Building a Privacy-First Expense Sorter with Open-Source AI for Freelancers

Описание и применение

LedgerShield — локальное решение для автоматической классификации и извлечения данных из чеков и счетов, защищающее конфиденциальность и экономя время фрилансеров.

Задача

Freelancers need automated bookkeeping without exposing sensitive financial records to third‑party cloud services.

Результат

In a test with 18 mixed receipts, LedgerShield parsed line totals and vendor details in under three minutes, eliminating manual spreadsheet entry and earning positive user feedback for potential paid usage.

Рабочий процесс

• 1. User drags and drops mixed receipts into LedgerShield’s web dashboard.
• 2. The local Python backend loads an open‑weight vision‑language model to process each image on the user’s device.
• 3. The model extracts vendor name, date, total amount, taxes, and category.
• 4. Extracted data is stored in a lightweight SQLite database and exported as CSV or JSON.
• 5. Users review and optionally export the structured data for bookkeeping.

Доказательства

LedgerShield extracts key metadata (vendor name, date, total amount, taxes, and category) and exports them into structured CSV or JSON formats.

Источник

The extraction parsed line totals and vendor details in under three minutes, eliminating manual spreadsheet entry.

Источник

Open-weight models run locally on the user's laptop, ensuring sensitive financial documents, client names, and tax identifiers never leave their hardware or get used to train closed corporate systems.

Источник