langchain 0.3.23__py3-none-any.whl → 0.3.24__py3-none-any.whl

langchain/chains/router/llm_router.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict, List, Optional, Type, cast
+from typing import Any, Optional, cast
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import (
@@ -114,42 +114,42 @@ class LLMRouterChain(RouterChain):
         return self
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Will be whatever keys the LLM chain prompt expects.
 
         :meta private:
         """
         return self.llm_chain.input_keys
 
-    def _validate_outputs(self, outputs: Dict[str, Any]) -> None:
+    def _validate_outputs(self, outputs: dict[str, Any]) -> None:
         super()._validate_outputs(outputs)
         if not isinstance(outputs["next_inputs"], dict):
             raise ValueError
 
     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()
         callbacks = _run_manager.get_child()
 
         prediction = self.llm_chain.predict(callbacks=callbacks, **inputs)
         output = cast(
-            Dict[str, Any],
+            dict[str, Any],
             self.llm_chain.prompt.output_parser.parse(prediction),
         )
         return output
 
     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 CallbackManagerForChainRun.get_noop_manager()
         callbacks = _run_manager.get_child()
         output = cast(
-            Dict[str, Any],
+            dict[str, Any],
             await self.llm_chain.apredict_and_parse(callbacks=callbacks, **inputs),
         )
         return output
@@ -163,14 +163,14 @@ class LLMRouterChain(RouterChain):
         return cls(llm_chain=llm_chain, **kwargs)
 
 
-class RouterOutputParser(BaseOutputParser[Dict[str, str]]):
+class RouterOutputParser(BaseOutputParser[dict[str, str]]):
     """Parser for output of router chain in the multi-prompt chain."""
 
     default_destination: str = "DEFAULT"
-    next_inputs_type: Type = str
+    next_inputs_type: type = str
     next_inputs_inner_key: str = "input"
 
-    def parse(self, text: str) -> Dict[str, Any]:
+    def parse(self, text: str) -> dict[str, Any]:
         try:
             expected_keys = ["destination", "next_inputs"]
             parsed = parse_and_check_json_markdown(text, expected_keys)

langchain/chains/router/multi_prompt.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.language_models import BaseLanguageModel
@@ -142,14 +142,14 @@ class MultiPromptChain(MultiRouteChain):
     """  # noqa: E501
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         return ["text"]
 
     @classmethod
     def from_prompts(
         cls,
         llm: BaseLanguageModel,
-        prompt_infos: List[Dict[str, str]],
+        prompt_infos: list[dict[str, str]],
         default_chain: Optional[Chain] = None,
         **kwargs: Any,
     ) -> MultiPromptChain:

langchain/chains/router/multi_retrieval_qa.py

@@ -2,7 +2,8 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict, List, Mapping, Optional
+from collections.abc import Mapping
+from typing import Any, Optional
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import PromptTemplate
@@ -19,7 +20,7 @@ from langchain.chains.router.multi_retrieval_prompt import (
 )
 
 
-class MultiRetrievalQAChain(MultiRouteChain):  # type: ignore[override]
+class MultiRetrievalQAChain(MultiRouteChain):
     """A multi-route chain that uses an LLM router chain to choose amongst retrieval
     qa chains."""
 
@@ -31,14 +32,14 @@ class MultiRetrievalQAChain(MultiRouteChain):  # type: ignore[override]
     """Default chain to use when router doesn't map input to one of the destinations."""
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         return ["result"]
 
     @classmethod
     def from_retrievers(
         cls,
         llm: BaseLanguageModel,
-        retriever_infos: List[Dict[str, Any]],
+        retriever_infos: list[dict[str, Any]],
         default_retriever: Optional[BaseRetriever] = None,
         default_prompt: Optional[PromptTemplate] = None,
         default_chain: Optional[Chain] = None,

langchain/chains/sequential.py

@@ -1,6 +1,6 @@
 """Chain pipeline where the outputs of one step feed directly into next."""
 
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForChainRun,
@@ -16,9 +16,9 @@ from langchain.chains.base import Chain
 class SequentialChain(Chain):
     """Chain where the outputs of one chain feed directly into next."""
 
