The chat 'Model Selector' defaults back to Granite-7b every time the page is refreshed

[aevo98765]

For users that are not using the Granite-7b model for chat inference, every time users visit another page and come back to http://localhost:3000/playground/chat or just refresh the page, the model selector defaults back to Granite-7b. This then causes the chat inference requests to fail because the incorrect model name is passed to the chat model server.

Possible solutions:

• Add the ability for the user to select an option as their default option.
• Model type wont change on a page reset. local web browser storage?

[aevo98765]

Help needed on what the best/preferable approach is to take on this one.

[nerdalert]

Can use local storage for sure (or any other thing you prefer). Ty! After we get done with the go live we can tackle a db running.

[aevo98765]

https://github.com/instructlab/ui/pull/79

[vishnoianil]

Approach proposed in #79 sounds good to me. Once we have a storage hooked up to UI, we can store the last selected model for individual user.