localai

# LocalAI - Local AI Inference API

## Overview

The `localai` command manages the LocalAI service using Podman Quadlet containers. It provides an OpenAI-compatible API for running AI models locally with GPU acceleration.

**Key Features:**

- OpenAI-compatible API endpoints
- GPU-specific container images (auto-selected)
- Multiple GPU support (NVIDIA, AMD, Intel)
- Cross-pod DNS via `bazzite-ai` network

## Quick Reference

| Action | Command | Description |
|--------|---------|-------------|
| Config | `ujust localai config` | Configure LocalAI |
| Delete | `ujust localai delete` | Remove instance config and container |
| Logs | `ujust localai logs [--lines=N]` | View container logs |
| Restart | `ujust localai restart` | Restart server |
| Shell | `ujust localai shell [-- CMD]` | Open shell or execute command in container |
| Start | `ujust localai start` | Start LocalAI server |
| Status | `ujust localai status` | Show instance status |
| Stop | `ujust localai stop` | Stop LocalAI server |
| URL | `ujust localai url` | Show OpenAI-compatible API URL |

## Parameters

| Parameter | Long Flag | Short | Default | Description |
|-----------|-----------|-------|---------|-------------|
| Port | `--port` | `-p` | `8080` | Host port for API |
| Image | `--image` | `-i` | (auto by GPU) | Container image |
| Tag | `--tag` | `-t` | `latest` | Image tag |
| Bind | `--bind` | `-b` | `127.0.0.1` | Bind address |
| Config Dir | `--config-dir` | `-c` | `~/.config/localai/1` | Config/models directory |
| Workspace | `--workspace-dir` | `-w` | (empty) | Workspace mount |
| GPU Type | `--gpu-type` | `-g` | `auto` | GPU type |
| Instance | `--instance` | `-n` | `1` | Instance number or `all` |
| Lines | `--lines` | `-l` | `50` | Log lines to show |

## GPU-Specific Images

LocalAI uses different container images optimized for each GPU type:

| GPU Type | Image | Auto-Selected? |
|----------|-------|----------------|
| CPU (none) | `localai/localai:latest` | Yes |
| NVIDIA | `loca