DEPLOY_GUIDE.md

# MyDuck AI - Hugging Face Spaces Deployment Guide

## 🚀 Quick Deploy to Hugging Face

### Step 1: Create Hugging Face Account
1. Go to https://huggingface.co/join
2. Sign up for free account

### Step 2: Create New Space
1. Go to https://huggingface.co/new-space
2. Fill in details:
   - **Space name**: `myduck-ai` (or your choice)
   - **License**: MIT
   - **Select the Space SDK**: **Docker**
   - **Space hardware**: **CPU basic** (Free)
3. Click **Create Space**

### Step 3: Upload Files
Upload these 4 files to your Space:
1. `Dockerfile`
2. `README.md`
3. `app.py`
4. `requirements.txt`

**Method 1**: Web Interface
- Click "Files" tab → "Add file" → Upload each file

**Method 2**: Git (Recommended)
```bash
# Clone your space
git clone https://huggingface.co/spaces/YOUR_USERNAME/myduck-ai
cd myduck-ai

# Copy files
copy C:\Users\admin\Downloads\duckai\MyDuck-HuggingFace\* .

# Push to Hugging Face
git add .
git commit -m "Initial deployment"
git push
```

### Step 4: Wait for Build
- Hugging Face will automatically build your Docker container
- Takes 2-5 minutes
- Watch the "Building" status in the Space

### Step 5: Test Your API
Once built, your API will be at:
```
https://YOUR_USERNAME-myduck-ai.hf.space/api/chat
```

Test with PowerShell:
```powershell
(Invoke-WebRequest -Method Post -Uri "https://YOUR_USERNAME-myduck-ai.hf.space/api/chat" -Headers @{ "Content-Type" = "application/json" } -Body '{"prompt":"do you know english"}').Content
```

## 📝 API Usage

**Endpoint**: POST `/api/chat`

**Request**:
```json
{
  "prompt": "Your message here",
  "model": "gpt-4o-mini"
}
```

**Response**:
```json
{
  "status": "success",
  "text": "AI response text"
}
```

## 🎯 Supported Models

- `gpt-4o-mini` (default) - Fast and efficient
- `claude-3-haiku` - Anthropic's Claude
- `llama` - Llama 3.3 70B
- `mistral` - Mixtral 8x7B
- `o3-mini` - OpenAI O3

## 🔧 Configuration

Default settings work out of the box. No API keys needed!

The app runs on port 7860 (Hugging Face default).

## ✅ Advantages over Vercel

- ✅ **Works with DuckDuckGo** (Vercel IPs are blocked)
- ✅ **Free forever** (CPU basic tier)
- ✅ **No rate limits** from Hugging Face
- ✅ **Easy deployment**
- ✅ **Always online**

## 📚 Files in This Directory

```
MyDuck-HuggingFace/
├── Dockerfile          # Docker container configuration
├── README.md           # Hugging Face Space description
├── app.py             # Flask API application
├── requirements.txt    # Python dependencies
└── DEPLOY_GUIDE.md    # This file
```

## 🎓 Troubleshooting

**Space shows error**: Check the "Logs" tab in your Space

**Build fails**: Make sure all 4 files are uploaded correctly

**Empty responses**: The DuckDuckGo API may be temporarily unavailable, try again

**429 errors**: Too many requests, wait a few seconds and retry

## 🌟 Success!

Once deployed, share your API:
```
https://YOUR_USERNAME-myduck-ai.hf.space/api/chat
```

Enjoy free DuckDuckGo AI! 🦆✨