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

21–30 of 141 posts

Re: ChatPDF – Chat with Any PDF

#21

Post by simonw »

simonw wrote: post #20

How are you solving for PDFs that are too large to fit in the token context? I know of a few approaches for that: - Ignore the problem and let it hallucinate answers to anything that's not in the first 5-10 pages - Attempt to recursively summarize the PDF at the start - so summarize e.g. pages 1-3, then 4-6 etc, then if the resulting summaries are still too long for the context window run a summary of those summaries…

The FAQ answers my question:

> In the analyzing step, ChatPDF creates a semantic index over all paragraphs of the PDF. When answering a question, ChatPDF finds the most relevant parapgrahs from the PDF and uses the ChatGPT API from OpenAI to generate an answer.

Are you using OpenAI's embeddings to implement that?

Re: ChatPDF – Chat with Any PDF

#25

Post by simonw »

loie wrote: post #14
manishsharan wrote: post #9

So what happens to the data from the PDF and the uploaded once I have stopped chatting with it ? A hard pass if you cant ensure the privacy of my data.

right? But of course it HAS to save the pdf, otherwise how is it going to learn off it? The model can't possibly rely on ML processing only while the user has the file open.

I don't think that's an accurate mental model of how a tool like this works.

It's not training a new model on the PDF, or accumulating additional training into its existing model.

Instead, it basically copies and pastes relevant chunks of the PDF into the prompt (invisibly) and then pastes in your question.

It does use calculated embeddings in order to help it spot which are the most relevant sections to use, and it will store those (since they cost money in API calls to retrieve) - but it could be implemented to delete those stored embeddings and the PDF itself when the user stops interacting, or requests that the document is deleted.

Re: ChatPDF – Chat with Any PDF

#27

Post by derwiki »

I uploaded a 750 page novel and asked to summarize the plot, to which it responded:

> I'm sorry, but I cannot provide a summary of the plot of this book as the PDF file does not contain any information about the plot. The PDF file only includes the cover design, copyright information, table of contents, and details about the author. It is possible that the book itself contains a summary or synopsis of its plot.

Is there a data truncation issue?

Post reply on HN