Sebastian Goscinski

What about something like https://www.easycron.com/ it would be possible to just add a API endpoint that can be called with a POST Request and some kind of Webhook-Secret. Whenever the...

Would be great to be able to enable pgbouncer on my postgres databases

Ok but I also have some poor loading time in the app itself, could this be related to my Vercel Postgres db?

> > Ok but I also have some poor loading time in the app itself, could this be related to my Vercel Postgres db? > > Hard to say. We...

Yes and no, the problem in #55 was the fact that the /api/models call had a timeout. But the /api/chat call has the same problem when using Ollama. Everything longer...

No not now, I will try to create a more powerfull server with a gpu, maybe that will make ollama more reliable.

@jorge-menjivar I think this issue can be closed

You mean like a database table just for available models instead of the types integration?

I just removed the PossibleAiModels types integration and returning every possible AiModel now, but I dont know how to get the correct information for maxLength, tokenLimit, requestLimit from the OpenAi...

@jorge-menjivar What do you think of a new service that will be hosted by me or us, that will have a database of every possible AI model and that will...