1 Building with GenAI

 

In this chapter

  • You will learn what’s needed to develop useful GenAI applications.
  • You will get an intuition of how Large Language Models work.

GenAI is a strange animal. Deep inside, it is one of a kind. While it feels natural to use a chatbot these days, you realize what a strange animal a GenAI (short for Generative AI) app can be when you try to build one.

How do AI systems communicate in fluent, human-like language? Does ChatGPT truly think like we do, or is something else at play? In this book, we’ll explore what makes GenAI so unique, mysterious, and fascinating.

Our goal is to help you understand how GenAI applications work. We’ll consider what tasks they can handle well and where you should steer clear. Along the way, we’ll roll up our sleeves and build a few applications of our own using a low-code tool called LangFlow. To begin our journey, let’s take a look at the fundamental characteristics that set GenAI applications apart and make our ride worth the effort.

The uniqueness of GenAI programming

Let’s consider the key differences between programming a traditional application and a GenAI one. Both aim to define the behavior of an application that does something helpful for the user, generating a useful output given an input. But they get there in very different ways.

Dealing with LLMs

 
 
 

Building a GenAI application

 
 
 

Overcoming the “Stateless” Barrier

 
 

Providing Fresh Knowledge in Prompts

 
 

Why do you need this book to build real-world applications

 
 

Inside the LLM

 
 
 

Learning how to speak

 
 
 

Where everything starts: sentence completions

 
 
 
 

Understanding GPT-3: how a real LLM works

 
 
 

Embeddings

 
 
 

Context Calculation

 
 

Combination Process

 
 
 
 

Pre-training the model

 

Keeping the knowledge up to date

 
 
 

Summary

 
 
sitemap

Unable to load book!

The book could not be loaded.

(try again in a couple of minutes)

manning.com homepage
test yourself with a liveTest