←back to thread

Mutool – all purpose tool for dealing with PDF files

(www.mankier.com)
43 points rahimnathwani | 5 comments | 02 Feb 25 17:18 UTC | HN request time: 0s | source
1. nico ◴[02 Feb 25 18:01 UTC] No.42910359[source]▶
It would be cool if it could also do “LLM style” operations, like summarizing or extracting key points of the documents
replies(3): >>42910444 #>>42910556 #>>42910603 #
2. yapyap ◴[02 Feb 25 18:12 UTC] No.42910444[source]▶
not really, very out of scope IMO
3. pkal ◴[02 Feb 25 18:26 UTC] No.42910556[source]▶
If you really have to "mutool draw -F txt somefile.pdf" will extract the text contents, that you can then pipe to a LLM.
replies(1): >>42910606 #
4. tough ◴[02 Feb 25 18:32 UTC] No.42910603[source]▶
found this pymupdf4llm w a fast google search https://medium.com/@danushidk507/using-pymupdf4llm-a-practic...
5. tough ◴[02 Feb 25 18:33 UTC] No.42910606[source]▶
how will it handle things like tables let me try