Ask HN: I have many PDFs – what is the best local way to leverage AI for search?

Re:Ask HN: I have many PDFs – what is the best local way to ... by 1123581321 on Thursday May 30, 2024 @06:02PM (#40529216)

Devonthink would do this with a tiny model to translate your natural length search prompts into its syntax and your folder/tag tree.

If you're okay with some false positives, Devonthink would work as is, actually.

[ Parent | on HN ]

Re:Ask HN: I have many PDFs – what is the best local way to ... by bendsawyer on Thursday May 30, 2024 @06:16PM (#40529341)

I used to use this, but the LLM approach allows for much deeper interactions. Not "find all times I've typed X" but

"act as an expert in Y, looking across all times I've typed X, summarize my changing position over thee years, and suggest other terms that have a similar pattern of change, in a list."

The kind of thing I used to give to an intern over a month, with results that are not far off what that intern produced...

[ Parent | on HN ]

Re:Ask HN: I have many PDFs – what is the best local way to ... by 1123581321 on Saturday June 01, 2024 @10:00AM (#40545800)

I’d love to see that built in as well.

The devonthink crab-bucket community is hostile to any use of LLMs but I don’t think they understand how the app would structure and augment the input and output to keep it from returning fanciful output.

[ Parent | on HN ]