How To: Host Phoenix + Persistence
With Arize Phoenix, getting started is relatively straightforward because you can run it locally and start iterating quickly during the development and experiment phases of building an LLM application. However, once you’re ready for production — or if you want to collaborate with your teammates — it’s time to deploy Phoenix.
In addition to a managed hosted version of Phoenix, there are self-hosted options for AI engineers who want greater control, custom configurations, or enhanced data privacy.
Demo
This demo shows how to deploy Phoenix via Docker/Kubernetes.
What Are the Data Persistence Options for Hosted Phoenix?
You can either persist data via a SQLite database (default), or you can use a PostgreSQL database. If you run Phoenix without any configuration, it will use SQLite by default.
What Does Hosted Phoenix Enable You To Do?
Phoenix is an open source tool that helps you trace, evaluate, and iterate on generative AI applications. The hosted version of Phoenix offers the ability to persist application telemetry data generated during AI development in order to better experiment, iterate, and collaborate in development or production. AI engineers can instantly log traces, persist datasets, run experiments, run evaluations – and share those insights with colleagues.
Helpful Resources
Some helpful resources for getting started:
- 📓Hosted Phoenix: Docs + Cookbooks
- Phoenix on GitHub (please consider a ⭐)
Questions? Feel free to reach out in the Arize community.