{"product_id":"genai-on-aws-isbn-9781394281282","title":"GenAI on AWS","description":"\u003cp\u003e\u003cb\u003eThe definitive guide to leveraging AWS for generative AI\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003ci\u003eGenAI on AWS: A Practical Approach to Building Generative AI Applications on AWS\u003c\/i\u003e is an essential guide for anyone looking to dive into the world of generative AI with the power of Amazon Web Services (AWS). Crafted by a team of experienced cloud and software engineers, this book offers a direct path to developing innovative AI applications. It lays down a hands-on roadmap filled with actionable strategies, enabling you to write secure, efficient, and reliable generative AI applications utilizing the latest AI capabilities on AWS.\u003c\/p\u003e \u003cp\u003eThis comprehensive guide starts with the basics, making it accessible to both novices and seasoned professionals. You'll explore the history of artificial intelligence, understand the fundamentals of machine learning, and get acquainted with deep learning concepts. It also demonstrates how to harness AWS's extensive suite of generative AI tools effectively. Through practical examples and detailed explanations, the book empowers you to bring your generative AI projects to life on the AWS platform.\u003c\/p\u003e \u003cp\u003eIn the book, you'll:\u003c\/p\u003e \u003cul\u003e \u003cli\u003eGain invaluable insights from practicing cloud and software engineers on developing cutting-edge generative AI applications using AWS\u003c\/li\u003e \u003cli\u003eDiscover beginner-friendly introductions to AI and machine learning, coupled with advanced techniques for leveraging AWS's AI tools\u003c\/li\u003e \u003cli\u003eLearn from a resource that's ideal for a broad audience, from technical professionals like cloud engineers and software developers to non-technical business leaders looking to innovate with AI\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eWhether you're a cloud engineer, software developer, business leader, or simply an AI enthusiast, \u003ci\u003eGen AI on AWS\u003c\/i\u003e is your gateway to mastering generative AI development on AWS. Seize this opportunity for an enduring competitive advantage in the rapidly evolving field of AI. Embark on your journey to building practical, impactful AI applications by grabbing a copy today.\u003c\/p\u003e \u003cp\u003eAcknowledgments xiii\u003c\/p\u003e \u003cp\u003eAbout the Authors xv\u003c\/p\u003e \u003cp\u003eForeword xvii\u003c\/p\u003e \u003cp\u003eIntroduction xix\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1: A Brief History of AI 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Precursors of the Mechanical or “Formal” Reasoning 2\u003c\/p\u003e \u003cp\u003eThe Digital Computer Era 4\u003c\/p\u003e \u003cp\u003eCybernetics and the Beginning of the Robotic Era 6\u003c\/p\u003e \u003cp\u003eBirth of AI and Symbolic AI (1955–1985) 10\u003c\/p\u003e \u003cp\u003eSubsymbolic AI Era (1985–2010) 14\u003c\/p\u003e \u003cp\u003eDeep Learning and LLM (2010–Present) 16\u003c\/p\u003e \u003cp\u003eKey Takeaways 17\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2: Machine Learning 19\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhat Is Machine Learning? 