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

Open AI addon does not describe images in as much detail as it should #103

Open
M3198 opened this issue May 18, 2024 · 0 comments
Open

Open AI addon does not describe images in as much detail as it should #103

M3198 opened this issue May 18, 2024 · 0 comments

Comments

@M3198
Copy link

M3198 commented May 18, 2024

Hi,

Hope you're doing well.
I would appreciate it if you responded to this issue as soon as possible.
One issue I have been facing with your addon is that it doesn't describe all images on a page in as much detail as it should.
For example, with AI content describer by cartertem, if there are for example 12 or 10 images on a page, it would describe them, whereas open AI might only describe 10 or 8. How do I fix this?
I hve tried maximizing the page.
I tried changing the default prompt to, please describe each and every image in a huge amount of detail as I am completely blind, but that doesn't completely fix the problem.
The problem also arises when the image itself is being described, the description is not as detailed as much as I would like it to be.
Also, when you told me about using object navigation to describe to me the webpage, it gives me some irrelevant information, such as the history bar and other related information. I don't want that. I only want the current focus described, i.e. just the current page and not the tabs tool bar, history toolbar, etc.
Best regards,
Muhammad

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

1 participant