Conversation

Notices

1. Embed this notice
   phiofx (phiofx@hachyderm.io)'s status on Tuesday, 26-Dec-2023 01:31:47 JST phiofx

   in reply to

   • Simon Willison

   @simon I suspect its an unsolvable problem as there has been plenty of motivation to do so already.

   Pdf is really a black hole. You cant recover something that has been sucked inside the pdf horizon (except maybe at the end of the Universe according to some fancy physics theories).

   • Embed this notice
     Simon Willison (simon@fedi.simonwillison.net)'s status on Tuesday, 26-Dec-2023 01:31:48 JST Simon Willison

     I suspect a neat benefit of everyone wanting to build "chat with your PDF" things is that there's a sudden flood of extra effort being put into PDF text extraction and parsing libraries right now, across a bunch of different languages