base.py — langchain Source File

Source Code

"""Base classes for indexing."""

from __future__ import annotations

import abc
import time
from abc import ABC, abstractmethod
from typing import TYPE_CHECKING, Any, TypedDict

from typing_extensions import override

from langchain_core._api import beta
from langchain_core.retrievers import BaseRetriever
from langchain_core.runnables import run_in_executor

if TYPE_CHECKING:
    from collections.abc import Sequence

    from langchain_core.documents import Document


class RecordManager(ABC):
    """Abstract base class representing the interface for a record manager.

    The record manager abstraction is used by the langchain indexing API.

    The record manager keeps track of which documents have been
    written into a `VectorStore` and when they were written.

    The indexing API computes hashes for each document and stores the hash
    together with the write time and the source id in the record manager.

    On subsequent indexing runs, the indexing API can check the record manager
    to determine which documents have already been indexed and which have not.

    This allows the indexing API to avoid re-indexing documents that have
    already been indexed, and to only index new documents.

    The main benefit of this abstraction is that it works across many vectorstores.
    To be supported, a `VectorStore` needs to only support the ability to add and
    delete documents by ID. Using the record manager, the indexing API will
    be able to delete outdated documents and avoid redundant indexing of documents
    that have already been indexed.

    The main constraints of this abstraction are:

    1. It relies on the time-stamps to determine which documents have been
        indexed and which have not. This means that the time-stamps must be
        monotonically increasing. The timestamp should be the timestamp
        as measured by the server to minimize issues.
    2. The record manager is currently implemented separately from the
        vectorstore, which means that the overall system becomes distributed
        and may create issues with consistency. For example, writing to
        record manager succeeds, but corresponding writing to `VectorStore` fails.
    """

    def __init__(
        self,
        namespace: str,
    ) -> None:
// ... (602 more lines)