Adding support for Ollama/local LLMs

[NumberChiffre]

Hey guys,

Thanks for making your work public. I'm wondering if you have or will be exploring LLMs other than GPT4 for your evaluations. For instance, you've used Llama 3 in your benchmarks, would you be using some sort of Llama 3.1 with Ollama or even Claude/DeepSeek? Am wondering if you'll support those APIs in your code soon.

[l4b4r4b4b4]

cant you do that with setting OPENAI_API_BASE to your localhost?

You might need to point at a tool calling compatible endpoint like functionary ;)

[dmccrearytg]

We are also huge fans of Ollama. It allows us to run our text-to-graph NLP pipelines on a local consumer grade GPU with reasonable quality.

We are inspired by this open-source project:

They fine-tuned Phi-3 to get results as good as GPT-4 but on a much smaller model:
Phi-3 Graph on HuggingFace