Ollama now supports tool calling with popular models in local LLM

Pretty sweet to get to run models locally and have more advanced usages like tool calling, excited to try it out

Where is `get_current_weather` implemented?<p>&gt; Tool responses can be provided via messages with the `tool` role.

I see Command-R+ but not Command-R marked for tool use. The model is geared for it, much easier to fit on commodity hardware like 4090s, and Ollama&#x27;s own description for it even includes tool use. I think it&#x27;s just not labeled for some reason. It works really well with the provided ollama-python package and other tools that already brought function calling capabilities via Ollama&#x27;s API.<p><a href="https:&#x2F;&#x2F;ollama.com&#x2F;library&#x2F;command-r">https:&#x2F;&#x2F;ollama.com&#x2F;library&#x2F;command-r</a>

How does this compare to Agent Zero (frdel&#x2F;agent-zero on GitHub)? Seems that provides similar functionality and uses docker for running the scripts &#x2F; code generated.

The first I think of when anyone mentions agent-like “tool use” is:<p>- Is the environment that the tools are run from sandboxed?<p>I’m unclear on when&#x2F;how&#x2F;why you’d want an LLM executing code on your machine or in a non-sandboxed environment.<p>Anyone care to enlighten?

My guess since programmer blog post writing (plus autism?) assumes <i>“Everyone already knows everything about my project because I do!”</i>…<p>Is this to the effect of running a local LLM, that reads your prompt and then decides which correct&#x2F;specialized LLM to hand it off to? If that is the case, isn’t it going to be a lot of latency to switch models back and forth as most people usually run the single largest model that will fit on their GPU?