Rodrigo Rodriguez (Pragmatismo)
8d7c4d3770
- Add mobile deployment guide for Android & HarmonyOS (BotOS) - Add hardware guide for SBCs (Raspberry Pi, Orange Pi, etc.) - Add quick start guide for 5-minute deployment - Add local LLM guide with llama.cpp for offline AI - Update SUMMARY.md to place chapter after Security (Part XII) - Include bloatware removal, Magisk module, GSI instructions - Cover NPU acceleration on Orange Pi 5 with rkllm |
||
|---|---|---|
| .. | ||
| hardware.md | ||
| local-llm.md | ||
| mobile.md | ||
| quick-start.md | ||
| README.md | ||
Chapter 13: Device & Offline Deployment
Deploy General Bots to any device - from smartphones to Raspberry Pi to industrial kiosks - with local LLM inference for fully offline AI capabilities.
Overview
General Bots can run on any device, from mobile phones to minimal embedded hardware with displays as small as 16x2 character LCDs, enabling AI-powered interactions anywhere:
- Kiosks - Self-service terminals in stores, airports, hospitals
- Industrial IoT - Factory floor assistants, machine interfaces
- Smart Home - Wall panels, kitchen displays, door intercoms
- Retail - Point-of-sale systems, product information terminals
- Education - Classroom assistants, lab equipment interfaces
- Healthcare - Patient check-in, medication reminders
┌─────────────────────────────────────────────────────────────────────────────┐
│ Embedded GB Architecture │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Display │ │ botserver │ │ llama.cpp │ │
│ │ LCD/OLED │────▶│ (Rust) │────▶│ (Local) │ │
│ │ TFT/HDMI │ │ Port 8088 │ │ Port 8080 │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
│ │ │ │ │
│ │ │ │ │
│ ┌──────▼──────┐ ┌──────▼──────┐ ┌──────▼──────┐ │
│ │ Keyboard │ │ SQLite │ │ TinyLlama │ │
│ │ Buttons │ │ (Data) │ │ GGUF │ │
│ │ Touch │ │ │ │ (~700MB) │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
What's in This Chapter
Mobile Deployment
- Mobile (Android & HarmonyOS) - BotOS for smartphones and tablets
Embedded Deployment
- Supported Hardware - SBCs, displays, and peripherals
- Quick Start - Deploy in 5 minutes
- Local LLM - Offline AI with llama.cpp
Deployment Options
| Platform | Use Case | Requirements |
|---|---|---|
| Android/HarmonyOS | Smartphones, tablets, kiosks | Any Android 8+ device |
| Raspberry Pi | IoT, displays, terminals | 1GB+ RAM |
| Orange Pi | Full offline AI | 4GB+ RAM for LLM |
| Industrial | Factory, retail, healthcare | Any ARM/x86 SBC |