recipescout README

Link to working demo: https://alexandergardiner.com/recipescout

Overview

This project, recipescout, is a privacy-focused web application that transforms ingredients into personalized recipes using cutting-edge AI. Users can take a picture of ingredients, and the system leverages in-browser YOLO object detection to identify items without sending raw images to the server. Only detected ingredient data is securely passed to ChatGPT for recipe generation.

The application eliminates reliance on external recipe APIs, ensuring both privacy and high-quality recipe suggestions. It integrates secure Google OAuth authentication, stores recipes in MongoDB, and supports rich social features including recipe sharing, commenting, and feedback forums. Users also control recipe visibility through privacy controls and shareable recipe links.

This is a full-stack AI-powered solution combining computer vision, large language models, and modern web technologies.

Built With

Features

• In-Browser YOLO Detection: Ingredient recognition happens locally in the browser, ensuring no raw images leave the device.
• ChatGPT-Powered Recipes: Personalized, high-quality recipe suggestions generated without external recipe APIs.
• Secure Authentication: Integrated with Google OAuth for safe and easy sign-in.
• Recipe Storage: Save and manage your personal recipes in MongoDB.
• Social Features: Share recipes, comment on others, and join community feedback forums.
• Privacy Controls: Choose between public or private recipes, with shareable links for easy access.
• Full-Stack AI: Combines computer vision, LLMs, and modern web technologies for a seamless experience.

Installation

1. Clone the Repository

git clone https://github.com/yourusername/recipescout.git

2. Navigate to the Project Directory

cd recipescout

3. Install Dependencies

npm install

4. Set Up Environment Variables Create a .env.local file with the following variables:

# MONGO_URI=your_mongodb_connection_string
# GOOGLE_CLIENT_ID=your_google_client_id
# GOOGLE_CLIENT_SECRET=your_google_client_secret
# OPENAI_API_KEY=your_openai_api_key

5. Run the Development Server

npm run dev

License

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