pulumi-gcp-kotlin/com.pulumi.gcp.vertex.kotlin.outputs/AiFeatureOnlineStoreFeatureviewVectorSearchConfig

AiFeatureOnlineStoreFeatureviewVectorSearchConfig

data class AiFeatureOnlineStoreFeatureviewVectorSearchConfig(val bruteForceConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigBruteForceConfig? = null, val crowdingColumn: String? = null, val distanceMeasureType: String? = null, val embeddingColumn: String, val embeddingDimension: Int? = null, val filterColumns: List<String>? = null, val treeAhConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigTreeAhConfig? = null)

Constructors

constructor(bruteForceConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigBruteForceConfig? = null, crowdingColumn: String? = null, distanceMeasureType: String? = null, embeddingColumn: String, embeddingDimension: Int? = null, filterColumns: List<String>? = null, treeAhConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigTreeAhConfig? = null)

Types

Companion

object Companion

Properties

bruteForceConfig

val bruteForceConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigBruteForceConfig? = null

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

val crowdingColumn: String? = null

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 crowdingAttribute.

distanceMeasureType

val distanceMeasureType: String? = null

The distance measure used in nearest neighbor search. For details on allowed values, see the API documentation. Possible values are: SQUARED_L2_DISTANCE, COSINE_DISTANCE, DOT_PRODUCT_DISTANCE.

embeddingColumn

val embeddingColumn: String

Column of embedding. This column contains the source data to create index for vector search.

embeddingDimension

val embeddingDimension: Int? = null

The number of dimensions of the input embedding.

filterColumns

val filterColumns: List<String>? = null

Columns of features that are used to filter vector search results.

treeAhConfig

val treeAhConfig: AiFeatureOnlineStoreFeatureviewVectorSearchConfigTreeAhConfig? = null

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 Structure is documented below.