Skip to content

QUICKSTART.md

Latest commit

 

History

History
142 lines (110 loc) · 3.61 KB

QUICKSTART.md

File metadata and controls

142 lines (110 loc) · 3.61 KB
Raw

Aerial Site Intelligence - Quick Start Guide

Development Setup (5 minutes)

1. Initial Setup

# Clone and setup
git clone <repo-url>
cd ariealsiteintelligence
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your AWS and OpenAI API keys

2. Start with Docker Compose

# Start all services
docker-compose up -d

# Run migrations
docker-compose exec django python manage.py migrate

# Create superuser
docker-compose exec django python manage.py createsuperuser

# Visit http://localhost:8000

3. Local Development (Without Docker)

# Start PostgreSQL and Redis (locally or via Docker)
# Update .env with local database and Redis URLs

# Run migrations
python manage.py migrate

# Start dev server
python manage.py runserver

# In separate terminal, start Celery
celery -A aerial_site_intelligence worker -l info

Upload First Image

  1. Go to http://localhost:8000/admin
  2. Create a Site
  3. Create a Mission for that Site
  4. Upload image via API:
curl -X POST http://localhost:8000/api/images/ \
  -H "Authorization: Token YOUR_TOKEN" \
  -F "image=@test_image.jpg" \
  -F "mission=1" \
  -F "captured_at=2024-01-01T12:00:00Z"

Project Structure

ariealsiteintelligence/
├── aerial_site_intelligence/
│   ├── core/              # Django models
│   ├── api/               # REST endpoints
│   ├── config/            # Django settings
│   ├── aws_integration/   # AWS services
│   ├── vlm_pipeline/      # GPT-4o Vision
│   ├── agent_memory/      # Persistent memory
│   └── tasks/             # Celery tasks
├── deploy/                # Deployment files
├── tests/                 # Test suite
├── manage.py              # Django CLI
├── requirements.txt       # Dependencies
├── docker-compose.yml     # Service orchestration
└── README.md              # Full documentation

Key Features

✅ Vision-Language Model Integration - GPT-4o Vision for scene understanding ✅ Multi-Modal Detection - Rekognition + SageMaker inference ✅ Persistent Agent Memory - Autonomous reasoning about site history ✅ Async Processing - Celery for scalable image processing ✅ RESTful API - Complete CRUD operations ✅ Docker Ready - Full docker-compose setup ✅ AWS Integration - CloudFormation templates included ✅ Production Ready - Gunicorn, NGINX config included

Next Steps

  1. Configure AWS credentials in .env
  2. Set up OpenAI API key
  3. Create Sites and Missions via admin or API
  4. Upload drone images and watch them get processed
  5. View anomalies and alerts in real-time
  6. Deploy to AWS using CloudFormation template

Useful Commands

# Admin panel
http://localhost:8000/admin

# API documentation
http://localhost:8000/api/

# Celery monitoring
celery -A aerial_site_intelligence flower

# View logs
docker-compose logs -f

# Database migrations
python manage.py makemigrations
python manage.py migrate

# Run tests
python manage.py test

Troubleshooting

Images not processing?

  • Check Celery worker: docker-compose logs celery
  • Verify Redis: redis-cli ping
  • Check AWS credentials in .env

API authentication issues?

  • Create token: python manage.py drf_create_token username
  • Add header: Authorization: Token YOUR_TOKEN

Database errors?

  • Check PostgreSQL: docker-compose exec db psql -U postgres
  • Run migrations: python manage.py migrate

See README.md for complete documentation.