Interface FindNeighborsRequest.QueryOrBuilder (3.56.0)

public static interface FindNeighborsRequest.QueryOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getApproximateNeighborCount()

public abstract int getApproximateNeighborCount()

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.

int32 approximate_neighbor_count = 4;

Returns
Type Description
int

The approximateNeighborCount.

getDatapoint()

public abstract IndexDatapoint getDatapoint()

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

.google.cloud.aiplatform.v1beta1.IndexDatapoint datapoint = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
IndexDatapoint

The datapoint.

getDatapointOrBuilder()

public abstract IndexDatapointOrBuilder getDatapointOrBuilder()

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

.google.cloud.aiplatform.v1beta1.IndexDatapoint datapoint = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
IndexDatapointOrBuilder

getFractionLeafNodesToSearchOverride()

public abstract double getFractionLeafNodesToSearchOverride()

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.

double fraction_leaf_nodes_to_search_override = 5;

Returns
Type Description
double

The fractionLeafNodesToSearchOverride.

getNeighborCount()

public abstract int getNeighborCount()

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).

int32 neighbor_count = 2;

Returns
Type Description
int

The neighborCount.

getPerCrowdingAttributeNeighborCount()

public abstract int getPerCrowdingAttributeNeighborCount()

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.

int32 per_crowding_attribute_neighbor_count = 3;

Returns
Type Description
int

The perCrowdingAttributeNeighborCount.

getRankingCase()

public abstract FindNeighborsRequest.Query.RankingCase getRankingCase()
Returns
Type Description
FindNeighborsRequest.Query.RankingCase

getRrf()

public abstract FindNeighborsRequest.Query.RRF getRrf()

Optional. Represents RRF algorithm that combines search results.

.google.cloud.aiplatform.v1beta1.FindNeighborsRequest.Query.RRF rrf = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
FindNeighborsRequest.Query.RRF

The rrf.

getRrfOrBuilder()

public abstract FindNeighborsRequest.Query.RRFOrBuilder getRrfOrBuilder()

Optional. Represents RRF algorithm that combines search results.

.google.cloud.aiplatform.v1beta1.FindNeighborsRequest.Query.RRF rrf = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
FindNeighborsRequest.Query.RRFOrBuilder

hasDatapoint()

public abstract boolean hasDatapoint()

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

.google.cloud.aiplatform.v1beta1.IndexDatapoint datapoint = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
boolean

Whether the datapoint field is set.

hasRrf()

public abstract boolean hasRrf()

Optional. Represents RRF algorithm that combines search results.

.google.cloud.aiplatform.v1beta1.FindNeighborsRequest.Query.RRF rrf = 6 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type Description
boolean

Whether the rrf field is set.