pytest-jev
allebee/pytest-jev
Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.
Python
- 星标
- 8
- 派生
- 1
收录依据
pytest-jev 为 LLM 应用输出增加语义断言,用返回概率的 Jev 判断含义,而不是逐字比对。
allebee/pytest-jev
Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.
pytest-jev 为 LLM 应用输出增加语义断言,用返回概率的 Jev 判断含义,而不是逐字比对。
Record/replay regression tests for Jev (TypeSafe System One) question packs — accuracy, calibration and cost gates in CI
共同主题: llm-evaluation, testing
YAML-based evaluation runner for recorded LLM outputs, with TypeSafe Jev API integration, offline mock mode, and CI reports.
共同主题: testing
A Jev-powered quality gate for GitHub issues, pull requests, and commits.
共同主题: llm-evaluation