Class HuggingFaceTransformersEmbeddings

Example

const model = new HuggingFaceTransformersEmbeddings({
  model: "Xenova/all-MiniLM-L6-v2",
});

// Embed a single query
const res = await model.embedQuery(
  "What would be a good company name for a company that makes colorful socks?"
);
console.log({ res });

// Embed multiple documents
const documentRes = await model.embedDocuments(["Hello world", "Bye bye"]);
console.log({ documentRes });

Hierarchy

  • Embeddings
    • HuggingFaceTransformersEmbeddings

Implements

Constructors

constructor

Properties

batchSize caller model modelName pipelineOptions? pretrainedOptions? stripNewLines timeout?

Methods

embedDocuments embedQuery

Constructors

constructor

Properties

batchSize

batchSize: number = 512

The maximum number of documents to embed in a single request.

caller

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.

model

model: string = "Xenova/all-MiniLM-L6-v2"

Model name to use

modelName

modelName: string = "Xenova/all-MiniLM-L6-v2"

Model name to use Alias for model

OptionalpipelineOptions

pipelineOptions?: FeatureExtractionPipelineOptions

Optional parameters for the pipeline.

OptionalpretrainedOptions

pretrainedOptions?: PretrainedOptions

Optional parameters for the pretrained model.

stripNewLines

stripNewLines: boolean = true

Whether to strip new lines from the input text. This is recommended by OpenAI, but may not be suitable for all use cases.

Optionaltimeout

timeout?: number

Timeout to use when making requests to OpenAI.

Methods

embedDocuments

  • embedDocuments(texts): Promise<number[][]>

  • An abstract method that takes an array of documents as input and returns a promise that resolves to an array of vectors for each document.

    Parameters

    • texts: string[]

    Returns Promise<number[][]>

    A promise that resolves to an array of vectors for each document.

embedQuery

  • embedQuery(text): Promise<number[]>

  • An abstract method that takes a single document as input and returns a promise that resolves to a vector for the query document.

    Parameters

    • text: string

    Returns Promise<number[]>

    A promise that resolves to a vector for the query document.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods