Open-source AI observability and evaluation platform for LLM applications. Provides OpenTelemetry-based tracing, LLM evaluation, versioned datasets, and experiment tracking.
Project overview
Open-source AI observability and evaluation platform for LLM applications. Provides OpenTelemetry-based tracing, LLM evaluation, versioned datasets, and experiment tracking.
Project type
Evaluation & Observability · Infrastructure
Deployment
Python environment
License
License pending
Best for
AI engineers, developers, and data teams working with LLM applications who require evaluation, observability, and prompt experimentation.
Key capabilities
Trace LLM application's runtime using OpenTelemetry-based instrumentation.
Leverage LLMs to benchmark application performance using response and retrieval evals.
Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
Track and evaluate changes to prompts, LLMs, and retrieval.
Provides a unified interface to Phoenix's capabilities via Model Context Protocol.
Limitations and risks
The Azure template serves plain HTTP and requires a TLS proxy for production use.
Getting started
Installable via pip or conda with a single command to start. The initial setup is considered easy, starting with 'pip install arize-phoenix'. Telemetry is disabled by default.
Evidence and sources
README: Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:
README: Install Phoenix via `pip` or `conda` and have a fully functional Phoenix ```shell pip install arize-phoenix phoenix serve ```
README: Phoenix container images are available via [Docker Hub](https://hub.docker.com/r/arizephoenix/phoenix) and can be deployed using Docker or Kubernetes. Arize AI also provides cloud…
Release: arize-phoenix: v18.1.0
README: MCP server implementation for Arize Phoenix providing unified interface to Phoenix's capabilities