In this session, we will explore Gemini and Gemma, as well as the most recent announcements from Google IO.

Gemini is a cutting-edge model that empowers developers to streamline the creation of innovative applications. We will dive into the details of Gemini's capabilities, demonstrating how to harness its power for rapid prototyping and seamless scaling.

Gemma is an open model by Google. We’ll cover the types of models available and how to customize them to tune for new tasks. You will gain insights into performing training and inference with LangChain and HuggingFace in just a few lines of code, deploying models to Android, and serving them on Google Cloud.

Additionally, we will walk through deploying a Gemini API and Vertex application using Cloud Run.

The session will conclude with a series of live demos showcasing the practical applications of these technologies.