Documentation/FASTAPI_QUICKSTART.md

# FastAPI Quick Start Guide

## 🎯 First Time Setup

### Step 1: Create Vector Database (ONE TIME ONLY)
```bash
python setup_db.py
```

This will:
- Load 3400+ schemes from `updated_data.csv`
- Convert them into embeddings
- Create and save vector database to `./chroma_db/`
- Takes 2-5 minutes (only need to do this once!)

**When to run `setup_db.py` again:**
- When you have new/updated CSV data
- If you delete the `chroma_db` folder
- If you want to rebuild the database with different settings

---

## 🚀 Start the API Server (Every Time)

1. **Activate virtual environment:**
   ```bash
   .venv\Scripts\activate
   ```

2. **Run the application:**
   ```bash
   python app.py
   ```
   
   This now starts in **seconds** (not minutes!) because it loads the pre-built database.

3. **Access the API:**
   - API Server: http://127.0.0.1:8000
   - Interactive Docs: http://127.0.0.1:8000/docs
   - Alternative Docs: http://127.0.0.1:8000/redoc

---

## 🧪 Test the API

### Option 1: Use the test script
```bash
python test_api.py
```

### Option 2: Use the interactive docs
1. Open http://127.0.0.1:8000/docs in your browser
2. Click on "POST /query"
3. Click "Try it out"
4. Enter your question and click "Execute"

### Option 3: Use cURL
```bash
curl -X POST http://127.0.0.1:8000/query -H "Content-Type: application/json" -d "{\"question\": \"What schemes are available for students?\"}"
```

---

## 📝 Sample API Calls

### Python Example
```python
import requests

response = requests.post(
    "http://127.0.0.1:8000/query",
    json={
        "question": "My daughter is studying in 9th standard. What schemes are applicable?",
        "state": "Maharashtra"
    }
)

print(response.json()["answer"])
```

### JavaScript Example
```javascript
const response = await fetch('http://127.0.0.1:8000/query', {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    question: 'What scholarships are available for SC students?'
  })
});

const data = await response.json();
console.log(data.answer);
```

---

## 📚 Available Endpoints

| Method | Endpoint | Description |
|--------|----------|-------------|
| GET | `/` | API information |
| GET | `/health` | Health check |
| GET | `/states` | List of Indian states |
| POST | `/query` | Query government schemes |

---

## 🛠️ Troubleshooting

**"Vector database not found" error?**
- Run `python setup_db.py` first to create the database

**API won't start?**
- Check if port 8000 is already in use
- Verify `.env` file has `GROQ_API_KEY`

**Slow first query?**
- Normal! First query loads the model
- Subsequent queries will be faster

**Error 500?**
- Check your Groq API key is valid
- Ensure `chroma_db` folder exists

**Need to update data?**
- Update `updated_data.csv`
- Delete `chroma_db` folder
- Run `python setup_db.py` again

---

## 📖 Full Documentation

See `API_DOCUMENTATION.md` for complete API reference.