langchain-core 1.0.0a5__py3-none-any.whl → 1.0.0a7__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
+    !!! warning "Behavior changed in 0.3.25"
         Added ``scoped_full`` cleanup mode.
 
-    .. important::
+    !!! important
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -350,7 +352,7 @@ def index(
             metadata. Default is "sha1".
             Other 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 +369,7 @@ 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
@@ -462,13 +464,13 @@ 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 +494,7 @@ 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 +565,7 @@ 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 +593,7 @@ 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 +615,18 @@ 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 +639,10 @@ 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
+    !!! warning "Behavior changed in 0.3.25"
         Added ``scoped_full`` cleanup mode.
 
-    .. important::
+    !!! important
 
         * In full mode, the loader should be returning
           the entire dataset, and not just a subset of the dataset.
@@ -692,7 +693,7 @@ async def aindex(
             metadata. Default is "sha1".
             Other 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 +710,7 @@ 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
@@ -815,13 +816,13 @@ 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 +846,7 @@ 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 +918,7 @@ 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
 
@@ -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
 
 
@@ -270,8 +270,8 @@ 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.
 
@@ -307,8 +307,8 @@ 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.
 
@@ -352,10 +352,10 @@ 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.
 
@@ -388,10 +388,10 @@ 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.
 
@@ -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
@@ -564,7 +564,7 @@ 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!
@@ -581,7 +581,7 @@ class DocumentIndex(BaseRetriever):
         """
 
     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.
 

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:

langchain_core/language_models/_utils.py

@@ -3,10 +3,8 @@ from collections.abc import Sequence
 from typing import (
     TYPE_CHECKING,
     Literal,
-    Optional,
     TypedDict,
     TypeVar,
-    Union,
 )
 
 if TYPE_CHECKING:
@@ -17,7 +15,7 @@ from langchain_core.messages.content import (
 
 
 def is_openai_data_block(
-    block: dict, filter_: Union[Literal["image", "audio", "file"], None] = None
+    block: dict, filter_: Literal["image", "audio", "file"] | None = None
 ) -> bool:
     """Check whether a block contains multimodal data in OpenAI Chat Completions format.
 
@@ -88,7 +86,7 @@ class ParsedDataUri(TypedDict):
     mime_type: str
 
 
-def _parse_data_uri(uri: str) -> Optional[ParsedDataUri]:
+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.
@@ -142,13 +140,13 @@ def _normalize_messages(
             directly; this may change in the future
     - LangChain v0 standard content blocks for backward compatibility
 
-    .. versionchanged:: 1.0.0
+    !!! warning "Behavior changed in 1.0.0"
         In previous versions, this function returned messages in LangChain v0 format.
         Now, it returns messages in LangChain v1 format, which upgraded chat models now
         expect to receive when passing back in message history. For backward
         compatibility, this function will convert v0 message content to v1 format.
 
-    .. dropdown:: v0 Content Block Schemas
+    ??? note "v0 Content Block Schemas"
 
         ``URLContentBlock``:
 
@@ -304,7 +302,7 @@ def _ensure_message_copy(message: T, formatted_message: T) -> T:
 
 
 def _update_content_block(
-    formatted_message: "BaseMessage", idx: int, new_block: Union[ContentBlock, dict]
+    formatted_message: "BaseMessage", idx: int, new_block: ContentBlock | dict
 ) -> None:
     """Update a content block at the given index, handling type issues."""
     # Type ignore needed because: