langchain.js
    Preparing search index...

    A retriever that retrieves documents from a vector store and a document store. It uses the vector store to find relevant documents based on a query, and then retrieves the full documents from the document store.

    const retriever = new MultiVectorRetriever({
    vectorstore: new FaissStore(),
    byteStore: new InMemoryStore<Unit8Array>(),
    idKey: "doc_id",
    childK: 20,
    parentK: 5,
    });

    const retrieverResult = await retriever.getRelevantDocuments("justice breyer");
    console.log(retrieverResult[0].pageContent.length);

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    childK?: number
    docstore: BaseStoreInterface<string, Document>
    idKey: string
    lc_namespace: string[] = ...
    parentK?: number
    vectorstore: VectorStoreInterface

    Methods

    • Parameters

      • query: string

      Returns Promise<Document[]>

    • Returns string