In this course, you learned about two different types of Gemini models. Explored prompting multi-modal models with text, images, and video, and examined best practices for effective multimodal prompting. Additionally, to learn about the different use cases involving images and videos, such as extracting specific content and solving the needle in a haystack problem, and integrated real-time data using function calling to enhance language models. I'm looking forward to seeing what you build on your own.