A receipt-to-recipe generator that uses Python's EasyOCR library to extract ingredients from grocery receipts and generates personalized recipes using Google Gemini.
Make sure you have the following installed on your system:
- Python 3.8+
- Node.js 16+
- npm as the package manager
- MongoDB (for recipe storage)
Before running, please make sure to download the MongoDB Community Server and Node.js.
git clone https://github.com/narcistiq/FoodTracker.git
cd Cooks-Matchcd receipt-recipes/backendpython3 -m venv venv
source venv/bin/activate (Mac/Linux)
venv\Scripts\Activate.ps1(Windows)pip3 install -r requirements.txtCreate .env file with your Gemini API key at project root:
Backend configuration:
GEMINI_API_KEY=your_gemini_api_key_hereuvicorn main:app --reload --port 8000The backend will be available at: http://127.0.0.1:8000
cd receipt-recipes/frontendnpm installnpm run devThe frontend will be available at: http://localhost:5173
- Backend API: Visit
http://127.0.0.1:8000/docsfor FastAPI interactive documentation - Upload Test: Use the frontend to upload a receipt image
- Example Files: Test with images in
receipt-recipes/backend/uploads/