Class: Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig

Inherits:

Object

Object
Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig

show all

Extended by:: Protobuf::MessageExts::ClassMethods

Includes:: Protobuf::MessageExts

Defined in:: proto_docs/google/cloud/aiplatform/v1/feature_view.rb

Overview

Configuration for vector indexing.

Defined Under Namespace

Modules: DistanceMeasureType Classes: BruteForceConfig, TreeAHConfig

Instance Attribute Summary collapse

#brute_force_config ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig
Optional.
#crowding_column ⇒ ::String
Optional.
#distance_measure_type ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType
Optional.
#embedding_column ⇒ ::String
Optional.
#embedding_dimension ⇒ ::Integer
Optional.
#filter_columns ⇒ ::Array<::String>
Optional.
#tree_ah_config ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig
Optional.

Instance Attribute Details

#brute_force_config ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig`

Returns 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.

Note: The following fields are mutually exclusive: brute_force_config, tree_ah_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

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.

Note: The following fields are mutually exclusive: brute_force_config, tree_ah_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#crowding_column ⇒ `::String`

Returns 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.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#distance_measure_type ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType`

Returns 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.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#embedding_column ⇒ `::String`

Returns 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.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#embedding_dimension ⇒ `::Integer`

Returns Optional. The number of dimensions of the input embedding.

Returns:

(::Integer) —
Optional. The number of dimensions of the input embedding.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#filter_columns ⇒ `::Array<::String>`

Returns 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.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

#tree_ah_config ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig`

Returns 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

Note: The following fields are mutually exclusive: tree_ah_config, brute_force_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

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
Note: The following fields are mutually exclusive: tree_ah_config, brute_force_config. If a field in that set is populated, all other fields in the set will automatically be cleared.

# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 183

class IndexConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Configuration options for using brute force search.
  class BruteForceConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configuration options for the tree-AH algorithm.
  # @!attribute [rw] leaf_node_embedding_count
  #   @return [::Integer]
  #     Optional. Number of embeddings on each leaf node. The default value is
  #     1000 if not set.
  class TreeAHConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # The distance measure used in nearest neighbor search.
  module DistanceMeasureType
    # Should not be set.
    DISTANCE_MEASURE_TYPE_UNSPECIFIED = 0

    # Euclidean (L_2) Distance.
    SQUARED_L2_DISTANCE = 1

    # 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.
    COSINE_DISTANCE = 2

    # Dot Product Distance. Defined as a negative of the dot product.
    DOT_PRODUCT_DISTANCE = 3
  end
end

Class: Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig

Overview

Defined Under Namespace

Instance Attribute Summary collapse

Instance Attribute Details

#brute_force_config ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig

#crowding_column ⇒ ::String

#distance_measure_type ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType

#embedding_column ⇒ ::String

#embedding_dimension ⇒ ::Integer

#filter_columns ⇒ ::Array<::String>

#tree_ah_config ⇒ ::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig

#brute_force_config ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::BruteForceConfig`

#crowding_column ⇒ `::String`

#distance_measure_type ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::DistanceMeasureType`

#embedding_column ⇒ `::String`

#embedding_dimension ⇒ `::Integer`

#filter_columns ⇒ `::Array<::String>`

#tree_ah_config ⇒ `::Google::Cloud::AIPlatform::V1::FeatureView::IndexConfig::TreeAHConfig`