Request: Ollama as an LLM backend

[rdamron]

I was wondering if adding Ollama as a backend server would be an option. It's a polished wrapper for llama cpp I believe. https://ollama.com

[neph1]

Does it have an open ai compatible api? In that case it should be possible to set up already.

https://github.com/neph1/LlamaTale/wiki/Configure-OpenAI-as-backend