_get_relevant_documents() — langchain Function Reference

Architecture documentation for the _get_relevant_documents() function in in_memory.py from the langchain codebase.

Function python DataProcessing TextSplitters

Entity Profile

DataProcessing→ TextSplitters→ _get_relevant_documents() — langchain Function Reference

Dependency Diagram

graph TD
  85f0d8ef_91db_faa4_cabf_954ae4a31f14["_get_relevant_documents()"]
  1d0fbace_6fae_3047_1833_452998c80662["InMemoryDocumentIndex"]
  85f0d8ef_91db_faa4_cabf_954ae4a31f14 -->|defined in| 1d0fbace_6fae_3047_1833_452998c80662
  style 85f0d8ef_91db_faa4_cabf_954ae4a31f14 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/indexing/in_memory.py lines 94–104

    def _get_relevant_documents(
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> list[Document]:
        counts_by_doc = []

        for document in self.store.values():
            count = document.page_content.count(query)
            counts_by_doc.append((document, count))

        counts_by_doc.sort(key=operator.itemgetter(1), reverse=True)
        return [doc.model_copy() for doc, count in counts_by_doc[: self.top_k]]