Local Receipt Extractor

A developer built a command-line tool that extracts structured data—vendor, date, total, currency, and expense category—from receipt and invoice images using an open-weight vision model (qwen2.5vl:7b by default) run locally through Ollama. The tool outputs one JSON line per receipt, supports batch processing to CSV, and lets users swap models via a flag such as --model gemma3:4b, keeping sensitive financial documents off cloud services. The developer notes small local models can misread blurry or unusual receipts and recommends spot-checking output before handing it to an accountant.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle https://dev.to/challenges/hacktoberfest-week2-2026-10-12 A small command-line tool that reads receipt and invoice images and returns clean, structured data: vendor, date, total, currency, and expense category. Who would pay for it: freelancers and small-business owners who spend every quarter digging through photos and screenshots of receipts before tax season. A bookkeeper handling several clients' receipts could use it too. The problem it solves: manual data entry is slow and tedious, and receipts contain client names and payment details that people don't want to upload to a cloud service. This tool turns a folder of messy images into structured data, and everything stays on the user's machine. Example output: {"file": "receipt 01.jpg", "vendor": "Starbucks", "date": "2024-03-12", "total": 8.45, "currency": "USD", "category": "meals"} A tiny script that reads receipt images with an open-weight vision model running locally via Ollama and returns structured data: vendor, date, total, currency, and expense category. No cloud API, no per-page fees, and receipts never leave your machine. 1. Install Ollama: https://ollama.com ollama pull qwen2.5vl:7b 2. Install dependencies pip install ollama pydantic python receipt extract.py receipt.jpg python receipt extract.py ./receipts --csv results.csv python receipt extract.py ./receipts --model gemma3:4b Example output one JSON line per receipt : {"file": "receipt.jpg", "vendor": "Starbucks", "date": "2024-03-12", "total": 8.45, "currency": "USD", "category": "meals"} Usage is one line: python receipt extract.py ./receipts --csv results.csv The model is a command-line flag --model gemma3:4b , so swapping models needs no code changes. Where it fell short: small local models can misread blurry or unusual receipts. A larger closed model would probably do better on those. For a tool that handles sensitive financial documents, I think the privacy and zero-cost trade is worth it, as long as the output is spot-checked before it goes to an accountant.