participatory-planner / QUICKSTART.md
thadillo
Security hardening and HuggingFace deployment fixes
d038974
# Quick Start Guide
## πŸš€ Get Running in 3 Minutes
### 1. Install Dependencies
```bash
cd participatory_planner
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
```
### 2. Configure
```bash
cp .env.example .env
# Edit .env and set FLASK_SECRET_KEY to any random string
```
### 3. Run
```bash
python run.py
```
Visit **http://localhost:5000**
## πŸ“ First Login
- Default admin token: **`<your-admin-token-from-startup>`**
- Login and start managing your participatory planning session!
## πŸ€– AI Model Info
- **Completely FREE** - No API keys needed!
- **Offline** - Runs locally after initial download
- **First run**: Downloads model (~1.5GB) - this happens once
- **After that**: Instant offline classification
## 🎯 Basic Workflow
1. **Admin** β†’ Share registration link with participants
2. **Participants** β†’ Generate tokens, login, submit ideas
3. **Admin** β†’ Click "Analyze Submissions" to categorize
4. **Admin** β†’ View analytics, charts, and maps
5. **Export** β†’ Save as JSON or CSV
## πŸ’‘ Key Features
βœ… Token-based authentication
βœ… 6 contributor types (Government, Community, Industry, NGO, Academic, Other)
βœ… AI categorization (Vision, Problem, Objectives, Directives, Values, Actions)
βœ… Geographic mapping with Leaflet
βœ… Charts and analytics
βœ… Export/Import sessions
βœ… Flag offensive content
## πŸ”§ Troubleshooting
**Model download slow?**
- It's a one-time 1.5GB download
- Use good internet connection for first run
- Model is cached locally afterward
**Out of memory?**
- Model needs ~2-4GB RAM
- Close other applications during analysis
**Want faster analysis?**
- If you have a GPU, edit `app/analyzer.py` line 31:
```python
device=0 # Use GPU instead of device=-1 (CPU)
```
Enjoy your participatory planning session! πŸŽ‰