merge_documents() — langchain Function Reference

Architecture documentation for the merge_documents() function in merger_retriever.py from the langchain codebase.

Function python LangChainCore ApiManagement called by 1

Entity Profile

LangChainCore→ ApiManagement→ merge_documents() — langchain Function Reference

Dependency Diagram

graph TD
  98b9ac16_6db8_bf8a_3842_55f116fd8b89["merge_documents()"]
  d3431bb4_b3e7_972f_7bf0_e9f01c630ed7["MergerRetriever"]
  98b9ac16_6db8_bf8a_3842_55f116fd8b89 -->|defined in| d3431bb4_b3e7_972f_7bf0_e9f01c630ed7
  b36313ed_19de_20c2_3cb5_aea6296aa51a["_get_relevant_documents()"]
  b36313ed_19de_20c2_3cb5_aea6296aa51a -->|calls| 98b9ac16_6db8_bf8a_3842_55f116fd8b89
  style 98b9ac16_6db8_bf8a_3842_55f116fd8b89 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/merger_retriever.py lines 53–84

    def merge_documents(
        self,
        query: str,
        run_manager: CallbackManagerForRetrieverRun,
    ) -> list[Document]:
        """Merge the results of the retrievers.

        Args:
            query: The query to search for.
            run_manager: The callback handler to use.

        Returns:
            A list of merged documents.
        """
        # Get the results of all retrievers.
        retriever_docs = [
            retriever.invoke(
                query,
                config={"callbacks": run_manager.get_child(f"retriever_{i + 1}")},
            )
            for i, retriever in enumerate(self.retrievers)
        ]

        # Merge the results of the retrievers.
        merged_documents = []
        max_docs = max(map(len, retriever_docs), default=0)
        for i in range(max_docs):
            for _retriever, doc in zip(self.retrievers, retriever_docs, strict=False):
                if i < len(doc):
                    merged_documents.append(doc[i])

        return merged_documents