How do we move from an AI that simply "labels" a photo to one that can "reason" about it? In this hands-on workshop, we bridge the gap between Computer Vision and Generative AI.

Traditional vision systems are great at identifying objects, but they lack context. Generative AI is brilliant at reasoning, but it is "blind" without an interface. By combining the Google Vision API with Gemini’s Multimodal capabilities, we will build applications that don't just see the world—they understand and interact with it.