Plant Disease Detector

An AI-powered web application for detecting plant diseases from leaf images using state-of-the-art vision models. Built with React, FastAPI, and multimodal LLMs.

Features

• Real-time Analysis: Upload a leaf photo and get instant disease detection
• Multiple AI Providers: Choose between OpenAI GPT-4 Vision and Anthropic Claude 3 Opus
• Comprehensive Reports: Detailed diagnosis including disease name, severity, confidence, symptoms, treatment, and prevention
• Modern UI: Visually appealing, responsive interface with drag-and-drop upload
• RESTful API: FastAPI backend with automatic OpenAPI documentation

Tech Stack

Frontend

• React 18 with Vite
• Tailwind CSS for styling
• Axios for API communication

Backend

• FastAPI (Python 3.10+)
• Pydantic for data validation
• OpenAI Python SDK
• Anthropic Python SDK
• Pillow for image processing
• python-magic for file validation

Prerequisites

• Python 3.10 or higher
• Node.js 18 or higher
• OpenAI API key (for GPT-4 Vision)
• Anthropic API key (for Claude 3 Opus)

Installation

Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your API keys

Frontend Setup

cd frontend
npm install

Configuration

Create a .env file in the backend directory:

OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
DEFAULT_LLM_PROVIDER=openai
DEBUG=True

Running the Application

Development Mode

Start the backend (Terminal 1):

cd backend
source venv/bin/activate
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Start the frontend (Terminal 2):

cd frontend
npm run dev

Access the application at http://localhost:5173

Production Build

Build the frontend:

cd frontend
npm run build

The built files will be in frontend/dist/

API Documentation

Once the backend is running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

Endpoints

POST /api/v1/detect

Detect plant disease from uploaded image.

Parameters:

• file (multipart/form-data): Image file (JPEG, PNG, WebP, max 10MB)
• provider (form): openai or anthropic (default: openai)
• include_treatment (form): boolean (default: true)
• include_prevention (form): boolean (default: true)

Response:

{
  "success": true,
  "disease": {
    "name": "Early Blight",
    "scientific_name": "Alternaria solani",
    "description": "A common fungal disease affecting tomatoes and potatoes...",
    "severity": "moderate",
    "confidence": 0.92,
    "affected_area": "Lower leaves, progressing upward",
    "symptoms": ["Dark brown spots with concentric rings", "Yellowing around spots"],
    "treatment": "Apply fungicide containing chlorothalonil...",
    "prevention": "Rotate crops, avoid overhead watering..."
  },
  "processing_time_ms": 2341.5
}

GET /api/v1/health

Health check endpoint.

GET /api/v1/providers

List available LLM providers.

Project Structure

plant-disease-detector/
├── backend/
│   ├── app/
│   │   ├── api/
│   │   │   └── routes.py          # API endpoints
│   │   ├── core/
│   │   │   └── config.py          # Configuration settings
│   │   ├── models/
│   │   │   └── schemas.py         # Pydantic models
│   │   ├── services/
│   │   │   └── llm_vision.py      # LLM vision integration
│   │   ├── utils/
│   │   └── main.py                # FastAPI application
│   ├── tests/
│   ├── requirements.txt
│   └── .env.example
├── frontend/
│   ├── src/
│   │   ├── components/
│   │   │   ├── Header.jsx
│   │   │   ├── Footer.jsx
│   │   │   ├── UploadZone.jsx
│   │   │   └── ResultDisplay.jsx
│   │   ├── utils/
│   │   │   └── api.js
│   │   ├── styles/
│   │   │   └── index.css
│   │   ├── App.jsx
│   │   └── main.jsx
│   ├── index.html
│   ├── package.json
│   ├── vite.config.js
│   ├── tailwind.config.js
│   └── postcss.config.js
├── docs/
└── README.md

Supported Image Formats

• JPEG (.jpg, .jpeg)
• PNG (.png)
• WebP (.webp)

Maximum file size: 10MB

Disease Detection Capabilities

The application can identify various plant diseases including but not limited to:

• Early Blight
• Late Blight
• Powdery Mildew
• Leaf Spot
• Rust
• Mosaic Virus
• Bacterial Spot
• And many more

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Run tests and linting
5. Submit a pull request

License

MIT License - see LICENSE file for details.

Author

Created by kv-creates

Acknowledgments

• OpenAI for GPT-4 Vision
• Anthropic for Claude 3 Opus
• PlantVillage dataset for reference
• All contributors and testers