21–30 of 65 posts
How do you get value from chatting with documents? I can scan and read a pdf faster than I can chat with an AI about it. There must be more to it than I realize.
How do you get value from chatting with documents? I can scan and read a pdf faster than I can chat with an AI about it. There must be more to it than I realize.
I am very new to this field, so forgive my ignorance when I ask super basic questions. 1. Does chat-with-pdfs function work with scanned PDFs? 2. In the video example for chat-with-pdfs you show uploading a document interactively. The part of processing is quite slow. Can the tool be fed these documents offline as well? My use case for each user, there are many, to have their own list of documents that they upload. T…
Great questions. > 1. Does chat-with-pdfs function work with scanned PDFs? Not yet. We don't do OCR or anything to extract text from images yet. But that would be an awesome feature, so we would love to add it in the future. > 2. In the video example for chat-with-pdfs you show uploading a document interactively. The part of processing is quite slow. Can the tool be fed these documents offline as well? Not as of righ…
Great job. This is a relatively crowded area, particularly RAG style chat systems. It might be nice for SecureAI to call out what makes their product different from other open source players in the same space, specifically Khoj and Danswer, both of which allow you to chat with your documents, offer network authentication, and allow you to plug in your own LLM. Danswer https://github.com/danswer-ai/danswer Khoj https:…
Earlier quoted context omitted.
Maybe they mean walking a file tree and cleaning up file names to match the titles on the covers of them more accurately?
Exactly. You download something from arxiv and the filename has no meaningful content in it. Generally speaking, you want the filename to be descriptive in some way, extracting the title of the document is a good start.
How do you get value from chatting with documents? I can scan and read a pdf faster than I can chat with an AI about it. There must be more to it than I realize.
a one-page PDF, sure. But if it's a 500 page pdf of a law and/or regulation, then definitely not.
Earlier quoted context omitted.
Great questions. > 1. Does chat-with-pdfs function work with scanned PDFs? Not yet. We don't do OCR or anything to extract text from images yet. But that would be an awesome feature, so we would love to add it in the future. > 2. In the video example for chat-with-pdfs you show uploading a document interactively. The part of processing is quite slow. Can the tool be fed these documents offline as well? Not as of righ…
I haven't found an OCR tool reliable enough when it comes to scanned PDFs containing financial data where accuracy of amounts in the document is very important.
Earlier quoted context omitted.
a one-page PDF, sure. But if it's a 500 page pdf of a law and/or regulation, then definitely not.
You can screenshot the first page and use gpt vision
But going further, for large bills you might need (|n|..|m|) pages to capture full index
for research papers you also want to look at last (|n2|..|m2|) pages for bibliography, etc..