DocuFlow – Automate invoice data extraction with local AI

Summary: DocuFlow is an open-source, containerized pipeline that automates OCR, parsing, and analytics of invoices using Gemini 2.5 Flash AI. It extracts vendor, date, and amount data from PDFs and updates the database in real-time.

What it does

DocuFlow processes invoices by ingesting files dropped into a folder, then uses AI to perform OCR and extract key financial data automatically.

Who it's for

It is designed for users needing automated extraction and analysis of invoice and financial document data.

Why it matters

It replaces manual regex-based extraction with an intelligent, real-time AI-driven pipeline for accurate data processing.