Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# dispatchAI API Server
|
| 2 |
+
|
| 3 |
+
OpenAI-compatible inference API running on real phone hardware.
|
| 4 |
+
|
| 5 |
+
## Files
|
| 6 |
+
|
| 7 |
+
- api/gateway.py - FastAPI gateway (port 8081)
|
| 8 |
+
- api/phone_proxy_v2.py - Phone proxy (HTTP to ADB to llama-cli)
|
| 9 |
+
- api/mcp_server.py - MCP server (4 tools)
|
| 10 |
+
- api/test_api.py - Test script
|
| 11 |
+
- api/security_audit.py - Security audit
|
| 12 |
+
- api/Caddyfile - HTTPS config
|
| 13 |
+
- api/openapi.yaml - OpenAPI spec
|
| 14 |
+
|
| 15 |
+
## Quick Start
|
| 16 |
+
|
| 17 |
+
pip install fastapi uvicorn httpx
|
| 18 |
+
python -m uvicorn api.gateway:app --port 8081
|
| 19 |
+
|
| 20 |
+
## API
|
| 21 |
+
|
| 22 |
+
POST /v1/chat/completions
|
| 23 |
+
GET /v1/models
|
| 24 |
+
GET /v1/usage
|
| 25 |
+
GET /admin/phones
|