Vertex AI V1 API - Class Google::Cloud::AIPlatform::V1::Candidate (v0.47.0)

Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::Candidate.

A response candidate generated from the model.

Inherits

def citation_metadata() -> ::Google::Cloud::AIPlatform::V1::CitationMetadata

Returns

(::Google::Cloud::AIPlatform::V1::CitationMetadata) — Output only. Source attribution of the generated content.

def content() -> ::Google::Cloud::AIPlatform::V1::Content

Returns

(::Google::Cloud::AIPlatform::V1::Content) — Output only. Content parts of the candidate.

def finish_message() -> ::String

Returns

(::String) — Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when finish_reason is set.

def finish_reason() -> ::Google::Cloud::AIPlatform::V1::Candidate::FinishReason

Returns

(::Google::Cloud::AIPlatform::V1::Candidate::FinishReason) — Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

def grounding_metadata() -> ::Google::Cloud::AIPlatform::V1::GroundingMetadata

Returns

(::Google::Cloud::AIPlatform::V1::GroundingMetadata) — Output only. Metadata specifies sources used to ground generated content.

def index() -> ::Integer

Returns

def safety_ratings() -> ::Array<::Google::Cloud::AIPlatform::V1::SafetyRating>

Returns

(::Array<::Google::Cloud::AIPlatform::V1::SafetyRating>) — Output only. List of ratings for the safety of a response candidate.

There is at most one rating per category.

def score() -> ::Float

Returns