Receipt Sorter: a private, offline bookkeeping helper for freelancers, powered by Qwen2.5-VL

A developer built receipt-sorter, an open-source command-line tool that uses a local Qwen2.5-VL vision model via Ollama to rename receipt and invoice files, generate an accountant-ready receipts.csv, and produce per-category summaries without sending client financial documents to a cloud service. Testing on seven synthetic receipts, the model correctly extracted vendor, date, total, currency and category from five, including tilted photos and German comma-decimal formats, but confidently misread a deliberately blurry receipt, returning 2026-09-17 and 375.0 from an image that actually read 1?/09/2026 and 3?5.00. The developer added safeguards that flag unparseable or mismatched quotes and route uncertain results to a needs_review folder, plus an optional --verify mode that reads each document twice.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle https://dev.to/challenges/hacktoberfest-week2-2026-10-12 receipt-sorter is a command-line tool that turns a messy folder of receipts and invoices PDFs and phone photos into something an accountant can use. It renames each file 2026-10-14 Brew-Bean-Cafe 441.0.png , writes an accountant-ready receipts.csv date, vendor, total, tax, currency, category , and produces a summary.md with totals per category. Who would pay for it: freelancers, consultants and tiny agencies who dread tax season and handle other people's financial documents. Their problem is twofold: the sorting is tedious, and they don't want client invoices and bank details uploaded to a third-party cloud. A tool that runs entirely on their own laptop solves both. Drop a folder of receipts and invoices PDFs and phone photos in, get back renamed files an accountant-ready receipts.csv , and a category summary. A local open-weight vision model does the reading, so client invoices and bank details never leave your laptop . sorted output/ sorted/ 2026-03-04 Figma 15.0.pdf ... confident results needs review/ anything unreadable, low-confidence or possibly duplicated receipts.csv date, vendor, total, tax, currency, category, notes ... summary.md totals per currency and category + a review list Originals are copied, never moved or modified. 1. Install Ollama https://ollama.com and pull an open vision model ollama pull qwen2.5vl:7b ~6 GB; use gemma3:4b or qwen2.5vl:3b on smaller machines 2. Install deps pip install -r requirements.txt 3. Run python -m sorter ~/Documents/receipts -o ~/Documents/receipts sorted python -m sorter ./receipts --model gemma3:4b --dry-run preview, writes nothing Add --verify to read every document twice second pass at a different… ₹1,234.50 and 1.234,50 are normalised, dates are converted to ISO, tax greater than total is flagged, and unknown categories are caught. Anything uncertain goes to a needs review/ folder rather than being silently accepted. Exact duplicates are skipped by SHA-256 without spending any inference. categories.json holds your own categories and vendor rules which always override the model , and examples.json holds corrected examples used as few-shot guidance. --model swaps in any Ollama vision model. I generated seven fake receipts to test with: a café bill in INR, a SaaS invoice in USD, a tilted Uber photo, a German hardware-store receipt with comma decimals, an internet bill, a deliberately unreadable one, and an exact duplicate. On my first run, the model got the first five right: vendor, date, total, currency and category, including the tilted photos and the German number format. The duplicate was skipped. The deliberately blurry receipt slipped through . The real image read 1?/09/2026 and 3?5.00 , but the model confidently returned 2026-09-17 and 375.0 , with no warning. For a bookkeeping tool, a quiet wrong number is worse than a flagged one. I added two safeguards: ? , an unparseable quote, or a quote that disagrees with the extracted value gets flagged. --verify mode: Performance: YOUR LAPTOP: RAM, CPU/GPU processed the 7 documents in about X minutes without --verify and Y minutes with it. localhost Ollama . Client invoices never leave the laptop, which is something a cloud API can't honestly promise.