Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

A query to find a number of the nearest neighbors (most similar vectors) of a vector.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery

Returns a new instance of GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery.



10943
10944
10945
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10943

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#approximate_neighbor_countFixnum

The number of neighbors to find via approximate search before exact reordering is performed. If not set, the default value from scam config is used; if set, this value must be > 0. Corresponds to the JSON property approximateNeighborCount

Returns:

  • (Fixnum)


10910
10911
10912
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10910

def approximate_neighbor_count
  @approximate_neighbor_count
end

#datapointGoogle::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1IndexDatapoint

A datapoint of Index. Corresponds to the JSON property datapoint



10915
10916
10917
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10915

def datapoint
  @datapoint
end

#fraction_leaf_nodes_to_search_overrideFloat

The fraction of the number of leaves to search, set at query time allows user to tune search performance. This value increase result in both search accuracy and latency increase. The value should be between 0.0 and 1.0. If not set or set to 0.0, query uses the default value specified in NearestNeighborSearchConfig.TreeAHConfig.fraction_leaf_nodes_to_search. Corresponds to the JSON property fractionLeafNodesToSearchOverride

Returns:

  • (Float)


10924
10925
10926
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10924

def fraction_leaf_nodes_to_search_override
  @fraction_leaf_nodes_to_search_override
end

#neighbor_countFixnum

The number of nearest neighbors to be retrieved from database for each query. If not set, will use the default from the service configuration (https://cloud. google.com/vertex-ai/docs/matching-engine/configuring-indexes#nearest-neighbor- search-config). Corresponds to the JSON property neighborCount

Returns:

  • (Fixnum)


10932
10933
10934
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10932

def neighbor_count
  @neighbor_count
end

#per_crowding_attribute_neighbor_countFixnum

Crowding 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 crowding_attribute. It's used for improving result diversity. This field is the maximum number of matches with the same crowding tag. Corresponds to the JSON property perCrowdingAttributeNeighborCount

Returns:

  • (Fixnum)


10941
10942
10943
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10941

def per_crowding_attribute_neighbor_count
  @per_crowding_attribute_neighbor_count
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



10948
10949
10950
10951
10952
10953
10954
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10948

def update!(**args)
  @approximate_neighbor_count = args[:approximate_neighbor_count] if args.key?(:approximate_neighbor_count)
  @datapoint = args[:datapoint] if args.key?(:datapoint)
  @fraction_leaf_nodes_to_search_override = args[:fraction_leaf_nodes_to_search_override] if args.key?(:fraction_leaf_nodes_to_search_override)
  @neighbor_count = args[:neighbor_count] if args.key?(:neighbor_count)
  @per_crowding_attribute_neighbor_count = args[:per_crowding_attribute_neighbor_count] if args.key?(:per_crowding_attribute_neighbor_count)
end