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

langchain/chains/combine_documents/map_rerank.py

@@ -2,7 +2,8 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict, List, Optional, Sequence, Tuple, Type, Union, cast
+from collections.abc import Sequence
+from typing import Any, Optional, Union, cast
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import Callbacks
@@ -79,7 +80,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
     """Key in output of llm_chain to rank on."""
     answer_key: str
     """Key in output of llm_chain to return as answer."""
-    metadata_keys: Optional[List[str]] = None
+    metadata_keys: Optional[list[str]] = None
     """Additional metadata from the chosen document to return."""
     return_intermediate_steps: bool = False
     """Return intermediate steps.
@@ -92,19 +93,19 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
 
     def get_output_schema(
         self, config: Optional[RunnableConfig] = None
-    ) -> Type[BaseModel]:
-        schema: Dict[str, Any] = {
+    ) -> type[BaseModel]:
+        schema: dict[str, Any] = {
             self.output_key: (str, None),
         }
         if self.return_intermediate_steps:
-            schema["intermediate_steps"] = (List[str], None)
+            schema["intermediate_steps"] = (list[str], None)
         if self.metadata_keys:
             schema.update({key: (Any, None) for key in self.metadata_keys})
 
         return create_model("MapRerankOutput", **schema)
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Expect input key.
 
         :meta private:
@@ -140,7 +141,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
 
     @model_validator(mode="before")
     @classmethod
-    def get_default_document_variable_name(cls, values: Dict) -> Any:
+    def get_default_document_variable_name(cls, values: dict) -> Any:
         """Get default document variable name, if not provided."""
         if "llm_chain" not in values:
             raise ValueError("llm_chain must be provided")
@@ -163,8 +164,8 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
         return values
 
     def combine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Combine documents in a map rerank manner.
 
         Combine by mapping first chain over all documents, then reranking the results.
@@ -187,8 +188,8 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
         return self._process_results(docs, results)
 
     async def acombine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Combine documents in a map rerank manner.
 
         Combine by mapping first chain over all documents, then reranking the results.
@@ -212,10 +213,10 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
 
     def _process_results(
         self,
-        docs: List[Document],
-        results: Sequence[Union[str, List[str], Dict[str, str]]],
-    ) -> Tuple[str, dict]:
-        typed_results = cast(List[dict], results)
+        docs: list[Document],
+        results: Sequence[Union[str, list[str], dict[str, str]]],
+    ) -> tuple[str, dict]:
+        typed_results = cast(list[dict], results)
         sorted_res = sorted(
             zip(typed_results, docs), key=lambda x: -int(x[0][self.rank_key])
         )

langchain/chains/combine_documents/reduce.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Any, Callable, List, Optional, Protocol, Tuple
+from typing import Any, Callable, Optional, Protocol
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import Callbacks
@@ -15,20 +15,20 @@ from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
 class CombineDocsProtocol(Protocol):
     """Interface for the combine_docs method."""
 
-    def __call__(self, docs: List[Document], **kwargs: Any) -> str:
+    def __call__(self, docs: list[Document], **kwargs: Any) -> str:
         """Interface for the combine_docs method."""
 
 
 class AsyncCombineDocsProtocol(Protocol):
     """Interface for the combine_docs method."""
 
-    async def __call__(self, docs: List[Document], **kwargs: Any) -> str:
+    async def __call__(self, docs: list[Document], **kwargs: Any) -> str:
         """Async interface for the combine_docs method."""
 
 
 def split_list_of_docs(
-    docs: List[Document], length_func: Callable, token_max: int, **kwargs: Any
-) -> List[List[Document]]:
+    docs: list[Document], length_func: Callable, token_max: int, **kwargs: Any
+) -> list[list[Document]]:
     """Split Documents into subsets that each meet a cumulative length constraint.
 
