Phoenix is an open-source AI observability platform that can help you trace, evaluate, and experiment with your Groq applications.
It provides:
- Tracing - Trace your Groq application's runtime using OpenTelemetry-based instrumentation.
- Evaluation - Leverage Groq 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.
Phoenix runs practically anywhere, including your Jupyter notebook, local machine, containerized deployment, or in the cloud.
The latest Phoenix + Groq docs can be found here.
