langchain-core 0.3.79__py3-none-any.whl → 1.0.0__py3-none-any.whl

langchain_core/indexing/api.py

@@ -6,16 +6,20 @@ import hashlib
 import json
 import uuid
 import warnings
-from collections.abc import AsyncIterable, AsyncIterator, Iterable, Iterator, Sequence
+from collections.abc import (
+    AsyncIterable,
+    AsyncIterator,
+    Callable,
+    Iterable,
+    Iterator,
+    Sequence,
+)
 from itertools import islice
 from typing import (
     Any,
-    Callable,
     Literal,
-    Optional,
     TypedDict,
     TypeVar,
-    Union,
     cast,
 )
 
@@ -107,8 +111,8 @@ async def _abatch(size: int, iterable: AsyncIterable[T]) -> AsyncIterator[list[T
 
 
 def _get_source_id_assigner(
-    source_id_key: Union[str, Callable[[Document], str], None],
-) -> Callable[[Document], Union[str, None]]:
+    source_id_key: str | Callable[[Document], str] | None,
+) -> Callable[[Document], str | None]:
     """Get the source id from the document."""
     if source_id_key is None:
         return lambda _doc: None
@@ -162,9 +166,8 @@ def _calculate_hash(
 def _get_document_with_hash(
     document: Document,
     *,
-    key_encoder: Union[
-        Callable[[Document], str], Literal["sha1", "sha256", "sha512", "blake2b"]
-    ],
+    key_encoder: Callable[[Document], str]
+    | Literal["sha1", "sha256", "sha512", "blake2b"],
 ) -> Document:
     """Calculate a hash of the document, and assign it to the uid.
 
@@ -233,7 +236,7 @@ class _HashedDocument:
 
 
 def _delete(
-    vector_store: Union[VectorStore, DocumentIndex],
+    vector_store: VectorStore | DocumentIndex,
     ids: list[str],
 ) -> None:
     if isinstance(vector_store, VectorStore):
@@ -271,19 +274,18 @@ class IndexingResult(TypedDict):
 
 
 def index(
-    docs_source: Union[BaseLoader, Iterable[Document]],
+    docs_source: BaseLoader | Iterable[Document],
     record_manager: RecordManager,
-    vector_store: Union[VectorStore, DocumentIndex],
+    vector_store: VectorStore | DocumentIndex,
     *,
     batch_size: int = 100,
-    cleanup: Optional[Literal["incremental", "full", "scoped_full"]] = None,
-    source_id_key: Union[str, Callable[[Document], str], None] = None,
+    cleanup: Literal["incremental", "full", "scoped_full"] | None = None,
+    source_id_key: str | Callable[[Document], str] | None = None,
     cleanup_batch_size: int = 1_000,
     force_update: bool = False,
-    key_encoder: Union[
-        Literal["sha1", "sha256", "sha512", "blake2b"], Callable[[Document], str]
-    ] = "sha1",
-    upsert_kwargs: Optional[dict[str, Any]] = None,
+    key_encoder: Literal["sha1", "sha256", "sha512", "blake2b"]
+    | Callable[[Document], str] = "sha1",
+    upsert_kwargs: dict[str, Any] | None = None,
 ) -> IndexingResult:
     """Index data from the loader into the vector store.
 
@@ -296,10 +298,10 @@ def index(
     For the time being, documents are indexed using their hashes, and users
     are not able to specify the uid of the document.
 
-    .. versionchanged:: 0.3.25
-        Added ``scoped_full`` cleanup mode.
+    !!! warning "Behavior changed in 0.3.25"
+        Added `scoped_full` cleanup mode.
 
-    .. important::
+    !!! warning
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -313,7 +315,7 @@ def index(
           chunks, and we index them using a batch size of 5, we'll have 3 batches
           all with the same source id. In general, to avoid doing too much
           redundant work select as big a batch size as possible.
-        * The ``scoped_full`` mode is suitable if determining an appropriate batch size
+        * The `scoped_full` mode is suitable if determining an appropriate batch size
           is challenging or if your data loader cannot return the entire dataset at
           once. This mode keeps track of source IDs in memory, which should be fine
           for most use cases. If your dataset is large (10M+ docs), you will likely
@@ -324,8 +326,8 @@ def index(
         record_manager: Timestamped set to keep track of which documents were
             updated.
         vector_store: VectorStore or DocumentIndex to index the documents into.
-        batch_size: Batch size to use when indexing. Default is 100.
-        cleanup: How to handle clean up of documents. Default is None.
+        batch_size: Batch size to use when indexing.
+        cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
               that are associated with source ids that were seen during indexing.
@@ -340,17 +342,14 @@ def index(
               source ids that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
-            of the document. Default is None.
+            of the document.
         cleanup_batch_size: Batch size to use when cleaning up documents.
-            Default is 1_000.
         force_update: Force update documents even if they are present in the
             record manager. Useful if you are re-indexing with updated embeddings.
-            Default is False.
         key_encoder: Hashing algorithm to use for hashing the document content and
-            metadata. Default is "sha1".
-            Other options include "blake2b", "sha256", and "sha512".
+            metadata. Options include "blake2b", "sha256", and "sha512".
 
-            .. versionadded:: 0.3.66
+            !!! version-added "Added in version 0.3.66"
 
         key_encoder: Hashing algorithm to use for hashing the document.
             If not provided, a default encoder using SHA-1 will be used.
@@ -367,7 +366,7 @@ def index(
             method of the VectorStore or the upsert method of the DocumentIndex.
             For example, you can use this to specify a custom vector_field:
             upsert_kwargs={"vector_field": "embedding"}
-            .. versionadded:: 0.3.10
+            !!! version-added "Added in version 0.3.10"
 
     Returns:
         Indexing result which contains information about how many documents
@@ -379,8 +378,8 @@ def index(
         ValueError: If vectorstore does not have
             "delete" and "add_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If ``vectorstore`` is not a VectorStore or a DocumentIndex.
-        AssertionError: If ``source_id`` is None when cleanup mode is incremental.
+        TypeError: If `vectorstore` is not a VectorStore or a DocumentIndex.
+        AssertionError: If `source_id` is None when cleanup mode is incremental.
             (should be unreachable code).
     """
     # Behavior is deprecated, but we keep it for backwards compatibility.
@@ -462,13 +461,13 @@ def index(
         # Count documents removed by within-batch deduplication
         num_skipped += original_batch_size - len(hashed_docs)
 
-        source_ids: Sequence[Optional[str]] = [
+        source_ids: Sequence[str | None] = [
             source_id_assigner(hashed_doc) for hashed_doc in hashed_docs
         ]
 
         if cleanup in {"incremental", "scoped_full"}:
             # source ids are required.
-            for source_id, hashed_doc in zip(source_ids, hashed_docs):
+            for source_id, hashed_doc in zip(source_ids, hashed_docs, strict=False):
                 if source_id is None:
                     msg = (
                         f"Source ids are required when cleanup mode is "
@@ -492,7 +491,7 @@ def index(
         docs_to_index = []
         uids_to_refresh = []
         seen_docs: set[str] = set()
-        for hashed_doc, doc_exists in zip(hashed_docs, exists_batch):
+        for hashed_doc, doc_exists in zip(hashed_docs, exists_batch, strict=False):
             hashed_id = cast("str", hashed_doc.id)
             if doc_exists:
                 if force_update:
@@ -563,7 +562,7 @@ def index(
     if cleanup == "full" or (
         cleanup == "scoped_full" and scoped_full_cleanup_source_ids
     ):
-        delete_group_ids: Optional[Sequence[str]] = None
+        delete_group_ids: Sequence[str] | None = None
         if cleanup == "scoped_full":
             delete_group_ids = list(scoped_full_cleanup_source_ids)
         while uids_to_delete := record_manager.list_keys(
@@ -591,7 +590,7 @@ async def _to_async_iterator(iterator: Iterable[T]) -> AsyncIterator[T]:
 
