BaseVectorSearchCompression interface

  • Reference
Package:
@azure/search-documents

Contains configuration options specific to the compression method used during indexing or querying.

Properties

compressionName

The name to associate with this particular configuration.
defaultOversampling

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

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

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.

Property Details

compressionName

The name to associate with this particular configuration.

compressionName: string

Property Value

string

defaultOversampling

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.

defaultOversampling?: number

Property Value

number

kind

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

kind: "scalarQuantization" | "binaryQuantization"

Property Value

"scalarQuantization" | "binaryQuantization"

rerankWithOriginalVectors

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.

rerankWithOriginalVectors?: boolean

Property Value

boolean