GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigResponse class

Configuration for vector search.

Constructors

GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigResponse({required Input<Map<String, dynamic>> bruteForceConfig, required Input<String> crowdingColumn, required Input<String> distanceMeasureType, required Input<String> embeddingColumn, required Input<int> embeddingDimension, required Input<List<String>> filterColumns, required Input<GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigTreeAHConfigResponse> treeAhConfig})

Creates a new GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigResponse. bruteForceConfig Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search. crowdingColumn Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute. distanceMeasureType Optional. The distance measure used in nearest neighbor search. embeddingColumn Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search. embeddingDimension Optional. The number of dimensions of the input embedding. filterColumns Optional. Columns of features that're used to filter vector search results. treeAhConfig Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396

const

GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigResponse.fromMap(Map<String, dynamic> map)

factory

Properties

bruteForceConfig → Input<Map<String, dynamic>>

Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search.

final

crowdingColumn → Input<String>

Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.

final

distanceMeasureType → Input<String>

Optional. The distance measure used in nearest neighbor search.

final

embeddingColumn → Input<String>

Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search.

final

embeddingDimension → Input<int>

Optional. The number of dimensions of the input embedding.

final

filterColumns → Input<List<String>>

Optional. Columns of features that're used to filter vector search results.

final

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

treeAhConfig → Input<GoogleCloudAiplatformV1beta1FeatureViewVectorSearchConfigTreeAHConfigResponse>

Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toMap() → Map<String, dynamic>

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited