🥑 NutriScan: Your AI-Powered Food Detective

Scan meals, menus, and packaged foods for instant nutrition snapshots.

---

✨ Features

• 📸 AI Food Scanning: Snap a photo of a meal, menu, snack, or packaged food, and NutriScan will identify the food items.
• 🥗 Instant Macro Snapshot: Get average calories, protein, carbs, and fat in the first scan result.
• 🌿 Vegan & Health Ratings: Quickly identify vegan-friendly options with a leaf icon and see a health rating (from 1 to 10) for each item.
• 😂 Fun Loading Experience: Enjoy a variety of playful and quirky loading messages while the AI analyzes your food.
• 🔐 Secure Authentication: User accounts are protected with a secure authentication flow powered by Supabase.
• 📱 Responsive Design: A beautiful and intuitive UI that works seamlessly on any device, built with Next.js, TypeScript, and Tailwind CSS.

---

🛠️ Tech Stack

• Framework: Next.js
• Language: TypeScript
• Styling: Tailwind CSS
• AI: Google's Genkit
• Backend & Auth: Supabase
• UI Components: shadcn/ui
• Runtime for Supabase Functions: Deno

---

🚀 Getting Started

Prerequisites

• Node.js (v18+ recommended)
• npm or yarn
• Docker (for running Supabase locally)

Installation & Setup

1. Clone the repository:

   git clone https://github.com/yourusername/NutriScan.git
   cd NutriScan

2. Install the dependencies:

   npm install

3. Set up Supabase:

   • Start the Supabase local development environment:

     npx supabase start

   • The first time you run this, it will download the necessary Docker images.
   • Once it's running, you'll see your local Supabase credentials in the terminal.

4. Run the application:

   npm run dev

🎉 Your app should now be running at http://localhost:9002.

---

🗂️ Project Structure

/
├── src/
│   ├── ai/
│   │   └── flows/          # Genkit AI flows
│   ├── app/                # Next.js app directory (pages, routes, etc.)
│   ├── components/         # Reusable UI components
│   ├── hooks/              # Custom React hooks
│   └── lib/                # Utility functions and libraries
├── supabase/
│   ├── functions/          # Deno-based edge functions
│   └── migrations/         # Database migrations
└── README.md               # You are here!

---

🤖 AI Flows

NutriScan uses a lean scan-first AI workflow:

1. scan-menu-for-food-options: This flow takes a food image as input and returns detected foods plus average calories, carbs, protein, fat, allergens, and health rating data.

2. generate-nutritional-data: This fallback flow can still fill in details if a scanned item is missing macro data.

The prompts for these flows have been carefully refined to be concise and to minimize the chances of inaccurate or "hallucinated" information.

---

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.