Receipt Parser

This project automates the extraction and organization of data from receipt images. It simplifies manual data entry by converting raw receipt images into structured JSON data and persistent local records.

Inspired by @IAmTomShaw's Receipt Vision.

Features

• Image Processing: Upload receipt images for automated text extraction using Tesseract OCR.
• Language Model Parsing: OpenAI's GPT-4 processes the raw OCR text into strict, structured JSON formatting.
• Mock Testing Mode: Bypass external API calls and Tesseract processing by using the built-in test API key, enabling rapid local UI development.
• Data Export: Export parsed receipt details (products, quantities, prices, categories) directly to standard CSV format.
• Local Storage: Parsed data is securely stored in a lightweight SQLite database.
• Responsive Interface: A clean, minimalistic web interface for uploading, viewing, and exporting receipts on any device.

Preview

Tech Stack

• Backend: Flask (Python)
• Frontend: HTML, CSS, Vanilla JavaScript
• Database: SQLite
• External APIs: OpenAI API
• OCR Engine: Tesseract

Getting Started

Prerequisites

• Python 3.10 or higher
• OpenAI API Key (or use test for mock data)
• Tesseract OCR installed on your system (optional if using mock mode)

Installation

1. Clone the repository:

   git clone https://github.com/JustCabaret/receipt-parser.git
   cd receipt-parser
   

2. Set up the virtual environment:

   python -m venv venv
   source venv/bin/activate   # On Windows: venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt