| Command | Description |
|---|---|
| acceleration | Manage dataset acceleration features |
| add (opens in a new tab) | Add Spicepod - adds a Spicepod to the project |
| catalogs (opens in a new tab) | List catalogs (opens in a new tab) loaded by the Spice runtime |
| chat (opens in a new tab) | Chat with an LLM |
| cloud | Manage Spice Cloud resources |
| cluster | Cluster operations for the Spice runtime |
| completion (opens in a new tab) | Generate the autocompletion script for the specified shell |
| connect (opens in a new tab) | Connect to a Spice.ai Cloud Platform app |
| dataset (opens in a new tab) | Dataset operations (configure datasets) |
| datasets (opens in a new tab) | Lists datasets loaded by the Spice runtime |
| eval | Run model evaluation |
| help | Help about any command |
| init (opens in a new tab) | Initialize Spice app - creates a new spicepod.yaml |
| install (opens in a new tab) | Install or reinstall the Spice.ai runtime |
| login (opens in a new tab) | Login to Spice.ai or configure credentials for data sources |
| models (opens in a new tab) | Lists models loaded by the Spice runtime |
| nsql | Text-to-SQL REPL - translate natural language to SQL |
| pods (opens in a new tab) | Lists Spicepods loaded by the Spice runtime |
| query (opens in a new tab) | Submit an async query or start an interactive async query REPL |
| refresh (opens in a new tab) | Refresh a dataset loaded by the Spice runtime |
| run (opens in a new tab) | Run Spice - starts the Spice runtime, installing if necessary |
| search (opens in a new tab) | Search datasets with embeddings |
| sql (opens in a new tab) | Start an interactive SQL query session against the Spice runtime |
| status (opens in a new tab) | Spice runtime status |
| trace (opens in a new tab) | Return traces for operations that occurred in Spice |
| upgrade (opens in a new tab) | Upgrades the Spice CLI and runtime to the latest release |
| version (opens in a new tab) | Spice CLI version |
| workers | Lists workers loaded by the Spice runtime |
All commands have a help flag --help or -h to print its usage documentation:
