Overview

The Agentic RAG Handbook Building Retrieval-Driven AI Agents for Dynamic Problem Solving and Knowledge IntegrationBuild AI that retrieves, reasons, and acts.Most Large Language Models are powerful-but reactive. They answer based on training data, forget context, and can't take real action. Retrieval-Augmented Generation (RAG) changes that by giving models access to fresh, external knowledge at runtime. But to create true intelligent agents, you need more than retrieval-you need agency.This practical handbook by Mark Wendell shows you how to build Agentic RAG systems that combine RAG pipelines with memory, tool use, and decision-making logic. You'll learn to design agents that can plan multi-step tasks, adapt to new information, and execute actions in real time.Inside you'll find: Clear, code-driven tutorials in Python for building robust RAG pipelines.Proven patterns for adding memory, reasoning loops, and API/tool orchestration.Strategies for grounding agents in accurate, up-to-date information.Deployment guidance for cloud, local, or edge environments.Real-world applications in enterprise, research, and regulated industries.A complete final project to design, build, and launch your first Agentic RAG system.If you've worked with chatbots, copilots, or assistants-and want them to become goal-driven, autonomous problem solvers-this book is your blueprint.Don't just retrieve answers. Build agents that think, adapt, and act. Get your copy today and start building the future of AI.

Full Product Details

9798262168538

Table of Contents

Reviews

Author Information

Tab Content 6

Countries Available