counts the given query appears in the document.
 
-    .. versionadded:: 0.2.29
+    !!! version-added "Added in version 0.2.29"
     """
 
     store: dict[str, Document] = Field(default_factory=dict)
@@ -32,7 +32,17 @@ class InMemoryDocumentIndex(DocumentIndex):
 
     @override
     def upsert(self, items: Sequence[Document], /, **kwargs: Any) -> UpsertResponse:
-        """Upsert items into the index."""
+        """Upsert documents into the index.
+
+        Args:
+            items: Sequence of documents to add to the index.
+            **kwargs: Additional keyword arguments.
+
+        Returns:
+            A response object that contains the list of IDs that were
+            successfully added or updated in the index and the list of IDs that
+            failed to be added or updated.
+        """
         ok_ids = []
 
         for item in items:
@@ -50,8 +60,19 @@ class InMemoryDocumentIndex(DocumentIndex):
         return UpsertResponse(succeeded=ok_ids, failed=[])
 
     @override
-    def delete(self, ids: Optional[list[str]] = None, **kwargs: Any) -> DeleteResponse:
-        """Delete by ID."""
+    def delete(self, ids: list[str] | None = None, **kwargs: Any) -> DeleteResponse:
+        """Delete by IDs.
+
+        Args:
+            ids: List of ids to delete.
+
+        Raises:
+            ValueError: If ids is None.
+
+        Returns:
+            A response object that contains the list of IDs that were successfully
+            deleted and the list of IDs that failed to be deleted.
+        """
         if ids is None:
             msg = "IDs must be provided for deletion"
             raise ValueError(msg)
@@ -69,7 +90,6 @@ class InMemoryDocumentIndex(DocumentIndex):
 
     @override
     def get(self, ids: Sequence[str], /, **kwargs: Any) -> list[Document]:
-        """Get by ids."""
         return [self.store[id_] for id_ in ids if id_ in self.store]
 
     @override

langchain_core/language_models/__init__.py

@@ -1,49 +1,35 @@
 """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).
 
-"""  # noqa: E501
+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
 
 from langchain_core._import_utils import import_attr
+from langchain_core.language_models._utils import is_openai_data_block
 
 if TYPE_CHECKING:
     from langchain_core.language_models.base import (
@@ -84,6 +70,7 @@ __all__ = (
     "ParrotFakeChatModel",
     "SimpleChatModel",
     "get_tokenizer",
+    "is_openai_data_block",
 )
 
 _dynamic_imports = {
@@ -103,6 +90,7 @@ _dynamic_imports = {
     "ParrotFakeChatModel": "fake_chat_models",
     "LLM": "llms",
     "BaseLLM": "llms",
+    "is_openai_data_block": "_utils",
 }