PlatePredict Backend API

A Node.js backend service that analyzes food waste using Google's Gemini AI and manages student ration data.

📋 Overview

PlatePredict is a solution designed to monitor and reduce food waste in school cafeterias. The system analyzes images of leftover food on plates, assigns a waste score, and adjusts student ration allocations accordingly to promote more responsible consumption habits.

🚀 Features

• AI-Powered Waste Analysis: Uses Google's Gemini AI to analyze food waste from plate images
• Student Management: Track individual student waste patterns and ration allocations
• RESTful API: Simple API endpoints for integration with frontend applications
• MongoDB Integration: Persistent storage for student data and waste history

🛠️ Tech Stack

• Node.js - JavaScript runtime
• Express - Web framework
• MongoDB - Database
• Google Gemini AI - Image analysis
• Docker - Containerization

📦 Installation

Prerequisites

• Node.js (v16+)
• MongoDB connection string
• Google Gemini AI API key

Setup

1. Clone the repository:

   git clone <repository-url>
   cd platePredit-js-backend

2. Install dependencies:

   npm install

3. Create a .env file in the root directory:

   MONGO_URI=your_mongodb_connection_string
   GENAI_API_KEY=your_google_gemini_ai_key
   PORT=5000
   

4. Start the server:

   npm start

Using Docker

1. Build and run using Docker Compose:

   docker-compose up -d

2. Or build and push using the provided script:

   ./build.cmd

🔌 API Endpoints

Add a new student entry

• POST /add_entry
• Body: { "student_id": "string" }
• Response: { "message": "entry added successfully" }

Record waste for a student

• POST /add_waste
• Body: { "student_id": "string", "image": "base64_encoded_image" }
• Response: { "message": "waste updated successfully" }

Get all student entries

• GET /get_all_entries
• Response: Array of student records

Get a specific student entry

• GET /get_entry?student_id=123
• Query Parameter: student_id
• Response: Student record object

🧪 How It Works

1. Student Registration: A new student is registered with a unique ID
2. Waste Recording: After a meal, a photo of the student's plate is submitted
3. AI Analysis: The Gemini AI analyzes the image and assigns a waste score (0-10)
4. Ration Adjustment:
   • Low waste scores (0-1) increase rations
   • High waste scores (4+) decrease rations

🔒 Environment Variables

Variable	Description
MONGO_URI	MongoDB connection string
GENAI_API_KEY	Google Gemini AI API key
PORT	Port to run the server (default: 5000)

🐳 Deployment

The application is containerized with Docker and can be deployed to any platform that supports Docker containers.

👥 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

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