[Feature] Any plans to extend this to other LLMs especially local ones?

[PRESIDENT810]

Looks like magentic already supports running local LLMs using MAGENTIC_LITELLM_MODEL which can be a local server run by Ollama. Is there any plan to support user to use LLMs running locally on their device instead of only OpenAI's model?

[LegalPrimes]

I'm also curious to know of any plans to support local LLMs in light of the llama 3.1 405B release.

[jmaslek]

This is definitely something we are interested in exploring, but will lilkely not be for a little bit of time. It will be interesting to see how the function calling compares.

This is definitely open to be explored by the community as well.

[kairoswealth]

It would be great if you could at least support Azure OpenAI.

[bala-ceg]

I can explore this for running in local llms