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

Hierarchy

  • Embeddings
    • HuggingFaceInferenceEmbeddings

Implements

Constructors

Properties

apiKey?: string
caller: AsyncCaller

The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.

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

Methods

  • 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.