     Args:
@@ -59,7 +59,7 @@ def split_list_of_docs(
 
 
 def collapse_docs(
-    docs: List[Document],
+    docs: list[Document],
     combine_document_func: CombineDocsProtocol,
     **kwargs: Any,
 ) -> Document:
@@ -91,7 +91,7 @@ def collapse_docs(
 
 
 async def acollapse_docs(
-    docs: List[Document],
+    docs: list[Document],
     combine_document_func: AsyncCombineDocsProtocol,
     **kwargs: Any,
 ) -> Document:
@@ -229,11 +229,11 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
 
     def combine_docs(
         self,
-        docs: List[Document],
+        docs: list[Document],
         token_max: Optional[int] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
-    ) -> Tuple[str, dict]:
+    ) -> tuple[str, dict]:
         """Combine multiple documents recursively.
 
         Args:
@@ -258,11 +258,11 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
 
     async def acombine_docs(
         self,
-        docs: List[Document],
+        docs: list[Document],
         token_max: Optional[int] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
-    ) -> Tuple[str, dict]:
+    ) -> tuple[str, dict]:
         """Async combine multiple documents recursively.
 
         Args:
@@ -287,16 +287,16 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
 
     def _collapse(
         self,
-        docs: List[Document],
+        docs: list[Document],
         token_max: Optional[int] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
-    ) -> Tuple[List[Document], dict]:
+    ) -> tuple[list[Document], dict]:
         result_docs = docs
         length_func = self.combine_documents_chain.prompt_length
         num_tokens = length_func(result_docs, **kwargs)
 
-        def _collapse_docs_func(docs: List[Document], **kwargs: Any) -> str:
+        def _collapse_docs_func(docs: list[Document], **kwargs: Any) -> str:
             return self._collapse_chain.run(
                 input_documents=docs, callbacks=callbacks, **kwargs
             )
@@ -322,16 +322,16 @@ class ReduceDocumentsChain(BaseCombineDocumentsChain):
 
     async def _acollapse(
         self,
-        docs: List[Document],
+        docs: list[Document],
         token_max: Optional[int] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
-    ) -> Tuple[List[Document], dict]:
+    ) -> tuple[list[Document], dict]:
         result_docs = docs
         length_func = self.combine_documents_chain.prompt_length
         num_tokens = length_func(result_docs, **kwargs)
 
-        async def _collapse_docs_func(docs: List[Document], **kwargs: Any) -> str:
+        async def _collapse_docs_func(docs: list[Document], **kwargs: Any) -> str:
             return await self._collapse_chain.arun(
                 input_documents=docs, callbacks=callbacks, **kwargs
             )

langchain/chains/combine_documents/refine.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict, List, Tuple
+from typing import Any
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import Callbacks
@@ -98,7 +98,7 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
     """Return the results of the refine steps in the output."""
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Expect input key.
 
         :meta private:
@@ -115,7 +115,7 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
 
     @model_validator(mode="before")
     @classmethod
-    def get_return_intermediate_steps(cls, values: Dict) -> Any:
+    def get_return_intermediate_steps(cls, values: dict) -> Any:
         """For backwards compatibility."""
         if "return_refine_steps" in values:
             values["return_intermediate_steps"] = values["return_refine_steps"]
@@ -124,7 +124,7 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
 
     @model_validator(mode="before")
     @classmethod
-    def get_default_document_variable_name(cls, values: Dict) -> Any:
+    def get_default_document_variable_name(cls, values: dict) -> Any:
         """Get default document variable name, if not provided."""
         if "initial_llm_chain" not in values:
             raise ValueError("initial_llm_chain must be provided")
@@ -147,8 +147,8 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
         return values
 
     def combine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Combine by mapping first chain over all, then stuffing into final chain.
 
         Args:
@@ -172,8 +172,8 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
         return self._construct_result(refine_steps, res)
 
     async def acombine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Async combine by mapping a first chain over all, then stuffing
          into a final chain.
 
