haiku.rag/evaluations/tests
Yiorgis Gozadinos a528ab912f
Record per-case retrieval diagnostics in evaluations
Count tool traffic from the message history, where refused and repeated
calls stay visible, unlike state.searches which is keyed by query.
2026-07-30 14:56:17 +03:00
..
__init__.py Tests for gepa 2026-03-12 12:05:25 +02:00
test_benchmark.py replace haiku.skills with native Pydantic AI capabilities 2026-07-24 15:26:17 +03:00
test_capability_runner.py Record per-case retrieval diagnostics in evaluations 2026-07-30 14:56:17 +03:00
test_citation_evaluators.py Remove unecessary Mean Reciprocal Rank metric 2026-06-01 10:40:52 +03:00
test_config.py remove dataset-specific system prompts 2026-04-28 14:33:25 +03:00
test_datasets.py Restore hotpotqa evaluation dataset 2026-07-17 16:25:27 +03:00
test_evaluators.py Match the numeric scale convention in Number-Match 2026-06-06 14:52:05 +03:00
test_numbers.py Normalize unicode signs 2026-06-06 14:52:04 +03:00
test_submission.py Add T²-RAGBench leaderboard submission exporter 2026-06-08 11:51:02 +03:00