setup
Start here to get Spice.ai working end to end — take a directory from nothing to a running local runtime that answers SQL with real rows. Checks the existing installation, creates or reuses a spicepod, seeds a local dataset, starts spice run in the background, waits for /v1/ready, and verifies with a query, using a bundled helper script. Also the reference for the Spice CLI, runtime ports and endpoints, and the /v1/sql request format. Installation and upgrades get documentation guidance only; this skill does not install software. Use it whenever the user wants to set up, try, start, run, or get started with Spice, create a new Spice project or spicepod, see a first query result, asks why spice sql shows no tables, how to install Spice, or which port or HTTP endpoint to use. For a cookbook recipe use cookbook; to add a specific source to a project that already runs, use connectors.
Pinned to revision 5f5e66ce0a22, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/setup/SKILL.md
- skills/setup/evals/evals.json
- skills/setup/examples/data/sales.csv
- skills/setup/examples/spicepod.local-csv.yaml
- skills/setup/scripts/spice-local.sh
Every link opens the file at its source, pinned to the revision this page describes.