jevassert
dtduc-git/jevassert
Record/replay regression tests for Jev (TypeSafe System One) question packs — accuracy, calibration and cost gates in CI
Python
- 星标
- 0
- 派生
- 0
收录依据
jevassert 为 Jev 问题集提供回归测试:记录在线预测后,可离线、确定性地检查保存结果;检查阶段不调用模型。
dtduc-git/jevassert
Record/replay regression tests for Jev (TypeSafe System One) question packs — accuracy, calibration and cost gates in CI
jevassert 为 Jev 问题集提供回归测试:记录在线预测后,可离线、确定性地检查保存结果;检查阶段不调用模型。
YAML-based evaluation runner for recorded LLM outputs, with TypeSafe Jev API integration, offline mock mode, and CI reports.
共同主题: evals, testing
Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.
共同主题: llm-evaluation, testing
Test, calibrate and route System One decision models (Jev, Laya, kev, llama.cpp, Ollama) on your own data.
共同主题: calibration, llm-evaluation