Ingrid Stevens

You can use Gemma via [Ollama](https://docs.privategpt.dev/manual/advanced-setup/llm-backends#using-ollama) or [LM Studio](https://docs.privategpt.dev/manual/advanced-setup/llm-backends#using-openai-compatible-api) (lm studio provides a server that can stand in for openai, so you can use it with the "openailike" settings-vllm.yaml file...

@Vivek-C-Shah For using Ollama, I never used or modified the default `settings.yaml` file. Instead I created a file for ollama. This is what worked for me on my Mac, I...

@imartinez I believe I've resolved the conflict, but let me know if there's something else I should do to get this PR ready to merge. Thanks!