 
 async def _adelete(
-    vector_store: Union[VectorStore, DocumentIndex],
+    vector_store: VectorStore | DocumentIndex,
     ids: list[str],
 ) -> None:
     if isinstance(vector_store, VectorStore):
@@ -613,19 +612,18 @@ async def _adelete(
 
 
 async def aindex(
-    docs_source: Union[BaseLoader, Iterable[Document], AsyncIterator[Document]],
+    docs_source: BaseLoader | Iterable[Document] | AsyncIterator[Document],
     record_manager: RecordManager,
-    vector_store: Union[VectorStore, DocumentIndex],
+    vector_store: VectorStore | DocumentIndex,
     *,
     batch_size: int = 100,
-    cleanup: Optional[Literal["incremental", "full", "scoped_full"]] = None,
-    source_id_key: Union[str, Callable[[Document], str], None] = None,
+    cleanup: Literal["incremental", "full", "scoped_full"] | None = None,
+    source_id_key: str | Callable[[Document], str] | None = None,
     cleanup_batch_size: int = 1_000,
     force_update: bool = False,
-    key_encoder: Union[
-        Literal["sha1", "sha256", "sha512", "blake2b"], Callable[[Document], str]
-    ] = "sha1",
-    upsert_kwargs: Optional[dict[str, Any]] = None,
+    key_encoder: Literal["sha1", "sha256", "sha512", "blake2b"]
+    | Callable[[Document], str] = "sha1",
+    upsert_kwargs: dict[str, Any] | None = None,
 ) -> IndexingResult:
     """Async index data from the loader into the vector store.
 
@@ -638,10 +636,10 @@ async def aindex(
     For the time being, documents are indexed using their hashes, and users
     are not able to specify the uid of the document.
 
-    .. versionchanged:: 0.3.25
-        Added ``scoped_full`` cleanup mode.
+    !!! warning "Behavior changed in 0.3.25"
+        Added `scoped_full` cleanup mode.
 
-    .. important::
+    !!! warning
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -655,7 +653,7 @@ async def aindex(
           chunks, and we index them using a batch size of 5, we'll have 3 batches
           all with the same source id. In general, to avoid doing too much
           redundant work select as big a batch size as possible.
-        * The ``scoped_full`` mode is suitable if determining an appropriate batch size
+        * The `scoped_full` mode is suitable if determining an appropriate batch size
           is challenging or if your data loader cannot return the entire dataset at
           once. This mode keeps track of source IDs in memory, which should be fine
           for most use cases. If your dataset is large (10M+ docs), you will likely
@@ -666,8 +664,8 @@ async def aindex(
         record_manager: Timestamped set to keep track of which documents were
             updated.
         vector_store: VectorStore or DocumentIndex to index the documents into.
-        batch_size: Batch size to use when indexing. Default is 100.
-        cleanup: How to handle clean up of documents. Default is None.
+        batch_size: Batch size to use when indexing.
+        cleanup: How to handle clean up of documents.
 
             - incremental: Cleans up all documents that haven't been updated AND
               that are associated with source ids that were seen during indexing.
@@ -682,17 +680,14 @@ async def aindex(
               source ids that were seen during indexing.
             - None: Do not delete any documents.
         source_id_key: Optional key that helps identify the original source
-            of the document. Default is None.
+            of the document.
         cleanup_batch_size: Batch size to use when cleaning up documents.
-            Default is 1_000.
         force_update: Force update documents even if they are present in the
             record manager. Useful if you are re-indexing with updated embeddings.
-            Default is False.
         key_encoder: Hashing algorithm to use for hashing the document content and
-            metadata. Default is "sha1".
-            Other options include "blake2b", "sha256", and "sha512".
+            metadata. Options include "blake2b", "sha256", and "sha512".
 
