Struct ContextRecall 

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

RAGAS context recall: share of the reference answer’s claims that the retrieved contexts support.

The reference is split into atomic claims (same splitter faithfulness uses) and each claim is judged against the union of retrieved contexts; recall = attributable claims / total claims.

Implementations

impl<M: BaseChatModel> ContextRecall<M>

pub fn new(judge: M) -> Self

Creates a context-recall evaluator.

pub fn with_max_context_chars(self, max: usize) -> Self

Character cap for the joined context block sent per claim.

pub fn with_empty_score(self, score: f64) -> Self

Score when there is nothing to attribute (no claims / no contexts; default 0.0).

Trait Implementations

impl<M: BaseChatModel> RagEvaluator for ContextRecall<M>

fn eval_rag<'life0, 'life1, 'life2, 'life3, 'life4, 'async_trait>( &'life0 self, _input: &'life1 str, _prediction: &'life2 str, contexts: &'life3 [String], reference: &'life4 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, 'life4: 'async_trait,

Scores a single prediction given the question, retrieved contexts, and reference answer.

fn name(&self) -> &str

Evaluator name (used in report summaries)