3 months ago I built and launched ClarifyPDF.com, a "chat with PDF" app, mainly to learn how to build a chatbot, and to learn what's it like to launch a SaaS around this type of GPT app. I share my lessons and observations in this post.
Sorry, to be more precise, "same document" could mean the same content but in different formats. OR just slightly tweaked to result in a different hash each time. Harder to abuse for sure, but still has holes.
That UX flow seems strange because the screen flow should just be: 1) upload, 2) pay, 3) chat. It shouldn't have asked you to check your email for anything.
Please feel free to email me at alfarez at gmail dot com if you're still seeing this issue.
As for handling large files, I'm using a popular method of breaking down the doc into small chunks and then just sending the relevant chunks to the AI.
How to pick the "relevant" chunks? Use embeddings and search for the embeddings that are "semantically closest" to the question being asked.
I built a simple posture monitor that runs in the browser. Why? Because my neck pain has gotten to epic proportions, and this not making me happy.
Finally put it online today, so if you want to try it out, here it is: https://posturemonitorapp.com.
No installation, no signup, none of that BS. Just go to the URL and start monitoring. Yeah, it's free.
If you do use it, please do let me know what you think. I'd love to know what I can do to improve it.
Thanks!
Farez