-            .. versionadded:: 0.3.66
+            !!! version-added "Added in version 0.3.66"
 
         key_encoder: Hashing algorithm to use for hashing the document.
             If not provided, a default encoder using SHA-1 will be used.
@@ -709,7 +704,7 @@ async def aindex(
             method of the VectorStore or the upsert method of the DocumentIndex.
             For example, you can use this to specify a custom vector_field:
             upsert_kwargs={"vector_field": "embedding"}
-            .. versionadded:: 0.3.10
+            !!! version-added "Added in version 0.3.10"
 
     Returns:
         Indexing result which contains information about how many documents
@@ -721,9 +716,9 @@ async def aindex(
         ValueError: If vectorstore does not have
             "adelete" and "aadd_documents" required methods.
         ValueError: If source_id_key is not None, but is not a string or callable.
-        TypeError: If ``vector_store`` is not a VectorStore or DocumentIndex.
-        AssertionError: If ``source_id_key`` is None when cleanup mode is
-            incremental or ``scoped_full`` (should be unreachable).
+        TypeError: If `vector_store` is not a VectorStore or DocumentIndex.
+        AssertionError: If `source_id_key` is None when cleanup mode is
+            incremental or `scoped_full` (should be unreachable).
     """
     # Behavior is deprecated, but we keep it for backwards compatibility.
     # # Warn only once per process.
@@ -815,13 +810,13 @@ async def aindex(
         # Count documents removed by within-batch deduplication
         num_skipped += original_batch_size - len(hashed_docs)
 
-        source_ids: Sequence[Optional[str]] = [
+        source_ids: Sequence[str | None] = [
             source_id_assigner(doc) for doc in hashed_docs
         ]
 
         if cleanup in {"incremental", "scoped_full"}:
             # If the cleanup mode is incremental, source ids are required.
-            for source_id, hashed_doc in zip(source_ids, hashed_docs):
+            for source_id, hashed_doc in zip(source_ids, hashed_docs, strict=False):
                 if source_id is None:
                     msg = (
                         f"Source ids are required when cleanup mode is "
@@ -845,7 +840,7 @@ async def aindex(
         docs_to_index: list[Document] = []
         uids_to_refresh = []
         seen_docs: set[str] = set()
-        for hashed_doc, doc_exists in zip(hashed_docs, exists_batch):
+        for hashed_doc, doc_exists in zip(hashed_docs, exists_batch, strict=False):
             hashed_id = cast("str", hashed_doc.id)
             if doc_exists:
                 if force_update:
@@ -917,7 +912,7 @@ async def aindex(
     if cleanup == "full" or (
         cleanup == "scoped_full" and scoped_full_cleanup_source_ids
     ):
-        delete_group_ids: Optional[Sequence[str]] = None
+        delete_group_ids: Sequence[str] | None = None
         if cleanup == "scoped_full":
             delete_group_ids = list(scoped_full_cleanup_source_ids)
         while uids_to_delete := await record_manager.alist_keys(

langchain_core/indexing/base.py

@@ -5,7 +5,7 @@ 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
 
@@ -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
 
@@ -100,8 +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.
 
@@ -128,8 +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.
 
@@ -177,10 +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.
 
@@ -198,10 +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.
 
@@ -233,7 +233,7 @@ class RecordManager(ABC):
 
 
 class _Record(TypedDict):
-    group_id: Optional[str]
+    group_id: str | None
     updated_at: float
 
 
@@ -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
@@ -270,18 +270,18 @@ 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:
         """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.
@@ -307,18 +307,18 @@ 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.
@@ -352,22 +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.
@@ -388,22 +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.
@@ -485,7 +485,7 @@ class DeleteResponse(TypedDict, total=False):
     failed: Sequence[str]
     """The IDs that failed to be deleted.
 
-    .. warning::
+    !!! warning
         Deleting an ID that does not exist is **NOT** considered a failure.
     """
 
@@ -509,7 +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
@@ -522,14 +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.
         """
@@ -545,14 +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.
         """
@@ -564,24 +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.
 
@@ -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/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)
@@ -60,7 +60,7 @@ class InMemoryDocumentIndex(DocumentIndex):
         return UpsertResponse(succeeded=ok_ids, failed=[])
 
     @override
-    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.
 
         Args: