How to setup local network LLM's

[nPHYN1T3]

I have ollama running on another machine and can not get this to work. I've read the docs which are clear as mud, tried various things syntax wise in my config.yaml but select model shows nothing. Trying to add a model just keeps giving me options for third party services or local only to this machine style setups.

How do you add an ollama instance on your network!?

[bdougie]

You'll need to configure Ollama to accept network connections first - check out the official docs here: https://docs.ollama.com/faq (see "How do I configure Ollama server?")

Once that's set up, here's your config.yaml:

models:
  -  name: Llama 3.1
     provider: ollama
     model: llama3.1:latest
     apiBase: http://192.168.1.100:11434  # Replace with your Ollama machine's IP

[CentUser]

I am setting up a local instance too, while I need config.yaml have the ability to add custom extra options. I read the docs in detail, found two configuration options: defaultCompletionOptions and extraBodyProperties, neither works. the defaultConpletionOptions only accept a few options specified in docs. If nobody considering the feature, maybe I should build one myself.