Название: Programming Large Language Models With Azure Open AI: Conversational Programming and Prompt Engineering With LLMs
Автор: Francesco Esposito
Издательство: Microsoft Press/Pearson Education
Год: 2024
Страниц: 257
Язык: английский
Формат: pdf (true), epub
Размер: 32.0 MB

Use LLMs to build better business software applications.

Autonomously communicate with users and optimize business tasks with applications built to make the interaction between humans and computers smooth and natural. Artificial Intelligence expert Francesco Esposito illustrates several scenarios for which a LLM is effective: crafting sophisticated business solutions, shortening the gap between humans and software-equipped machines, and building powerful reasoning engines. Insight into prompting and conversational programming—with specific techniques for patterns and frameworks—unlock how natural language can also lead to a new, advanced approach to coding. Concrete end-to-end demonstrations (featuring Python and ASP.NET Core) showcase versatile patterns of interaction between existing processes, APIs, data, and human input.

Over the past two years, generative AI has become a prominent buzzword. It refers to a field of artificial intelligence (AI) focused on creating systems that can generate new, original content autonomously. Large language models (LLMs) like GPT-3 and GPT-4 are notable examples of generative AI, capable of producing human-like text based on given input. The rapid adoption of LLMs is leading to a paradigm shift in programming. This chapter discusses this shift, the reasons for it, and its prospects. Its prospects include conversational programming, in which you explain with words—rather than with code—what you want to achieve. This type of programming will likely become very prevalent in the future.

Artificial Intelligence expert Francesco Esposito helps you:

Understand the history of large language models and conversational programming
Apply prompting as a new way of coding
Learn core prompting techniques and fundamental use-cases
Engineer advanced prompts, including connecting LLMs to data and function calling to build reasoning engines
Use natural language in code to define workflows and orchestrate existing APIs
Master external LLM frameworks
Evaluate responsible AI security, privacy, and accuracy concerns
Explore the AI regulatory landscape
Build and implement a personal assistant
Apply a retrieval augmented generation (RAG) pattern to formulate responses based on a knowledge base
Construct a conversational user interface

Who should read this book:
Software architects, lead developers, and individuals with a background in programming—particularly those familiar with languages like Python and possibly C# (for ASP.NET Core)—will find the content in this book accessible and valuable. In the vast realm of software professionals who might find the book useful, I’d call out those who have an interest in ML, especially in the context of LLMs. I’d also list cloud and IT professionals with an interest in using cloud services (specifically Microsoft Azure) or in sophisticated, real-world applications of human-like language in software. While this book focuses primarily on the services available on the Microsoft Azure platform, the concepts covered are easily applicable to analogous platforms. At the end of the day, using an LLM involves little more than calling a bunch of API endpoints, and, by design, APIs are completely independent of the underlying platform.

In summary, this book caters to a diverse audience, including programmers, ML enthusiasts, cloud-computing professionals, and those interested in natural language processing, with a specific emphasis on leveraging Azure services to program LLMs.

Contents: