Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class Query.
A query to find a number of the nearest neighbors (most similar vectors) of a vector.
Generated from protobuf message google.cloud.aiplatform.v1.FindNeighborsRequest.Query
Namespace
Google \ Cloud \ AIPlatform \ V1 \ FindNeighborsRequestMethods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ rrf |
Google\Cloud\AIPlatform\V1\FindNeighborsRequest\Query\RRF
Optional. Represents RRF algorithm that combines search results. |
↳ datapoint |
Google\Cloud\AIPlatform\V1\IndexDatapoint
Required. The datapoint/vector whose nearest neighbors should be searched for. |
↳ neighbor_count |
int
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). |
↳ per_crowding_attribute_neighbor_count |
int
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. |
↳ approximate_neighbor_count |
int
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. |
↳ 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. |
getRrf
Optional. Represents RRF algorithm that combines search results.
| Returns | |
|---|---|
| Type | Description |
Google\Cloud\AIPlatform\V1\FindNeighborsRequest\Query\RRF|null |
|
hasRrf
setRrf
Optional. Represents RRF algorithm that combines search results.
| Parameter | |
|---|---|
| Name | Description |
var |
Google\Cloud\AIPlatform\V1\FindNeighborsRequest\Query\RRF
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getDatapoint
Required. The datapoint/vector whose nearest neighbors should be searched for.
| Returns | |
|---|---|
| Type | Description |
Google\Cloud\AIPlatform\V1\IndexDatapoint|null |
|
hasDatapoint
clearDatapoint
setDatapoint
Required. The datapoint/vector whose nearest neighbors should be searched for.
| Parameter | |
|---|---|
| Name | Description |
var |
Google\Cloud\AIPlatform\V1\IndexDatapoint
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
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).
| Returns | |
|---|---|
| Type | Description |
int |
|
setNeighborCount
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).
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
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.
| Returns | |
|---|---|
| Type | Description |
int |
|
setPerCrowdingAttributeNeighborCount
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.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
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.
| Returns | |
|---|---|
| Type | Description |
int |
|
setApproximateNeighborCount
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.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
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.
| Returns | |
|---|---|
| Type | Description |
float |
|
setFractionLeafNodesToSearchOverride
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.
| Parameter | |
|---|---|
| Name | Description |
var |
float
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getRanking
| Returns | |
|---|---|
| Type | Description |
string |
|