langchain 0.3.23__py3-none-any.whl → 0.3.25__py3-none-any.whl

langchain/chains/loading.py

@@ -39,16 +39,14 @@ try:
     from langchain_community.llms.loading import load_llm, load_llm_from_config
 except ImportError:
 
-    def load_llm(*args: Any, **kwargs: Any) -> None:  # type: ignore
+    def load_llm(*args: Any, **kwargs: Any) -> None:
         raise ImportError(
             "To use this load_llm functionality you must install the "
             "langchain_community package. "
             "You can install it with `pip install langchain_community`"
         )
 
-    def load_llm_from_config(  # type: ignore
-        *args: Any, **kwargs: Any
-    ) -> None:
+    def load_llm_from_config(*args: Any, **kwargs: Any) -> None:
         raise ImportError(
             "To use this load_llm_from_config functionality you must install the "
             "langchain_community package. "
@@ -95,9 +93,9 @@ def _load_hyde_chain(config: dict, **kwargs: Any) -> HypotheticalDocumentEmbedde
     else:
         raise ValueError("`embeddings` must be present.")
     return HypotheticalDocumentEmbedder(
-        llm_chain=llm_chain,  # type: ignore[arg-type]
+        llm_chain=llm_chain,
         base_embeddings=embeddings,
-        **config,  # type: ignore[arg-type]
+        **config,
     )
 
 
@@ -160,7 +158,7 @@ def _load_map_reduce_documents_chain(
     )
 
 
-def _load_reduce_documents_chain(config: dict, **kwargs: Any) -> ReduceDocumentsChain:  # type: ignore[valid-type]
+def _load_reduce_documents_chain(config: dict, **kwargs: Any) -> ReduceDocumentsChain:
     combine_documents_chain = None
     collapse_documents_chain = None
 
@@ -213,7 +211,7 @@ def _load_reduce_documents_chain(config: dict, **kwargs: Any) -> ReduceDocuments
             config.pop("collapse_document_chain_path"), **kwargs
         )
 
-    return ReduceDocumentsChain(  # type: ignore[misc]
+    return ReduceDocumentsChain(
         combine_documents_chain=combine_documents_chain,
         collapse_documents_chain=collapse_documents_chain,
         **config,
@@ -245,7 +243,7 @@ def _load_llm_bash_chain(config: dict, **kwargs: Any) -> Any:
     elif "prompt_path" in config:
         prompt = load_prompt(config.pop("prompt_path"))
     if llm_chain:
-        return LLMBashChain(llm_chain=llm_chain, prompt=prompt, **config)  # type: ignore[arg-type]
+        return LLMBashChain(llm_chain=llm_chain, prompt=prompt, **config)
     else:
         return LLMBashChain(llm=llm, prompt=prompt, **config)
 
@@ -347,7 +345,7 @@ def _load_pal_chain(config: dict, **kwargs: Any) -> Any:
         llm_chain = load_chain(config.pop("llm_chain_path"), **kwargs)
     else:
         raise ValueError("One of `llm_chain` or `llm_chain_path` must be present.")
-    return PALChain(llm_chain=llm_chain, **config)  # type: ignore[arg-type]
+    return PALChain(llm_chain=llm_chain, **config)
 
 
 def _load_refine_documents_chain(config: dict, **kwargs: Any) -> RefineDocumentsChain:
@@ -410,7 +408,7 @@ def _load_sql_database_chain(config: dict, **kwargs: Any) -> Any:
     if "llm_chain" in config:
         llm_chain_config = config.pop("llm_chain")
         chain = load_chain_from_config(llm_chain_config, **kwargs)
-        return SQLDatabaseChain(llm_chain=chain, database=database, **config)  # type: ignore[arg-type]
+        return SQLDatabaseChain(llm_chain=chain, database=database, **config)
     if "llm" in config:
         llm_config = config.pop("llm")
         llm = load_llm_from_config(llm_config, **kwargs)
@@ -563,8 +561,8 @@ def _load_graph_cypher_chain(config: dict, **kwargs: Any) -> GraphCypherQAChain:
         )
     return GraphCypherQAChain(
         graph=graph,
-        cypher_generation_chain=cypher_generation_chain,  # type: ignore[arg-type]
-        qa_chain=qa_chain,  # type: ignore[arg-type]
+        cypher_generation_chain=cypher_generation_chain,
+        qa_chain=qa_chain,
         **config,
     )
 
@@ -702,7 +700,7 @@ def _load_chain_from_file(file: Union[str, Path], **kwargs: Any) -> Chain:
         with open(file_path) as f:
             config = json.load(f)
     elif file_path.suffix.endswith((".yaml", ".yml")):
-        with open(file_path, "r") as f:
+        with open(file_path) as f:
             config = yaml.safe_load(f)
     else:
         raise ValueError("File type must be json or yaml")

langchain/chains/mapreduce.py

@@ -6,7 +6,8 @@ then combines the results with another one.
 
 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._api import deprecated
 from langchain_core.callbacks import CallbackManagerForChainRun, Callbacks
@@ -84,7 +85,7 @@ class MapReduceChain(Chain):
     )
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Expect input key.
 
         :meta private:
@@ -92,7 +93,7 @@ class MapReduceChain(Chain):
         return [self.input_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return output key.
 
         :meta private:
@@ -101,15 +102,15 @@ class MapReduceChain(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()
         # Split the larger text into smaller chunks.
         doc_text = inputs.pop(self.input_key)
         texts = self.text_splitter.split_text(doc_text)
         docs = [Document(page_content=text) for text in texts]
-        _inputs: Dict[str, Any] = {
+        _inputs: dict[str, Any] = {
             **inputs,
             self.combine_documents_chain.input_key: docs,
         }

langchain/chains/moderation.py

@@ -1,6 +1,6 @@
 """Pass input through a moderation endpoint."""
 
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForChainRun,
@@ -42,7 +42,7 @@ class OpenAIModerationChain(Chain):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_environment(cls, values: Dict) -> Any:
+    def validate_environment(cls, values: dict) -> Any:
         """Validate that api key and python package exists in environment."""
         openai_api_key = get_from_dict_or_env(
             values, "openai_api_key", "OPENAI_API_KEY"
@@ -78,7 +78,7 @@ class OpenAIModerationChain(Chain):
         return values
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Expect input key.
 
         :meta private:
@@ -86,7 +86,7 @@ class OpenAIModerationChain(Chain):
         return [self.input_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return output key.
 
         :meta private:
@@ -108,9 +108,9 @@ class OpenAIModerationChain(Chain):
 
     def _call(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         text = inputs[self.input_key]
         if self.openai_pre_1_0:
             results = self.client.create(text)
@@ -122,9 +122,9 @@ class OpenAIModerationChain(Chain):
 
     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.openai_pre_1_0:
             return await super()._acall(inputs, run_manager=run_manager)
         text = inputs[self.input_key]

langchain/chains/natbot/base.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import warnings
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.caches import BaseCache as BaseCache
@@ -68,7 +68,7 @@ class NatBotChain(Chain):
 
     @model_validator(mode="before")
     @classmethod
-    def raise_deprecation(cls, values: Dict) -> Any:
+    def raise_deprecation(cls, values: dict) -> Any:
         if "llm" in values:
             warnings.warn(
                 "Directly instantiating an NatBotChain with an llm is deprecated. "
@@ -97,7 +97,7 @@ class NatBotChain(Chain):
         return cls(llm_chain=llm_chain, objective=objective, **kwargs)
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         """Expect url and browser content.
 
         :meta private:
@@ -105,7 +105,7 @@ class NatBotChain(Chain):
         return [self.input_url_key, self.input_browser_content_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         """Return command.
 
         :meta private:
@@ -114,9 +114,9 @@ class NatBotChain(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()
         url = inputs[self.input_url_key]
         browser_content = inputs[self.input_browser_content_key]

langchain/chains/openai_functions/base.py

@@ -1,12 +1,10 @@
 """Methods for creating chains that use OpenAI function-calling APIs."""
 
+from collections.abc import Sequence
 from typing import (
     Any,
     Callable,
-    Dict,
     Optional,
-    Sequence,
-    Type,
     Union,
 )
 
@@ -45,7 +43,7 @@ __all__ = [
 
 @deprecated(since="0.1.1", removal="1.0", alternative="create_openai_fn_runnable")
 def create_openai_fn_chain(
-    functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
+    functions: Sequence[Union[dict[str, Any], type[BaseModel], Callable]],
     llm: BaseLanguageModel,
     prompt: BasePromptTemplate,
     *,
@@ -53,7 +51,7 @@ def create_openai_fn_chain(
     output_key: str = "function",
     output_parser: Optional[BaseLLMOutputParser] = None,
     **kwargs: Any,
-) -> LLMChain:  # type: ignore[valid-type]
+) -> LLMChain:
     """[Legacy] Create an LLM chain that uses OpenAI functions.
 
     Args:
@@ -128,12 +126,12 @@ def create_openai_fn_chain(
         raise ValueError("Need to pass in at least one function. Received zero.")
     openai_functions = [convert_to_openai_function(f) for f in functions]
     output_parser = output_parser or get_openai_output_parser(functions)
-    llm_kwargs: Dict[str, Any] = {
+    llm_kwargs: dict[str, Any] = {
         "functions": openai_functions,
     }
     if len(openai_functions) == 1 and enforce_single_function_usage:
         llm_kwargs["function_call"] = {"name": openai_functions[0]["name"]}
-    llm_chain = LLMChain(  # type: ignore[misc]
+    llm_chain = LLMChain(
         llm=llm,
         prompt=prompt,
         output_parser=output_parser,
@@ -148,14 +146,14 @@ def create_openai_fn_chain(
     since="0.1.1", removal="1.0", alternative="ChatOpenAI.with_structured_output"
 )
 def create_structured_output_chain(
-    output_schema: Union[Dict[str, Any], Type[BaseModel]],
+    output_schema: Union[dict[str, Any], type[BaseModel]],
     llm: BaseLanguageModel,
     prompt: BasePromptTemplate,
     *,
     output_key: str = "function",
     output_parser: Optional[BaseLLMOutputParser] = None,
     **kwargs: Any,
-) -> LLMChain:  # type: ignore[valid-type]
+) -> LLMChain:
     """[Legacy] Create an LLMChain that uses an OpenAI function to get a structured output.
 
     Args:
@@ -218,7 +216,7 @@ def create_structured_output_chain(
         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/openai_functions/citation_fuzzy_match.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List
+from collections.abc import Iterator
 
 from langchain_core._api import deprecated
 from langchain_core.language_models import BaseChatModel, BaseLanguageModel
@@ -21,7 +21,7 @@ class FactWithEvidence(BaseModel):
     """
 
     fact: str = Field(..., description="Body of the sentence, as part of a response")
-    substring_quote: List[str] = Field(
+    substring_quote: list[str] = Field(
         ...,
         description=(
             "Each source should be a direct quote from the context, "
@@ -54,7 +54,7 @@ class QuestionAnswer(BaseModel):
     each sentence contains a body and a list of sources."""
 
     question: str = Field(..., description="Question that was asked")
-    answer: List[FactWithEvidence] = Field(
+    answer: list[FactWithEvidence] = Field(
         ...,
         description=(
             "Body of the answer, each fact should be "
@@ -148,7 +148,7 @@ def create_citation_fuzzy_match_chain(llm: BaseLanguageModel) -> LLMChain:
             )
         ),
     ]
-    prompt = ChatPromptTemplate(messages=messages)  # type: ignore[arg-type, call-arg]
+    prompt = ChatPromptTemplate(messages=messages)  # type: ignore[arg-type]
 
     chain = LLMChain(
         llm=llm,

langchain/chains/openai_functions/extraction.py

@@ -1,4 +1,4 @@
-from typing import Any, List, Optional
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.language_models import BaseLanguageModel
@@ -83,7 +83,7 @@ def create_extraction_chain(
     schema: dict,
     llm: BaseLanguageModel,
     prompt: Optional[BasePromptTemplate] = None,
-    tags: Optional[List[str]] = None,
+    tags: Optional[list[str]] = None,
     verbose: bool = False,
 ) -> Chain:
     """Creates a chain that extracts information from a passage.
@@ -170,7 +170,7 @@ def create_extraction_chain_pydantic(
     """
 
     class PydanticSchema(BaseModel):
-        info: List[pydantic_schema]  # type: ignore
+        info: list[pydantic_schema]
 
     if hasattr(pydantic_schema, "model_json_schema"):
         openai_schema = pydantic_schema.model_json_schema()

langchain/chains/openai_functions/openapi.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import json
 import re
 from collections import defaultdict
-from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Callable, Optional, Union
 
 import requests
 from langchain_core._api import deprecated
@@ -70,14 +70,14 @@ def _format_url(url: str, path_params: dict) -> str:
     return url.format(**new_params)
 
 
-def _openapi_params_to_json_schema(params: List[Parameter], spec: OpenAPISpec) -> dict:
+def _openapi_params_to_json_schema(params: list[Parameter], spec: OpenAPISpec) -> dict:
     properties = {}
     required = []
     for p in params:
         if p.param_schema:
             schema = spec.get_schema(p.param_schema)
         else:
-            media_type_schema = list(p.content.values())[0].media_type_schema  # type: ignore
+            media_type_schema = list(p.content.values())[0].media_type_schema
             schema = spec.get_schema(media_type_schema)
         if p.description and not schema.description:
             schema.description = p.description
@@ -89,7 +89,7 @@ def _openapi_params_to_json_schema(params: List[Parameter], spec: OpenAPISpec) -
 
 def openapi_spec_to_openai_fn(
     spec: OpenAPISpec,
-) -> Tuple[List[Dict[str, Any]], Callable]:
+) -> tuple[list[dict[str, Any]], Callable]:
     """Convert a valid OpenAPI spec to the JSON Schema format expected for OpenAI
         functions.
 
@@ -208,18 +208,18 @@ class SimpleRequestChain(Chain):
     """Key to use for the input of the request."""
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         return [self.input_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         return [self.output_key]
 
     def _call(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """Run the logic of this chain and return the output."""
         _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
         name = inputs[self.input_key].pop("name")
@@ -257,10 +257,10 @@ def get_openapi_chain(
     llm: Optional[BaseLanguageModel] = None,
     prompt: Optional[BasePromptTemplate] = None,
     request_chain: Optional[Chain] = None,
-    llm_chain_kwargs: Optional[Dict] = None,
+    llm_chain_kwargs: Optional[dict] = None,
     verbose: bool = False,
-    headers: Optional[Dict] = None,
-    params: Optional[Dict] = None,
+    headers: Optional[dict] = None,
+    params: Optional[dict] = None,
     **kwargs: Any,
 ) -> SequentialChain:
     """Create a chain for querying an API from a OpenAPI spec.
@@ -363,7 +363,7 @@ def get_openapi_chain(
             OpenAPISpec.from_text,
         ):
             try:
-                spec = conversion(spec)  # type: ignore[arg-type]
+                spec = conversion(spec)
                 break
             except ImportError as e:
                 raise e

langchain/chains/openai_functions/qa_with_structure.py

@@ -1,4 +1,4 @@
-from typing import Any, List, Optional, Type, Union, cast
+from typing import Any, Optional, Union, cast
 
 from langchain_core._api import deprecated
 from langchain_core.language_models import BaseLanguageModel
@@ -21,7 +21,7 @@ class AnswerWithSources(BaseModel):
     """An answer to the question, with sources."""
 
     answer: str = Field(..., description="Answer to the question that was asked")
-    sources: List[str] = Field(
+    sources: list[str] = Field(
         ..., description="List of sources used to answer the question"
     )
 
@@ -37,7 +37,7 @@ class AnswerWithSources(BaseModel):
 )
 def create_qa_with_structure_chain(
     llm: BaseLanguageModel,
-    schema: Union[dict, Type[BaseModel]],
+    schema: Union[dict, type[BaseModel]],
     output_parser: str = "base",
     prompt: Optional[Union[PromptTemplate, ChatPromptTemplate]] = None,
     verbose: bool = False,
@@ -96,7 +96,7 @@ def create_qa_with_structure_chain(
         HumanMessagePromptTemplate.from_template("Question: {question}"),
         HumanMessage(content="Tips: Make sure to answer in the correct format"),
     ]
-    prompt = prompt or ChatPromptTemplate(messages=messages)  # type: ignore[arg-type, call-arg]
+    prompt = prompt or ChatPromptTemplate(messages=messages)  # type: ignore[arg-type]
 
     chain = LLMChain(
         llm=llm,

langchain/chains/openai_functions/utils.py

@@ -1,7 +1,7 @@
-from typing import Any, Dict
+from typing import Any
 
 
-def _resolve_schema_references(schema: Any, definitions: Dict[str, Any]) -> Any:
+def _resolve_schema_references(schema: Any, definitions: dict[str, Any]) -> Any:
     """
     Resolve the $ref keys in a JSON schema object using the provided definitions.
     """

langchain/chains/openai_tools/extraction.py

@@ -1,4 +1,4 @@
-from typing import List, Type, Union
+from typing import Union
 
 from langchain_core._api import deprecated
 from langchain_core.language_models import BaseLanguageModel
@@ -51,7 +51,7 @@ If a property is not present and is not required in the function parameters, do
     ),
 )
 def create_extraction_chain_pydantic(
-    pydantic_schemas: Union[List[Type[BaseModel]], Type[BaseModel]],
+    pydantic_schemas: Union[list[type[BaseModel]], type[BaseModel]],
     llm: BaseLanguageModel,
     system_message: str = _EXTRACTION_TEMPLATE,
 ) -> Runnable:

langchain/chains/prompt_selector.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Callable, List, Tuple
+from typing import Callable
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.language_models.chat_models import BaseChatModel
@@ -21,8 +21,8 @@ class ConditionalPromptSelector(BasePromptSelector):
 
     default_prompt: BasePromptTemplate
     """Default prompt to use if no conditionals match."""
-    conditionals: List[
-        Tuple[Callable[[BaseLanguageModel], bool], BasePromptTemplate]
+    conditionals: list[
+        tuple[Callable[[BaseLanguageModel], bool], BasePromptTemplate]
     ] = Field(default_factory=list)
     """List of conditionals and prompts to use if the conditionals match."""
 

langchain/chains/qa_generation/base.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import json
-from typing import Any, Dict, List, Optional
+from typing import Any, Optional
 
 from langchain_core._api import deprecated
 from langchain_core.callbacks import CallbackManagerForChainRun
@@ -103,18 +103,18 @@ class QAGenerationChain(Chain):
         raise NotImplementedError
 
     @property
-    def input_keys(self) -> List[str]:
+    def input_keys(self) -> list[str]:
         return [self.input_key]
 
     @property
-    def output_keys(self) -> List[str]:
+    def output_keys(self) -> list[str]:
         return [self.output_key]
 
     def _call(
         self,
-        inputs: Dict[str, Any],
+        inputs: dict[str, Any],
         run_manager: Optional[CallbackManagerForChainRun] = None,
-    ) -> Dict[str, List]:
+    ) -> dict[str, list]:
         docs = self.text_splitter.create_documents([inputs[self.input_key]])
         results = self.llm_chain.generate(
             [{"text": d.page_content} for d in docs], run_manager=run_manager