Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig.
Configuration for vector indexing.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#brute_force_config
def brute_force_config() -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig
Returns
- (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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.
#brute_force_config=
def brute_force_config=(value) -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig
Parameter
- value (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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.
Returns
- (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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.
#crowding_column
def crowding_column() -> ::String
Returns
- (::String) — Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by FeatureOnlineStoreService.SearchNearestEntities to diversify search results. If NearestNeighborQuery.per_crowding_attribute_neighbor_count is set to K in SearchNearestEntitiesRequest, it's guaranteed that no more than K entities of the same crowding attribute are returned in the response.
#crowding_column=
def crowding_column=(value) -> ::String
Parameter
- value (::String) — Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by FeatureOnlineStoreService.SearchNearestEntities to diversify search results. If NearestNeighborQuery.per_crowding_attribute_neighbor_count is set to K in SearchNearestEntitiesRequest, it's guaranteed that no more than K entities of the same crowding attribute are returned in the response.
Returns
- (::String) — Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by FeatureOnlineStoreService.SearchNearestEntities to diversify search results. If NearestNeighborQuery.per_crowding_attribute_neighbor_count is set to K in SearchNearestEntitiesRequest, it's guaranteed that no more than K entities of the same crowding attribute are returned in the response.
#distance_measure_type
def distance_measure_type() -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType
Returns
- (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType) — Optional. The distance measure used in nearest neighbor search.
#distance_measure_type=
def distance_measure_type=(value) -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType
Parameter
- value (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType) — Optional. The distance measure used in nearest neighbor search.
Returns
- (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType) — Optional. The distance measure used in nearest neighbor search.
#embedding_column
def embedding_column() -> ::String
Returns
- (::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.
#embedding_column=
def embedding_column=(value) -> ::String
Parameter
- value (::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.
Returns
- (::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.
#embedding_dimension
def embedding_dimension() -> ::Integer
Returns
- (::Integer) — Optional. The number of dimensions of the input embedding.
#embedding_dimension=
def embedding_dimension=(value) -> ::Integer
Parameter
- value (::Integer) — Optional. The number of dimensions of the input embedding.
Returns
- (::Integer) — Optional. The number of dimensions of the input embedding.
#filter_columns
def filter_columns() -> ::Array<::String>
Returns
- (::Array<::String>) — Optional. Columns of features that're used to filter vector search results.
#filter_columns=
def filter_columns=(value) -> ::Array<::String>
Parameter
- value (::Array<::String>) — Optional. Columns of features that're used to filter vector search results.
Returns
- (::Array<::String>) — Optional. Columns of features that're used to filter vector search results.
#tree_ah_config
def tree_ah_config() -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig
Returns
-
(::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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
#tree_ah_config=
def tree_ah_config=(value) -> ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig
Parameter
-
value (::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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
Returns
-
(::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::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