wangwei b870ed8730 feat: make contexts optional in /api/score ...

When contexts is absent, metrics that require retrieved_contexts
(faithfulness, context_recall, context_precision, noise_sensitivity)
are automatically skipped and appear in skipped_metrics.
Only answer_relevancy, factual_correctness, semantic_similarity
remain computable without contexts.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

2026-06-24 14:42:03 +08:00

..

webapp

feat: make contexts optional in /api/score

2026-06-24 14:42:03 +08:00

__init__.py

test: ensure test package structure and all webapp tests pass

2026-06-16 16:27:54 +08:00

test_advisor_rules.py

test: ensure test package structure and all webapp tests pass

2026-06-16 16:27:54 +08:00

test_advisor_writer.py

feat(advisor): add optimization advisor module

2026-06-16 17:06:19 +08:00

test_dataset_build.py

first commit

2026-06-12 14:02:15 +08:00

test_offline_eval.py

feat: use weighted metric means and add weighted_score row to summary.md

2026-06-18 16:59:56 +08:00

test_online_eval.py

first commit

2026-06-12 14:02:15 +08:00

test_webapp_report_builder.py

feat: report_builder uses weighted means; ReportData gains weighted_score_mean

2026-06-18 17:16:09 +08:00

test_weights.py

feat: add metric/doc weight computation module (weights.py)

2026-06-18 16:47:47 +08:00