Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Roadmap] PDF Upload Default "Attach File As..." #727

Open
2 tasks
matrix303 opened this issue Jan 20, 2025 · 2 comments
Open
2 tasks

[Roadmap] PDF Upload Default "Attach File As..." #727

matrix303 opened this issue Jan 20, 2025 · 2 comments

Comments

@matrix303
Copy link
Contributor

Why
Users will be able to easily upload PDFs in their selected format quicker.

Description
Right now, when you want to upload a PDF as text and image, you have to select each PDF and then manually select this option. A "default" setting for every uploaded PDF would make it more convenient for users. They should still be able to select manually as it currently happens but a default would be great especially when you routinely upload PDFS.

Requirements
If you can, Please break-down the changes use cases, UX, technology, architecture, etc.

  • Create a Settings/Pane to be able to set a "default" option for pdf's
  • Expand to other file types
@enricoros
Copy link
Owner

Very good point. I try to minimize the options as they all add uncertainty and load, however I see why this could be very useful. I can't enable it by default because some PDFs have dozens of pages, which will end up overflowing the context window.

I plan to have a "Pages Selector" so the user will just pick the interesting pages (or even auto-select the pages with images rather than text) which adds just the important bits to the context window.

@matrix303
Copy link
Contributor Author

Thanks for the quick look into this. Thats a great point as well. I don't think you should enable it by default but for example, under labs a simple drop down called "Defualt PDF Import as..." with options "Text", "Images", and "Text and Images".
The native default should still be Text, but if users wanted to change it they could?

Also I think because you have a GREAT Ui for showing how much context window is taken (the blue bar at the bottom, turning red when over context window) can make it much easier. This may also be a faster dev time compared to a "pages selector".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants