Part 1 Foundations of generative AI
This section introduces the fundamental concepts and technologies that underpin generative AI. We start with a general overview of what generative AI can do, how it works, and how it can be applied in various enterprise settings. Then we examine the details of large language models (LLMs), such as their structures, categories, and main concepts. The final chapters in this section cover generating text, images, and similar things through APIs, offering a hands-on guide to accessing and utilizing these technologies.
Chapter 1 introduces the concept of generative AI and explains its ability to create new content, such as text, images, and code. It discusses various enterprise use cases, compares generative to traditional AI, and provides guidance for organizations considering adopting this technology.
Chapter 2 dives into large language models, explaining their foundational concepts and architecture, particularly focusing on the transformer model. It also covers different types of LLMs and essential concepts such as prompts, tokens, and embeddings.
Chapter 3 explores how to generate text using APIs, starting with basic implementations and moving on to more advanced options. It explains model categories and dependencies, providing practical examples of text generation applications.