Food2Vec 🍕

An AI-powered food discovery application that uses vector similarity search to find similar foods.

Project Structure

HacknRoll/
├── backend/           # Flask API server
│   ├── app.py         # Main Flask application
│   ├── requirements.txt
│   └── .env.example   # Environment variables template
│
└── frontend/          # React application
    ├── public/
    ├── src/
    │   ├── components/
    │   │   ├── LandingPage.js
    │   │   ├── SearchBar.js
    │   │   └── SearchResults.js
    │   ├── App.js
    │   └── index.js
    └── package.json

Features

• 🔍 Smart Autocomplete - Real-time food suggestions as you type
• 🤖 AI-Powered Search - Vector similarity search using Pinecone
• ⚡ Instant Results - Fast and responsive search experience
• 📱 Responsive Design - Works on desktop and mobile

Getting Started

Prerequisites

• Python 3.8+
• Node.js 16+
• Pinecone account (optional, has mock data fallback)

Backend Setup

1. Navigate to the backend directory:

   cd backend

2. Create a virtual environment:

   python -m venv venv

3. Activate the virtual environment:

   • Windows: venv\Scripts\activate
   • Mac/Linux: source venv/bin/activate

4. Install dependencies:

   pip install -r requirements.txt

5. Add the environment file and add your Supabase conn key:

   SUPABASE_URL=URL
   SUPABASE_KEY=KEY
   
   FLASK_ENV=development
   FLASK_DEBUG=1
   
   OPENAI_API_KEY=KEY

Edit .env with your Supbase credentials.

6. Run the Flask server:

python app.py

The backend will run on http://localhost:5000

Frontend Setup

1. Navigate to the frontend directory:

   cd frontend

2. Install dependencies:

   npm install

3. Start the development server:

   npm run dev

   The frontend will run on http://localhost:3000

API Endpoints

Endpoint	Method	Description
/api/health	GET	Health check
/api/autocomplete?q=<query>	GET	Get food suggestions
/api/search	POST	Search for similar foods
/api/categories	GET	Get all food categories

Supabase Setup (Optional)

To enable real vector search:

1. Create a Supabase account at https://supabase.com/
2. Create a new project
3. Enable the pgvector extension in your database (Database → Extensions → enable vector)
4. Create a table for food vectors
5. Add your Supabase URL and key to the .env file:

   SUPABASE_URL=your_project_url
   SUPABASE__KEY=your_anon_key

6. Populate the table with food embeddings

Technologies Used

• Backend: Flask, Flask-CORS, Supabase
• Frontend: React, CSS3
• Vector Database: Pinecone