Azure OpenAI for Cloud Native Applications

Preface
How This Book Is Organized
Conventions Used in This Book
Using Code Examples
O’Reilly Online Learning
How to Contact Us
Acknowledgments
Introduction

1. Introduction to Generative AI and Azure OpenAI Service
What Is Artificial Intelligence?
Current Level of AI Adoption
The Many Technologies of AI
Typical AI Use Cases
Types of AI Learning Approaches
About Generative AI
Primary Capabilities of Generative AI
Relevant Industry Actors
The Key Role of Foundation Models
Road to Artificial General Intelligence
Microsoft, OpenAI, and Azure OpenAI Service
The Rise of AI Copilots
Azure OpenAI Service Capabilities and Use Cases
LLM Tokens as the New Unit of Measure
Conclusion

2. Designing Cloud Native Architectures for Generative AI
Modernizing Applications for Generative AI
Cloud Native Development with Azure OpenAI Service
Microservice-Based Apps and Containers
Serverless Workflows
Azure-Based Web Development and CI/CD
Understanding the Azure Portal
General Azure OpenAI Service Considerations
Available Azure OpenAI Service Models
Architectural Elements of Generative AI Systems
Conclusion

3. Implementing Cloud Native Generative AI with Azure OpenAI Service
Defining the Knowledge Scope of Azure OpenAI Service–Enabled Apps
Generative AI Modeling with Azure OpenAI Service
Azure OpenAI Service Building Blocks
Potential Implementation Approaches
Approach Comparison and Final Recommendation
AI Performance Evaluation Methods
Conclusion

4. Additional Cloud and AI Capabilities
Plug-ins
LLM Development, Orchestration, and Integration
LangChain
Semantic Kernel
LlamaIndex
Bot Framework
Power Platform, Microsoft Copilot, and AI Builder
Databases and Vector Stores
Vector Search from Azure AI Search
Vector Search from Cosmos DB
Azure Databricks Vector Search
Redis Databases on Azure
Other Relevant Databases (Including Open Source)
Additional Microsoft Building Blocks for Generative AI
Azure AI Document Intelligence (formerly Azure Form Recognizer) for OCR
Microsoft Fabric’s Lakehouse
Microsoft Azure AI Speech
Microsoft Azure API Management
Ongoing Microsoft Open Source and Research Projects
Conclusion

5. Operationalizing Generative AI Implementations
The Art of Prompt Engineering
Generative AI and LLMOps
Prompt Flow and Azure ML
Securing LLMs
Managing Privacy and Compliance
Responsible AI and New Regulations
Relevant Regulatory Context for Generative AI Systems
Company-Level AI Governance Resources
Technical-Level Responsible AI Tools
Conclusion

6. Elaborating Generative AI Business Cases
Premortem, or What to Consider Before Implementing a Generative AI Project
Defining Implementation Approach, Resources, and Project Roadmap
Defining Project Workstreams
Identifying Required Resources
Estimating Duration and Effort
Creating a “Living” Roadmap
Creating Usage Scenarios
Calculating Cost and Potential ROI
Conclusion

7. Exploring the Big Picture
What’s Next? The Evolution Toward Microsoft Copilot
Expert Insights for the Generative AI Era
David Carmona: AI Adoption and the Future of Generative AI
Brendan Burns: The Role of Cloud Native for Generative AI Developments
John Maeda: About AI Design and Orchestration
Sarah Bird: Responsible AI for LLMs and Generative AI
Tim Ward: The Impact of Data Quality on LLM Implementations
Seth Juarez: From Generative AI Models to a Full LLM Platform
Saurabh Tiwary: The New Microsoft Copilot Era
Conclusion
Appendix. Other Learning Resources
Relevant O’Reilly Books for Your Upskilling Journey
Other Resources and Repositories

Index
About the Author