Logan Yang

Do they have an API and where can I find it?

@rayxsong Thanks! Great stuff! I'll need some refactor to make this kind of changes easier in the future

@leethobbit Thanks for the suggestion. I believe Smart Connections uses transformers.js for that and not Ollama for that to happen. I tried once before but couldn't make transformers.js work in...

With custom models, closing this old issue. If anything is not working with custom model, please open separate issues with details.

I can run Llama 3 70B on my macbook pro M3 max 96GB smoothly, a bit hot after a while though. However, I predict that we will have 13B or...

What do you mean by restarting the plugin? You should be able to change Ollama model name in settings, restart ollama server without restarting the plugin.

Does LM Studio support spinning up two local servers at the same time? One chat, one embedding?

@mhafellner That's interesting, didn't know that! But from a glance it seems it won't work. The real question is can it load 2 models at the same time? There's no...

Does anybody know what the context length is here, is it 512 or 2048, I'm confused

@shwanton I noticed you have "serve on local network" on, then you must use `3rd party openai format` as provider instead of lm-studio. And you must **provide the correct base...