Struct LLMAsJudge 

pub struct LLMAsJudge<M: BaseChatModel> { /* private fields */ }

LLM-judge evaluator: has the LLM score the prediction against a rubric (0 to max_score).

Implementations

impl<M: BaseChatModel> LLMAsJudge<M>

pub fn new(judge: M) -> Self

Creates an LLM-judge evaluator using the default rubric on a 10-point scale.

pub fn with_rubric(self, rubric: impl Into<String>) -> Self

Sets a custom rubric (builder style).

pub fn with_max_score(self, max_score: u8) -> Self

Sets the maximum score (at least 1).

Trait Implementations

impl<M: BaseChatModel> Evaluator for LLMAsJudge<M>

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

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

Scores a single prediction

fn name(&self) -> &str

Evaluator name (used in report summaries)