| from evaluation.rag_benchmark import run_benchmark | |
| def test_end_to_end_rag_benchmark(): | |
| x = run_benchmark() | |
| assert x['clean']['bayesian']['end_to_end_accuracy'] == 1.0 | |
| assert x['conflict']['bayesian']['recall_at_1'] == 1.0 | |
| assert x['conflict']['bayesian']['abstention_accuracy'] == 1.0 | |
| assert x['conflict']['bayesian']['grounding_accuracy'] == 1.0 | |