Documentation Index
Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Vercel Sandbox runs each evaluation in ephemeral compute on Vercel’s infrastructure, scoped to a specific Vercel team and project. It supports both Python and TypeScript evaluators.
Setup
Vercel Sandbox needs three values:| Value | What it is | Where to find it |
|---|---|---|
VERCEL_TOKEN | A personal access token | Account Settings → Tokens |
VERCEL_PROJECT_ID | The project’s resource ID | Project Settings → General |
VERCEL_TEAM_ID | The team’s resource ID | https://vercel.com/teams/<your-team>/settings#team-id |
- Add the credentials to Phoenix. Open Settings → Sandboxes, find the Vercel Sandbox row, click the gear icon, and paste each value into the matching field. You can also set them as environment variables on the Phoenix server.
- Create a configuration. In Sandbox Configurations, click New Sandbox, pick Vercel Sandbox, choose the language (Python or TypeScript), set the timeout and any environment variables or dependencies, and save.