I'm creating a LlamaIndex agent with OpenAIAssistantAgent.from_existing(). The assistant uses OpenAI's code interpreter, and generates text and images (eg a rendered graph). I can't figure out how to set this up - I get a single text response from a .chat() call to the agent. How do I receive an image and how do I see the intermediate steps?

The SQLDatabase class here accepts a parameter called custom_table_info but it doesn't seem to get used. It seems like a bug ?

More generally, what's the best way to add custom SQL table and column descriptions to get into the prompt ? (text-to-sql use case)