19\u003c\/p\u003e \u003cp\u003eTypes of Machine Learning 20\u003c\/p\u003e \u003cp\u003eSupervised Learning 21\u003c\/p\u003e \u003cp\u003eUnsupervised and Semi-Supervised Learning 22\u003c\/p\u003e \u003cp\u003eReinforcement Learning 23\u003c\/p\u003e \u003cp\u003eMethodology for Machine Learning 24\u003c\/p\u003e \u003cp\u003eImplementation of Machine Learning 26\u003c\/p\u003e \u003cp\u003eMachine Learning Applications 27\u003c\/p\u003e \u003cp\u003eNatural Language Processing (NLP) 27\u003c\/p\u003e \u003cp\u003eComputer Vision 27\u003c\/p\u003e \u003cp\u003eRecommender System 27\u003c\/p\u003e \u003cp\u003ePredictive Analytics 28\u003c\/p\u003e \u003cp\u003eFraud Detection 28\u003c\/p\u003e \u003cp\u003eMachine Learning Frameworks and Libraries 28\u003c\/p\u003e \u003cp\u003eTensorFlow 28\u003c\/p\u003e \u003cp\u003ePyTorch 31\u003c\/p\u003e \u003cp\u003eScikit-learn 34\u003c\/p\u003e \u003cp\u003eKeras 35\u003c\/p\u003e \u003cp\u003eApache Spark MLlib 37\u003c\/p\u003e \u003cp\u003eFuture Trends in Machine Learning 40\u003c\/p\u003e \u003cp\u003eRise of Edge Computing and Edge AI 40\u003c\/p\u003e \u003cp\u003eConvergence with Emerging Technologies 40\u003c\/p\u003e \u003cp\u003eAdvancements in Unsupervised Learning, Reinforcement Learning, and Generative Models 41\u003c\/p\u003e \u003cp\u003eIncreased Specialization and Customization 41\u003c\/p\u003e \u003cp\u003eExplainable and Trustworthy AI 42\u003c\/p\u003e \u003cp\u003eKey Takeaways 42\u003c\/p\u003e \u003cp\u003eReferences 43\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3: Deep Learning 45\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eDeep Learning vs. Machine Learning 45\u003c\/p\u003e \u003cp\u003eComputer Vision Example 46\u003c\/p\u003e \u003cp\u003eNatural Language Processing Example 47\u003c\/p\u003e \u003cp\u003eThe History of Deep Learning 47\u003c\/p\u003e \u003cp\u003eUnderstanding Deep Learning 52\u003c\/p\u003e \u003cp\u003eNeurons 52\u003c\/p\u003e \u003cp\u003eWeights and Biases 54\u003c\/p\u003e \u003cp\u003eLayers 54\u003c\/p\u003e \u003cp\u003eActivation Function(s) 55\u003c\/p\u003e \u003cp\u003eAn Introduction to the Perceptron 58\u003c\/p\u003e \u003cp\u003eOvercoming Perceptron Limitations 59\u003c\/p\u003e \u003cp\u003eFeedForward Neural Networks 60\u003c\/p\u003e \u003cp\u003eBackpropagation 60\u003c\/p\u003e \u003cp\u003eParameters vs. Hyperparameters 62\u003c\/p\u003e \u003cp\u003eHyperparameters in Artificial Neural Networks 64\u003c\/p\u003e \u003cp\u003eLoss Functions – a Measure of Success of a Neural Network 64\u003c\/p\u003e \u003cp\u003eOptimization Algorithms 64\u003c\/p\u003e \u003cp\u003eNeural Network Architectures 68\u003c\/p\u003e \u003cp\u003ePutting It All Together 71\u003c\/p\u003e \u003cp\u003eDeep Learning on AWS 71\u003c\/p\u003e \u003cp\u003eChipsets and EC2 Instances 71\u003c\/p\u003e \u003cp\u003eAWS P5 Instances 72\u003c\/p\u003e \u003cp\u003eAWS Inferentia 72\u003c\/p\u003e \u003cp\u003eAmazon Elastic Inference 73\u003c\/p\u003e \u003cp\u003ePre-built Containers: Deep Learning AMIs and Containers 74\u003c\/p\u003e \u003cp\u003eDeep Learning AMIs 74\u003c\/p\u003e \u003cp\u003eDeep Learning Containers 74\u003c\/p\u003e \u003cp\u003eManaged Services for Building, Training, and Deployment 74\u003c\/p\u003e \u003cp\u003ePre-trained Services 75\u003c\/p\u003e \u003cp\u003eKey Takeaways 77\u003c\/p\u003e \u003cp\u003eReferences 77\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4: Introduction to Generative AI 79\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eGenerative AI Core Technologies 80\u003c\/p\u003e \u003cp\u003eNeural Networks 80\u003c\/p\u003e \u003cp\u003eGenerative Adversarial Networks (GANs) 80\u003c\/p\u003e \u003cp\u003eVariational Autoencoders (VAEs) 81\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTMs) 82\u003c\/p\u003e \u003cp\u003eLimitations of Recurrent Neural Networks 84\u003c\/p\u003e \u003cp\u003eTransformer Models 85\u003c\/p\u003e \u003cp\u003eSelf-Attention 86\u003c\/p\u003e \u003cp\u003eParallelism 86\u003c\/p\u003e \u003cp\u003eDiffusion Models 86\u003c\/p\u003e \u003cp\u003eAutoregressive Models 87\u003c\/p\u003e \u003cp\u003eReinforcement Learning (RL) 87\u003c\/p\u003e \u003cp\u003eTransfer Learning and Fine-Tuning 87\u003c\/p\u003e \u003cp\u003eOptimization Algorithms 87\u003c\/p\u003e \u003cp\u003eTransformer Architecture: Deep Dive 87\u003c\/p\u003e \u003cp\u003eDeep Dive 89\u003c\/p\u003e \u003cp\u003eStep 1: Tokenization (Preprocessing) 89\u003c\/p\u003e \u003cp\u003eStep 2: Embedding 89\u003c\/p\u003e \u003cp\u003eStep 3: Encoder 92\u003c\/p\u003e \u003cp\u003eStep 4: Encoder Output to Decoder Input 97\u003c\/p\u003e \u003cp\u003eStep 5: Decoder 98\u003c\/p\u003e \u003cp\u003eStep 6: Translation Generation 99\u003c\/p\u003e \u003cp\u003eStep 7: Detokenization 99\u003c\/p\u003e \u003cp\u003eTerminology in Generative AI 99\u003c\/p\u003e \u003cp\u003ePrompt 104\u003c\/p\u003e \u003cp\u003eInference 105\u003c\/p\u003e \u003cp\u003eContext Window 106\u003c\/p\u003e \u003cp\u003ePrompt Engineering 106\u003c\/p\u003e \u003cp\u003eIn-Context Learning (ICL) 107\u003c\/p\u003e \u003cp\u003eZero-Shot\/One-Shot\/Few-Shot Inference 108\u003c\/p\u003e \u003cp\u003eInference Configuration 109\u003c\/p\u003e \u003cp\u003eMaximum Length 110\u003c\/p\u003e \u003cp\u003eDiversity (Top P\/Nucleus Sampling) 111\u003c\/p\u003e \u003cp\u003eTop K 111\u003c\/p\u003e \u003cp\u003eRandomness (Temperature) 112\u003c\/p\u003e \u003cp\u003eSystem Prompts 112\u003c\/p\u003e \u003cp\u003ePrompt Engineering 113\u003c\/p\u003e \u003cp\u003eKey Elements of a Prompt 113\u003c\/p\u003e \u003cp\u003eDesigning Effective Prompts 114\u003c\/p\u003e \u003cp\u003ePrompting Techniques 115\u003c\/p\u003e \u003cp\u003eZero-Shot Prompting 115\u003c\/p\u003e \u003cp\u003eFew-Shot Prompting 115\u003c\/p\u003e \u003cp\u003eChain-of-Thought Prompting 116\u003c\/p\u003e \u003cp\u003eAdvanced Prompting Techniques 117\u003c\/p\u003e \u003cp\u003eSelf-Consistency 118\u003c\/p\u003e \u003cp\u003eTree of Thoughts (ToT) 119\u003c\/p\u003e \u003cp\u003eRetrieval-Augmented Generation (RAG) 120\u003c\/p\u003e \u003cp\u003eAutomatic Reasoning and Tool-Use (ART) 122\u003c\/p\u003e \u003cp\u003eReAct Prompting 123\u003c\/p\u003e \u003cp\u003eCoherence Enhancement 124\u003c\/p\u003e \u003cp\u003eProgressive Prompting 126\u003c\/p\u003e \u003cp\u003eHandling