langchain.js
    Preparing search index...

    Interface BaiduQianfanEmbeddingsParams

    Install and import from @langchain/baidu-qianfan instead.

    interface BaiduQianfanEmbeddingsParams {
        batchSize?: number;
        modelName: "embedding-v1" | "bge_large_zh" | "bge_large_en" | "tao-8k";
        stripNewLines?: boolean;
        timeout?: number;
    }

    Hierarchy (View Summary)

    Implemented by

    Index

    Properties

    batchSize? modelName stripNewLines? timeout?

    Properties

    batchSize?: number

    The maximum number of characters allowed for embedding in a single request varies by model:

    • Embedding-V1 model: up to 1000 characters
    • bge-large-zh model: up to 2000 characters
    • bge-large-en model: up to 2000 characters
    • tao-8k model: up to 28000 characters

    Note: These limits are model-specific and should be adhered to for optimal performance.

    modelName: "embedding-v1" | "bge_large_zh" | "bge_large_en" | "tao-8k"

    Model name to use

    stripNewLines?: boolean

    Whether to strip new lines from the input text.

    timeout?: number

    Timeout to use when making requests to BaiduQianfan.

    Settings

    Member Visibility

    On This Page

    Properties