langchain.js
    Preparing search index...

    Class that extends the Embeddings class and provides methods for generating embeddings using Hugging Face models through the HuggingFaceInference API.

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    Properties

    apiKey?: string
    client: InferenceClient
    endpointUrl?: string
    model: string
    provider?:
        | "auto"
        | "black-forest-labs"
        | "cerebras"
        | "cohere"
        | "fal-ai"
        | "featherless-ai"
        | "fireworks-ai"
        | "groq"
        | "hf-inference"
        | "hyperbolic"
        | "nebius"
        | "novita"
        | "nscale"
        | "openai"
        | "ovhcloud"
        | "replicate"
        | "sambanova"
        | "together"

    Methods

    • Parameters

      • texts: string[]

      Returns Promise<number[][]>

    • Method that takes an array of documents as input and returns a promise that resolves to a 2D array of embeddings for each document. It calls the _embed method with the documents as the input.

      Parameters

      • documents: string[]

        Array of documents to generate embeddings for.

      Returns Promise<number[][]>

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

    • Method that takes a document as input and returns a promise that resolves to an embedding for the document. It calls the _embed method with the document as the input and returns the first embedding in the resulting array.

      Parameters

      • document: string

        Document to generate an embedding for.

      Returns Promise<number[]>

      Promise that resolves to an embedding for the document.