PDF

tags : Image Compression, OCR

Resources §

• https://excalibur-py.readthedocs.io/en/master/ : table extraction
  • Reducto Document Ingestion API (extraction dataset)
• ColPali (see OCR)
  • Ingesting PDFs and why Gemini 2.0 changes everything | Hacker News
  • Tips for using Gemini 2.0 for PDF ingestion | Hacker News
• Doctly AI
• PDF/A - Wikipedia
• https://github.com/ocrmypdf/OCRmyPDF (uses pike, pretty useful)
• Ask HN: What is the best method for turning a scanned book as a PDF into text? | Hacker News
• Processing
  • https://zerodha.tech/blog/1-5-million-pdfs-in-25-minutes/
  • https://gotenberg.dev/

PDF generation §

• Using Pandoc and Typst to Produce PDFs | Hacker News