llm-observability-evals

【数据与研究】LLM and agent observability, tracing, and evaluation workflows with langfuse, phoenix-cli, and phoenix-evals. Use when instrumenting Langfuse, Phoenix, OpenTelemetry GenAI traces, eval datasets, prompt experiments, latency/cost debugging, trace scoring, or regression testing agent behavior.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准