Type alias Multi2VecClipConfig

Multi2VecClipConfig: {
    imageFields?: string[];
    inferenceUrl?: string;
    textFields?: string[];
    vectorizeCollectionName?: boolean;
    weights?: {
        imageFields?: number[];
        textFields?: number[];
    };
}

The configuration for multi-media vectorization using the CLIP module.

See the documentation for detailed usage.

Type declaration

  • Optional imageFields?: string[]

    The image fields used when vectorizing.

  • Optional inferenceUrl?: string

    The URL where inference requests are sent.

  • Optional textFields?: string[]

    The text fields used when vectorizing.

  • Optional vectorizeCollectionName?: boolean

    Whether the collection name is vectorized.

  • Optional weights?: {
        imageFields?: number[];
        textFields?: number[];
    }

    The weights of the fields used for vectorization.

    • Optional imageFields?: number[]

      The weights of the image fields.

    • Optional textFields?: number[]

      The weights of the text fields.

Settings

Member Visibility

Theme