Class AlibabaTongyiEmbeddings

Hierarchy

  • Embeddings
    • AlibabaTongyiEmbeddings

Implements

Constructors

constructor

Properties

apiKey batchSize caller modelName parameters stripNewLines

Methods

embedDocuments embedQuery

Constructors

constructor

Properties

apiKey

apiKey: string

batchSize

batchSize: number = 24

The maximum number of documents to embed in a single request. This is limited by the AlibabaTongyi API to a maximum of 2048.

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.

modelName

modelName: "text-embedding-v2" = "text-embedding-v2"

Model name to use

parameters

parameters: undefined | {
    text_type?: "document" | "query";
}

Type declaration

  • Optionaltext_type?: "document" | "query"

    取值：query 或者 document，默认值为 document 说明：文本转换为向量后可以应用于检索、聚类、分类等下游任务， 对检索这类非对称任务为了达到更好的检索效果建议区分查询文本（query）和 底库文本（document）类型, 聚类、分类等对称任务可以不用特殊指定， 采用系统默认值"document"即可

stripNewLines

stripNewLines: boolean = true

Whether to strip new lines from the input text.

Methods

embedDocuments

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

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

embedQuery

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

  • Method to generate an embedding for a single document. Calls the embeddingWithRetry 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.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods