An efficient OCR engine for structured data extraction from receipt images.
Extract structured JSON data or raw text from receipts using Python and FastAPI.
Receipt OCR is an open-source toolkit designed for extracting text and structured data from receipt images. It suits developers and financial data processors looking to automate invoice and receipt parsing using multiple LLM providers or local Tesseract OCR.
The engine offers two core modules: a higher-level LLM-powered package for structured data extraction into custom schemas, and a dedicated Tesseract OCR module for raw text extraction. It includes a FastAPI web service, CLI interfaces, and Docker support for deployment.
It suits Python developers and data engineers building automated accounting or expense management pipelines. It does not suit non-technical users who require a ready-to-use desktop application without command-line configuration.
Extract structured data using OpenAI, Gemini, or Groq backends.
Define precise extraction formats using standard JSON schema rules.
Deploy a production-ready REST API for receipt processing using Docker.
Perform raw OCR text extraction locally via CLI or Python scripts.
Free under its MIT licence. The only financial cost is running it yourself and paying for any third-party LLM API usage.
877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
The tool supports OpenAI, Gemini (Google), and Groq via configurable base URLs and models.
Yes, you can use the Tesseract OCR module for raw text extraction locally without relying on external LLMs.
Yes, you can run the receipt processing service using the provided Docker compose configuration.
See Zekai first in Google