_get_rescored_docs() — langchain Function Reference

Architecture documentation for the _get_rescored_docs() function in time_weighted_retriever.py from the langchain codebase.

Function python LangChainCore MessageInterface calls 1 called by 2

Entity Profile

LangChainCore→ MessageInterface→ _get_rescored_docs() — langchain Function Reference

Dependency Diagram

graph TD
  35a5a812_9087_0a29_b7c9_ebcab9fe35fa["_get_rescored_docs()"]
  57cc5b02_6622_339b_0806_ef06db1bc8c7["TimeWeightedVectorStoreRetriever"]
  35a5a812_9087_0a29_b7c9_ebcab9fe35fa -->|defined in| 57cc5b02_6622_339b_0806_ef06db1bc8c7
  b35afa73_55af_e573_98eb_b51115b185a7["_get_relevant_documents()"]
  b35afa73_55af_e573_98eb_b51115b185a7 -->|calls| 35a5a812_9087_0a29_b7c9_ebcab9fe35fa
  ae43f3d7_ce4c_57f0_7d32_9aaacf63415b["_aget_relevant_documents()"]
  ae43f3d7_ce4c_57f0_7d32_9aaacf63415b -->|calls| 35a5a812_9087_0a29_b7c9_ebcab9fe35fa
  de9ececd_a24c_a706_c8b7_9e9cc434d9ae["_get_combined_score()"]
  35a5a812_9087_0a29_b7c9_ebcab9fe35fa -->|calls| de9ececd_a24c_a706_c8b7_9e9cc434d9ae
  style 35a5a812_9087_0a29_b7c9_ebcab9fe35fa fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/time_weighted_retriever.py lines 115–132

    def _get_rescored_docs(
        self,
        docs_and_scores: dict[Any, tuple[Document, float | None]],
    ) -> list[Document]:
        current_time = datetime.datetime.now()
        rescored_docs = [
            (doc, self._get_combined_score(doc, relevance, current_time))
            for doc, relevance in docs_and_scores.values()
        ]
        rescored_docs.sort(key=lambda x: x[1], reverse=True)
        result = []
        # Ensure frequently accessed memories aren't forgotten
        for doc, _ in rescored_docs[: self.k]:
            # TODO: Update vector store doc once `update` method is exposed.
            buffered_doc = self.memory_stream[doc.metadata["buffer_idx"]]
            buffered_doc.metadata["last_accessed_at"] = current_time
            result.append(buffered_doc)
        return result