Package version:

Interface ScalarQuantizationCompression

Contains configuration options specific to the scalar quantization compression method used during indexing and querying.

interface ScalarQuantizationCompression {
    compressionName: string;
    defaultOversampling?: number;
    kind: "scalarQuantization";
    parameters?: ScalarQuantizationParameters;
    rerankWithOriginalVectors?: boolean;
}

Hierarchy (view full)

Properties

compressionName defaultOversampling? kind parameters? rerankWithOriginalVectors?

Properties

compressionName

compressionName: string

The name to associate with this particular configuration.

OptionaldefaultOversampling

defaultOversampling?: number

Default oversampling factor. Oversampling will internally request more documents (specified by this multiplier) in the initial search. This increases the set of results that will be reranked using recomputed similarity scores from full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when rerankWithOriginalVectors is true. Higher values improve recall at the expense of latency.

kind

kind: "scalarQuantization"

Polymorphic discriminator, which specifies the different types this object can be

Optionalparameters

parameters?: ScalarQuantizationParameters

Contains the parameters specific to Scalar Quantization.

OptionalrerankWithOriginalVectors

rerankWithOriginalVectors?: boolean

If set to true, once the ordered set of results calculated using compressed vectors are obtained, they will be reranked again by recalculating the full-precision similarity scores. This will improve recall at the expense of latency.

Settings

Member Visibility