English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 12h 28m | 2.51 GB
Generative AI can transform your business by streamlining the process of creating text, images, and code. This book will show you how to get in on the action!
Generative AI in Action is the comprehensive and concrete guide to generative AI you’ve been searching for. It introduces both AI’s fundamental principles and its practical applications in an enterprise context—from generating text and images for product catalogs and marketing campaigns, to technical reporting, and even writing software. Inside, author Amit Bahree shares his experience leading Generative AI projects at Microsoft for nearly a decade, starting well before the current GPT revolution.
Inside Generative AI in Action you will find:
- A practical overview of of generative AI applications
- Architectural patterns, integration guidance, and best practices for generative AI
- The latest techniques like RAG, prompt engineering, and multi-modality
- The challenges and risks of generative AI like hallucinations and jailbreaks
- How to integrate generative AI into your business and IT strategy
Generative AI in Action is full of real-world use cases for generative AI, showing you where and how to start integrating this powerful technology into your products and workflows. You’ll benefit from tried-and-tested implementation advice, as well as application architectures to deploy GenAI in production at enterprise scale.
In controlled environments, deep learning systems routinely surpass humans in reading comprehension, image recognition, and language understanding. Large Language Models (LLMs) can deliver similar results in text and image generation and predictive reasoning. Outside the lab, though, generative AI can both impress and fail spectacularly. So how do you get the results you want? Keep reading!
Generative AI in Action presents concrete examples, insights, and techniques for using LLMs and other modern AI technologies successfully and safely. In it, you’ll find practical approaches for incorporating AI into marketing, software development, business report generation, data storytelling, and other typically-human tasks. You’ll explore the emerging patterns for GenAI apps, master best practices for prompt engineering, and learn how to address hallucination, high operating costs, the rapid pace of change and other common problems.
What’s inside
- Best practices for deploying Generative AI apps
- Production-quality RAG
- Adapting GenAI models to your specific domain
Table of Contents
1 Part 1. Foundations of generative AI
2 Introduction to generative AI
3 What is generative AI
4 What can we generate
5 Enterprise use cases
6 When not to use generative AI
7 How is generative AI different from traditional AI
8 What approach should enterprises take
9 Architecture considerations
10 So your enterprise wants to use generative AI. Now what
11 Summary
12 Introduction to large language models
13 Overview of LLMs
14 Transformer architecture
15 Training cutoff
16 Types of LLMs
17 Small language models
18 Open source vs. commercial LLMs
19 Key concepts of LLMs
20 Summary
21 Working through an API Generating text
22 Completion API
23 Advanced completion API options
24 Chat completion API
25 Summary
26 From pixels to pictures Generating images
27 Image generation with Stable Diffusion
28 Image generation with other providers
29 Editing and enhancing images using Stable Diffusion
30 Summary
31 What else can AI generate
32 Additional code-related tasks
33 Other code generation tools
34 Video generation
35 Audio and music generation
36 Summary
37 Part 2. Advanced techniques and applications
38 Guide to prompt engineering
39 The basics of prompt engineering
40 In-context learning and prompting
41 Prompt engineering techniques
42 Image prompting
43 Prompt injection
44 Prompt engineering challenges
45 Best practices
46 Summary
47 Retrieval-augmented generation The secret weapon
48 RAG benefits
49 RAG architecture
50 Retriever system
51 Understanding vector databases
52 RAG challenges
53 Overcoming challenges for chunking
54 Chunking PDFs
55 Summary
56 Chatting with your data
57 Using a vector database
58 Planning for retrieving the information
59 Retrieving the data
60 Search using Redis
61 An end-to-end chat implementation powered by RAG
62 Using Azure OpenAI on your data
63 Benefits of bringing your data using RAG
64 Summary
65 Tailoring models with model adaptation and fine-tuning
66 When to fine-tune an LLM
67 Fine-tuning OpenAI models
68 Deployment of a fine-tuned model
69 Training an LLM
70 Model adaptation techniques
71 RLHF overview
72 Summary
73 Part 3. Deployment and ethical considerations
74 Application architecture for generative AI apps
75 Generative AI Application stack
76 Orchestration layer
77 Grounding layer
78 Model layer
79 Response filtering
80 Summary
81 Scaling up Best practices for production deployment
82 Deployment options
83 Managed LLMs via API
84 Best practices for production deployment
85 GenAI operational considerations
86 LLMOps and MLOps
87 Checklist for production deployment
88 Summary
89 Evaluations and benchmarks
90 Traditional evaluation metrics
91 LLM task-specific benchmarks
92 New evaluation benchmarks
93 Human evaluation
94 Summary
95 Guide to ethical GenAI Principles, practices, and pitfalls
96 Understanding GenAI attacks
97 A responsible AI lifecycle
98 Red-teaming
99 Content safety
100 Summary
101 The book s GitHub repository
102 Responsible AI tools
103 Transparency notes
104 HAX Toolkit
105 Responsible AI Toolbox
106 Learning Interpretability Tool (LIT)
107 AI Fairness 360
108 C2PA
Resolve the captcha to access the links!