@@ -197,22 +197,22 @@ class RefineDocumentsChain(BaseCombineDocumentsChain):
             refine_steps.append(res)
         return self._construct_result(refine_steps, res)
 
-    def _construct_result(self, refine_steps: List[str], res: str) -> Tuple[str, dict]:
+    def _construct_result(self, refine_steps: list[str], res: str) -> tuple[str, dict]:
         if self.return_intermediate_steps:
             extra_return_dict = {"intermediate_steps": refine_steps}
         else:
             extra_return_dict = {}
         return res, extra_return_dict
 
-    def _construct_refine_inputs(self, doc: Document, res: str) -> Dict[str, Any]:
+    def _construct_refine_inputs(self, doc: Document, res: str) -> dict[str, Any]:
         return {
             self.document_variable_name: format_document(doc, self.document_prompt),
             self.initial_response_name: res,
         }
 
     def _construct_initial_inputs(
-        self, docs: List[Document], **kwargs: Any
-    ) -> Dict[str, Any]:
+        self, docs: list[Document], **kwargs: Any
+    ) -> dict[str, Any]:
         base_info = {"page_content": docs[0].page_content}
         base_info.update(docs[0].metadata)
         document_info = {k: base_info[k] for k in self.document_prompt.input_variables}

langchain/chains/combine_documents/stuff.py

@@ -1,6 +1,6 @@
 """Chain that combines documents by stuffing into context."""
 
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import Callbacks
@@ -29,7 +29,7 @@ def create_stuff_documents_chain(
     document_prompt: Optional[BasePromptTemplate] = None,
     document_separator: str = DEFAULT_DOCUMENT_SEPARATOR,
     document_variable_name: str = DOCUMENTS_KEY,
-) -> Runnable[Dict[str, Any], Any]:
+) -> Runnable[dict[str, Any], Any]:
     """Create a chain for passing a list of Documents to a model.
 
     Args:
@@ -163,7 +163,7 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
 
     @model_validator(mode="before")
     @classmethod
-    def get_default_document_variable_name(cls, values: Dict) -> Any:
+    def get_default_document_variable_name(cls, values: dict) -> Any:
         """Get default document variable name, if not provided.
 
         If only one variable is present in the llm_chain.prompt,
@@ -188,13 +188,13 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
         return values
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         extra_keys = [
             k for k in self.llm_chain.input_keys if k != self.document_variable_name
         ]
         return super().input_keys + extra_keys
 
-    def _get_inputs(self, docs: List[Document], **kwargs: Any) -> dict:
+    def _get_inputs(self, docs: list[Document], **kwargs: Any) -> dict:
         """Construct inputs from kwargs and docs.
 
         Format and then join all the documents together into one input with name
@@ -220,7 +220,7 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
         inputs[self.document_variable_name] = self.document_separator.join(doc_strings)
         return inputs
 
-    def prompt_length(self, docs: List[Document], **kwargs: Any) -> Optional[int]:
+    def prompt_length(self, docs: list[Document], **kwargs: Any) -> Optional[int]:
         """Return the prompt length given the documents passed in.
 
         This can be used by a caller to determine whether passing in a list
@@ -241,8 +241,8 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
         return self.llm_chain._get_num_tokens(prompt)
 
     def combine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Stuff all documents into one prompt and pass to LLM.
 
         Args:
@@ -259,8 +259,8 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
         return self.llm_chain.predict(callbacks=callbacks, **inputs), {}
 
     async def acombine_docs(
-        self, docs: List[Document], callbacks: Callbacks = None, **kwargs: Any
-    ) -> Tuple[str, dict]:
+        self, docs: list[Document], callbacks: Callbacks = None, **kwargs: Any
+    ) -> tuple[str, dict]:
         """Async stuff all documents into one prompt and pass to LLM.
 
         Args:

langchain/chains/constitutional_ai/base.py

@@ -1,6 +1,6 @@
 """Chain for applying constitutional principles to the outputs of another chain."""
 
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import CallbackManagerForChainRun
@@ -190,15 +190,15 @@ class ConstitutionalChain(Chain):
     """  # noqa: E501
 
     chain: LLMChain
-    constitutional_principles: List[ConstitutionalPrinciple]
+    constitutional_principles: list[ConstitutionalPrinciple]
     critique_chain: LLMChain
     revision_chain: LLMChain
     return_intermediate_steps: bool = False
 
     @classmethod
     def get_principles(
-        cls, names: Optional[List[str]] = None
-    ) -> List[ConstitutionalPrinciple]:
+        cls, names: Optional[list[str]] = None
+    ) -> list[ConstitutionalPrinciple]:
         if names is None:
             return list(PRINCIPLES.values())
         else:
@@ -224,12 +224,12 @@ class ConstitutionalChain(Chain):
         )
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Input keys."""
         return self.chain.input_keys
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Output keys."""
         if self.return_intermediate_steps:
             return ["output", "critiques_and_revisions", "initial_output"]
@@ -237,9 +237,9 @@ class ConstitutionalChain(Chain):
 
     def _call(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
         response = self.chain.run(
             **inputs,
@@ -305,7 +305,7 @@ class ConstitutionalChain(Chain):
                 color="yellow",
             )
 
-        final_output: Dict[str, Any] = {"output": response}
+        final_output: dict[str, Any] = {"output": response}
         if self.return_intermediate_steps:
             final_output["initial_output"] = initial_response
             final_output["critiques_and_revisions"] = critiques_and_revisions

langchain/chains/conversation/base.py

@@ -1,7 +1,5 @@
 """Chain that carries on a conversation and calls an LLM."""
 
-from typing import List
-
 from langchain_core._api import deprecated
 from langchain_core.memory import BaseMemory
 from langchain_core.prompts import BasePromptTemplate
@@ -21,7 +19,7 @@ from langchain.memory.buffer import ConversationBufferMemory
     ),
     removal="1.0",
 )
-class ConversationChain(LLMChain):  # type: ignore[override, override]
+class ConversationChain(LLMChain):
     """Chain to have a conversation and load context from memory.
 
     This class is deprecated in favor of ``RunnableWithMessageHistory``. Please refer
@@ -121,7 +119,7 @@ class ConversationChain(LLMChain):  # type: ignore[override, override]
         return False
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Use this since so some prompt vars come from history."""
         return [self.input_key]
 

langchain/chains/conversational_retrieval/base.py

@@ -6,7 +6,7 @@ import inspect
 import warnings
 from abc import abstractmethod
 from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional, Tuple, Type, Union
+from typing import Any, Callable, Optional, Union
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import (
@@ -32,13 +32,13 @@ from langchain.chains.question_answering import load_qa_chain
 
 # Depending on the memory type and configuration, the chat history format may differ.
 # This needs to be consolidated.
-CHAT_TURN_TYPE = Union[Tuple[str, str], BaseMessage]
+CHAT_TURN_TYPE = Union[tuple[str, str], BaseMessage]
 
 
 _ROLE_MAP = {"human": "Human: ", "ai": "Assistant: "}
 
 
-def _get_chat_history(chat_history: List[CHAT_TURN_TYPE]) -> str:
+def _get_chat_history(chat_history: list[CHAT_TURN_TYPE]) -> str:
     buffer = ""
     for dialogue_turn in chat_history:
         if isinstance(dialogue_turn, BaseMessage):
@@ -64,7 +64,7 @@ class InputType(BaseModel):
 
     question: str
     """The question to answer."""
-    chat_history: List[CHAT_TURN_TYPE] = Field(default_factory=list)
+    chat_history: list[CHAT_TURN_TYPE] = Field(default_factory=list)
     """The chat history to use for retrieval."""
 
 
@@ -89,7 +89,7 @@ class BaseConversationalRetrievalChain(Chain):
     """Return the retrieved source documents as part of the final result."""
     return_generated_question: bool = False
     """Return the generated question as part of the final result."""
-    get_chat_history: Optional[Callable[[List[CHAT_TURN_TYPE]], str]] = None
+    get_chat_history: Optional[Callable[[list[CHAT_TURN_TYPE]], str]] = None
     """An optional function to get a string of the chat history.
     If None is provided, will use a default."""
     response_if_no_docs_found: Optional[str] = None
@@ -103,17 +103,17 @@ class BaseConversationalRetrievalChain(Chain):
     )
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Input keys."""
         return ["question", "chat_history"]
 
     def get_input_schema(
         self, config: Optional[RunnableConfig] = None
-    ) -> Type[BaseModel]:
+    ) -> type[BaseModel]:
         return InputType
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return the output keys.
 
         :meta private:
@@ -129,17 +129,17 @@ class BaseConversationalRetrievalChain(Chain):
     def _get_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: CallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
 
     def _call(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
         question = inputs["question"]
         get_chat_history = self.get_chat_history or _get_chat_history
@@ -159,7 +159,7 @@ class BaseConversationalRetrievalChain(Chain):
             docs = self._get_docs(new_question, inputs, run_manager=_run_manager)
         else:
             docs = self._get_docs(new_question, inputs)  # type: ignore[call-arg]
-        output: Dict[str, Any] = {}
+        output: dict[str, Any] = {}
         if self.response_if_no_docs_found is not None and len(docs) == 0:
             output[self.output_key] = self.response_if_no_docs_found
         else:
@@ -182,17 +182,17 @@ class BaseConversationalRetrievalChain(Chain):
     async def _aget_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: AsyncCallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
 
     async def _acall(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[AsyncCallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         _run_manager = run_manager or AsyncCallbackManagerForChainRun.get_noop_manager()
         question = inputs["question"]
         get_chat_history = self.get_chat_history or _get_chat_history
@@ -212,7 +212,7 @@ class BaseConversationalRetrievalChain(Chain):
         else:
             docs = await self._aget_docs(new_question, inputs)  # type: ignore[call-arg]
 
-        output: Dict[str, Any] = {}
+        output: dict[str, Any] = {}
         if self.response_if_no_docs_found is not None and len(docs) == 0:
             output[self.output_key] = self.response_if_no_docs_found
         else:
@@ -368,7 +368,7 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
     """If set, enforces that the documents returned are less than this limit.
     This is only enforced if `combine_docs_chain` is of type StuffDocumentsChain."""
 
-    def _reduce_tokens_below_limit(self, docs: List[Document]) -> List[Document]:
+    def _reduce_tokens_below_limit(self, docs: list[Document]) -> list[Document]:
         num_docs = len(docs)
 
         if self.max_tokens_limit and isinstance(
@@ -388,10 +388,10 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
     def _get_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: CallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
         docs = self.retriever.invoke(
             question, config={"callbacks": run_manager.get_child()}
@@ -401,10 +401,10 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
     async def _aget_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: AsyncCallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
         docs = await self.retriever.ainvoke(
             question, config={"callbacks": run_manager.get_child()}
@@ -420,7 +420,7 @@ class ConversationalRetrievalChain(BaseConversationalRetrievalChain):
         chain_type: str = "stuff",
         verbose: bool = False,
         condense_question_llm: Optional[BaseLanguageModel] = None,
-        combine_docs_chain_kwargs: Optional[Dict] = None,
+        combine_docs_chain_kwargs: Optional[dict] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
     ) -> BaseConversationalRetrievalChain:
@@ -485,7 +485,7 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
 
     @model_validator(mode="before")
     @classmethod
-    def raise_deprecation(cls, values: Dict) -> Any:
+    def raise_deprecation(cls, values: dict) -> Any:
         warnings.warn(
             "`ChatVectorDBChain` is deprecated - "
             "please use `from langchain.chains import ConversationalRetrievalChain`"
@@ -495,10 +495,10 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
     def _get_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: CallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
         vectordbkwargs = inputs.get("vectordbkwargs", {})
         full_kwargs = {**self.search_kwargs, **vectordbkwargs}
@@ -509,10 +509,10 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
     async def _aget_docs(
         self,
         question: str,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         *,
         run_manager: AsyncCallbackManagerForChainRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         """Get docs."""
         raise NotImplementedError("ChatVectorDBChain does not support async")
 
@@ -523,7 +523,7 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
         vectorstore: VectorStore,
         condense_question_prompt: BasePromptTemplate = CONDENSE_QUESTION_PROMPT,
         chain_type: str = "stuff",
-        combine_docs_chain_kwargs: Optional[Dict] = None,
+        combine_docs_chain_kwargs: Optional[dict] = None,
         callbacks: Callbacks = None,
         **kwargs: Any,
     ) -> BaseConversationalRetrievalChain: