langchain 0.3.27__py3-none-any.whl → 0.4.0.dev0__py3-none-any.whl

langchain/output_parsers/structured.py

@@ -5,6 +5,7 @@ from typing import Any
 from langchain_core.output_parsers import BaseOutputParser
 from langchain_core.output_parsers.json import parse_and_check_json_markdown
 from pydantic import BaseModel
+from typing_extensions import override
 
 from langchain.output_parsers.format_instructions import (
     STRUCTURED_FORMAT_INSTRUCTIONS,
@@ -44,6 +45,14 @@ class StructuredOutputParser(BaseOutputParser[dict[str, Any]]):
         cls,
         response_schemas: list[ResponseSchema],
     ) -> StructuredOutputParser:
+        """Create a StructuredOutputParser from a list of ResponseSchema.
+
+        Args:
+            response_schemas: The schemas for the response.
+
+        Returns:
+            An instance of StructuredOutputParser.
+        """
         return cls(response_schemas=response_schemas)
 
     def get_format_instructions(
@@ -97,6 +106,7 @@ class StructuredOutputParser(BaseOutputParser[dict[str, Any]]):
             return STRUCTURED_FORMAT_SIMPLE_INSTRUCTIONS.format(format=schema_str)
         return STRUCTURED_FORMAT_INSTRUCTIONS.format(format=schema_str)
 
+    @override
     def parse(self, text: str) -> dict[str, Any]:
         expected_keys = [rs.name for rs in self.response_schemas]
         return parse_and_check_json_markdown(text, expected_keys)

langchain/output_parsers/yaml.py

@@ -6,6 +6,7 @@ import yaml
 from langchain_core.exceptions import OutputParserException
 from langchain_core.output_parsers import BaseOutputParser
 from pydantic import BaseModel, ValidationError
+from typing_extensions import override
 
 from langchain.output_parsers.format_instructions import YAML_FORMAT_INSTRUCTIONS
 
@@ -24,6 +25,7 @@ class YamlOutputParser(BaseOutputParser[T]):
     """Regex pattern to match yaml code blocks
     within triple backticks with optional yaml or yml prefix."""
 
+    @override
     def parse(self, text: str) -> T:
         try:
             # Greedy search for 1st yaml candidate.
@@ -41,6 +43,7 @@ class YamlOutputParser(BaseOutputParser[T]):
             msg = f"Failed to parse {name} from completion {text}. Got: {e}"
             raise OutputParserException(msg, llm_output=text) from e
 
+    @override
     def get_format_instructions(self) -> str:
         # Copy schema to avoid altering original Pydantic schema.
         if hasattr(self.pydantic_object, "model_json_schema"):
@@ -69,5 +72,6 @@ class YamlOutputParser(BaseOutputParser[T]):
         return "yaml"
 
     @property
+    @override
     def OutputType(self) -> type[T]:
         return self.pydantic_object

langchain/pydantic_v1/__init__.py

@@ -7,7 +7,7 @@ from langchain_core._api import warn_deprecated
 # attempt to import pydantic since it adds pydantic_v1 and pydantic_v2 to sys.modules.
 #
 # This hack is done for the following reasons:
-# * Langchain will attempt to remain compatible with both pydantic v1 and v2 since
+# * LangChain will attempt to remain compatible with both pydantic v1 and v2 since
 #   both dependencies and dependents may be stuck on either version of v1 or v2.
 # * Creating namespaces for pydantic v1 and v2 should allow us to write code that
 #   unambiguously uses either v1 or v2 API.

langchain/retrievers/document_compressors/chain_extract.py

@@ -12,6 +12,7 @@ from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
 from langchain_core.prompts import PromptTemplate
 from langchain_core.runnables import Runnable
 from pydantic import ConfigDict
+from typing_extensions import override
 
 from langchain.chains.llm import LLMChain
 from langchain.retrievers.document_compressors.chain_extract_prompt import (
@@ -29,6 +30,7 @@ class NoOutputParser(BaseOutputParser[str]):
 
     no_output_str: str = "NO_OUTPUT"
 
+    @override
     def parse(self, text: str) -> str:
         cleaned_text = text.strip()
         if cleaned_text == self.no_output_str:
@@ -80,7 +82,7 @@ class LLMChainExtractor(BaseDocumentCompressor):
             if len(output) == 0:
                 continue
             compressed_docs.append(
-                Document(page_content=cast(str, output), metadata=doc.metadata),
+                Document(page_content=cast("str", output), metadata=doc.metadata),
             )
         return compressed_docs
 
@@ -108,7 +110,7 @@ class LLMChainExtractor(BaseDocumentCompressor):
         llm: BaseLanguageModel,
         prompt: Optional[PromptTemplate] = None,
         get_input: Optional[Callable[[str, Document], str]] = None,
-        llm_chain_kwargs: Optional[dict] = None,
+        llm_chain_kwargs: Optional[dict] = None,  # noqa: ARG003
     ) -> LLMChainExtractor:
         """Initialize from LLM."""
         _prompt = prompt if prompt is not None else _get_default_chain_prompt()

langchain/retrievers/document_compressors/cohere_rerank.py

@@ -9,6 +9,7 @@ from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
 from langchain_core.utils import get_from_dict_or_env
 from pydantic import ConfigDict, model_validator
+from typing_extensions import override
 
 
 @deprecated(
@@ -98,6 +99,7 @@ class CohereRerank(BaseDocumentCompressor):
             for res in results
         ]
 
+    @override
     def compress_documents(
         self,
         documents: Sequence[Document],

langchain/retrievers/document_compressors/cross_encoder_rerank.py

@@ -7,6 +7,7 @@ from typing import Optional
 from langchain_core.callbacks import Callbacks
 from langchain_core.documents import BaseDocumentCompressor, Document
 from pydantic import ConfigDict
+from typing_extensions import override
 
 from langchain.retrievers.document_compressors.cross_encoder import BaseCrossEncoder
 
@@ -25,6 +26,7 @@ class CrossEncoderReranker(BaseDocumentCompressor):
         extra="forbid",
     )
 
+    @override
     def compress_documents(
         self,
         documents: Sequence[Document],

langchain/retrievers/document_compressors/embeddings_filter.py

@@ -6,6 +6,7 @@ from langchain_core.documents import BaseDocumentCompressor, Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.utils import pre_init
 from pydantic import ConfigDict, Field
+from typing_extensions import override
 
 
 def _get_similarity_function() -> Callable:
@@ -50,6 +51,7 @@ class EmbeddingsFilter(BaseDocumentCompressor):
             raise ValueError(msg)
         return values
 
+    @override
     def compress_documents(
         self,
         documents: Sequence[Document],
@@ -93,6 +95,7 @@ class EmbeddingsFilter(BaseDocumentCompressor):
             stateful_documents[i].state["query_similarity_score"] = similarity[i]
         return [stateful_documents[i] for i in included_idxs]
 
+    @override
     async def acompress_documents(
         self,
         documents: Sequence[Document],

langchain/retrievers/document_compressors/listwise_rerank.py

@@ -70,6 +70,7 @@ class LLMListwiseRerank(BaseDocumentCompressor):
             compressed_docs = reranker.compress_documents(documents, "Who is steve")
             assert len(compressed_docs) == 3
             assert "Steve" in compressed_docs[0].page_content
+
     """
 
     reranker: Runnable[dict, list[Document]]

langchain/retrievers/ensemble.py

@@ -81,7 +81,7 @@ 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
@@ -236,7 +236,7 @@ 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=cast(str, doc)) if isinstance(doc, str) else doc
+                Document(page_content=cast("str", doc)) if isinstance(doc, str) else doc
                 for doc in retriever_docs[i]
             ]
 

langchain/retrievers/multi_query.py

@@ -14,6 +14,7 @@ from langchain_core.prompts import BasePromptTemplate
 from langchain_core.prompts.prompt import PromptTemplate
 from langchain_core.retrievers import BaseRetriever
 from langchain_core.runnables import Runnable
+from typing_extensions import override
 
 from langchain.chains.llm import LLMChain
 
@@ -23,6 +24,7 @@ logger = logging.getLogger(__name__)
 class LineListOutputParser(BaseOutputParser[list[str]]):
     """Output parser for a list of lines."""
 
+    @override
     def parse(self, text: str) -> list[str]:
         lines = text.strip().split("\n")
         return list(filter(None, lines))  # Remove empty lines
@@ -65,7 +67,7 @@ class MultiQueryRetriever(BaseRetriever):
         retriever: BaseRetriever,
         llm: BaseLanguageModel,
         prompt: BasePromptTemplate = DEFAULT_QUERY_PROMPT,
-        parser_key: Optional[str] = None,
+        parser_key: Optional[str] = None,  # noqa: ARG003
         include_original: bool = False,  # noqa: FBT001,FBT002
     ) -> "MultiQueryRetriever":
         """Initialize from llm using default template.

langchain/retrievers/multi_vector.py

@@ -10,6 +10,7 @@ from langchain_core.retrievers import BaseRetriever
 from langchain_core.stores import BaseStore, ByteStore
 from langchain_core.vectorstores import VectorStore
 from pydantic import Field, model_validator
+from typing_extensions import override
 
 from langchain.storage._lc_store import create_kv_docstore
 
@@ -43,7 +44,7 @@ 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:
@@ -54,6 +55,7 @@ class MultiVectorRetriever(BaseRetriever):
         values["docstore"] = docstore
         return values
 
+    @override
     def _get_relevant_documents(
         self,
         query: str,
@@ -91,6 +93,7 @@ class MultiVectorRetriever(BaseRetriever):
         docs = self.docstore.mget(ids)
         return [d for d in docs if d is not None]
 
+    @override
     async def _aget_relevant_documents(
         self,
         query: str,

langchain/retrievers/parent_document_retriever.py

@@ -54,6 +54,7 @@ class ParentDocumentRetriever(MultiVectorRetriever):
                 child_splitter=child_splitter,
                 parent_splitter=parent_splitter,
             )
+
     """  # noqa: E501
 
     child_splitter: TextSplitter
@@ -147,6 +148,20 @@ class ParentDocumentRetriever(MultiVectorRetriever):
         add_to_docstore: bool = True,  # noqa: FBT001,FBT002
         **kwargs: Any,
     ) -> None:
+        """Adds documents to the docstore and vectorstores.
+
+        Args:
+            documents: List of documents to add
+            ids: Optional list of ids for documents. If provided should be the same
+                length as the list of documents. Can be provided if parent documents
+                are already in the document store and you don't want to re-add
+                to the docstore. If not provided, random UUIDs will be used as
+                ids.
+            add_to_docstore: Boolean of whether to add documents to docstore.
+                This can be false if and only if `ids` are provided. You may want
+                to set this to False if the documents are already in the docstore
+                and you don't want to re-add them.
+        """
         docs, full_docs = self._split_docs_for_adding(
             documents,
             ids,

langchain/retrievers/self_query/base.py

@@ -360,6 +360,25 @@ class SelfQueryRetriever(BaseRetriever):
         use_original_query: bool = False,  # noqa: FBT001,FBT002
         **kwargs: Any,
     ) -> "SelfQueryRetriever":
+        """Create a SelfQueryRetriever from an LLM and a vector store.
+
+        Args:
+            llm: The language model to use for generating queries.
+            vectorstore: The vector store to use for retrieving documents.
+            document_contents: Description of the page contents of the document to be
+                queried.
+            metadata_field_info: Metadata field information for the documents.
+            structured_query_translator: Optional translator for turning internal query
+                language into vectorstore search params.
+            chain_kwargs: Additional keyword arguments for the query constructor.
+            enable_limit: Whether to enable the limit operator.
+            use_original_query: Whether to use the original query instead of the revised
+                query from the LLM.
+            **kwargs: Additional keyword arguments for the SelfQueryRetriever.
+
+        Returns:
+            An instance of SelfQueryRetriever.
+        """
         if structured_query_translator is None:
             structured_query_translator = _get_builtin_translator(vectorstore)
         chain_kwargs = chain_kwargs or {}

langchain/retrievers/time_weighted_retriever.py

@@ -10,6 +10,7 @@ from langchain_core.documents import Document
 from langchain_core.retrievers import BaseRetriever
 from langchain_core.vectorstores import VectorStore
 from pydantic import ConfigDict, Field
+from typing_extensions import override
 
 
 def _get_hours_passed(time: datetime.datetime, ref_time: datetime.datetime) -> float:
@@ -128,6 +129,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
             result.append(buffered_doc)
         return result
 
+    @override
     def _get_relevant_documents(
         self,
         query: str,
@@ -142,6 +144,7 @@ class TimeWeightedVectorStoreRetriever(BaseRetriever):
         docs_and_scores.update(self.get_salient_docs(query))
         return self._get_rescored_docs(docs_and_scores)
 
+    @override
     async def _aget_relevant_documents(
         self,
         query: str,

langchain/runnables/hub.py

@@ -19,6 +19,18 @@ class HubRunnable(RunnableBindingBase[Input, Output]):
         api_key: Optional[str] = None,
         **kwargs: Any,
     ) -> None:
+        """Initialize the HubRunnable.
+
+        Args:
+            owner_repo_commit: The full name of the prompt to pull from in the format of
+                `owner/prompt_name:commit_hash` or `owner/prompt_name`
+                or just `prompt_name` if it's your own prompt.
+            api_url: The URL of the LangChain Hub API.
+                Defaults to the hosted API service if you have an api key set,
+                or a localhost instance if not.
+            api_key: The API key to use to authenticate with the LangChain Hub API.
+            **kwargs: Additional keyword arguments to pass to the parent class.
+        """
         from langchain.hub import pull
 
         pulled = pull(owner_repo_commit, api_url=api_url, api_key=api_key)

langchain/runnables/openai_functions.py

@@ -36,6 +36,12 @@ class OpenAIFunctionsRouter(RunnableBindingBase[BaseMessage, Any]):
         ],
         functions: Optional[list[OpenAIFunction]] = None,
     ):
+        """Initialize the OpenAIFunctionsRouter.
+
+        Args:
+            runnables: A mapping of function names to runnables.
+            functions: Optional list of functions to check against the runnables.
+        """
         if functions is not None:
             if len(functions) != len(runnables):
                 msg = "The number of functions does not match the number of runnables."

langchain/smith/__init__.py

@@ -87,6 +87,7 @@ or LangSmith's `RunEvaluator` classes.
 - :func:`arun_on_dataset <langchain.smith.evaluation.runner_utils.arun_on_dataset>`: Asynchronous function to evaluate a chain, agent, or other LangChain component over a dataset.
 - :func:`run_on_dataset <langchain.smith.evaluation.runner_utils.run_on_dataset>`: Function to evaluate a chain, agent, or other LangChain component over a dataset.
 - :class:`RunEvalConfig <langchain.smith.evaluation.config.RunEvalConfig>`: Class representing the configuration for running evaluation. You can select evaluators by :class:`EvaluatorType <langchain.evaluation.schema.EvaluatorType>` or config, or you can pass in `custom_evaluators`
+
 """  # noqa: E501
 
 from langchain.smith.evaluation import (

langchain/smith/evaluation/config.py

@@ -10,6 +10,7 @@ from langsmith import RunEvaluator
 from langsmith.evaluation.evaluator import EvaluationResult, EvaluationResults
 from langsmith.schemas import Example, Run
 from pydantic import BaseModel, ConfigDict, Field
+from typing_extensions import override
 
 from langchain.evaluation.criteria.eval_chain import CRITERIA_TYPE
 from langchain.evaluation.embedding_distance.base import (
@@ -78,6 +79,7 @@ class SingleKeyEvalConfig(EvalConfig):
     """The key from the traced run's inputs dictionary to use to represent the
     input. If not provided, it will be inferred automatically."""
 
+    @override
     def get_kwargs(self) -> dict[str, Any]:
         kwargs = super().get_kwargs()
         # Filer out the keys that are not needed for the evaluator.
@@ -176,13 +178,6 @@ class RunEvalConfig(BaseModel):
         llm: Optional[BaseLanguageModel] = None
         evaluator_type: EvaluatorType = EvaluatorType.CRITERIA
 
-        def __init__(
-            self,
-            criteria: Optional[CRITERIA_TYPE] = None,
-            **kwargs: Any,
-        ) -> None:
-            super().__init__(criteria=criteria, **kwargs)  # type: ignore[call-arg]
-
     class LabeledCriteria(SingleKeyEvalConfig):
         """Configuration for a labeled (with references) criteria evaluator.
 
@@ -198,13 +193,6 @@ class RunEvalConfig(BaseModel):
         llm: Optional[BaseLanguageModel] = None
         evaluator_type: EvaluatorType = EvaluatorType.LABELED_CRITERIA
 
-        def __init__(
-            self,
-            criteria: Optional[CRITERIA_TYPE] = None,
-            **kwargs: Any,
-        ) -> None:
-            super().__init__(criteria=criteria, **kwargs)  # type: ignore[call-arg]
-
     class EmbeddingDistance(SingleKeyEvalConfig):
         """Configuration for an embedding distance evaluator.
 
@@ -345,6 +333,7 @@ class RunEvalConfig(BaseModel):
 
     class ScoreString(SingleKeyEvalConfig):
         """Configuration for a score string evaluator.
+
         This is like the criteria evaluator but it is configured by
         default to return a score on the scale from 1-10.
 
@@ -370,13 +359,7 @@ class RunEvalConfig(BaseModel):
         normalize_by: Optional[float] = None
         prompt: Optional[BasePromptTemplate] = None
 
-        def __init__(
-            self,
-            criteria: Optional[CRITERIA_TYPE] = None,
-            normalize_by: Optional[float] = None,
-            **kwargs: Any,
-        ) -> None:
-            super().__init__(criteria=criteria, normalize_by=normalize_by, **kwargs)  # type: ignore[call-arg]
-
     class LabeledScoreString(ScoreString):
+        """ "Configuration for a labeled score string evaluator."""
+
         evaluator_type: EvaluatorType = EvaluatorType.LABELED_SCORE_STRING

langchain/smith/evaluation/progress.py

@@ -2,12 +2,14 @@
 
 import threading
 from collections.abc import Sequence
-from typing import Any, Optional
+from typing import Any, Optional, Union
 from uuid import UUID
 
 from langchain_core.callbacks import base as base_callbacks
 from langchain_core.documents import Document
 from langchain_core.outputs import LLMResult
+from langchain_core.v1.messages import AIMessage
+from typing_extensions import override
 
 
 class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
@@ -18,7 +20,6 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         total: int,
         ncols: int = 50,
         end_with: str = "\n",
-        **kwargs: Any,
     ):
         """Initialize the progress bar.
 
@@ -48,6 +49,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         end = "" if self.counter < self.total else self.end_with
         print(f"\r[{arrow + spaces}] {self.counter}/{self.total}", end=end)  # noqa: T201
 
+    @override
     def on_chain_error(
         self,
         error: BaseException,
@@ -59,6 +61,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_chain_end(
         self,
         outputs: dict[str, Any],
@@ -70,6 +73,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_retriever_error(
         self,
         error: BaseException,
@@ -81,6 +85,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_retriever_end(
         self,
         documents: Sequence[Document],
@@ -92,6 +97,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_llm_error(
         self,
         error: BaseException,
@@ -103,9 +109,10 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_llm_end(
         self,
-        response: LLMResult,
+        response: Union[LLMResult, AIMessage],
         *,
         run_id: UUID,
         parent_run_id: Optional[UUID] = None,
@@ -114,6 +121,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_tool_error(
         self,
         error: BaseException,
@@ -125,6 +133,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
         if parent_run_id is None:
             self.increment()
 
+    @override
     def on_tool_end(
         self,
         output: str,