by Arize-ai · LLM 插件 · ★ 11.9k
Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides: Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation. Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals. Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning. Experiments - Track and evaluate changes to prompts, LLMs, and retrieval. Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
| Stars | 11,910 |
| Forks | 1,221 |
| Language | Python |
| Category | LLM 插件 |
| Quality Score | 51.0222649602654/100 |
| Open Issues | 1174 |
| Last Updated | 2026-10-19 |
| Created | 2022-11-09 |
| Platforms | python |
| Est. Tokens | ~22k |
These tools work well together with phoenix for enhanced workflows:
Explore other popular llm 插件 tools:
phoenix is AI Observability & Evaluation. It is categorized as a LLM 插件 with 11.9k GitHub stars.
phoenix is primarily written in Python. It covers topics such as agents, ai-monitoring, ai-observability.
You can find installation instructions and usage details in the phoenix GitHub repository at github.com/Arize-ai/phoenix. The project has 11.9k stars and 1221 forks, indicating an active community.