langchain 0.3.22__py3-none-any.whl → 0.3.24__py3-none-any.whl

langchain/retrievers/document_compressors/listwise_rerank.py

@@ -1,6 +1,7 @@
 """Filter that uses an LLM to rerank documents listwise and select top-k."""
 
-from typing import Any, Dict, List, Optional, Sequence
+from collections.abc import Sequence
+from typing import Any, Optional
 
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
@@ -17,7 +18,7 @@ _DEFAULT_PROMPT = ChatPromptTemplate.from_messages(
 )
 
 
-def _get_prompt_input(input_: dict) -> Dict[str, Any]:
+def _get_prompt_input(input_: dict) -> dict[str, Any]:
     """Return the compression chain input."""
     documents = input_["documents"]
     context = ""
@@ -27,7 +28,7 @@ def _get_prompt_input(input_: dict) -> Dict[str, Any]:
     return {"query": input_["query"], "context": context}
 
 
-def _parse_ranking(results: dict) -> List[Document]:
+def _parse_ranking(results: dict) -> list[Document]:
     ranking = results["ranking"]
     docs = results["documents"]
     return [docs[i] for i in ranking.ranked_document_ids]
@@ -68,7 +69,7 @@ class LLMListwiseRerank(BaseDocumentCompressor):
             assert "Steve" in compressed_docs[0].page_content
     """
 
-    reranker: Runnable[Dict, List[Document]]
+    reranker: Runnable[dict, list[Document]]
     """LLM-based reranker to use for filtering documents. Expected to take in a dict 
         with 'documents: Sequence[Document]' and 'query: str' keys and output a 
         List[Document]."""
@@ -121,7 +122,7 @@ class LLMListwiseRerank(BaseDocumentCompressor):
             """Rank the documents by their relevance to the user question.
             Rank from most to least relevant."""
 
-            ranked_document_ids: List[int] = Field(
+            ranked_document_ids: list[int] = Field(
                 ...,
                 description=(
                     "The integer IDs of the documents, sorted from most to least "

langchain/retrievers/ensemble.py

@@ -5,15 +5,11 @@ multiple retrievers by using weighted  Reciprocal Rank Fusion
 
 import asyncio
 from collections import defaultdict
-from collections.abc import Hashable
+from collections.abc import Hashable, Iterable, Iterator
 from itertools import chain
 from typing import (
     Any,
     Callable,
-    Dict,
-    Iterable,
-    Iterator,
-    List,
     Optional,
     TypeVar,
     cast,
@@ -70,13 +66,13 @@ class EnsembleRetriever(BaseRetriever):
             If not specified, page_content is used.
     """
 
-    retrievers: List[RetrieverLike]
-    weights: List[float]
+    retrievers: list[RetrieverLike]
+    weights: list[float]
     c: int = 60
     id_key: Optional[str] = None
 
     @property
-    def config_specs(self) -> List[ConfigurableFieldSpec]:
+    def config_specs(self) -> list[ConfigurableFieldSpec]:
         """List configurable fields for this runnable."""
         return get_unique_config_specs(
             spec for retriever in self.retrievers for spec in retriever.config_specs
@@ -84,7 +80,7 @@ class EnsembleRetriever(BaseRetriever):
 
     @model_validator(mode="before")
     @classmethod
-    def set_weights(cls, values: Dict[str, Any]) -> Any:
+    def set_weights(cls, values: dict[str, Any]) -> Any:
         if not values.get("weights"):
             n_retrievers = len(values["retrievers"])
             values["weights"] = [1 / n_retrievers] * n_retrievers
@@ -92,7 +88,7 @@ class EnsembleRetriever(BaseRetriever):
 
     def invoke(
         self, input: str, config: Optional[RunnableConfig] = None, **kwargs: Any
-    ) -> List[Document]:
+    ) -> list[Document]:
         from langchain_core.callbacks import CallbackManager
 
         config = ensure_config(config)
@@ -125,7 +121,7 @@ class EnsembleRetriever(BaseRetriever):
 
     async def ainvoke(
         self, input: str, config: Optional[RunnableConfig] = None, **kwargs: Any
-    ) -> List[Document]:
+    ) -> list[Document]:
         from langchain_core.callbacks import AsyncCallbackManager
 
         config = ensure_config(config)
@@ -163,7 +159,7 @@ class EnsembleRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Get the relevant documents for a given query.
 
@@ -184,7 +180,7 @@ class EnsembleRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: AsyncCallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Asynchronously get the relevant documents for a given query.
 
@@ -206,7 +202,7 @@ class EnsembleRetriever(BaseRetriever):
         run_manager: CallbackManagerForRetrieverRun,
         *,
         config: Optional[RunnableConfig] = None,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Retrieve the results of the retrievers and use rank_fusion_func to get
         the final result.
@@ -247,7 +243,7 @@ class EnsembleRetriever(BaseRetriever):
         run_manager: AsyncCallbackManagerForRetrieverRun,
         *,
         config: Optional[RunnableConfig] = None,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Asynchronously retrieve the results of the retrievers
         and use rank_fusion_func to get the final result.
@@ -276,7 +272,7 @@ class EnsembleRetriever(BaseRetriever):
         # Enforce that retrieved docs are Documents for each list in retriever_docs
         for i in range(len(retriever_docs)):
             retriever_docs[i] = [
-                Document(page_content=doc) if not isinstance(doc, Document) else doc  # type: ignore[arg-type]
+                Document(page_content=doc) if not isinstance(doc, Document) else doc
                 for doc in retriever_docs[i]
             ]
 
@@ -286,8 +282,8 @@ class EnsembleRetriever(BaseRetriever):
         return fused_documents
 
     def weighted_reciprocal_rank(
-        self, doc_lists: List[List[Document]]
-    ) -> List[Document]:
+        self, doc_lists: list[list[Document]]
+    ) -> list[Document]:
         """
         Perform weighted Reciprocal Rank Fusion on multiple rank lists.
         You can find more details about RRF here:
@@ -307,7 +303,7 @@ class EnsembleRetriever(BaseRetriever):
 
         # Associate each doc's content with its RRF score for later sorting by it
         # Duplicated contents across retrievers are collapsed & scored cumulatively
-        rrf_score: Dict[str, float] = defaultdict(float)
+        rrf_score: dict[str, float] = defaultdict(float)
         for doc_list, weight in zip(doc_lists, self.weights):
             for rank, doc in enumerate(doc_list, start=1):
                 rrf_score[

langchain/retrievers/merger_retriever.py

@@ -1,5 +1,4 @@
 import asyncio
-from typing import List
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForRetrieverRun,
@@ -12,7 +11,7 @@ from langchain_core.retrievers import BaseRetriever
 class MergerRetriever(BaseRetriever):
     """Retriever that merges the results of multiple retrievers."""
 
-    retrievers: List[BaseRetriever]
+    retrievers: list[BaseRetriever]
     """A list of retrievers to merge."""
 
     def _get_relevant_documents(
@@ -20,7 +19,7 @@ class MergerRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Get the relevant documents for a given query.
 
@@ -41,7 +40,7 @@ class MergerRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: AsyncCallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Asynchronously get the relevant documents for a given query.
 
@@ -59,7 +58,7 @@ class MergerRetriever(BaseRetriever):
 
     def merge_documents(
         self, query: str, run_manager: CallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Merge the results of the retrievers.
 
@@ -74,9 +73,7 @@ class MergerRetriever(BaseRetriever):
         retriever_docs = [
             retriever.invoke(
                 query,
-                config={
-                    "callbacks": run_manager.get_child("retriever_{}".format(i + 1))
-                },
+                config={"callbacks": run_manager.get_child(f"retriever_{i + 1}")},
             )
             for i, retriever in enumerate(self.retrievers)
         ]
@@ -93,7 +90,7 @@ class MergerRetriever(BaseRetriever):
 
     async def amerge_documents(
         self, query: str, run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """
         Asynchronously merge the results of the retrievers.
 
@@ -109,9 +106,7 @@ class MergerRetriever(BaseRetriever):
             *(
                 retriever.ainvoke(
                     query,
-                    config={
-                        "callbacks": run_manager.get_child("retriever_{}".format(i + 1))
-                    },
+                    config={"callbacks": run_manager.get_child(f"retriever_{i + 1}")},
                 )
                 for i, retriever in enumerate(self.retrievers)
             )

langchain/retrievers/multi_query.py

@@ -1,6 +1,7 @@
 import asyncio
 import logging
-from typing import List, Optional, Sequence
+from collections.abc import Sequence
+from typing import Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForRetrieverRun,
@@ -19,10 +20,10 @@ from langchain.chains.llm import LLMChain
 logger = logging.getLogger(__name__)
 
 
-class LineListOutputParser(BaseOutputParser[List[str]]):
+class LineListOutputParser(BaseOutputParser[list[str]]):
     """Output parser for a list of lines."""
 
-    def parse(self, text: str) -> List[str]:
+    def parse(self, text: str) -> list[str]:
         lines = text.strip().split("\n")
         return list(filter(None, lines))  # Remove empty lines
 
@@ -40,7 +41,7 @@ DEFAULT_QUERY_PROMPT = PromptTemplate(
 )
 
 
-def _unique_documents(documents: Sequence[Document]) -> List[Document]:
+def _unique_documents(documents: Sequence[Document]) -> list[Document]:
     return [doc for i, doc in enumerate(documents) if doc not in documents[:i]]
 
 
@@ -93,7 +94,7 @@ class MultiQueryRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: AsyncCallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get relevant documents given a user query.
 
         Args:
@@ -110,7 +111,7 @@ class MultiQueryRetriever(BaseRetriever):
 
     async def agenerate_queries(
         self, question: str, run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[str]:
+    ) -> list[str]:
         """Generate queries based upon user input.
 
         Args:
@@ -131,8 +132,8 @@ class MultiQueryRetriever(BaseRetriever):
         return lines
 
     async def aretrieve_documents(
-        self, queries: List[str], run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[Document]:
+        self, queries: list[str], run_manager: AsyncCallbackManagerForRetrieverRun
+    ) -> list[Document]:
         """Run all LLM generated queries.
 
         Args:
@@ -156,7 +157,7 @@ class MultiQueryRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get relevant documents given a user query.
 
         Args:
@@ -173,7 +174,7 @@ class MultiQueryRetriever(BaseRetriever):
 
     def generate_queries(
         self, question: str, run_manager: CallbackManagerForRetrieverRun
-    ) -> List[str]:
+    ) -> list[str]:
         """Generate queries based upon user input.
 
         Args:
@@ -194,8 +195,8 @@ class MultiQueryRetriever(BaseRetriever):
         return lines
 
     def retrieve_documents(
-        self, queries: List[str], run_manager: CallbackManagerForRetrieverRun
-    ) -> List[Document]:
+        self, queries: list[str], run_manager: CallbackManagerForRetrieverRun
+    ) -> list[Document]:
         """Run all LLM generated queries.
 
         Args:
@@ -212,7 +213,7 @@ class MultiQueryRetriever(BaseRetriever):
             documents.extend(docs)
         return documents
 
-    def unique_union(self, documents: List[Document]) -> List[Document]:
+    def unique_union(self, documents: list[Document]) -> list[Document]:
         """Get unique Documents.
 
         Args:

langchain/retrievers/multi_vector.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForRetrieverRun,
@@ -43,7 +43,7 @@ class MultiVectorRetriever(BaseRetriever):
 
     @model_validator(mode="before")
     @classmethod
-    def shim_docstore(cls, values: Dict) -> Any:
+    def shim_docstore(cls, values: dict) -> Any:
         byte_store = values.get("byte_store")
         docstore = values.get("docstore")
         if byte_store is not None:
@@ -55,7 +55,7 @@ class MultiVectorRetriever(BaseRetriever):
 
     def _get_relevant_documents(
         self, query: str, *, run_manager: CallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get documents relevant to a query.
         Args:
             query: String to find relevant documents for
@@ -87,7 +87,7 @@ class MultiVectorRetriever(BaseRetriever):
 
     async def _aget_relevant_documents(
         self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Asynchronously get documents relevant to a query.
         Args:
             query: String to find relevant documents for

langchain/retrievers/parent_document_retriever.py

@@ -1,5 +1,6 @@
 import uuid
-from typing import Any, List, Optional, Sequence, Tuple
+from collections.abc import Sequence
+from typing import Any, Optional
 
 from langchain_core.documents import Document
 from langchain_text_splitters import TextSplitter
@@ -71,10 +72,10 @@ class ParentDocumentRetriever(MultiVectorRetriever):
 
     def _split_docs_for_adding(
         self,
-        documents: List[Document],
-        ids: Optional[List[str]] = None,
+        documents: list[Document],
+        ids: Optional[list[str]] = None,
         add_to_docstore: bool = True,
-    ) -> Tuple[List[Document], List[Tuple[str, Document]]]:
+    ) -> tuple[list[Document], list[tuple[str, Document]]]:
         if self.parent_splitter is not None:
             documents = self.parent_splitter.split_documents(documents)
         if ids is None:
@@ -110,8 +111,8 @@ class ParentDocumentRetriever(MultiVectorRetriever):
 
     def add_documents(
         self,
-        documents: List[Document],
-        ids: Optional[List[str]] = None,
+        documents: list[Document],
+        ids: Optional[list[str]] = None,
         add_to_docstore: bool = True,
         **kwargs: Any,
     ) -> None:
@@ -136,8 +137,8 @@ class ParentDocumentRetriever(MultiVectorRetriever):
 
     async def aadd_documents(
         self,
-        documents: List[Document],
-        ids: Optional[List[str]] = None,
+        documents: list[Document],
+        ids: Optional[list[str]] = None,
         add_to_docstore: bool = True,
         **kwargs: Any,
     ) -> None:

langchain/retrievers/re_phraser.py

@@ -1,5 +1,4 @@
 import logging
-from typing import List
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForRetrieverRun,
@@ -62,7 +61,7 @@ class RePhraseQueryRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get relevant documents given a user question.
 
         Args:
@@ -85,5 +84,5 @@ class RePhraseQueryRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: AsyncCallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         raise NotImplementedError

langchain/retrievers/self_query/base.py

@@ -1,7 +1,8 @@
 """Retriever that generates and executes structured queries over its own data source."""
 
 import logging
-from typing import Any, Dict, List, Optional, Sequence, Tuple, Type, Union
+from collections.abc import Sequence
+from typing import Any, Optional, Union
 
 from langchain_core.callbacks.manager import (
     AsyncCallbackManagerForRetrieverRun,
@@ -95,7 +96,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
         Pinecone as CommunityPinecone,
     )
 
-    BUILTIN_TRANSLATORS: Dict[Type[VectorStore], Type[Visitor]] = {
+    BUILTIN_TRANSLATORS: dict[type[VectorStore], type[Visitor]] = {
         AstraDB: AstraDBTranslator,
         PGVector: PGVectorTranslator,
         CommunityPinecone: PineconeTranslator,
@@ -179,7 +180,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
                 return ChromaTranslator()
 
         try:
-            from langchain_postgres import PGVector  # type: ignore[no-redef]
+            from langchain_postgres import PGVector
             from langchain_postgres import PGVectorTranslator as NewPGVectorTranslator
         except ImportError:
             pass
@@ -249,7 +250,7 @@ class SelfQueryRetriever(BaseRetriever):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_translator(cls, values: Dict) -> Any:
+    def validate_translator(cls, values: dict) -> Any:
         """Validate translator."""
         if "structured_query_translator" not in values:
             values["structured_query_translator"] = _get_builtin_translator(
@@ -264,7 +265,7 @@ class SelfQueryRetriever(BaseRetriever):
 
     def _prepare_query(
         self, query: str, structured_query: StructuredQuery
-    ) -> Tuple[str, Dict[str, Any]]:
+    ) -> tuple[str, dict[str, Any]]:
         new_query, new_kwargs = self.structured_query_translator.visit_structured_query(
             structured_query
         )
@@ -276,20 +277,20 @@ class SelfQueryRetriever(BaseRetriever):
         return new_query, search_kwargs
 
     def _get_docs_with_query(
-        self, query: str, search_kwargs: Dict[str, Any]
-    ) -> List[Document]:
+        self, query: str, search_kwargs: dict[str, Any]
+    ) -> list[Document]:
         docs = self.vectorstore.search(query, self.search_type, **search_kwargs)
         return docs
 
     async def _aget_docs_with_query(
-        self, query: str, search_kwargs: Dict[str, Any]
-    ) -> List[Document]:
+        self, query: str, search_kwargs: dict[str, Any]
+    ) -> list[Document]:
         docs = await self.vectorstore.asearch(query, self.search_type, **search_kwargs)
         return docs
 
     def _get_relevant_documents(
         self, query: str, *, run_manager: CallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get documents relevant for a query.
 
         Args:
@@ -309,7 +310,7 @@ class SelfQueryRetriever(BaseRetriever):
 
     async def _aget_relevant_documents(
         self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get documents relevant for a query.
 
         Args:
@@ -335,7 +336,7 @@ class SelfQueryRetriever(BaseRetriever):
         document_contents: str,
         metadata_field_info: Sequence[Union[AttributeInfo, dict]],
         structured_query_translator: Optional[Visitor] = None,
-        chain_kwargs: Optional[Dict] = None,
+        chain_kwargs: Optional[dict] = None,
         enable_limit: bool = False,
         use_original_query: bool = False,
         **kwargs: Any,

langchain/retrievers/time_weighted_retriever.py

@@ -1,6 +1,6 @@
 import datetime
 from copy import deepcopy
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForRetrieverRun,
@@ -28,7 +28,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
     """Keyword arguments to pass to the vectorstore similarity search."""
 
     # TODO: abstract as a queue
-    memory_stream: List[Document] = Field(default_factory=list)
+    memory_stream: list[Document] = Field(default_factory=list)
     """The memory_stream of documents to search through."""
 
     decay_rate: float = Field(default=0.01)
@@ -37,7 +37,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
     k: int = 4
     """The maximum number of documents to retrieve in a given call."""
 
-    other_score_keys: List[str] = []
+    other_score_keys: list[str] = []
     """Other keys in the metadata to factor into the score, e.g. 'importance'."""
 
     default_salience: Optional[float] = None
@@ -77,9 +77,9 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
             score += vector_relevance
         return score
 
-    def get_salient_docs(self, query: str) -> Dict[int, Tuple[Document, float]]:
+    def get_salient_docs(self, query: str) -> dict[int, tuple[Document, float]]:
         """Return documents that are salient to the query."""
-        docs_and_scores: List[Tuple[Document, float]]
+        docs_and_scores: list[tuple[Document, float]]
         docs_and_scores = self.vectorstore.similarity_search_with_relevance_scores(
             query, **self.search_kwargs
         )
@@ -91,9 +91,9 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
                 results[buffer_idx] = (doc, relevance)
         return results
 
-    async def aget_salient_docs(self, query: str) -> Dict[int, Tuple[Document, float]]:
+    async def aget_salient_docs(self, query: str) -> dict[int, tuple[Document, float]]:
         """Return documents that are salient to the query."""
-        docs_and_scores: List[Tuple[Document, float]]
+        docs_and_scores: list[tuple[Document, float]]
         docs_and_scores = (
             await self.vectorstore.asimilarity_search_with_relevance_scores(
                 query, **self.search_kwargs
@@ -108,8 +108,8 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
         return results
 
     def _get_rescored_docs(
-        self, docs_and_scores: Dict[Any, Tuple[Document, Optional[float]]]
-    ) -> List[Document]:
+        self, docs_and_scores: dict[Any, tuple[Document, Optional[float]]]
+    ) -> list[Document]:
         current_time = datetime.datetime.now()
         rescored_docs = [
             (doc, self._get_combined_score(doc, relevance, current_time))
@@ -127,7 +127,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
 
     def _get_relevant_documents(
         self, query: str, *, run_manager: CallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         docs_and_scores = {
             doc.metadata["buffer_idx"]: (doc, self.default_salience)
             for doc in self.memory_stream[-self.k :]
@@ -138,7 +138,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
 
     async def _aget_relevant_documents(
         self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
-    ) -> List[Document]:
+    ) -> list[Document]:
         docs_and_scores = {
             doc.metadata["buffer_idx"]: (doc, self.default_salience)
             for doc in self.memory_stream[-self.k :]
@@ -147,7 +147,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
         docs_and_scores.update(await self.aget_salient_docs(query))
         return self._get_rescored_docs(docs_and_scores)
 
-    def add_documents(self, documents: List[Document], **kwargs: Any) -> List[str]:
+    def add_documents(self, documents: list[Document], **kwargs: Any) -> list[str]:
         """Add documents to vectorstore."""
         current_time = kwargs.get("current_time")
         if current_time is None:
@@ -164,8 +164,8 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
         return self.vectorstore.add_documents(dup_docs, **kwargs)
 
     async def aadd_documents(
-        self, documents: List[Document], **kwargs: Any
-    ) -> List[str]:
+        self, documents: list[Document], **kwargs: Any
+    ) -> list[str]:
         """Add documents to vectorstore."""
         current_time = kwargs.get("current_time")
         if current_time is None:

langchain/runnables/openai_functions.py

@@ -1,5 +1,6 @@
+from collections.abc import Mapping
 from operator import itemgetter
-from typing import Any, Callable, List, Mapping, Optional, Union
+from typing import Any, Callable, Optional, Union
 
 from langchain_core.messages import BaseMessage
 from langchain_core.output_parsers.openai_functions import JsonOutputFunctionsParser
@@ -22,7 +23,7 @@ class OpenAIFunction(TypedDict):
 class OpenAIFunctionsRouter(RunnableBindingBase[BaseMessage, Any]):
     """A runnable that routes to the selected function."""
 
-    functions: Optional[List[OpenAIFunction]]
+    functions: Optional[list[OpenAIFunction]]
 
     def __init__(
         self,
@@ -33,7 +34,7 @@ class OpenAIFunctionsRouter(RunnableBindingBase[BaseMessage, Any]):
                 Callable[[dict], Any],
             ],
         ],
-        functions: Optional[List[OpenAIFunction]] = None,
+        functions: Optional[list[OpenAIFunction]] = None,
     ):
         if functions is not None:
             assert len(functions) == len(runnables)