With Arize Phoenix, getting started is relatively straightforward because you can run it locally and start iterating quickly during the development and experiment phases. 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. Data persistence options for Phoenix include a SQLite database (default), or PostgreSQL.
This demo walks through how to host Phoenix and uses PostgreSQL.
🔗 Helpful Links
Arize Phoenix on GitHub (please consider a ⭐) https://github.com/Arize-ai/phoenix
Hosted Phoenix: https://docs.arize.com/phoenix/hosted-phoenix
Follow Trevor Laviale: https://www.linkedin.com/in/trevor-laviale/
More about Arize Phoenix: 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. The solution has a foundation in open source and features a fully hosted, online, persistent deployment option for teams that do not want to self host. AI engineers can instantly log traces, persist datasets, run experiments, run evaluations – and share those insights with colleagues.
