public sealed class FeatureView.Types.IndexConfig : IMessage<FeatureView.Types.IndexConfig>, IEquatable<FeatureView.Types.IndexConfig>, IDeepCloneable<FeatureView.Types.IndexConfig>, IBufferMessage, IMessageReference documentation and code samples for the Cloud AI Platform v1beta1 API class FeatureView.Types.IndexConfig.
Configuration for vector indexing.
Implements
IMessageFeatureViewTypesIndexConfig, IEquatableFeatureViewTypesIndexConfig, IDeepCloneableFeatureViewTypesIndexConfig, IBufferMessage, IMessageNamespace
Google.Cloud.AIPlatform.V1Beta1Assembly
Google.Cloud.AIPlatform.V1Beta1.dll
Constructors
IndexConfig()
public IndexConfig()IndexConfig(IndexConfig)
public IndexConfig(FeatureView.Types.IndexConfig other)| Parameter | |
|---|---|
| Name | Description |
other |
FeatureViewTypesIndexConfig |
Properties
AlgorithmConfigCase
public FeatureView.Types.IndexConfig.AlgorithmConfigOneofCase AlgorithmConfigCase { get; }| Property Value | |
|---|---|
| Type | Description |
FeatureViewTypesIndexConfigAlgorithmConfigOneofCase |
|
BruteForceConfig
public FeatureView.Types.IndexConfig.Types.BruteForceConfig BruteForceConfig { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
FeatureViewTypesIndexConfigTypesBruteForceConfig |
|
CrowdingColumn
public string CrowdingColumn { get; set; }Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by [FeatureOnlineStoreService.SearchNearestEntities][google.cloud.aiplatform.v1beta1.FeatureOnlineStoreService.SearchNearestEntities] to diversify search results. If [NearestNeighborQuery.per_crowding_attribute_neighbor_count][google.cloud.aiplatform.v1beta1.NearestNeighborQuery.per_crowding_attribute_neighbor_count] is set to K in [SearchNearestEntitiesRequest][google.cloud.aiplatform.v1beta1.SearchNearestEntitiesRequest], it's guaranteed that no more than K entities of the same crowding attribute are returned in the response.
| Property Value | |
|---|---|
| Type | Description |
string |
|
DistanceMeasureType
public FeatureView.Types.IndexConfig.Types.DistanceMeasureType DistanceMeasureType { get; set; }Optional. The distance measure used in nearest neighbor search.
| Property Value | |
|---|---|
| Type | Description |
FeatureViewTypesIndexConfigTypesDistanceMeasureType |
|
EmbeddingColumn
public string EmbeddingColumn { get; set; }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.
| Property Value | |
|---|---|
| Type | Description |
string |
|
EmbeddingDimension
public int EmbeddingDimension { get; set; }Optional. The number of dimensions of the input embedding.
| Property Value | |
|---|---|
| Type | Description |
int |
|
FilterColumns
public RepeatedField<string> FilterColumns { get; }Optional. Columns of features that're used to filter vector search results.
| Property Value | |
|---|---|
| Type | Description |
RepeatedFieldstring |
|
HasEmbeddingDimension
public bool HasEmbeddingDimension { get; }Gets whether the "embedding_dimension" field is set
| Property Value | |
|---|---|
| Type | Description |
bool |
|
TreeAhConfig
public FeatureView.Types.IndexConfig.Types.TreeAHConfig TreeAhConfig { get; set; }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
| Property Value | |
|---|---|
| Type | Description |
FeatureViewTypesIndexConfigTypesTreeAHConfig |
|