generate_queries() — langchain Function Reference

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

Function python LangChainCore Runnables called by 1

Entity Profile

LangChainCore→ Runnables→ generate_queries() — langchain Function Reference

Dependency Diagram

graph TD
  92994c00_54f5_7dc8_1872_bd196eeaf0c3["generate_queries()"]
  cc26ec3b_70dc_5b02_e974_582867b22f34["MultiQueryRetriever"]
  92994c00_54f5_7dc8_1872_bd196eeaf0c3 -->|defined in| cc26ec3b_70dc_5b02_e974_582867b22f34
  381195e9_91cc_fe16_d905_8daed773ffb5["_get_relevant_documents()"]
  381195e9_91cc_fe16_d905_8daed773ffb5 -->|calls| 92994c00_54f5_7dc8_1872_bd196eeaf0c3
  style 92994c00_54f5_7dc8_1872_bd196eeaf0c3 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/multi_query.py lines 185–206

    def generate_queries(
        self,
        question: str,
        run_manager: CallbackManagerForRetrieverRun,
    ) -> list[str]:
        """Generate queries based upon user input.

        Args:
            question: user query
            run_manager: run manager for callbacks

        Returns:
            List of LLM generated queries that are similar to the user input
        """
        response = self.llm_chain.invoke(
            {"question": question},
            config={"callbacks": run_manager.get_child()},
        )
        lines = response["text"] if isinstance(self.llm_chain, LLMChain) else response
        if self.verbose:
            logger.info("Generated queries: %s", lines)
        return lines