Building AI Applications on the Web

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.This book shows you step-by-step and example-by-example how to build sites and applications that take advantage of large language models (LLMs) like GPT, Claude, and Llama. Written especially for web developers comfortable with React or Next.js, this book introduces the tools and techniques you need to add sophisticated AI features like Retrieval Augmented Generation (RAG), document summarization, chatbots, and more to your web-based projects.It guides you through AI development using only JavaScript and other common web dev skills–no Python or Machine Learning experience required. You’ll learn by working with full-scale AI projects that solve actual business problems. You’ll soon be delivering user-friendly, efficient interfaces that make the absolute best use of AI tech.In Build AI-Enhanced Web Apps you'll learn how to:Integrate AI models into React and Next.js applicationsImplement streaming responses and real-time AI interactionsManage conversation history and context in chat applicationsImplement LangChain.js for complex AI workflows and reasoningBuild a web application for summarizing documents using LangChain.jsUtilize Retrieval-Augmented Generation (RAG) systems for knowledge managementDevelop an AI-powered interview preparation system with voice feedbackAbout the technologyThe users have spoken! Agents, personalized responses, and other LLM-powered features are required in modern web applications. Build AI-Enhanced Web Apps presents the end-to-end architecture of AI web apps, including UI, backend infrastructure, data processing, API integration, deployment, and scaling, with examples and language perfect for professional web developers.About the bookThis accessible book shows you how to ship real AI features—not just toy demos—using a JavaScript stack you already know: React for UI, Next.js for backend integration, and the Vercel AI SDK to connect to LLMs like Gemini and GPT. In it, you’ll acquire the skills you need to complete two portfolio-ready projects: a voice-based interview assistant and a RAG-powered corporate knowledge system. You’ll also learn how to design workflows that balance latency, cost, and UX and implement responsible guardrails for security, quality control, hallucinations, and bias.What's insideBuild AI features using a professional stackShip production-ready featuresLearn from concrete projectsAbout the readerFor web developers familiar with JavaScript and React.About the authorTheo Despoudis is a Senior Engineer at WP Engine specializing in AI-powered search and headless WordPress. He is an expert in integrating LLMs, RAG, and Vercel AI SDK into React and Next.js apps.Table of ContentsPart 11 Using generative AI in web apps2 Building your first generative AI web application3 Connecting AI models with the Vercel AI SDK4 Managing conversation and state in your applicationPart 25 Prompt engineering in web applications6 Building AI workflows with LangChain.js7 Document summarization and RAG with LangChain.js8 Testing and debugging techniques9 Deployment and securityPart 310 Building an AI interview assistant: Project walk-through11 Building an AI RAG agent: Project walk-throughPart 412 Integrating web apps with the Model Context ProtocolA Running the examples

Sdílet