Phoenix does not currently support running datasets as payloads to arbitrary APIs natively via the UI or a "test run" button; this workflow must be set up manually using the Python API or client. However, this feature has been requested by users, and the Phoenix team welcomes contributions—especially for enhancements like this. You are encouraged to start with a "good first issue" on the GitHub board and submit a pull request for new features or improvements. The team reviews PRs promptly and provides feedback for approval and merging.
If you want to contribute, fork the Phoenix repository, create a new branch, and open a PR describing your changes and motivation. For more details, see the contribution guidelines and development guide in the documentation. Would you like more detail on the current experiment/dataset API or guidance on where to start your contribution?
Sources:
- <https://github.com/Arize-ai/phoenix/issues/7528|https://github.com/Arize-ai/phoenix/issues/7528>
- <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1751374792.815499|https://arize-ai.slack.com/archives/C04R3GXC8HK/p1751374792.815499>
