Google Cloud Ai Platform V1 Client - Class DistanceMeasureType (0.38.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class DistanceMeasureType.

The distance measure used in nearest neighbor search.

Protobuf type google.cloud.aiplatform.v1.FeatureView.IndexConfig.DistanceMeasureType

Namespace

Google \ Cloud \ AIPlatform \ V1 \ FeatureView \ IndexConfig

Methods

static::name

Parameter
Name	Description
`value`	`mixed`

static::value

Parameter
Name	Description
`name`	`mixed`

Constants

DISTANCE_MEASURE_TYPE_UNSPECIFIED

Value: 0

Should not be set.

Generated from protobuf enum DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0;

SQUARED_L2_DISTANCE

Value: 1

Euclidean (L_2) Distance.

Generated from protobuf enum SQUARED_L2_DISTANCE = 1;

COSINE_DISTANCE

Value: 2

Cosine Distance. Defined as 1 - cosine similarity.

We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead of COSINE distance. Our algorithms have been more optimized for DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is mathematically equivalent to COSINE distance and results in the same ranking.

Generated from protobuf enum COSINE_DISTANCE = 2;

DOT_PRODUCT_DISTANCE

Value: 3

Dot Product Distance. Defined as a negative of the dot product.

Generated from protobuf enum DOT_PRODUCT_DISTANCE = 3;