-    chains: List[Chain]
-    input_variables: List[str]
-    output_variables: List[str]  #: :meta private:
+    chains: list[Chain]
+    input_variables: list[str]
+    output_variables: list[str]  #: :meta private:
     return_all: bool = False
 
     model_config = ConfigDict(
@@ -27,7 +27,7 @@ class SequentialChain(Chain):
     )
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Return expected input keys to the chain.
 
         :meta private:
@@ -35,7 +35,7 @@ class SequentialChain(Chain):
         return self.input_variables
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return output key.
 
         :meta private:
@@ -44,7 +44,7 @@ class SequentialChain(Chain):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_chains(cls, values: Dict) -> Any:
+    def validate_chains(cls, values: dict) -> Any:
         """Validate that the correct inputs exist for all chains."""
         chains = values["chains"]
         input_variables = values["input_variables"]
@@ -97,9 +97,9 @@ class SequentialChain(Chain):
 
     def _call(
         self,
-        inputs: Dict[str, str],
+        inputs: dict[str, str],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, str]:
+    ) -> dict[str, str]:
         known_values = inputs.copy()
         _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
         for i, chain in enumerate(self.chains):
@@ -110,9 +110,9 @@ class SequentialChain(Chain):
 
     async def _acall(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[AsyncCallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         known_values = inputs.copy()
         _run_manager = run_manager or AsyncCallbackManagerForChainRun.get_noop_manager()
         callbacks = _run_manager.get_child()
@@ -127,7 +127,7 @@ class SequentialChain(Chain):
 class SimpleSequentialChain(Chain):
     """Simple chain where the outputs of one step feed directly into next."""
 
-    chains: List[Chain]
+    chains: list[Chain]
     strip_outputs: bool = False
     input_key: str = "input"  #: :meta private:
     output_key: str = "output"  #: :meta private:
@@ -138,7 +138,7 @@ class SimpleSequentialChain(Chain):
     )
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Expect input key.
 
         :meta private:
@@ -146,7 +146,7 @@ class SimpleSequentialChain(Chain):
         return [self.input_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return output key.
 
         :meta private:
@@ -171,9 +171,9 @@ class SimpleSequentialChain(Chain):
 
     def _call(
         self,
-        inputs: Dict[str, str],
+        inputs: dict[str, str],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, str]:
+    ) -> dict[str, str]:
         _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
         _input = inputs[self.input_key]
         color_mapping = get_color_mapping([str(i) for i in range(len(self.chains))])
@@ -190,9 +190,9 @@ class SimpleSequentialChain(Chain):
 
     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()
         _input = inputs[self.input_key]
         color_mapping = get_color_mapping([str(i) for i in range(len(self.chains))])

langchain/chains/sql_database/query.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, TypedDict, Union
+from typing import TYPE_CHECKING, Any, Optional, TypedDict, Union
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.output_parsers import StrOutputParser
@@ -27,7 +27,7 @@ class SQLInputWithTables(TypedDict):
     """Input for a SQL Chain."""
 
     question: str
-    table_names_to_use: List[str]
+    table_names_to_use: list[str]
 
 
 def create_sql_query_chain(
@@ -35,7 +35,7 @@ def create_sql_query_chain(
     db: SQLDatabase,
     prompt: Optional[BasePromptTemplate] = None,
     k: int = 5,
-) -> Runnable[Union[SQLInput, SQLInputWithTables, Dict[str, Any]], str]:
+) -> Runnable[Union[SQLInput, SQLInputWithTables, dict[str, Any]], str]:
     """Create a chain that generates SQL queries.
 
     *Security Note*: This chain generates SQL queries for the given database.
@@ -134,7 +134,7 @@ def create_sql_query_chain(
         ),
     }
     return (
-        RunnablePassthrough.assign(**inputs)  # type: ignore
+        RunnablePassthrough.assign(**inputs)  # type: ignore[return-value]
         | (
             lambda x: {
                 k: v

langchain/chains/structured_output/base.py

@@ -1,5 +1,6 @@
 import json
-from typing import Any, Callable, Dict, Literal, Optional, Sequence, Type, Union
+from collections.abc import Sequence
+from typing import Any, Callable, Literal, Optional, Union
 
 from langchain_core._api import deprecated
 from langchain_core.output_parsers import (
@@ -63,7 +64,7 @@ from pydantic import BaseModel
     ),
 )
 def create_openai_fn_runnable(
-    functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
+    functions: Sequence[Union[dict[str, Any], type[BaseModel], Callable]],
     llm: Runnable,
     prompt: Optional[BasePromptTemplate] = None,
     *,
@@ -135,7 +136,7 @@ def create_openai_fn_runnable(
     if not functions:
         raise ValueError("Need to pass in at least one function. Received zero.")
     openai_functions = [convert_to_openai_function(f) for f in functions]
-    llm_kwargs_: Dict[str, Any] = {"functions": openai_functions, **llm_kwargs}
+    llm_kwargs_: dict[str, Any] = {"functions": openai_functions, **llm_kwargs}
     if len(openai_functions) == 1 and enforce_single_function_usage:
         llm_kwargs_["function_call"] = {"name": openai_functions[0]["name"]}
     output_parser = output_parser or get_openai_output_parser(functions)
@@ -181,7 +182,7 @@ def create_openai_fn_runnable(
     ),
 )
 def create_structured_output_runnable(
-    output_schema: Union[Dict[str, Any], Type[BaseModel]],
+    output_schema: Union[dict[str, Any], type[BaseModel]],
     llm: Runnable,
     prompt: Optional[BasePromptTemplate] = None,
     *,
@@ -437,7 +438,7 @@ def create_structured_output_runnable(
 
 
 def _create_openai_tools_runnable(
-    tool: Union[Dict[str, Any], Type[BaseModel], Callable],
+    tool: Union[dict[str, Any], type[BaseModel], Callable],
     llm: Runnable,
     *,
     prompt: Optional[BasePromptTemplate],
@@ -446,7 +447,7 @@ def _create_openai_tools_runnable(
     first_tool_only: bool,
 ) -> Runnable:
     oai_tool = convert_to_openai_tool(tool)
-    llm_kwargs: Dict[str, Any] = {"tools": [oai_tool]}
+    llm_kwargs: dict[str, Any] = {"tools": [oai_tool]}
     if enforce_tool_usage:
         llm_kwargs["tool_choice"] = {
             "type": "function",
@@ -462,7 +463,7 @@ def _create_openai_tools_runnable(
 
 
 def _get_openai_tool_output_parser(
-    tool: Union[Dict[str, Any], Type[BaseModel], Callable],
+    tool: Union[dict[str, Any], type[BaseModel], Callable],
     *,
     first_tool_only: bool = False,
 ) -> Union[BaseOutputParser, BaseGenerationOutputParser]:
@@ -479,7 +480,7 @@ def _get_openai_tool_output_parser(
 
 
 def get_openai_output_parser(
-    functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
+    functions: Sequence[Union[dict[str, Any], type[BaseModel], Callable]],
 ) -> Union[BaseOutputParser, BaseGenerationOutputParser]:
     """Get the appropriate function output parser given the user functions.
 
@@ -496,7 +497,7 @@ def get_openai_output_parser(
     """
     if isinstance(functions[0], type) and is_basemodel_subclass(functions[0]):
         if len(functions) > 1:
-            pydantic_schema: Union[Dict, Type[BaseModel]] = {
+            pydantic_schema: Union[dict, type[BaseModel]] = {
                 convert_to_openai_function(fn)["name"]: fn for fn in functions
             }
         else:
@@ -510,7 +511,7 @@ def get_openai_output_parser(
 
