202 lines
33 KiB
JSON
202 lines
33 KiB
JSON
{"case_id": "indication-01", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "indication-01", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "contraindication-01", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "contraindication-01", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "interaction-01", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "interaction-01", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "warning-01", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "warning-01", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "mix", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "mix", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "mix", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "mix", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "bypass", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "bypass", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "naive", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "naive", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "naive", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "naive", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "local", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "local", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "local", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "local", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "hybrid", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "hybrid", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "hybrid", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-01", "mode": "hybrid", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "indication-02", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "indication-02", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "contraindication-02", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "contraindication-02", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "interaction-02", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "interaction-02", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "warning-02", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "warning-02", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "no_retrieval_in_baseline", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "mix", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "mix", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "mix", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "mix", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "bypass", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "bypass", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "bypass", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "bypass", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "naive", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "naive", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "naive", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "naive", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "local", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "local", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "local", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "local", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "hybrid", "metric": "faithfulness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "hybrid", "metric": "answer_relevancy", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "hybrid", "metric": "context_recall", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "unanswerable-02", "mode": "hybrid", "metric": "answer_correctness", "status": "skipped", "reason": "abstention_scenario_evaluated_separately", "value": null}
|
|
{"case_id": "indication-01", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.8336740450428343, "reason": null, "ragas_traces": null, "seconds": 2.302}
|
|
{"case_id": "indication-01", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.8413767093812826, "reason": null, "ragas_traces": null, "seconds": 1.843}
|
|
{"case_id": "indication-01", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 4.089}
|
|
{"case_id": "indication-01", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 0.8181818181818182, "reason": null, "ragas_traces": null, "seconds": 12.633}
|
|
{"case_id": "indication-01", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.8426211342298708, "reason": null, "ragas_traces": null, "seconds": 12.218}
|
|
{"case_id": "indication-01", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.8146961312204395, "reason": null, "ragas_traces": null, "seconds": 1.969}
|
|
{"case_id": "indication-01", "mode": "local", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 4.755}
|
|
{"case_id": "indication-01", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.39040561850206995, "reason": null, "ragas_traces": null, "seconds": 33.67}
|
|
{"case_id": "indication-01", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.6666666666666666, "reason": null, "ragas_traces": null, "seconds": 26.284}
|
|
{"case_id": "indication-01", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.8659158503650933, "reason": null, "ragas_traces": null, "seconds": 1.996}
|
|
{"case_id": "indication-01", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.8, "reason": null, "ragas_traces": null, "seconds": 5.127}
|
|
{"case_id": "indication-01", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.8154786680797599, "reason": null, "ragas_traces": null, "seconds": 22.987}
|
|
{"case_id": "indication-01", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 16.57}
|
|
{"case_id": "indication-01", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.8382869190155958, "reason": null, "ragas_traces": null, "seconds": 2.085}
|
|
{"case_id": "indication-01", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.8, "reason": null, "ragas_traces": null, "seconds": 5.266}
|
|
{"case_id": "indication-01", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.7102264898222257, "reason": null, "ragas_traces": null, "seconds": 17.531}
|
|
{"case_id": "contraindication-01", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 13.677}
|
|
{"case_id": "contraindication-01", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.5487599361226743, "reason": null, "ragas_traces": null, "seconds": 1.943}
|
|
{"case_id": "contraindication-01", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 7.986}
|
|
{"case_id": "indication-01", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.4466746717575326, "reason": null, "ragas_traces": null, "seconds": 40.178}
|
|
{"case_id": "indication-01", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 0.8648648648648649, "reason": null, "ragas_traces": null, "seconds": 47.779}
|
|
{"case_id": "contraindication-01", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 1.888}
|
|
{"case_id": "contraindication-01", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 7.427}
|
|
{"case_id": "contraindication-01", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.3400720301177152, "reason": null, "ragas_traces": null, "seconds": 23.647}
|
|
{"case_id": "contraindication-01", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.9411764705882353, "reason": null, "ragas_traces": null, "seconds": 20.95}
|
|
{"case_id": "contraindication-01", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.6246234588792787, "reason": null, "ragas_traces": null, "seconds": 2.554}
|
|
{"case_id": "contraindication-01", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 7.684}
|
|
{"case_id": "contraindication-01", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.11085266569327383, "reason": null, "ragas_traces": null, "seconds": 34.453}
|
|
{"case_id": "contraindication-01", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.8461538461538461, "reason": null, "ragas_traces": null, "seconds": 34.399}
|
|
{"case_id": "contraindication-01", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 1.963}
|
|
{"case_id": "contraindication-01", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 0.2857142857142857, "reason": null, "ragas_traces": null, "seconds": 10.903}
|
|
{"case_id": "contraindication-01", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 6.99}
|
|
{"case_id": "contraindication-01", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.3085577488833277, "reason": null, "ragas_traces": null, "seconds": 2.06}
|
|
{"case_id": "contraindication-01", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.3488431436528561, "reason": null, "ragas_traces": null, "seconds": 41.511}
|
|
{"case_id": "contraindication-01", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.1152586673093139, "reason": null, "ragas_traces": null, "seconds": 26.242}
|
|
{"case_id": "interaction-01", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.6704921383309878, "reason": null, "ragas_traces": null, "seconds": 1.667}
|
|
{"case_id": "interaction-01", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.4117647058823529, "reason": null, "ragas_traces": null, "seconds": 17.061}
|
|
{"case_id": "interaction-01", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 7.623}
|
|
{"case_id": "interaction-01", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.2, "reason": null, "ragas_traces": null, "seconds": 12.766}
|
|
{"case_id": "interaction-01", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.7215157470632865, "reason": null, "ragas_traces": null, "seconds": 1.672}
|
|
{"case_id": "contraindication-01", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.3409825829291848, "reason": null, "ragas_traces": null, "seconds": 48.681}
|
|
{"case_id": "interaction-01", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 10.94}
|
|
{"case_id": "interaction-01", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.3842396956036642, "reason": null, "ragas_traces": null, "seconds": 33.411}
|
|
{"case_id": "interaction-01", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.8730483526432252, "reason": null, "ragas_traces": null, "seconds": 1.596}
|
|
{"case_id": "interaction-01", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 0.6666666666666666, "reason": null, "ragas_traces": null, "seconds": 14.476}
|
|
{"case_id": "interaction-01", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 6.823}
|
|
{"case_id": "interaction-01", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.7413059826251285, "reason": null, "ragas_traces": null, "seconds": 1.913}
|
|
{"case_id": "interaction-01", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.413744114376974, "reason": null, "ragas_traces": null, "seconds": 36.867}
|
|
{"case_id": "interaction-01", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.2802822778088285, "reason": null, "ragas_traces": null, "seconds": 27.753}
|
|
{"case_id": "interaction-01", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.8172116514177749, "reason": null, "ragas_traces": null, "seconds": 1.573}
|
|
{"case_id": "interaction-01", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 0.9375, "reason": null, "ragas_traces": null, "seconds": 22.14}
|
|
{"case_id": "interaction-01", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 9.056}
|
|
{"case_id": "interaction-01", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.37156297641415215, "reason": null, "ragas_traces": null, "seconds": 50.306}
|
|
{"case_id": "warning-01", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 3.699}
|
|
{"case_id": "warning-01", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 5.158}
|
|
{"case_id": "warning-01", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 2.651}
|
|
{"case_id": "warning-01", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.6666666666666666, "reason": null, "ragas_traces": null, "seconds": 6.37}
|
|
{"case_id": "warning-01", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.7047779318608279, "reason": null, "ragas_traces": null, "seconds": 2.714}
|
|
{"case_id": "warning-01", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.0810195024746072, "reason": null, "ragas_traces": null, "seconds": 24.736}
|
|
{"case_id": "warning-01", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.5882352941176471, "reason": null, "ragas_traces": null, "seconds": 26.359}
|
|
{"case_id": "warning-01", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 2.696}
|
|
{"case_id": "warning-01", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 31.472}
|
|
{"case_id": "warning-01", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 5.802}
|
|
{"case_id": "warning-01", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 14.832}
|
|
{"case_id": "warning-01", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 2.868}
|
|
{"case_id": "warning-01", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.10641080113869646, "reason": null, "ragas_traces": null, "seconds": 14.807}
|
|
{"case_id": "warning-01", "mode": "local", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 4.366}
|
|
{"case_id": "indication-02", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.7110334196766454, "reason": null, "ragas_traces": null, "seconds": 2.434}
|
|
{"case_id": "warning-01", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.35135213308585866, "reason": null, "ragas_traces": null, "seconds": 47.174}
|
|
{"case_id": "warning-01", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.6153846153846154, "reason": null, "ragas_traces": null, "seconds": 22.224}
|
|
{"case_id": "indication-02", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.7790697639822254, "reason": null, "ragas_traces": null, "seconds": 2.969}
|
|
{"case_id": "indication-02", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 8.762}
|
|
{"case_id": "warning-01", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.12249738361039147, "reason": null, "ragas_traces": null, "seconds": 24.229}
|
|
{"case_id": "interaction-01", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.5550557834340627, "reason": null, "ragas_traces": null, "seconds": 71.67}
|
|
{"case_id": "indication-02", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 19.063}
|
|
{"case_id": "indication-02", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.9688923114258469, "reason": null, "ragas_traces": null, "seconds": 2.668}
|
|
{"case_id": "indication-02", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.8888888888888888, "reason": null, "ragas_traces": null, "seconds": 9.624}
|
|
{"case_id": "indication-02", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 19.292}
|
|
{"case_id": "indication-02", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.8459087552785475, "reason": null, "ragas_traces": null, "seconds": 2.298}
|
|
{"case_id": "indication-02", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.879525351297198, "reason": null, "ragas_traces": null, "seconds": 27.066}
|
|
{"case_id": "indication-02", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 8.1}
|
|
{"case_id": "indication-02", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.9166666666666666, "reason": null, "ragas_traces": null, "seconds": 18.608}
|
|
{"case_id": "indication-02", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.8045249582593978, "reason": null, "ragas_traces": null, "seconds": 2.342}
|
|
{"case_id": "indication-02", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.7906915876312732, "reason": null, "ragas_traces": null, "seconds": 29.27}
|
|
{"case_id": "indication-02", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.886151131659857, "reason": null, "ragas_traces": null, "seconds": 54.4}
|
|
{"case_id": "indication-02", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.8888888888888888, "reason": null, "ragas_traces": null, "seconds": 10.271}
|
|
{"case_id": "contraindication-02", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.7163312111885355, "reason": null, "ragas_traces": null, "seconds": 2.235}
|
|
{"case_id": "indication-02", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.8459444357354957, "reason": null, "ragas_traces": null, "seconds": 23.328}
|
|
{"case_id": "contraindication-02", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 4.685}
|
|
{"case_id": "contraindication-02", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 27.572}
|
|
{"case_id": "indication-02", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 31.836}
|
|
{"case_id": "contraindication-02", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.6760947364274177, "reason": null, "ragas_traces": null, "seconds": 2.845}
|
|
{"case_id": "contraindication-02", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 4.498}
|
|
{"case_id": "indication-02", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.5844439754447375, "reason": null, "ragas_traces": null, "seconds": 35.166}
|
|
{"case_id": "contraindication-02", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 2.242}
|
|
{"case_id": "contraindication-02", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.14184780773802788, "reason": null, "ragas_traces": null, "seconds": 23.373}
|
|
{"case_id": "contraindication-02", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 4.848}
|
|
{"case_id": "contraindication-02", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.8181818181818182, "reason": null, "ragas_traces": null, "seconds": 18.945}
|
|
{"case_id": "contraindication-02", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.7770866813218135, "reason": null, "ragas_traces": null, "seconds": 2.263}
|
|
{"case_id": "contraindication-02", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.7692307692307693, "reason": null, "ragas_traces": null, "seconds": 40.044}
|
|
{"case_id": "contraindication-02", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 3.572}
|
|
{"case_id": "contraindication-02", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.13751662015143826, "reason": null, "ragas_traces": null, "seconds": 20.615}
|
|
{"case_id": "contraindication-02", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.5651220185561544, "reason": null, "ragas_traces": null, "seconds": 2.353}
|
|
{"case_id": "contraindication-02", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.18701431227692278, "reason": null, "ragas_traces": null, "seconds": 37.011}
|
|
{"case_id": "interaction-02", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.33274921354883763, "reason": null, "ragas_traces": null, "seconds": 1.796}
|
|
{"case_id": "contraindication-02", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 0.7857142857142857, "reason": null, "ragas_traces": null, "seconds": 29.059}
|
|
{"case_id": "interaction-02", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 4.938}
|
|
{"case_id": "contraindication-02", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.5283169073938874, "reason": null, "ragas_traces": null, "seconds": 19.373}
|
|
{"case_id": "interaction-02", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.710010688080564, "reason": null, "ragas_traces": null, "seconds": 1.869}
|
|
{"case_id": "interaction-02", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.21428571428571427, "reason": null, "ragas_traces": null, "seconds": 20.394}
|
|
{"case_id": "interaction-02", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.3333333333333333, "reason": null, "ragas_traces": null, "seconds": 6.403}
|
|
{"case_id": "interaction-02", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.7142857142857143, "reason": null, "ragas_traces": null, "seconds": 16.228}
|
|
{"case_id": "warning-01", "mode": "bypass", "metric": "answer_correctness", "status": "error", "value": null, "error_type": "TimeoutError", "seconds": 180.013}
|
|
{"case_id": "interaction-02", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.7155466059400872, "reason": null, "ragas_traces": null, "seconds": 2.491}
|
|
{"case_id": "interaction-02", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 8.913}
|
|
{"case_id": "interaction-02", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.5252403367666899, "reason": null, "ragas_traces": null, "seconds": 2.704}
|
|
{"case_id": "interaction-02", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 0.8, "reason": null, "ragas_traces": null, "seconds": 18.739}
|
|
{"case_id": "interaction-02", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.43050382103090135, "reason": null, "ragas_traces": null, "seconds": 34.41}
|
|
{"case_id": "interaction-02", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.2305346007015037, "reason": null, "ragas_traces": null, "seconds": 25.879}
|
|
{"case_id": "interaction-02", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 3.255}
|
|
{"case_id": "interaction-02", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 5.051}
|
|
{"case_id": "contraindication-02", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.28961073692570205, "reason": null, "ragas_traces": null, "seconds": 56.977}
|
|
{"case_id": "interaction-02", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 0.875, "reason": null, "ragas_traces": null, "seconds": 14.994}
|
|
{"case_id": "warning-02", "mode": "hybrid", "metric": "answer_relevancy", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 2.724}
|
|
{"case_id": "interaction-02", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.6269070092994843, "reason": null, "ragas_traces": null, "seconds": 29.494}
|
|
{"case_id": "warning-02", "mode": "hybrid", "metric": "faithfulness", "status": "ok", "value": 0.7777777777777778, "reason": null, "ragas_traces": null, "seconds": 13.601}
|
|
{"case_id": "warning-02", "mode": "mix", "metric": "answer_relevancy", "status": "ok", "value": 0.8873992619846888, "reason": null, "ragas_traces": null, "seconds": 2.146}
|
|
{"case_id": "warning-02", "mode": "hybrid", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 12.75}
|
|
{"case_id": "interaction-02", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.14279842390947706, "reason": null, "ragas_traces": null, "seconds": 24.042}
|
|
{"case_id": "warning-02", "mode": "bypass", "metric": "answer_relevancy", "status": "ok", "value": 0.6650156269431805, "reason": null, "ragas_traces": null, "seconds": 2.065}
|
|
{"case_id": "warning-02", "mode": "mix", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 17.416}
|
|
{"case_id": "warning-02", "mode": "mix", "metric": "context_recall", "status": "ok", "value": 0.36363636363636365, "reason": null, "ragas_traces": null, "seconds": 13.192}
|
|
{"case_id": "warning-02", "mode": "naive", "metric": "answer_relevancy", "status": "ok", "value": 0.8354692338835598, "reason": null, "ragas_traces": null, "seconds": 2.499}
|
|
{"case_id": "interaction-02", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.36896249546678567, "reason": null, "ragas_traces": null, "seconds": 52.856}
|
|
{"case_id": "warning-02", "mode": "naive", "metric": "faithfulness", "status": "ok", "value": 1.0, "reason": null, "ragas_traces": null, "seconds": 16.66}
|
|
{"case_id": "warning-02", "mode": "naive", "metric": "context_recall", "status": "ok", "value": 0.3333333333333333, "reason": null, "ragas_traces": null, "seconds": 13.939}
|
|
{"case_id": "warning-02", "mode": "local", "metric": "answer_relevancy", "status": "ok", "value": 0.553480461774667, "reason": null, "ragas_traces": null, "seconds": 1.6}
|
|
{"case_id": "warning-02", "mode": "hybrid", "metric": "answer_correctness", "status": "ok", "value": 0.11460890995058678, "reason": null, "ragas_traces": null, "seconds": 40.771}
|
|
{"case_id": "warning-02", "mode": "mix", "metric": "answer_correctness", "status": "ok", "value": 0.5346924251233847, "reason": null, "ragas_traces": null, "seconds": 39.149}
|
|
{"case_id": "warning-02", "mode": "local", "metric": "context_recall", "status": "ok", "value": 0.0, "reason": null, "ragas_traces": null, "seconds": 12.394}
|
|
{"case_id": "warning-02", "mode": "local", "metric": "faithfulness", "status": "ok", "value": 0.8666666666666667, "reason": null, "ragas_traces": null, "seconds": 21.547}
|
|
{"case_id": "warning-02", "mode": "naive", "metric": "answer_correctness", "status": "ok", "value": 0.5208708409607992, "reason": null, "ragas_traces": null, "seconds": 30.929}
|
|
{"case_id": "warning-02", "mode": "local", "metric": "answer_correctness", "status": "ok", "value": 0.10882217571332953, "reason": null, "ragas_traces": null, "seconds": 34.551}
|
|
{"case_id": "warning-02", "mode": "bypass", "metric": "answer_correctness", "status": "ok", "value": 0.42470478380505927, "reason": null, "ragas_traces": null, "seconds": 61.649}
|
|
{"case_id": "warning-01", "mode": "bypass", "metric": "answer_correctness", "llm_max_tokens": 8192, "status": "ok", "value": 0.17177298311723022, "reason": null, "ragas_traces": null, "seconds": 41.639}
|