compress_documents() — langchain Function Reference

Source Code

libs/langchain/langchain_classic/retrievers/document_compressors/cross_encoder_rerank.py lines 31–50

    def compress_documents(
        self,
        documents: Sequence[Document],
        query: str,
        callbacks: Callbacks | None = None,
    ) -> Sequence[Document]:
        """Rerank documents using CrossEncoder.

        Args:
            documents: A sequence of documents to compress.
            query: The query to use for compressing the documents.
            callbacks: Callbacks to run during the compression process.

        Returns:
            A sequence of compressed documents.
        """
        scores = self.model.score([(query, doc.page_content) for doc in documents])
        docs_with_scores = list(zip(documents, scores, strict=False))
        result = sorted(docs_with_scores, key=operator.itemgetter(1), reverse=True)
        return [doc for doc, _ in result[: self.top_n]]