So I've been testing with #OpenAI GPT4 API and I'm not a programmer at all, but this stuff is so easy using #n8n... I have now made a chatbot that I feed the live image of a (security) camera from #HomeAssistant with the question "What do you see in the driveway"? It then replies with audio in uncanny natural spoken language describing what it is seeing...

I imagine this could be the future of smart home assistants, security or just a general conversational assistant or "friend" for the elderly, responding to a person and the environment that it is seeing via a camera etc.