Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by Onavo

10 months ago

What's the PDF parsing like?

2 comments

Onavo

Reply

aaln  10 months ago

Extract all the text from the PDF, turn the pdf into images, send the text for each page along with the image to an LLM with a desired output strucutre.

  • Onavo  10 months ago

    You are not doing any of the fancy table extractor stuff?

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities