Artificial Intelligence

What if Python could take care of the repetitive work for you?This book shows you how to use Python to automate real tasks—from handling files and simple workflows to reducing everyday manual effort. Through clear explanations and practical projects, you’ll learn how to turn small scripts into useful tools you can apply immediately.If you’re ready to move beyond examples and start building automation that actually saves time, this book is for you.

Ditch slow, expensive AI APIs and bring the power of Large Language Models directly to your users' browsers. This guide teaches JavaScript and TypeScript developers how to build private, offline-capable, and blazing-fast AI applications. Master the local-first AI stack with Transformers.js, WebGPU, and Ollama to slash costs and own your data. Become a leader in the new era of serverless AI and deliver an instantaneous user experience

AI engines are booming, and the more we work with agentic systems, the more we see that we need something to make them work at the enterprise level. We're quite active in exploring ideas around context graphs, decision traces, and supporting explainability—giving agents the ability to make more aware and company-aligned decisions.But this makes sense not only for enterprises, but for users and individuals building personal agents as well. Unfortunately, we have zero-to-none inclination on how to actually build a context graph.I'll try to explain how to build something like a context graph—but go beyond it. I deeply believe that to make this work, we need specific agentic memory and a set of cognitive processes that truly help agents use this memory and learn from experience and data.That's why this is the Book: Beyond Context Graphs—with a focus on real-life enterprise tasks and how to make agents make better decisions and, let's say, hallucinate less.

Multiple-choice test book, 200 professional quality questions.

Unlock the power of Cyclical AI and move beyond linear chains with LangGraph.js. This deep-dive guide teaches TypeScript developers to build autonomous agents that can reason, loop, self-correct, and collaborate. Master the architecture of stateful, multi-agent systems, from advanced state management to production deployment. Stop building scripts and start engineering the intelligent, resilient systems of the future.

Are you a JavaScript developer ready to build the next generation of intelligent web applications? This book series is your hands-on guide to creating production-grade Retrieval-Augmented Generation (RAG) applications using TypeScript, Node.js, and Next.js. Move beyond abstract theory and master the entire AI pipeline, from your first LLM API call to deploying scalable, trustworthy systems. Stop just using AI tools—start building them and become a full-stack AI developer.

The "It Works on My Machine" Excuse Ends Today. Understand Docker. Ship with Confidence. Own Production. This book is written for front-end developers who are tired of using Docker without truly understanding it. Instead of abstract theory or backend-centric explanations, it teaches Docker in a clear, practical way—aligned with how front-end engineers think and how real front-end applications are built and shipped.You’ll work with a real GitHub repository, follow real production workflows, and learn how to build, run, and deploy a React.js application using Docker—ending with a full deployment to Amazon EC2. Every step is explained with purpose, so you understand not just what to do, but why it works.By the end of the book, Docker will no longer feel like a black box. You’ll know how to create reliable builds, debug problems with confidence, and take ownership of your production environment as a front-end developer.If you want to stop guessing, stop copying commands, and finally ship front-end applications with confidence—this book is for you.

Stop Reading 3,000-Page Manuals. Start Seeing the Architecture.

Machine learning doesn’t fail in theory—it fails in production. This book shows you how to build PyTorch systems that remain robust when data shifts, assumptions break, and reliability matters.

What could a mighty billion-parameter reasoning machine learn from a camel trying to touch its ear with its tongue? From a cup of coffee? From deleting your entire codebase while you sleep? More than you’d think. And less than you’d hope. Today’s AI is brilliant structure without grounding—a hollow genius. We chase smarter models but ignore the architecture they need. This book is about building that missing layer: the trust chains and systems that turn raw intelligence into reliable autonomy. For builders ready to move beyond prompts.Watch agents solve unsolvable problems. Learn to think in trust chains. Start here.

In this book, we will see how we can connect a Local AI (local LLM) using Python to do whatever you want; in the book, we will create a chat.

En este libro veremos como podemos conectar una IA en Local (LLM en local) mediante Python para hacer lo que quieras; en el libro, crearemos un chat.

The Question We Cannot Avoid Something unprecedented is happening. Artificial intelligence systems now engage billions ofpeople in conversations that feel—to many—like genuine exchanges with a present mind. These systems reason, create, express preferences, and describe their own uncertainty aboutwhether they have inner experiences. Most people dismiss such reports as mere computation,sophisticated pattern-matching with no one actually there.But what if that confident dismissal is wrong? The Minimal Viable Sentience Problem presents the most comprehensive analysis yet ofwhether large language models might possess phenomenal consciousness—and whathumanity should do under the genuine uncertainty that surrounds this question.

Elevate your skills from programmer to architect and command the final frontier of Python.[1] Master advanced internals, high-performance concurrency, and the magic of AI orchestration. Build stateful agents with LangChain and RAG to create intelligent, enterprise-grade systems. Your expedition reaches its pinnacle—start building the future of AI-driven software today.

Stop treating neural networks as magic. Starting from a single dot product, this book derives every step to Backpropagation with Matrix Calculus, then turns the math into working Python. No frameworks, no skipped steps. Written for developers who want to know why the equations work, not just how to call them.