GoogleCloudAiplatformV1NearestNeighborQuery
import type { GoogleCloudAiplatformV1NearestNeighborQuery } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";
A query to find a number of similar entities.
interface GoogleCloudAiplatformV1NearestNeighborQuery {
embedding?: GoogleCloudAiplatformV1NearestNeighborQueryEmbedding;
entityId?: string;
neighborCount?: number;
parameters?: GoogleCloudAiplatformV1NearestNeighborQueryParameters;
perCrowdingAttributeNeighborCount?: number;
stringFilters?: GoogleCloudAiplatformV1NearestNeighborQueryStringFilter[];
}§Properties
§
Optional. The embedding vector that be used for similar search.
§
entityId?: string
[src]Optional. The entity id whose similar entities should be searched for. If embedding is set, search will use embedding instead of entity_id.
§
neighborCount?: number
[src]Optional. The number of similar entities to be retrieved from feature view for each query.
§
Optional. Parameters that can be set to tune query on the fly.
§
perCrowdingAttributeNeighborCount?: number
[src]Optional. Crowding is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than sper_crowding_attribute_neighbor_count of the k neighbors returned have the same value of crowding_attribute. It's used for improving result diversity.
§
stringFilters?: GoogleCloudAiplatformV1NearestNeighborQueryStringFilter[]
[src]Optional. The list of string filters.