I believe there is a bug in the factory.py when using ResponseMode.NO_TEXT. I have different deployments with different API keys in Azure. This doesn't work unless I add in the llm=llm parameter to the NoText constructor.
Can you explain how the MockLLM helps? I'm already creating a proper LLM with the appropriate api_key and passing it into get_response_synthesizer. THe problem is when it doesn't paas along any llm to NoText.