retrieve_documents() — langchain Function Reference

Architecture documentation for the retrieve_documents() function in multi_query.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

LangChainCore→ MessageInterface→ retrieve_documents() — langchain Function Reference

Dependency Diagram

graph TD
  7750376a_7705_ea9a_a41e_4c29c32b85f1["retrieve_documents()"]
  cc26ec3b_70dc_5b02_e974_582867b22f34["MultiQueryRetriever"]
  7750376a_7705_ea9a_a41e_4c29c32b85f1 -->|defined in| cc26ec3b_70dc_5b02_e974_582867b22f34
  381195e9_91cc_fe16_d905_8daed773ffb5["_get_relevant_documents()"]
  381195e9_91cc_fe16_d905_8daed773ffb5 -->|calls| 7750376a_7705_ea9a_a41e_4c29c32b85f1
  style 7750376a_7705_ea9a_a41e_4c29c32b85f1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/multi_query.py lines 208–229

    def retrieve_documents(
        self,
        queries: list[str],
        run_manager: CallbackManagerForRetrieverRun,
    ) -> list[Document]:
        """Run all LLM generated queries.

        Args:
            queries: query list
            run_manager: run manager for callbacks

        Returns:
            List of retrieved Documents
        """
        documents = []
        for query in queries:
            docs = self.retriever.invoke(
                query,
                config={"callbacks": run_manager.get_child()},
            )
            documents.extend(docs)
        return documents