News for hackers. Stuff that matters.

gautiert

Re:Ask HN: What are you using to parse PDFs for RAG? on Tuesday July 30, 2024 @04:00AM (#41107016)
Hi! Show HN: Zerox – Document OCR with GPT-mini | https://news.ycombinator.com/item?id=41048194

This lib converts pdf page by page to image and feed it to gpt-4o-mini The results are pretty good!

I would like to try that! But I can't find it with Google. Can you provide a link? Thanks.
Nice work!

Is there some JavaScript/Typescript alternatives to Langchain?