fred-bf

> GOOGLE_URL > > @H0llyW00dzZ Cool! The base url of gemini api should be able to configured via `GOOGLE_URL`, have you encountered any issue while requesting with the variable? >...

@H0llyW00dzZ When requesting gemini api server, the client will check whether the googleUrl is configured first. If not set, will fallback to the url you just mentioned. https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/blob/08fa22749aea8f497811f684bd9c7ef68d698666/app/api/google/%5B...path%5D/route.ts#L20

Oh, for native clients, bypassing through a proxy service is still necessary. It might need to using a proxy service like `/api/cors` api

@H0llyW00dzZ have you checked the developer console in development build, it much likely the requests being block by CORS right now.

@H0llyW00dzZ it seems having some syntax issue in Chinese version https://github.com/H0llyW00dzZ/ChatGPT-Next-Web/issues/new?assignees=&labels=enhancement&projects=&template=%E5%8A%9F%E8%83%BD%E5%BB%BA%E8%AE%AE.yml&title=%5BFeature+Request%5D%3A+

There are no relevant plans to support custom models per chat

Due to the complexity of the implementation and the conflict with the current interaction mode, it will not be placed in the roadmap for the time being

@blackh1 could you share the original request & response via the chrome dev tools?

@blackh1 I mean the request error/log when the stream message is disconnected, this is very helpful for initially determining the root casue

At present, it is not expected to be configure according to user granularity. In the future, support for configure api key at the team level will be considered.