LedgerPrep Lite: Turning Receipt Chaos into Bookkeeping-Ready Records with Local AI
devchallenge
hf26challenge
ai
opensource
Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
What I Built
Imagine running a small business and keeping receipts in WhatsApp, invoices in email, and other bills in your phone gallery.
At the end of the month, someone has to collect everything, enter the details, find missing information, and prepare the records for the accountant.
That is the problem LedgerPrep Lite aims to solve.
LedgerPrep Lite is a local AI-powered bookkeeping preparation tool designed for small business owners and independent bookkeepers. Users upload invoice and receipt images, and the app extracts important information such as the seller's name, invoice number, date, and total amount.
It also flags possible duplicate invoices, missing information, and totals that may need checking. Users can review and correct the results before exporting an organized CSV for their existing accounting workflow.
The goal isn't to replace accountants. It's to reduce the manual work that happens before the actual accounting begins.
Demo
https://zenkaicode123-leaderprep-app-3xbjxn.streamlit.app/] The demo shows the journey from up scattered receipts to reviewing extracted information and exporting organized records.
Code
https://github.com/ZenkaiCode123/ledgerprep-.git How I Built It
I built LedgerPrep Lite with a simple Python-based stack, keeping the application focused on one complete workflow instead of building an entire accounting platform.
Streamlit: Provides the user interface for up documents, reviewing results, and down records.
Ollama and Gemma 3 4B: Run an open-weight language model locally to extract structured information from supported invoice and receipt images.
Python: Validates extracted data and flags missing fields, potential duplicates, and arithmetic inconsistencies where sufficient information is available.
Pandas: Organizes the reviewed records and exports them to CSV.
The model's output is not automatically treated as correct. Financial information can be ambiguous, so users must be able to inspect the original document, correct mistakes, and review flagged records.
Why Does Open Innovation Matter?
Financial documents contain sensitive business information. Sending every receipt and invoice to an external AI service isn't always desirable for a small business.
By using an open-weight model through local inference, LedgerPrep Lite is designed to process documents on the user's own computer without requiring a hosted AI API for extraction.
Open innovation also gives us more control over the technology. We can experiment with different models, change the extraction process, and evaluate their performance without being locked into a single provider's API pricing.
For this project, open-source AI isn't just a technical choice. It supports the goal of making AI-assisted bookkeeping preparation more private and affordable. Prize Categories
Best Use of Gemma