_get_relevant_documents() — langchain Function Reference

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

Function python LangChainCore MessageInterface calls 1

Entity Profile

LangChainCore→ MessageInterface→ _get_relevant_documents() — langchain Function Reference

Dependency Diagram

graph TD
  5cd1a72f_50ef_d2d2_ed38_f5ce81dd0a4b["_get_relevant_documents()"]
  593f1ee8_77ed_951c_9250_d51c39a1a7a2["ExaSearchRetriever"]
  5cd1a72f_50ef_d2d2_ed38_f5ce81dd0a4b -->|defined in| 593f1ee8_77ed_951c_9250_d51c39a1a7a2
  4ff29015_cd7b_30be_cf2e_cc8ce78e2742["_get_metadata()"]
  5cd1a72f_50ef_d2d2_ed38_f5ce81dd0a4b -->|calls| 4ff29015_cd7b_30be_cf2e_cc8ce78e2742
  style 5cd1a72f_50ef_d2d2_ed38_f5ce81dd0a4b fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/exa/langchain_exa/retrievers.py lines 82–110

    def _get_relevant_documents(
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> list[Document]:
        response = self.client.search_and_contents(  # type: ignore[call-overload]
            query,
            num_results=self.k,
            text=self.text_contents_options,
            highlights=self.highlights,
            include_domains=self.include_domains,
            exclude_domains=self.exclude_domains,
            start_crawl_date=self.start_crawl_date,
            end_crawl_date=self.end_crawl_date,
            start_published_date=self.start_published_date,
            end_published_date=self.end_published_date,
            use_autoprompt=self.use_autoprompt,
            livecrawl=self.livecrawl,
            summary=self.summary,
            type=self.type,
        )  # type: ignore[call-overload, misc]

        results = response.results

        return [
            Document(
                page_content=(result.text),
                metadata=_get_metadata(result),
            )
            for result in results
        ]