VIL Evaluation Framework (H10).

Provides metrics, datasets, batch evaluation, and reporting for LLM output quality.

use vil_eval::{EvalDataset, EvalCase, EvalRunner, AnswerRelevance};

let mut dataset = EvalDataset::new();
dataset.add_case(EvalCase {
    question: "What is Rust?".to_string(),
    context: "Rust is a systems programming language.".to_string(),
    answer: "Rust is a systems programming language focused on safety.".to_string(),
    reference: None,
});
let runner = EvalRunner::new(dataset).add_metric(Box::new(AnswerRelevance));
let report = runner.run();
assert_eq!(report.case_count(), 1);

vil_eval

VIL Evaluation Framework — metrics, dataset, batch evaluation, reporting (H10)

Part of VIL

This crate is part of VIL — a process-oriented language and framework for building zero-copy, high-performance distributed systems.

License

Licensed under either of Apache License 2.0 or MIT License.