haiku.rag/evaluations/evaluations/evaluators
2026-08-17 10:56:26 +03:00
..
__init__.py Simplify the eval harness and share the embed-fill path. 2026-08-17 10:56:26 +03:00
citation.py Add MTRAG ClapNQ multi-turn evaluation 2026-08-17 10:53:16 +03:00
conversation.py Simplify the eval harness and share the embed-fill path. 2026-08-17 10:56:26 +03:00
judge.py bump pydantic-ai-slim to 1.100 and haiku.skills to 0.17 2026-05-21 13:20:54 +03:00
map.py Simplify the eval harness and share the embed-fill path. 2026-08-17 10:56:26 +03:00
number_match.py Match the numeric scale convention in Number-Match 2026-06-06 14:52:05 +03:00
refusal.py Simplify the eval harness and share the embed-fill path. 2026-08-17 10:56:26 +03:00
retrieval.py Add MTRAG ClapNQ multi-turn evaluation 2026-08-17 10:53:16 +03:00
transcript.py Add MTRAG ClapNQ multi-turn evaluation 2026-08-17 10:53:16 +03:00