Class: Google::Cloud::AIPlatform::V1::FindNeighborsRequest::Query

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/aiplatform/v1/match_service.rb

Overview

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

Defined Under Namespace

Classes: RRF

Instance Attribute Summary collapse

Instance Attribute Details

#approximate_neighbor_count ⇒ ::Integer

Returns 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.

Returns:

  • (::Integer) —

    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.



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#datapoint ⇒ ::Google::Cloud::AIPlatform::V1::IndexDatapoint

Returns Required. The datapoint/vector whose nearest neighbors should be searched for.

Returns:



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#fraction_leaf_nodes_to_search_override ⇒ ::Float

Returns 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.

Returns:

  • (::Float) —

    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.



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#neighbor_count ⇒ ::Integer

Returns 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).

Returns:



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#per_crowding_attribute_neighbor_count ⇒ ::Integer

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.

Returns:

  • (::Integer) —

    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.



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#rrf ⇒ ::Google::Cloud::AIPlatform::V1::FindNeighborsRequest::Query::RRF

Returns Optional. Represents RRF algorithm that combines search results.

Returns:



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'proto_docs/google/cloud/aiplatform/v1/match_service.rb', line 86

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

  # Parameters for RRF algorithm that combines search results.
  # @!attribute [rw] alpha
  #   @return [::Float]
  #     Required. Users can provide an alpha value to give more weight to dense
  #     vs sparse results. For example, if the alpha is 0, we only return
  #     sparse and if the alpha is 1, we only return dense.
  class RRF
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end