Closed aevo98765 closed 1 month ago
Help needed on what the best/preferable approach is to take on this one.
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.
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.
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: