langchain.js
    Preparing search index...

    Class for interacting with a Xata database as a VectorStore. Provides methods to add documents and vectors to the database, delete entries, and perform similarity searches.

    Type Parameters

    • XataClient extends BaseClient

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    FilterType: object

    Methods

    • Returns string

    • Method to add documents to the Xata database. Maps the page content of each document, embeds the documents using the embeddings, and adds the vectors to the database.

      Parameters

      • documents: Document[]

        Array of documents to be added.

      • Optionaloptions: { ids?: string[] }

        Optional object containing an array of ids.

      Returns Promise<string[]>

      Promise resolving to an array of ids of the added documents.

    • Method to add vectors to the Xata database. Maps each vector to a row with the document's content, embedding, and metadata. Creates or replaces these rows in the Xata database.

      Parameters

      • vectors: number[][]

        Array of vectors to be added.

      • documents: Document[]

        Array of documents corresponding to the vectors.

      • Optionaloptions: { ids?: string[] }

        Optional object containing an array of ids.

      Returns Promise<string[]>

      Promise resolving to an array of ids of the added vectors.

    • Method to delete entries from the Xata database. Deletes the entries with the provided ids.

      Parameters

      • params: { ids: string[] }

        Object containing an array of ids of the entries to be deleted.

      Returns Promise<void>

      Promise resolving to void.

    • Method to perform a similarity search in the Xata database. Returns the k most similar documents along with their scores.

      Parameters

      • query: number[]

        Query vector for the similarity search.

      • k: number

        Number of most similar documents to return.

      • Optionalfilter: object

        Optional filter for the search.

      Returns Promise<[Document, number][]>

      Promise resolving to an array of tuples, each containing a Document and its score.