全部项目

better-cheaper-llm

davidzna/better-cheaper-llm

Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.

Python
星标
0
派生
0

收录依据

审计已有 LLM 日志中的决策调用,用 Jev 回放,并提供影子/执行检查及 LLM 回退;迁移前先按实际流量测量。

相关项目

  • jev-judge

    YAML-based evaluation runner for recorded LLM outputs, with TypeSafe Jev API integration, offline mock mode, and CI reports.

    共同主题: llm-as-a-judge

  • pytest-jev

    Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.

    共同主题: llm-evaluation

  • jev-github-quality-gate

    A Jev-powered quality gate for GitHub issues, pull requests, and commits.

    共同主题: llm-evaluation