Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery
- 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
-
#approximate_neighbor_count ⇒ Fixnum
The number of neighbors to find via approximate search before exact reordering is performed.
-
#datapoint ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1IndexDatapoint
A datapoint of Index.
-
#fraction_leaf_nodes_to_search_override ⇒ Float
The fraction of the number of leaves to search, set at query time allows user to tune search performance.
-
#neighbor_count ⇒ Fixnum
The number of nearest neighbors to be retrieved from database for each query.
-
#per_crowding_attribute_neighbor_count ⇒ Fixnum
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.
-
#rrf ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1FindNeighborsRequestQueryRrf
Parameters for RRF algorithm that combines search results.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery
constructor
A new instance of GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery
Returns a new instance of GoogleCloudAiplatformV1beta1FindNeighborsRequestQuery.
10376 10377 10378 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10376 def initialize(**args) update!(**args) end |
Instance Attribute Details
#approximate_neighbor_count ⇒ Fixnum
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
10338 10339 10340 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10338 def approximate_neighbor_count @approximate_neighbor_count end |
#datapoint ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1IndexDatapoint
A datapoint of Index.
Corresponds to the JSON property datapoint
10343 10344 10345 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10343 def datapoint @datapoint end |
#fraction_leaf_nodes_to_search_override ⇒ 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.
Corresponds to the JSON property fractionLeafNodesToSearchOverride
10352 10353 10354 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10352 def fraction_leaf_nodes_to_search_override @fraction_leaf_nodes_to_search_override end |
#neighbor_count ⇒ Fixnum
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
10360 10361 10362 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10360 def neighbor_count @neighbor_count end |
#per_crowding_attribute_neighbor_count ⇒ Fixnum
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
10369 10370 10371 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10369 def per_crowding_attribute_neighbor_count @per_crowding_attribute_neighbor_count end |
#rrf ⇒ Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1FindNeighborsRequestQueryRrf
Parameters for RRF algorithm that combines search results.
Corresponds to the JSON property rrf
10374 10375 10376 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10374 def rrf @rrf end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
10381 10382 10383 10384 10385 10386 10387 10388 |
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 10381 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) @rrf = args[:rrf] if args.key?(:rrf) end |