Struct LLMJudgeEvaluator 

pub struct LLMJudgeEvaluator { /* private fields */ }

Evaluator that uses an LLM to judge prediction quality.

Implementations

impl LLMJudgeEvaluator

pub fn new(model: Arc<dyn ChatModel>) -> Self

Create a new LLM judge evaluator with the default prompt template.

pub fn with_prompt( model: Arc<dyn ChatModel>, template: impl Into<String>, ) -> Self

Create a new LLM judge evaluator with a custom prompt template.

The template should contain {input}, {prediction}, and {reference} placeholders.

Trait Implementations

impl Evaluator for LLMJudgeEvaluator

fn evaluate<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, prediction: &'life1 str, reference: &'life2 str, input: &'life3 str, ) -> Pin<Box<dyn Future<Output = Result<EvalResult, SynapticError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Evaluate a prediction against a reference, given the original input.