langchain.js
    Preparing search index...

    Class GradientEmbeddings

    Class for generating embeddings using the Gradient AI's API. Extends the Embeddings class and implements GradientEmbeddingsParams and

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    constructor

    Properties

    batchSize gradientAccessKey? model workspaceId?

    Methods

    embedDocuments embedQuery setModel

    Constructors

    Properties

    batchSize: number = 128
    gradientAccessKey?: string

    Gradient AI Access Token. Provide Access Token if you do not wish to automatically pull from env.

    model: any
    workspaceId?: string

    Gradient Workspace Id. Provide workspace id if you do not wish to automatically pull from env.

    Methods

    • Method to generate embeddings for an array of documents. Splits the documents into batches and makes requests to the Gradient API to generate embeddings.

      Parameters

      • texts: string[]

        Array of documents to generate embeddings for.

      Returns Promise<number[][]>

      Promise that resolves to a 2D array of embeddings for each document.

    • Method to generate an embedding for a single document. Calls the embedDocuments method with the document as the input.

      Parameters

      • text: string

        Document to generate an embedding for.

      Returns Promise<number[]>

      Promise that resolves to an embedding for the document.

    • Method to set the model to use for generating embeddings.

      Returns Promise<void>

      the class' model value to that of the retrieved Embeddings Model.

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Methods