Zero-Cost, 100% Private: Building a Local Invoice & Receipt Sorter with Open-Source AI

Описание и применение

Создан локальный скрипт на Python, который без подключения к облаку обрабатывает счета и чеки, классифицирует поставщиков и выводит структурированный JSON, устраняя расходы на SaaS и обеспечивая полную конфиденциальность данных.

Задача

Freelancers and side hustles need to automate expense tracking without exposing sensitive financial data to cloud services or incurring recurring costs.

Результат

The script successfully parses invoices locally, outputs structured JSON, and eliminates the need for cloud APIs or subscription fees.

Рабочий процесс

• 1. Place invoice or receipt files (PDF, PNG, JPG) in the ./unprocessed_invoices folder.
• 2. Run the Python script.
• 3. The script traverses the folder, processes each file locally using open‑weight vision/text models, and prints a JSON object containing vendor_name, date, total_amount, and category.

Доказательства

An offline, zero-cost Python invoice and receipt sorter designed to automate expense tracking for freelancers and side hustles.

Источник

It processes financial documents locally, categorizes vendors, and outputs structured JSON without sending any data to cloud-based APIs or third-party servers.

Источник

The pipeline is built using a lightweight Python script leveraging open-source libraries and local file system traversal:

Источник

My First User Early Validation: Tested with a freelance design client processing monthly software subscriptions and equipment receipts entirely offline.

Источник