How should I automate sorting and renaming invoice files?
I'm building a small program for a construction company to automate our invoice intake process. Outlook already sorts incoming invoices into a dedicated folder, but I currently download…
PDF processing
How Can I Effectively Split PDF Text into Paragraphs?
Hey folks! I'm currently digging into processing scientific articles, mainly those formatted in the IEEE style, and I'm facing a little challenge. I need a reliable way to…
What’s the Best Way to Run OCR Workloads on AWS? EC2, EKS, or Lambda?
I'm experimenting with setting up OCR workflows on AWS, specifically for academic PDFs. Some of these PDFs are scanned or have complex layouts, like multi-column text and footnotes,…
Choosing the Best AWS Setup for PDF OCR Workflows
I'm setting up OCR workflows on AWS to convert academic PDFs—some scanned and others with tricky layouts like multi-columns and footnotes—into clean Markdown for processing. I started off…