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

Draft: Add support for Vision #34

Closed

Conversation

slashequip
Copy link

Adds support for Vision to OpenAI and Anthropic.

Includes mapping for OpenAI and Anthropic.
@slashequip
Copy link
Author

@sixlive what do you think of this approach?

@slashequip
Copy link
Author

Would resolve #32

@sixlive
Copy link
Contributor

sixlive commented Oct 19, 2024

I think this is a solid start, I'll sleep on it and might pick this up tomorrow. This is definitely high on my list of things I want to enable.

@slashequip
Copy link
Author

I've actually rolled almost exactly this logic out in a custom OpenAI provider from my app internally and it works great.

@sixlive sixlive self-assigned this Oct 20, 2024
@sixlive
Copy link
Contributor

sixlive commented Oct 20, 2024

image

I've got it it working with Prism Server for OpenAI but it will need some work for Anthropic. This isn't too far off how I was going to approach things. I'm going to run with this a bit. Its going to be my focus going into next week.

@sixlive
Copy link
Contributor

sixlive commented Oct 23, 2024

Closing in favor of #42

@sixlive sixlive closed this Oct 23, 2024
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

Successfully merging this pull request may close these issues.

2 participants