24 lines
2.4 KiB
Plaintext
24 lines
2.4 KiB
Plaintext
test_ambiguous_brand_does_not_invent_single_substance (test_agent_evaluation.AgentTests.test_ambiguous_brand_does_not_invent_single_substance) ... ok
|
|
test_failures_are_reported_not_scored_as_wrong (test_agent_evaluation.AgentTests.test_failures_are_reported_not_scored_as_wrong) ... ok
|
|
test_graph_budget_reserves_original_source_text (test_agent_evaluation.AgentTests.test_graph_budget_reserves_original_source_text) ... ok
|
|
test_judge_accepts_reasoning_prefix_without_scoring_it (test_agent_evaluation.AgentTests.test_judge_accepts_reasoning_prefix_without_scoring_it) ... ok
|
|
test_judge_rejects_more_supported_claims_than_claims (test_agent_evaluation.AgentTests.test_judge_rejects_more_supported_claims_than_claims) ... ok
|
|
test_missing_data_is_not_no_interaction (test_agent_evaluation.AgentTests.test_missing_data_is_not_no_interaction) ... ok
|
|
test_short_brand_and_full_name (test_agent_evaluation.AgentTests.test_short_brand_and_full_name) ... ok
|
|
test_slovak_inflection_and_brand (test_agent_evaluation.AgentTests.test_slovak_inflection_and_brand) ... ok
|
|
test_source_identity_accepts_pil_and_detail (test_agent_evaluation.AgentTests.test_source_identity_accepts_pil_and_detail) ... ok
|
|
test_unrelated_prefix_not_detected (test_agent_evaluation.AgentTests.test_unrelated_prefix_not_detected) ... ok
|
|
test_abstention_not_penalized_by_answerable_metrics (test_ragas_data.RagasDataTests.test_abstention_not_penalized_by_answerable_metrics) ... ok
|
|
test_bypass_context_metrics_are_not_zero (test_ragas_data.RagasDataTests.test_bypass_context_metrics_are_not_zero) ... ok
|
|
test_errors_not_included_in_score_mean (test_ragas_data.RagasDataTests.test_errors_not_included_in_score_mean) ... ok
|
|
test_nonfinite_scores_are_rejected (test_ragas_data.RagasDataTests.test_nonfinite_scores_are_rejected) ... ok
|
|
test_reference_never_leaks_into_retrieved_context (test_ragas_data.RagasDataTests.test_reference_never_leaks_into_retrieved_context) ... ok
|
|
test_resume_does_not_double_count (test_ragas_data.RagasDataTests.test_resume_does_not_double_count) ... ok
|
|
test_string_context_cannot_be_silently_split_into_characters (test_ragas_data.RagasDataTests.test_string_context_cannot_be_silently_split_into_characters) ... ok
|
|
test_undefined_metric_is_not_a_zero_score (test_ragas_data.RagasDataTests.test_undefined_metric_is_not_a_zero_score) ... ok
|
|
|
|
----------------------------------------------------------------------
|
|
Ran 18 tests in 0.001s
|
|
|
|
OK
|