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

GoogleCloudAiplatformV1Candidate

import type { GoogleCloudAiplatformV1Candidate } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";

A response candidate generated from the model.

interface GoogleCloudAiplatformV1Candidate {
readonly citationMetadata?: GoogleCloudAiplatformV1CitationMetadata;
readonly content?: GoogleCloudAiplatformV1Content;
readonly finishMessage?: string;
readonly finishReason?:
| "FINISH_REASON_UNSPECIFIED"
| "STOP"
| "MAX_TOKENS"
| "SAFETY"
| "RECITATION"
| "OTHER"
| "BLOCKLIST"
| "PROHIBITED_CONTENT"
| "SPII";
readonly groundingMetadata?: GoogleCloudAiplatformV1GroundingMetadata;
readonly index?: number;
readonly safetyRatings?: GoogleCloudAiplatformV1SafetyRating[];
}

§Properties

§

Output only. Source attribution of the generated content.

§

Output only. Content parts of the candidate.

§
readonly finishMessage?: string
[src]

Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when finish_reason is set.

§
readonly finishReason?: "FINISH_REASON_UNSPECIFIED" | "STOP" | "MAX_TOKENS" | "SAFETY" | "RECITATION" | "OTHER" | "BLOCKLIST" | "PROHIBITED_CONTENT" | "SPII"
[src]

Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

§

Output only. Metadata specifies sources used to ground generated content.

§
readonly index?: number
[src]

Output only. Index of the candidate.

§
readonly safetyRatings?: GoogleCloudAiplatformV1SafetyRating[]
[src]

Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.