Trying to get Graphrag running with locally hosted models from LM-Studio/Ollama but getting "invalid_api_key" error

[Branchenprimus]

Hi, I am trying this for a couple of days now and i don't seem to be progressing here. I tried different models and local hosting platforms like Ollama and LM-Studio to host the llm and embedding models. I understand, that an API key is needed if running openai models from the web but for local hosting it should not be an issue, so I tried different dummy values like GRAPHRAG_API_KEY=EMPTY or GRAPHRAG_API_KEY=1234 but I still get the error:

"Error code: 401 - {'error': {'message': 'Incorrect API key provided: EMPTY. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}"

Attached is my yaml file in .txt encoding.
settings.yaml.txt

[DStarEpoch]

I am stuck in here too, seems the graphrag did not replace the base_url with the settings.yaml .