Struct Candidate

pub struct Candidate {
    pub content: Content,
    pub safety_ratings: Option<Vec<SafetyRating>>,
    pub citation_metadata: Option<CitationMetadata>,
    pub finish_reason: Option<FinishReason>,
    pub grounding_attributions: Option<Vec<GroundingAtrribution>>,
}

Fields

content: Content

Generated content returned from the model.

safety_ratings: Option<Vec<SafetyRating>>

List of ratings for the safety of a response candidate.

There is at most one rating per category.

citation_metadata: Option<CitationMetadata>

Citation information for model-generated candidate.

This field may be populated with recitation information for any text included in the [content]. These are passages that are “recited” from copyrighted material in the foundational LLM’s training data.

finish_reason: Option<FinishReason>

The reason why the model stopped generating tokens.

If None, the model has not stopped generating the tokens.

grounding_attributions: Option<Vec<GroundingAtrribution>>

Implementations

impl Candidate

pub fn text(&self) -> Option<String>

Trait Implementations

impl Debug for Candidate

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Candidate

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.