Douyemiene/agrisense_rwanda

AgriSense Rwanda - AI-powered agricultural intelligence platform # AgriSense Rwanda — Early Warning System for Crop Water Stress A FastAPI microservice that detects crop water stress in Rwanda's Gatsibo district using satellite imagery (NDVI, evapotranspiration), rainfall data, a Neo4j knowledge graph, rule-based alert logic, and LLM-powered natural language explanations. ## Architecture ``` ┌──────────┐ ┌──────────────────┐ ┌────────────┐ │ Frontend │────▶│ FastAPI Gateway │────▶│ Neo4j KG │ │ (client) │◀────│ /api/v1/* │◀────│ │ └──────────┘ └──────┬───────────┘ └────────────┘ │ ┌───────────┼───────────┐ │ │ │ ┌──────▼──┐ ┌─────▼────┐ ┌───▼──────┐ │ Data │ │ Alert │ │ LLM │ │ Ingest │ │ Engine │ │ Layer │ └────┬────┘ └──────────┘ └──────────┘ │ ┌───────┼────────┬──────────┐ │ │ │ │ DEA CHIRPS WaPOR Agri Survey ``` ## Tech Stack - **API**: FastAPI + Uvicorn - **ORM**: SQLAlchemy + Alembic (PostgreSQL + PostGIS) - **Knowledge Graph**: Neo4j (Community Edition) - **Data Processing**: xarray, rasterio, geopandas - **Satellite Data**: Digital Earth Africa, CHIRPS, FAO WaPOR - **LLM**: Configurable (OpenAI / Anthropic Claude) - **Caching**: Redis - **Containerization**: Docker + Docker Compose - **Task Scheduling**: APScheduler ## Quick Start ```bash # Clone and configure cp .env.example .env # Edit .env with your API keys # Start all services docker-compose up -d # Run database migrations docker-compose exec api alembic upgrade head # Populate knowledge graph with base data docker-compose exec api python -m scripts.seed_knowledge_graph # Trigger initial data ingestion docker-compose exec api python -m scripts.ingest_data ``` ## API Endpoints | Method | Endpoint | Description | |--------|----------|-------------| | GET | `/api/v1/health` | Service health check | | GET | `/api/v1/districts` | List pilot districts | | GET | `/api/v1/districts/{id}` | District detail with crops | | GET | `/api/v1/crops` | List moni …