Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatPDF – Chat with Any PDF

chatpdf.com

Post reply on HN
Print view View original

71–80 of 141 posts

Re: ChatPDF – Chat with Any PDF

#71

Post by MuffinFlavored »

My first thought was "hmm, would this help with fillable forms?" but then I realized... that could be done without an LLM (some code filling in a PDF, maybe a low-code solution?)

The only advantage I can think of is how introducing an LLM is basically a way to hopefully/maybe (with low accuracy) go one step further than low-code? Like, you can type "in thought/in English" as if it was a robust instruction prompt with sophisticated understanding that was able to boil down to the equivalent of basically a few lines of code/shell script to fill in a PDF.

Re: ChatPDF – Chat with Any PDF

#72

Post by pedro_hab »

This was pretty bad for me, I tried asking the name of a person references in the PDF and it couldn't find it. I asked who is the claimant in this PDF and it said the claimant was empty.

But if I asked if the claimant name was in the PDF it answered yes.

I am assuming the PDF to Text is not working great here, which I supposed is the whole point.

Re: ChatPDF – Chat with Any PDF

#73

Post by dbecker »

I tried this a few times about a month ago. It sounded cool, and the experience of using it was even better than I expected.

I'm glad it was reposted so I get another chance at developing a habit of using it.

Re: ChatPDF – Chat with Any PDF

#74

Post by dabedee »

angadsg wrote: post #43

IMO folks are better off deploying their own version where they can adjust a few knobs (e.g. split chunk size) to get better results, given that PDF Q&A is such a commodity application. Wrote a https://github.com/angad/dharamshala/blob/main/docs.py return_source_documents is particularly helpful to get a sense of what is being sent in the prompt.

The link to your repo is returning a 404 now, whereas I could see it just a min ago.

Re: ChatPDF – Chat with Any PDF

#76

Post by kordlessagain »

pedro_hab wrote: post #72

This was pretty bad for me, I tried asking the name of a person references in the PDF and it couldn't find it. I asked who is the claimant in this PDF and it said the claimant was empty. But if I asked if the claimant name was in the PDF it answered yes. I am assuming the PDF to Text is not working great here, which I supposed is the whole point.

Yup. Having worked on this for a while it’s best to extract the images of the PDF, then send them to Google Vision for extraction.

I have it working with 600 page documents.

Post reply on HN