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

Inherits:
Object
  • Object
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

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.

Returns:



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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:



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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:



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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.



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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.



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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.



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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

Returns:



149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
 
# File 'proto_docs/google/cloud/aiplatform/v1/feature_view.rb', line 149

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