_process_results() — langchain Function Reference

Architecture documentation for the _process_results() function in map_rerank.py from the langchain codebase.

Function python AgentOrchestration ClassicChains called by 2

Entity Profile

AgentOrchestration→ ClassicChains→ _process_results() — langchain Function Reference

Dependency Diagram

graph TD
  04e51b41_5072_aa90_26eb_d0a9395e5846["_process_results()"]
  ee80b7d6_d087_8cc2_13e6_51659dee89b4["MapRerankDocumentsChain"]
  04e51b41_5072_aa90_26eb_d0a9395e5846 -->|defined in| ee80b7d6_d087_8cc2_13e6_51659dee89b4
  3ee542d4_6c5f_5591_2901_27a70f133c10["combine_docs()"]
  3ee542d4_6c5f_5591_2901_27a70f133c10 -->|calls| 04e51b41_5072_aa90_26eb_d0a9395e5846
  5744a8f1_eae7_a731_34d0_2d43bba6a9cc["acombine_docs()"]
  5744a8f1_eae7_a731_34d0_2d43bba6a9cc -->|calls| 04e51b41_5072_aa90_26eb_d0a9395e5846
  style 04e51b41_5072_aa90_26eb_d0a9395e5846 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/combine_documents/map_rerank.py lines 224–241

    def _process_results(
        self,
        docs: list[Document],
        results: Sequence[str | list[str] | dict[str, str]],
    ) -> tuple[str, dict]:
        typed_results = cast("list[dict]", results)
        sorted_res = sorted(
            zip(typed_results, docs, strict=False),
            key=lambda x: -int(x[0][self.rank_key]),
        )
        output, document = sorted_res[0]
        extra_info = {}
        if self.metadata_keys is not None:
            for key in self.metadata_keys:
                extra_info[key] = document.metadata[key]
        if self.return_intermediate_steps:
            extra_info["intermediate_steps"] = results
        return output[self.answer_key], extra_info