News for hackers. Stuff that matters.
Re:Qwen3-Next by cpursley on Friday September 12, 2025 @07:51AM (#45221134)
How are you prepping the PDF data before shoving it into Qwen?
Re:Qwen3-Next by navbaker on Friday September 12, 2025 @08:18AM (#45221333)
Not OP, but we use the docling library to extract text and put it in markdown before storing for use with an LLM.
Re:Qwen3-Next by Alifatisk on Friday September 12, 2025 @08:05AM (#45221227)
I just compress the file size as low as possible without losing the quality, didn't even know there was more ways to prep it.

I do sometimes chop up the PDF into smaller pdfs with their own individual chapters

Re:Qwen3-Next by amelius on Friday September 12, 2025 @08:14AM (#45221309)
On Linux you can use pdftotext also if you are only concerned with the text.