What this book covers

Chapter 1, Introduction to Large Language Models, introduces the foundational concept of LLMs, including their architecture, key examples such as ChatGPT, and the transformative impact they have on business and everyday life. It also covers the concept of foundation models and explores a variety of real-world use cases where LLMs solve complex problems.

Chapter 2, Azure OpenAI Fundamentals, dives into Azure OpenAI Service. It explores the Microsoft-OpenAI partnership, the types of models available, how to deploy them, and the pricing structure. The chapter will equip you with the knowledge to access, create, and utilize Azure OpenAI resources effectively.

Chapter 3, Azure OpenAI Advanced Topics, covers the advanced capabilities of Azure OpenAI, such as understanding context windows, different embedding models, and integrating vector databases. It also explores cutting-edge features such as Azure OpenAI On Your Data, multimodal models, function calling, the Assistants API, the Batch API, and fine-tuning, empowering you to build sophisticated AI applications.

Chapter 4, Developing an Enterprise Document Question-Answer Solution, explains how to design and build a solution for querying unstructured enterprise documents. Key topics include embedding concepts, leveraging Azure Cognitive Search, and integrating Azure OpenAI with LangChain and Semantic Kernel.

Chapter 5, Building a Contact Center Analytics Solution, explains how to develop a contact center analytics platform using Azure OpenAI and Azure Communication Services. This chapter covers identifying challenges, understanding technical requirements, designing architecture, and implementing a solution to enhance customer interactions.

Chapter 6, Querying From a Structured Database, explores SQL GPT, a tool that simplifies querying structured data using natural language. This chapter also demonstrates architecture design and creating a user-friendly interface for accessing database insights, empowering users of all expertise levels.

Chapter 7, Code Generation and Documentation, explores how Azure OpenAI can facilitate code creation and explanation for learners and professionals alike. This chapter also focuses on building a tool that generates code snippets and documentation, making coding accessible and efficient.

Chapter 8, Creating a Basic Recommender Solution with Azure OpenAI, looks at building a chatbot-powered recommendation system for personalized suggestions, such as movies or products. This chapter also guides you through designing and implementing a solution that enhances user experience.

Chapter 9, Transforming Text to Video, uncovers how to convert text prompts into videos using Azure OpenAI and Azure Cognitive Services. You will learn about architecture design, generating images from text, and integrating audio to create educational or promotional videos.

Chapter 10, Creating a Multimodal Multi-Agent Framework with the Azure OpenAI Assistant API, explores how to construct a system where multiple intelligent agents collaborate on tasks, such as image generation and refinement. This chapter also covers multi-agent frameworks, showcasing their potential in GenAI applications.

Chapter 11, Privacy and Security, focuses on safeguarding your Azure OpenAI applications with robust privacy and security measures. Topics include compliance with Azure OpenAI Service standards, ensuring data privacy, leveraging content filtering, and implementing managed identities. Additionally, it delves into configuring virtual networks, private endpoints, data encryption, and adopting Responsible AI practices for secure and ethical AI usage.

Chapter 12, Operationalizing Azure OpenAI, covers how to effectively deploy, manage, and scale Azure OpenAI services. It covers essential operational practices such as logging and monitoring, understanding service quotas and limits, managing quotas, provisioning throughput units, and implementing scalable strategies to handle growing workloads efficiently.

Chapter 13, Advanced Prompt Engineering, looks at mastering the art of prompt engineering to optimize the behavior and quality of AI responses. This chapter explores the elements and strategies of crafting effective prompts, comparing prompt engineering with fine-tuning, and techniques for improving LLM accuracy. It also addresses critical considerations such as mitigating prompt injection attacks and shaping AI outputs to meet specific requirements.