Live data from Hacker News

Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps

github.com

Post reply on HN

Print view View original

1–4 of 4 posts

Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps

Post by zalzal » Wed, Mar 05, 2025, 11:23 PM UTC

I couldn't find good Python libs to do this so ended up writing it myself.

Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps
github.com

Re: Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps

Post by zalzal » Wed, Mar 05, 2025, 11:24 PM UTC

I'm curious if it's useful! How do others try to solve use cases like this of mapping data between docs or strictly controlling LLM edits?

Re: Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps

Post by beebaween » Thu, Mar 06, 2025, 12:45 AM UTC

Can this be used with gemini 2 flash while OCR'ing pdfs?

Re: Show HN: Diff filtering, text mapping, and windowed transforms for LLM apps

Post by zalzal » Thu, Mar 06, 2025, 4:53 AM UTC

beebaween wrote: post #3

Can this be used with gemini 2 flash while OCR'ing pdfs?

It doesn't deal with images at all, but depending on what you're doing it might be useful in cleaning up the OCR text, e.g. asking LLMs to fix errors and then filtering the diffs.

Post reply on HN