retrievers.py — langchain Source File

Source Code

"""**Retriever** class returns `Document` objects given a text **query**.

It is more general than a vector store. A retriever does not need to be able to
store documents, only to return (or retrieve) it. Vector stores can be used as
the backbone of a retriever, but there are other types of retrievers as well.
"""

from __future__ import annotations

from abc import ABC, abstractmethod
from inspect import signature
from typing import TYPE_CHECKING, Any

from pydantic import ConfigDict
from typing_extensions import Self, TypedDict, override

from langchain_core.callbacks.manager import AsyncCallbackManager, CallbackManager
from langchain_core.documents import Document
from langchain_core.runnables import (
    Runnable,
    RunnableConfig,
    RunnableSerializable,
    ensure_config,
)
from langchain_core.runnables.config import run_in_executor

if TYPE_CHECKING:
    from langchain_core.callbacks.manager import (
        AsyncCallbackManagerForRetrieverRun,
        CallbackManagerForRetrieverRun,
    )

RetrieverInput = str
RetrieverOutput = list[Document]
RetrieverLike = Runnable[RetrieverInput, RetrieverOutput]
RetrieverOutputLike = Runnable[Any, RetrieverOutput]


class LangSmithRetrieverParams(TypedDict, total=False):
    """LangSmith parameters for tracing."""

    ls_retriever_name: str
    """Retriever name."""

    ls_vector_store_provider: str | None
    """Vector store provider."""

    ls_embedding_provider: str | None
    """Embedding provider."""

    ls_embedding_model: str | None
    """Embedding model."""


class BaseRetriever(RunnableSerializable[RetrieverInput, RetrieverOutput], ABC):
    """Abstract base class for a document retrieval system.

    A retrieval system is defined as something that can take string queries and return
    the most 'relevant' documents from some source.

// ... (269 more lines)