June 2026
Intermediate to advanced
454 pages
10h 8m
English
The world of software development is being reshaped by the rapid rise of generative AI. Among the many frameworks and libraries emerging, Google's Gemini family of models has paved the way, creating a powerful and accessible platform engineered from the ground up to be natively multimodal. In this context, multimodality means the model isn't restricted to text, but it can simultaneously process and reason across diverse data types, including images, video, audio, and code, within a single, unified interface. This approach enables advanced reasoning, developer ergonomics, and seamless integration with modern web technologies.
Before we can start building AI-powered applications, we need to cover some basic ...
Read now
Unlock full access