فهرست مطالب

• Foreword>
• Preface>
• Acknowledgments>
• About this Book>
• About the Author>
• About the Cover Illustration>
• Part 1: Foundations of Generative AI
• 1. Introduction to Generative AI
• 1.1 What is this book about?
• 1.2 What is generative AI?
• 1.3 What can we generate?
• 1.4 Enterprise use cases
• 1.5 When not to use generative AI
• 1.6 How is generative AI different from traditional AI?
• 1.7 What approach should enterprises take?
• 1.8 Architecture considerations
• 1.9 So your enterprise wants to use generative AI. Now what?
• Summary
• 2. Introduction to Large Language Models
• 2.1 Overview of foundational models
• 2.2 Overview of LLMs
• 2.3 Transformer architecture
• 2.4 Training cutoff
• 2.5 Types of LLMs
• 2.6 Small language models
• 2.7 Open source vs. commercial LLMs
• 2.8 Key concepts of LLMs
• Summary
• 3. Working Through an API: Generating Text
• 3.1 Model categories
• 3.2 Completion API
• 3.3 Advanced completion API options
• 3.4 Chat completion API
• Summary
• 4. From Pixels to Pictures: Generating Images
• 4.1 Vision models
• 4.2 Image generation with Stable Diffusion
• 4.3 Image generation with other providers
• 4.4 Editing and enhancing images using Stable Diffusion
• Summary
• 5. What Else Can AI Generate?
• 5.1 Code generation
• 5.2 Additional code-related tasks
• 5.3 Other code generation tools
• 5.4 Video generation
• 5.5 Audio and music generation
• Summary
• Part 2: Advanced Techniques and Applications
• 6. Guide to Prompt Engineering
• 6.1 What is prompt engineering?
• 6.2 The basics of prompt engineering
• 6.3 In-context learning and prompting
• 6.4 Prompt engineering techniques
• 6.5 Image prompting
• 6.6 Prompt injection
• 6.7 Prompt engineering challenges
• 6.8 Best practices
• Summary
• 7. Retrieval-Augmented Generation: The Secret Weapon
• 7.1 What is RAG?
• 7.2 RAG benefits
• 7.3 RAG architecture
• 7.4 Retriever system
• 7.5 Understanding vector databases
• 7.6 RAG challenges
• 7.7 Overcoming challenges for chunking
• 7.8 Chunking PDFs
• Summary
• 8. Chatting with Your Data
• 8.1 Advantages to enterprises using their data
• 8.2 Using a vector database
• 8.3 Planning for retrieving the information
• 8.4 Retrieving the data
• 8.5 Search using Redis
• 8.6 An end-to-end chat implementation powered by RAG
• 8.7 Using Azure OpenAI on your data
• 8.8 Benefits of bringing your data using RAG
• Summary
• 9. Tailoring Models with Model Adaptation and Fine-Tuning
• 9.1 What is model adaptation?
• 9.2 When to fine-tune an LLM
• 9.3 Fine-tuning OpenAI models
• 9.4 Deployment of a fine-tuned model
• 9.5 Training an LLM
• 9.6 Model adaptation techniques
• 9.7 RLHF overview
• Summary
• Part 3: Deployment and Ethical Considerations
• 10. Application Architecture for Generative AI Apps
• 10.1 Generative AI: Application architecture
• 10.2 Generative AI: Application stack
• 10.3 Orchestration layer
• 10.4 Grounding layer
• 10.5 Model layer
• 10.6 Response filtering
• Summary
• 11. Scaling Up: Best Practices for Production Deployment
• 11.1 Challenges for production deployments
• 11.2 Deployment options
• 11.3 Managed LLMs via API
• 11.4 Best practices for production deployment
• 11.5 GenAI operational considerations
• 11.6 LLMOps and MLOps
• 11.7 Checklist for production deployment
• Summary
• 12. Evaluations and Benchmarks
• 12.1 LLM evaluations
• 12.2 Traditional evaluation metrics
• 12.3 LLM task-specific benchmarks
• 12.4 New evaluation benchmarks
• 12.5 Human evaluation
• Summary
• 13. Guide to Ethical GenAI: Principles, Practices, and Pitfalls
• 13.1 GenAI risks
• 13.2 Understanding GenAI attacks
• 13.3 A responsible AI lifecycle
• 13.4 Red-teaming
• 13.5 Content safety
• Summary
• Appendix A. The Book’s GitHub Repository
• Appendix B. Responsible AI Tools
• References
• Index
• Back Cover