Hi there! Are you looking for the official Deno documentation? Try docs.deno.com for all your Deno learning needs.

GoogleCloudAiplatformV1IndexDatapoint

import type { GoogleCloudAiplatformV1IndexDatapoint } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";

A datapoint of Index.

interface GoogleCloudAiplatformV1IndexDatapoint {
crowdingTag?: GoogleCloudAiplatformV1IndexDatapointCrowdingTag;
datapointId?: string;
featureVector?: number[];
numericRestricts?: GoogleCloudAiplatformV1IndexDatapointNumericRestriction[];
restricts?: GoogleCloudAiplatformV1IndexDatapointRestriction[];
sparseEmbedding?: GoogleCloudAiplatformV1IndexDatapointSparseEmbedding;
}

§Properties

§
crowdingTag?: GoogleCloudAiplatformV1IndexDatapointCrowdingTag
[src]

Optional. CrowdingTag of the datapoint, the number of neighbors to return in each crowding can be configured during query.

§
datapointId?: string
[src]

Required. Unique identifier of the datapoint.

§
featureVector?: number[]
[src]

Required. Feature embedding vector for dense index. An array of numbers with the length of [NearestNeighborSearchConfig.dimensions].

§
numericRestricts?: GoogleCloudAiplatformV1IndexDatapointNumericRestriction[]
[src]

Optional. List of Restrict of the datapoint, used to perform "restricted searches" where boolean rule are used to filter the subset of the database eligible for matching. This uses numeric comparisons.

§
restricts?: GoogleCloudAiplatformV1IndexDatapointRestriction[]
[src]

Optional. List of Restrict of the datapoint, used to perform "restricted searches" where boolean rule are used to filter the subset of the database eligible for matching. This uses categorical tokens. See: https://cloud.google.com/vertex-ai/docs/matching-engine/filtering

§
sparseEmbedding?: GoogleCloudAiplatformV1IndexDatapointSparseEmbedding
[src]

Optional. Feature embedding vector for sparse index.