 
 def _create_openai_json_runnable(
-    output_schema: Union[Dict[str, Any], Type[BaseModel]],
+    output_schema: Union[dict[str, Any], type[BaseModel]],
     llm: Runnable,
     prompt: Optional[BasePromptTemplate] = None,
     *,
@@ -519,7 +520,7 @@ def _create_openai_json_runnable(
     """"""
     if isinstance(output_schema, type) and is_basemodel_subclass(output_schema):
         output_parser = output_parser or PydanticOutputParser(
-            pydantic_object=output_schema,  # type: ignore
+            pydantic_object=output_schema,
         )
         schema_as_dict = convert_to_openai_function(output_schema)["parameters"]
     else:
@@ -537,7 +538,7 @@ def _create_openai_json_runnable(
 
 
 def _create_openai_functions_structured_output_runnable(
-    output_schema: Union[Dict[str, Any], Type[BaseModel]],
+    output_schema: Union[dict[str, Any], type[BaseModel]],
     llm: Runnable,
     prompt: Optional[BasePromptTemplate] = None,
     *,
@@ -558,7 +559,7 @@ def _create_openai_functions_structured_output_runnable(
         class _OutputFormatter(BaseModel):
             """Output formatter. Should always be used to format your response to the user."""  # noqa: E501
 
-            output: output_schema  # type: ignore
+            output: output_schema  # type: ignore[valid-type]
 
         function = _OutputFormatter
         output_parser = output_parser or PydanticAttrOutputFunctionsParser(

langchain/chains/summarize/chain.py

@@ -1,6 +1,7 @@
 """Load summarizing chains."""
 
-from typing import Any, Mapping, Optional, Protocol
+from collections.abc import Mapping
+from typing import Any, Optional, Protocol
 
 from langchain_core.callbacks import Callbacks
 from langchain_core.language_models import BaseLanguageModel
@@ -61,14 +62,14 @@ def _load_map_reduce_chain(
         llm=llm,
         prompt=map_prompt,
         verbose=verbose,  # type: ignore[arg-type]
-        callbacks=callbacks,  # type: ignore[arg-type]
+        callbacks=callbacks,
     )
     _reduce_llm = reduce_llm or llm
     reduce_chain = LLMChain(
         llm=_reduce_llm,
         prompt=combine_prompt,
         verbose=verbose,  # type: ignore[arg-type]
-        callbacks=callbacks,  # type: ignore[arg-type]
+        callbacks=callbacks,
     )
     # TODO: document prompt
     combine_documents_chain = StuffDocumentsChain(

langchain/chains/transform.py

@@ -2,7 +2,8 @@
 
 import functools
 import logging
-from typing import Any, Awaitable, Callable, Dict, List, Optional
+from collections.abc import Awaitable
+from typing import Any, Callable, Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForChainRun,
@@ -26,13 +27,13 @@ class TransformChain(Chain):
              output_variables["entities"], transform=func())
     """
 
-    input_variables: List[str]
+    input_variables: list[str]
     """The keys expected by the transform's input dictionary."""
-    output_variables: List[str]
+    output_variables: list[str]
     """The keys returned by the transform's output dictionary."""
-    transform_cb: Callable[[Dict[str, str]], Dict[str, str]] = Field(alias="transform")
+    transform_cb: Callable[[dict[str, str]], dict[str, str]] = Field(alias="transform")
     """The transform function."""
-    atransform_cb: Optional[Callable[[Dict[str, Any]], Awaitable[Dict[str, Any]]]] = (
+    atransform_cb: Optional[Callable[[dict[str, Any]], Awaitable[dict[str, Any]]]] = (
         Field(None, alias="atransform")
     )
     """The async coroutine transform function."""
@@ -47,7 +48,7 @@ class TransformChain(Chain):
         logger.warning(msg)
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Expect input keys.
 
         :meta private:
@@ -55,7 +56,7 @@ class TransformChain(Chain):
         return self.input_variables
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return output keys.
 
         :meta private:
@@ -64,16 +65,16 @@ class TransformChain(Chain):
 
     def _call(
         self,
-        inputs: Dict[str, str],
+        inputs: dict[str, str],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, str]:
+    ) -> dict[str, str]:
         return self.transform_cb(inputs)
 
     async def _acall(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[AsyncCallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         if self.atransform_cb is not None:
             return await self.atransform_cb(inputs)
         else: