Skip to main content

Voyage AI

VoyageEmbeddings 类使用 Voyage AI REST API 为给定文本生成嵌入向量。

¥The VoyageEmbeddings class uses the Voyage AI REST API to generate embeddings for a given text.

inputType 参数允许你指定输入文本的类型，以获得更好的嵌入结果。你可以将其设置为 query、document，或保留未定义（相当于 None）。

¥The inputType parameter allows you to specify the type of input text for better embedding results. You can set it to query, document, or leave it undefined (which is equivalent to None).

  • query：将此 API 用于搜索或检索查询。Voyage AI 将在前面添加一个提示，以优化查询用例的嵌入。

    ¥query: Use this for search or retrieval queries. Voyage AI will prepend a prompt to optimize the embeddings for query use cases.

  • document：将此 API 用于你希望可检索的文档或内容。Voyage AI 将在前面添加一个提示，以优化文档用例的嵌入。

    ¥document: Use this for documents or content that you want to be retrievable. Voyage AI will prepend a prompt to optimize the embeddings for document use cases.

  • None（默认）：输入文本将直接进行编码，无需任何额外提示。

    ¥None (default): The input text will be directly encoded without any additional prompt.

此外，该类支持新的参数，以便进一步自定义嵌入过程：

¥Additionally, the class supports new parameters for further customization of the embedding process:

  • 截断：是否将输入文本截断为模型允许的最大长度。

    ¥truncation: Whether to truncate the input texts to the maximum length allowed by the model.

  • 输出维度：输出嵌入所需的维度。

    ¥outputDimension: The desired dimension of the output embeddings.

  • 输出类型：输出嵌入的数据类型。可以是 "float" 或 "int8"。

    ¥outputDtype: The data type of the output embeddings. Can be "float" or "int8".

  • 编码格式：输出嵌入的格式。可以是 "float"、"base64" 或 "ubinary"。

    ¥encodingFormat: The format of the output embeddings. Can be "float", "base64", or "ubinary".

import { VoyageEmbeddings } from "@langchain/community/embeddings/voyage";

const embeddings = new VoyageEmbeddings({
  apiKey: "YOUR-API-KEY", // In Node.js defaults to process.env.VOYAGEAI_API_KEY
  inputType: "document", // Optional: specify input type as 'query', 'document', or omit for None / Undefined / Null
  truncation: true, // Optional: enable truncation of input texts
  outputDimension: 768, // Optional: set desired output embedding dimension
  outputDtype: "float", // Optional: set output data type ("float" or "int8")
  encodingFormat: "float", // Optional: set output encoding format ("float", "base64", or "ubinary")
});

¥Related