Programming Large Language Models with Azure Open AI: Conversational programming and prompt engineering with LLMs

Title Page....1

Copyright Page....2

Dedication....5

Contents at a Glance....6

Contents....7

Acknowledgments....11

Introduction....13

Who should read this book....14

Assumptions....15

This book might not be for you if…....15

Organization of this book....15

Downloads: notebooks and samples....16

Errata, updates, & book support....16

Stay in touch....17

Chapter 1. The genesis and an analysis of large language models....18

LLMs at a glance....19

Facts of conversational programming....39

Summary....53

Chapter 2. Core prompt learning techniques....54

What is prompt engineering?....54

Basic techniques....69

Fundamental use cases....85

LLM limitations....91

Summary....91

Chapter 3. Engineering advanced learning prompts....93

What’s beyond prompt engineering?....94

Function calling....101

Talking to (separated) data....112

Summary....132

Chapter 4. Mastering language frameworks....134

The need for an orchestrator....135

LangChain....148

Microsoft Semantic Kernel....182

Microsoft Guidance....199

Summary....212

Chapter 5. Security, privacy, and accuracy concerns....213

Overview....214

Security and privacy....220

Evaluation and content filtering....234

Summary....253

Chapter 6. Building a personal assistant....254

Overview of the chatbot web application....255

The project....257

Summary....285

Chapter 7. Chat with your data....286

Overview....286

What is Streamlit?....288

The project....295

Progressing further....313

Summary....318

Chapter 8. Conversational UI....319

Overview....320

The project....324

Summary....340

Appendix. Inner functioning of LLMs....341

The role of probability....341

The case of GPT....356

Index....368

Code Snippets....395

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.

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

For IT Professionals and Consultants

• For software professionals, architects, lead developers, programmers, and Machine Learning enthusiasts
• For anyone else interested in natural language processing or real-world
• applications of human-like language in software