#pdf-parsing on Hacker News

2 stories tagged pdf-parsing, newest first.

Lightweight PDF parser with layout, tables, formulas and bounding boxes (github.com)

64 points by beatrizalmeidaf 24 days ago | 7 comments

GitHub repository for Papero, a fast open-source PDF text extraction API that handles layout, tables, formulas and bounding boxes.

1219 points by serjester 1 year ago | 396 comments

Blog post by Sergey Filimonov on chunking and ingesting millions of PDFs for RAG systems and how Gemini 2.0 improves accuracy and cost.