Prompt Misuse 127\u003c\/p\u003e \u003cp\u003ePrompt Injection 127\u003c\/p\u003e \u003cp\u003ePrompt Leaking 128\u003c\/p\u003e \u003cp\u003eMitigating Bias 129\u003c\/p\u003e \u003cp\u003eMitigating Bias in Prompt Engineering 130\u003c\/p\u003e \u003cp\u003eGenerative AI Business Value 133\u003c\/p\u003e \u003cp\u003eBuilding Value Within Your Enterprises 135\u003c\/p\u003e \u003cp\u003eTechnology: Creating a Flexible and Strong System 136\u003c\/p\u003e \u003cp\u003ePeople: Training and Adapting the Team 136\u003c\/p\u003e \u003cp\u003eProcesses: Good Management and Fair Use of AI 136\u003c\/p\u003e \u003cp\u003eWhy a Solid Foundation Is Crucial 136\u003c\/p\u003e \u003cp\u003eSummary 137\u003c\/p\u003e \u003cp\u003eReferences 137\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5: Introduction to Foundation Models 139\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eDefinition and Overview of Foundation Models 139\u003c\/p\u003e \u003cp\u003eCharacteristics of Foundation Models 142\u003c\/p\u003e \u003cp\u003eExamples of Foundation Models 144\u003c\/p\u003e \u003cp\u003eTypes of Foundation Models 147\u003c\/p\u003e \u003cp\u003eThe Large Language Model (LLM) 154\u003c\/p\u003e \u003cp\u003eNatural Language Processing 155\u003c\/p\u003e \u003cp\u003eEarly Approaches to NLP 156\u003c\/p\u003e \u003cp\u003eEvolution Toward Text-Based Foundation Model 160\u003c\/p\u003e \u003cp\u003eApplications of Foundation Models 162\u003c\/p\u003e \u003cp\u003eChallenges and Considerations 163\u003c\/p\u003e \u003cp\u003eInfrastructure 163\u003c\/p\u003e \u003cp\u003eEthics 164\u003c\/p\u003e \u003cp\u003eAreas of Evolution 165\u003c\/p\u003e \u003cp\u003eKey Takeaways 167\u003c\/p\u003e \u003cp\u003eReferences 168\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6: Introduction to Amazon SageMaker 169\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eData Preparation and Processing 172\u003c\/p\u003e \u003cp\u003eData Preparation 172\u003c\/p\u003e \u003cp\u003eData Processing 173\u003c\/p\u003e \u003cp\u003eModel Development 174\u003c\/p\u003e \u003cp\u003eModel Training and Tuning 175\u003c\/p\u003e \u003cp\u003eModel Deployment 177\u003c\/p\u003e \u003cp\u003eModel Management 178\u003c\/p\u003e \u003cp\u003eSecurity 179\u003c\/p\u003e \u003cp\u003eCompliance and Governance 180\u003c\/p\u003e \u003cp\u003eModel Explainability and Responsible AI 181\u003c\/p\u003e \u003cp\u003eMLOps with Amazon SageMaker 181\u003c\/p\u003e \u003cp\u003eBoost Your Generative AI Development with SageMaker JumpStart 182\u003c\/p\u003e \u003cp\u003eNo-Code ML with Amazon SageMaker Canvas 183\u003c\/p\u003e \u003cp\u003eAmazon Bedrock 184\u003c\/p\u003e \u003cp\u003eChoosing the Right Strategy for the Development of Your Generative AI Application with Amazon SageMaker 186\u003c\/p\u003e \u003cp\u003eConclusion 187\u003c\/p\u003e \u003cp\u003eReferences 188\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7: Generative AI on AWS 191\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eAWS Services for Generative AI 192\u003c\/p\u003e \u003cp\u003eGenerative AI Trade-Off Triangle 192\u003c\/p\u003e \u003cp\u003eHow AWS Solves the Generative AI Trade-Off Triangle 192\u003c\/p\u003e \u003cp\u003eGenerative AI on AWS: The Fundamentals 193\u003c\/p\u003e \u003cp\u003eInfrastructure for FM Training and Inference 194\u003c\/p\u003e \u003cp\u003eModels and Tools to Build Generative AI Apps 194\u003c\/p\u003e \u003cp\u003eApplications to Boost Productivity 195\u003c\/p\u003e \u003cp\u003eAmazon Bedrock 196\u003c\/p\u003e \u003cp\u003eFoundation Models with Bedrock 197\u003c\/p\u003e \u003cp\u003eAI21 Labs – Jurassic 197\u003c\/p\u003e \u003cp\u003eAmazon Titan 198\u003c\/p\u003e \u003cp\u003eAnthropic’s Claude 3 199\u003c\/p\u003e \u003cp\u003eCohere’s Family of Models 201\u003c\/p\u003e \u003cp\u003eKey Features of Cohere 201\u003c\/p\u003e \u003cp\u003eCohere Models on Amazon Bedrock 203\u003c\/p\u003e \u003cp\u003eMeta’s Family of Models – Llama 204\u003c\/p\u003e \u003cp\u003eWhen to Use Which Model 207\u003c\/p\u003e \u003cp\u003eMistral’s Family of Models 208\u003c\/p\u003e \u003cp\u003eWhen to Use Which Model 209\u003c\/p\u003e \u003cp\u003eStability.ai’s Family of Models – Stable Diffusion XL 1.0 209\u003c\/p\u003e \u003cp\u003ePoolside Family of Models 210\u003c\/p\u003e \u003cp\u003eLuma’s Family of Models 211\u003c\/p\u003e \u003cp\u003eAmazon’s Nova Family of Models 212\u003c\/p\u003e \u003cp\u003eModel Evaluation in Amazon Bedrock 213\u003c\/p\u003e \u003cp\u003eCommon Approaches to Customizing Your FMs 214\u003c\/p\u003e \u003cp\u003eAmazon Bedrock Prompt Management 214\u003c\/p\u003e \u003cp\u003eAmazon Bedrock Flows 216\u003c\/p\u003e \u003cp\u003eData Automation in Amazon Bedrock 219\u003c\/p\u003e \u003cp\u003eGraphRAG in Amazon Bedrock 220\u003c\/p\u003e \u003cp\u003eKnowledge Bases in Amazon Bedrock 222\u003c\/p\u003e \u003cp\u003eHow Knowledge Bases Work 223\u003c\/p\u003e \u003cp\u003ePre-Processing Data 224\u003c\/p\u003e \u003cp\u003eRuntime Execution 224\u003c\/p\u003e \u003cp\u003eCreating a Knowledge Base in Amazon Bedrock 225\u003c\/p\u003e \u003cp\u003eAgents for Amazon Bedrock 225\u003c\/p\u003e \u003cp\u003eHow Agents Work 226\u003c\/p\u003e \u003cp\u003eComponents of an Agent at Build Time 226\u003c\/p\u003e \u003cp\u003eComponents of an Agent at Runtime 228\u003c\/p\u003e \u003cp\u003eGuardrails for Amazon Bedrock 230\u003c\/p\u003e \u003cp\u003eSecurity in Amazon Bedrock 231\u003c\/p\u003e \u003cp\u003eAmazon Q 232\u003c\/p\u003e \u003cp\u003eAmazon Q Business 232\u003c\/p\u003e \u003cp\u003eAmazon Q in QuickSight 235\u003c\/p\u003e \u003cp\u003eAmazon Q Developer 238\u003c\/p\u003e \u003cp\u003eAmazon Q Connect 239\u003c\/p\u003e \u003cp\u003eAmazon Q in AWS Supply Chain 241\u003c\/p\u003e \u003cp\u003eSummary 241\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8: Customization of Your Foundation Model 243\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIntroduction to LLM Customization 244\u003c\/p\u003e \u003cp\u003eContinued Pre-Training (Domain Adaptation Fine-Tuning) 244\u003c\/p\u003e \u003cp\u003eFine-Tuning 245\u003c\/p\u003e \u003cp\u003ePrompt Engineering 245\u003c\/p\u003e \u003cp\u003eRetrieval Augmented Generation (RAG) 246\u003c\/p\u003e \u003cp\u003eChoosing Between These Customization Techniques 246\u003c\/p\u003e \u003cp\u003eCost of Customization 249\u003c\/p\u003e \u003cp\u003eCustomizing Foundation Models with AWS 250\u003c\/p\u003e \u003cp\u003eContinuous Pre-Training with Amazon Bedrock 250\u003c\/p\u003e \u003cp\u003eCreation of a Training and a Validation Dataset 250\u003c\/p\u003e \u003cp\u003eLaunch of a Continued Pre-Training Job 251\u003c\/p\u003e \u003cp\u003eAnalysis of Our Results and Adjustment of Our Hyperparameters 252\u003c\/p\u003e \u003cp\u003eDeployment of Our Model 254\u003c\/p\u003e \u003cp\u003eUse Your Customized Model 255\u003c\/p\u003e \u003cp\u003eInstruction Fine-Tuning with Amazon Bedrock 257\u003c\/p\u003e \u003cp\u003eInstruction Fine-Tuning with Amazon SageMaker JumpStart 257\u003c\/p\u003e \u003cp\u003eConclusion 260\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9: Retrieval-Augmented Generation 263\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhat Is RAG? 263\u003c\/p\u003e \u003cp\u003eBackground and Motivation 264\u003c\/p\u003e \u003cp\u003eOverview of RAG 266\u003c\/p\u003e \u003cp\u003eBuilding a RAG Solution 269\u003c\/p\u003e \u003cp\u003eDesign Considerations 269\u003c\/p\u003e \u003cp\u003eBest Practices 270\u003c\/p\u003e \u003cp\u003eCommon Patterns 271\u003c\/p\u003e \u003cp\u003ePerformance Optimization 271\u003c\/p\u003e \u003cp\u003eScaling Considerations 272\u003c\/p\u003e \u003cp\u003eThe Future of RAG Implementations 273\u003c\/p\u003e \u003cp\u003eRetrieval Module 274\u003c\/p\u003e \u003cp\u003eRetrieval Techniques and Algorithms 276\u003c\/p\u003e \u003cp\u003eAugmentation Module 278\u003c\/p\u003e \u003cp\u003eGeneration Module 280\u003c\/p\u003e \u003cp\u003eRAG on AWS 282\u003c\/p\u003e \u003cp\u003eCustom Data Pipeline to Build RAG 284\u003c\/p\u003e \u003cp\u003eCore Components of a RAG Pipeline 284\u003c\/p\u003e \u003cp\u003eImplementation Approaches 286\u003c\/p\u003e \u003cp\u003eBasic Solution: LangChain Implementation 286\u003c\/p\u003e \u003cp\u003eAdvanced Solution: Spark-Based Pipeline 287\u003c\/p\u003e \u003cp\u003eData Ingestion (Examples) 288\u003c\/p\u003e \u003cp\u003eParallel Processing (example) 288\u003c\/p\u003e \u003cp\u003eCase Studies and Applications 290\u003c\/p\u003e \u003cp\u003eQuestion-Answering Systems 290\u003c\/p\u003e \u003cp\u003eDialogue Systems 290\u003c\/p\u003e \u003cp\u003eKnowledge-Intensive Tasks 291\u003c\/p\u003e \u003cp\u003eImplementation Considerations and Best Practices 291\u003c\/p\u003e \u003cp\u003eChallenges and Future Directions 292\u003c\/p\u003e \u003cp\u003eExample Notebooks 293\u003c\/p\u003e \u003cp\u003eReferences 293\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10: Generative AI on AWS Labs 295\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eLab 1: Introduction to Generative AI with Bedrock 295\u003c\/p\u003e \u003cp\u003eOption 1: PartyRock Prompt Engineering Guide (for Non-Technical and Technical Audiences) 297\u003c\/p\u003e \u003cp\u003eOption 2: Amazon Bedrock Labs (for Technical Audiences) 298\u003c\/p\u003e \u003cp\u003eOverview of Amazon Bedrock and Streamlit 298\u003c\/p\u003e \u003cp\u003eSupported Regions 298\u003c\/p\u003e \u003cp\u003eCosts When Running from Your Own Account 298\u003c\/p\u003e \u003cp\u003eQuotas When Running from Your Own Account 299\u003c\/p\u003e \u003cp\u003eTime to Complete 299\u003c\/p\u003e \u003cp\u003eLab 2: Dive Deep into Gen AI with Amazon Bedrock 299\u003c\/p\u003e \u003cp\u003eLab 3: Building an Agentic LLM Assistant on AWS 300\u003c\/p\u003e \u003cp\u003eWhat Is an Agentic LLM Assistant? 300\u003c\/p\u003e \u003cp\u003eWhy Build an Agentic LLM Assistant? 301\u003c\/p\u003e \u003cp\u003eAbout This Workshop 301\u003c\/p\u003e \u003cp\u003eArchitecture 301\u003c\/p\u003e \u003cp\u003eLabs 302\u003c\/p\u003e \u003cp\u003eLab 4: Retrieval-Augmented Generation Workshop 303\u003c\/p\u003e \u003cp\u003eManaged RAG Workshop 304\u003c\/p\u003e \u003cp\u003eNaive RAG Workshop 304\u003c\/p\u003e \u003cp\u003eAdvance RAG Workshop 304\u003c\/p\u003e \u003cp\u003eAudience 304\u003c\/p\u003e \u003cp\u003eLab 5: Amazon Q for Business 304\u003c\/p\u003e \u003cp\u003eNext Steps 307\u003c\/p\u003e \u003cp\u003eLab 6: Building a Natural Language Query Engine for Data Lakes 308\u003c\/p\u003e \u003cp\u003eSummary 310\u003c\/p\u003e \u003cp\u003eReference 310\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11: Next Steps 311\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Future of Generative AI: Key Dimensions and Staying Informed 311\u003c\/p\u003e \u003cp\u003eTechnical Evolution and Capabilities 312\u003c\/p\u003e \u003cp\u003eThe Evolution of Scale and Architecture 312\u003c\/p\u003e \u003cp\u003eThe Multimodal Revolution 312\u003c\/p\u003e \u003cp\u003eThe Efficiency Breakthrough 313\u003c\/p\u003e \u003cp\u003eThe Context Window Revolution 313\u003c\/p\u003e \u003cp\u003eReal-time Processing and Generation 313\u003c\/p\u003e \u003cp\u003eThe Future Technological Landscape 314\u003c\/p\u003e \u003cp\u003eApplication Domains 314\u003c\/p\u003e \u003cp\u003eEnterprise Applications: The Quiet Revolution 315\u003c\/p\u003e \u003cp\u003eThe Scientific Frontier: Accelerating Discovery 315\u003c\/p\u003e \u003cp\u003eHealthcare: Personalized Medicine and Diagnosis 315\u003c\/p\u003e \u003cp\u003eEducation and Training: Personalizing Learning 316\u003c\/p\u003e \u003cp\u003eEnvironmental Applications: Tackling Global Challenges 316\u003c\/p\u003e \u003cp\u003eThe Future of Applications 317\u003c\/p\u003e \u003cp\u003eEthical and Societal Implications 317\u003c\/p\u003e \u003cp\u003eDigital Identity and Deep Fakes: The Crisis of Trust 318\u003c\/p\u003e \u003cp\u003eLabor Markets and Economic Disruption 318\u003c\/p\u003e \u003cp\u003ePrivacy and Data Rights in the Age of AI 318\u003c\/p\u003e \u003cp\u003eBias and Fairness: The Hidden Challenges 319\u003c\/p\u003e \u003cp\u003eDemocratic Access and Digital Divides 319\u003c\/p\u003e \u003cp\u003eEnvironmental and Sustainability Concerns 319\u003c\/p\u003e \u003cp\u003eThe Path Forward: Governance and Responsibility 319\u003c\/p\u003e \u003cp\u003eLooking to the Future 320\u003c\/p\u003e \u003cp\u003eStaying Current in the Rapidly Evolving AI Landscape 320\u003c\/p\u003e \u003cp\u003eGlossary 323\u003c\/p\u003e \u003cp\u003eIndex 333\u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e  \u003cp\u003e\u003cb\u003eOLIVIER BERGERET\u003c\/b\u003e is a technical leader at Amazon Web Services (AWS), working on database and analytics services. He has over 25 years of experience in data engineering and analytics. Since joining AWS in 2015, he’s supported the launch of most of AWS AI services including Amazon SageMaker and AWS DeepRacer. He is a regular speaker and presenter at various data, AI and cloud events such as AWS re:Invent, AWS Summits and third-party conferences.  \u003c\/p\u003e\u003cp\u003e\u003cb\u003eASIF ABBASI\u003c\/b\u003e is a Principal Solutions Architect at AWS and has spent the last 20 years working in various roles with focus around Data Analytics, AI\/ML, DWH Strategic and Technical Implementations, J2EE Enterprise applications design\/development and Project Management. Asif is an Amazon Certified SA, Hortonworks Certified Hadoop professional and Administrator, Certified Spark Developer, SAS Certified Predictive Modeler, along with being a Sun Certified Enterprise Architect and a Teradata Certified Master. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eJOEL FARVAULT\u003c\/b\u003e is a Principal Solutions Architect Analytics at Amazon Web Services. He has 25 years’ experience working on enterprise architecture, data strategy, and analytics, mainly in the financial services industry. Joel has led data transformation projects on fraud analytics, business intelligence, and data governance. He is also a lecturer on Data Analytics at IA School, at Neoma Business School and at Ecole Superieure de Genie Informatique (ESGI). Joel holds several associate and specialty certifications on AWS.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eCreate cutting-edge generative AI apps on the Amazon Web Services\u003csup\u003e®\u003c\/sup\u003e cloud\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eIn \u003ci\u003eGen AI on AWS\u003csup\u003e®\u003c\/sup\u003e: A Practical Approach to Building Generative AI Applications on AWS\u003c\/i\u003e, a team of expert cloud and software engineers deliver a hands-on roadmap to creating useful generative AI apps from scratch on the Amazon Web Services cloud platform. You’ll find actionable strategies and techniques you can deploy immediately to start writing secure, practical, and reliable applications that implement the latest generative artificial intelligence capabilities. \u003c\/p\u003e\u003cp\u003eBeginning with novice-friendly introductions to topics like the history of artificial intelligence, the basics of machine learning, and the definition of deep learning, the book goes on to explain exactly how to make use of AWS’s extensive library of generative AI tools. \u003c\/p\u003e\u003cp\u003ePerfect for cloud engineers, cloud solutions consultants, software engineers, and other technical professionals, \u003ci\u003eGen AI on AWS\u003c\/i\u003e is also a can’t-miss resource for non-technical business leaders, managers, executives, and directors who seek to better understand the opportunities and potential of the AWS-based AI tools already available to firms today.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989273231589,"sku":"NP9781394281282","price":60.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781394281282.jpg?v=1761783469","url":"https:\/\/k12savings.com\/products\/genai-on-aws-isbn-9781394281282","provider":"K12savings","version":"1.0","type":"link"}