feat: byok

[kah-seng]

This PR aims to allow users to use their own OpenAI-compatible endpoints and API keys (including those outside of OpenAI). The implementation is not completely done yet but I am creating this draft PR to get earlier feedback.

Settings

Replaces the OpenAI key input in the settings previously. Users can specify a name, slug, base URL and their API key.

Model Selection

Models with user-specified API keys have a "(Custom)" appended to the slug.

Questions

1. If users are allowed to specify their own models, should the disabled models be removed from the frontend in the model selection?
2. While working on this feature, I also noticed that the backend only stores the model that a conversation was started with. Subsequent changes of the model used are not updated in the database, is this intended? Or should conversations resume from the last used model for that specific conversation?

Todo

• Input validation
• Polishing of UI
• Allow any slugs. Currently slugs have to be chosen from a dropdown list of supported models as listed by the backend
• Show context window, prices as optional inputs (for user's reference), backend already supports this
• Further testing with other model providers
• Merge conflicts