Source code for langchain.retrievers.document_compressors.base

from inspect import signature
from typing import List, Optional, Sequence, Union

from langchain_core.callbacks.manager import Callbacks
from langchain_core.documents import (
    BaseDocumentCompressor,
    BaseDocumentTransformer,
    Document,
)


class DocumentCompressorPipeline(BaseDocumentCompressor):
    """使用一系列变换器的文档压缩器。"""

    transformers: List[Union[BaseDocumentTransformer, BaseDocumentCompressor]]
    """一系列按顺序链接在一起并依次运行的文档过滤器列表。"""

    class Config:
        """这个pydantic对象的配置。"""

        arbitrary_types_allowed = True

    def compress_documents(
        self,
        documents: Sequence[Document],
        query: str,
        callbacks: Optional[Callbacks] = None,
    ) -> Sequence[Document]:
        """转换文档列表。"""
        for _transformer in self.transformers:
            if isinstance(_transformer, BaseDocumentCompressor):
                accepts_callbacks = (
                    signature(_transformer.compress_documents).parameters.get(
                        "callbacks"
                    )
                    is not None
                )
                if accepts_callbacks:
                    documents = _transformer.compress_documents(
                        documents, query, callbacks=callbacks
                    )
                else:
                    documents = _transformer.compress_documents(documents, query)
            elif isinstance(_transformer, BaseDocumentTransformer):
                documents = _transformer.transform_documents(documents)
            else:
                raise ValueError(f"Got unexpected transformer type: {_transformer}")
        return documents

    async def acompress_documents(
        self,
        documents: Sequence[Document],
        query: str,
        callbacks: Optional[Callbacks] = None,
    ) -> Sequence[Document]:
        """在给定查询上下文的情况下压缩检索到的文档。"""
        for _transformer in self.transformers:
            if isinstance(_transformer, BaseDocumentCompressor):
                accepts_callbacks = (
                    signature(_transformer.acompress_documents).parameters.get(
                        "callbacks"
                    )
                    is not None
                )
                if accepts_callbacks:
                    documents = await _transformer.acompress_documents(
                        documents, query, callbacks=callbacks
                    )
                else:
                    documents = await _transformer.acompress_documents(documents, query)
            elif isinstance(_transformer, BaseDocumentTransformer):
                documents = await _transformer.atransform_documents(documents)
            else:
                raise ValueError(f"Got unexpected transformer type: {_transformer}")
        return documents