Type alias Text2VecTransformersConfig

Text2VecTransformersConfig: {
    dimensions?: number;
    inferenceUrl?: string;
    passageInferenceUrl?: string;
    poolingStrategy?: "masked_mean" | "cls" | string;
    queryInferenceUrl?: string;
    vectorizeCollectionName?: boolean;
}

The configuration for text vectorization using the Transformers module.

See the documentation for detailed usage.

Type declaration

  • Optional dimensions?: number

    The number of dimensions for the generated embeddings.

  • Optional inferenceUrl?: string

    The inference url to use where API requests should go. You can use either this OR (passage_inference_url & query_inference_url).

  • Optional passageInferenceUrl?: string

    The inference url to use where passage API requests should go. You can use either (this AND query_inference_url) OR inference_url.

  • Optional poolingStrategy?: "masked_mean" | "cls" | string

    The pooling strategy to use.

  • Optional queryInferenceUrl?: string

    The inference url to use where query API requests should go. You can use either (this AND passage_inference_url) OR inference_url.

  • Optional vectorizeCollectionName?: boolean

    Whether to vectorize the collection name.

Settings

Member Visibility

Theme