A local AI that types up a Brazilian accountant's receipts (and knows when it's wrong)

Описание и применение

Местный ИИ, работающий полностью локально, автоматически обрабатывает ~100 бухгалтерских документов в неделю, достигая 95 % точности полей и сокращая ручной ввод до 5 минут в неделю.

Задача

A self‑employed accountant in Brazil receives ~100 documents a week from small‑business clients and currently types each one into a spreadsheet by hand.

Результат

The system achieves 95% field accuracy on 10 fictitious documents, with all problematic documents routed to review. Average processing time is 2.2 s per text PDF and 4.0 s per image, totaling about 5 minutes for a week’s worth of documents.

Рабочий процесс

• Drop files into a Streamlit page and select the accounting month.
• Each document is read by an open‑weight model running locally in Ollama.
• Python validates the model output and flags rows that need human review.
• The accountant edits flagged rows in an editable table and exports the result to Excel (entries sheet and summary by category).

Доказательства

A self‑employed accountant in Brazil gets ~100 documents a week from her small‑business clients: NF‑e invoices (PDF), NFC‑e receipts photographed on a phone, Pix transfer screenshots, and the occasional handwritten recibo.

Источник

Each document is read by an open‑weight model running locally in Ollama.

Источник

Python validates everything the model returned and flags the rows a human must check.

Источник

95% of fields correct. All three misses come from the blurry receipt.

Источник

Average time on an AMD RX 9060 XT (Ollama, Vulkan): 2.2 s per text PDF, 4.0 s per image. That's about 5 minutes for a week of documents.

Источник