This application utilizes OpenAI's GPT-4 Vision model to identify essential text within images, focusing on receipts. Built with React, TypeScript, and Vite, it offers a user-friendly interface for efficient text extraction from images.
- Obtain an API key from OpenAI. You can get it here
- To use GPT-4 with Vision you need to get Tier 1 (at least $5 paid), check the Rate limits
- Add your API key to the .env file in the root directory:
OPENAI_API_KEY=your-api-key-here
- Run the app with
npm run dev
command
cd receiptRec
create .env with API key
npm i
npm run dev