News for hackers. Stuff that matters.

A comment on Systematically Improving Your RAG. Parent comment

Re:Systematically Improving Your RAG by cpursley on Wednesday May 22, 2024 @06:30PM (#40447523)
Any tips on effectively getting financial data out of PDFs into a RAG system (especially data contained in tables)? And locally, not via proprietary cloud PDF parsing thingy. That's the current nut I'm trying to crack.
[ Parent | on HN ]
Re:Systematically Improving Your RAG by rawsh on Wednesday May 22, 2024 @06:56PM (#40447807)
https://github.com/VikParuchuri/marker is solid, but slow and needs gpu(s) to be practical
[ Parent | on HN ]
Re:Systematically Improving Your RAG by serjester on Wednesday May 22, 2024 @07:00PM (#40447862)
You might find my library useful - https://github.com/Filimoa/open-parse
[ Parent | on HN ]