Spaces:

mrsavage1
/

mofh-api-proxy

Running

App Files Files Community

mofh-api-proxy / README.md

mrsavage1

Upload 14 files

90b617f verified 24 days ago

preview code

raw

history blame contribute delete

4.97 kB

metadata

title: MOFH API Proxy
emoji: 🌐
colorFrom: blue
colorTo: green
sdk: docker
sdk_version: 4.36.0
python_version: '3.11'
app_file: app.py
pinned: false

🚀 IONA AI + MOFH API Proxy

Intelligent Website Generator & MyOwnFreeHost API Proxy

✨ Features

🤖 AI Website Generation - Generate complete websites with HTML, CSS, JS, and MySQL
🏠 MOFH Integration - Create free hosting accounts via API
📊 Beautiful Dashboard - Real-time system monitoring with uptime display
🌐 External IP Display - Easy MOFH whitelist configuration
🏥 Health Checks - Monitor system health and performance
🧪 Test Endpoints - Verify AI functionality before use

🎯 Quick Start

1. Visit Dashboard

https://your-space.hf.space/

2. Copy External IP

Displayed prominently on dashboard
Add to MOFH API whitelist

3. Test AI

https://your-space.hf.space/test

4. Generate Website

curl -X POST https://your-space.hf.space/generate-website \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a modern portfolio website",
    "business_type": "portfolio",
    "color_scheme": "modern"
  }'

📡 API Endpoints

Method	Endpoint	Description
GET	`/`	System dashboard (HTML)
GET	`/health`	Health check (JSON)
GET	`/test`	Test AI generation
POST	`/generate-website`	Generate website with AI
POST	`/create`	Create MOFH hosting account

🔧 Configuration

Environment Variables

GROQ_API_KEYS - Groq AI API keys (4 keys for load balancing)
MOFH_API_USERNAME - MOFH API username
MOFH_API_PASSWORD - MOFH API password

AI Models (2026)

llama-3.1-8b-instant - Fastest (131K context)
llama-3.3-70b-versatile - Best quality
qwen/qwen3-32b - Large output (40K tokens)
meta-llama/llama-4-scout-17b-16e-instruct - New Llama 4

📊 Dashboard Features

⏱️ Uptime Tracking - Running since, uptime duration
🌐 Network Info - Hostname, local IP, external IP
💻 System Resources - CPU usage, memory usage with progress bars
🤖 AI Configuration - Active models, API keys, request counts
📈 Request Statistics - Total, generate, create, errors
🔄 Auto-Refresh - Updates every 30 seconds

🧪 Testing

Health Check

curl https://your-space.hf.space/health

AI Test

curl https://your-space.hf.space/test

Generate Website

curl -X POST https://your-space.hf.space/generate-website \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a simple landing page for a tech startup",
    "business_type": "landing",
    "color_scheme": "modern",
    "include_database": false,
    "features": ["contact_form", "testimonials"]
  }'

📝 Response Format

Success Response

{
  "success": true,
  "model_used": "llama-3.3-70b-versatile",
  "files": {
    "html": "<!DOCTYPE html>...",
    "css": "body { ... }",
    "js": "console.log('...');",
    "sql": "CREATE TABLE...",
    "config": "<?php...",
    "readme": "# Setup Guide..."
  },
  "tokens_used": {
    "prompt_tokens": 1234,
    "completion_tokens": 5678
  },
  "generation_time": 1234567890
}

Error Response

{
  "detail": "Error message here"
}

🔒 Security

✅ Input validation (Pydantic)
✅ Prompt length limits (10-10000 chars)
✅ Username validation (3-20 chars)
✅ Email format validation
✅ Error handling and logging
✅ Request tracking

📈 Monitoring

Dashboard Metrics

Uptime duration
Total requests
Error count
CPU usage
Memory usage
API key usage

Health Endpoint

{
  "status": "healthy",
  "uptime_seconds": 12345,
  "timestamp": "2026-01-15T10:30:00",
  "requests": {
    "total": 150,
    "generate": 100,
    "create": 45,
    "errors": 5
  }
}

🛠️ Development

Install Dependencies

pip install -r requirements.txt

Run Locally

uvicorn app:app --host 0.0.0.0 --port 7860 --reload

Deploy to HF Space

Create new Space on Hugging Face
Upload app.py and requirements.txt
Set Space SDK to "Docker" or "Gradio"
Space will auto-deploy

👨‍💻 Developer

Pratyush Srivastava

GitHub: @pratyush
Portfolio: pratyush.dev

📄 License

MIT License - Feel free to use and modify

🎉 Version

2026.1.0 - Enhanced with uptime dashboard, external IP display, and comprehensive monitoring

Status: ✅ Production Ready (Updated 2026-03-30)