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

[feature] Add third-party AI Vendor support #95

Open
Sma1lboy opened this issue Feb 9, 2025 · 3 comments
Open

[feature] Add third-party AI Vendor support #95

Sma1lboy opened this issue Feb 9, 2025 · 3 comments

Comments

@Sma1lboy
Copy link

Sma1lboy commented Feb 9, 2025

Support users to add custom OpenAI-compatible API endpoints, enabling users to:

Configure your own API endpoint URL and key
Use custom vendor on mobile
Support services compatible with the standard OpenAI API format
Select and switch different vendors in the conversation interface

Have we ever thought about doing something similar? I was just curious. I searched the Internet and didn't find a product that can support similar needs on mobile phones until I found that fullmoon is actually very complete. I'm not sure if you have ever considered something similar?

@agustif
Copy link

agustif commented Feb 13, 2025

I just made this, will add PR later, so i can use great fullmoon client to call my own ollama/lm studio server(which uses openai api spec)

but i think this might be out of scope for fullmoon (which is focused on privacy of local modules) so might entertain maintaing my own fork i guess idk

Image

@Sma1lboy
Copy link
Author

It's so wonderful. I will try to build your version. I think third-party APIs and privacy do not conflict, and if you are using the endpoint of your home rack server, I think it's very reasonable. I was originally implementing this part by myself.

@agustif
Copy link

agustif commented Feb 14, 2025

i got a bit hangup on making it support multiple servers snd openai reasoning models but will open pr soon and got confirmarion from fullmoon maintainers that the PR is welcome!

looks like this w multi-server support

Image Image

also openai has image models, maybe running stable-diffusion on mlx is viable too

Image

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