Building AI Agents with LLMs, RAG, and Knowledge Graphs

Master LLM fundamentals to advanced techniques like RAG, reinforcement learning, and knowledge graphs to build, deploy, and scale intelligent AI agents that reason, retrieve, and act autonomously

DRM-free PDF version + access to Packt's next-gen Reader

Key Features

• Implement RAG and knowledge graphs for advanced problem-solving
• Leverage innovative approaches like LangChain to create real-world intelligent systems
• Integrate large language models, graph databases, and tool use for next-gen AI solutions

Book Description

This book addresses the challenge of building AI that not only generates text but also grounds its responses in real data and takes action. Authored by AI specialists with expertise in drug discovery and systems optimization, this guide empowers you to leverage retrieval-augmented generation (RAG), knowledge graphs, and agent-based architectures to engineer truly intelligent behavior. By combining large language models (LLMs) with up-to-date information retrieval and structured knowledge, you'll create AI agents capable of deeper reasoning and more reliable problem-solving.

Inside, you'll find a practical roadmap from concept to implementation. You’ll discover how to connect language models with external data via RAG pipelines for increasing factual accuracy and incorporate knowledge graphs for context-rich reasoning. The chapters will help you build and orchestrate autonomous agents that combine planning, tool use, and knowledge retrieval to achieve complex goals. Concrete Python examples and real-world case studies reinforce each concept and show how the techniques fit together.

By the end of this book, you’ll be able to build intelligent AI agents that reason, retrieve, and interact dynamically, empowering you to deploy powerful AI solutions across industries.

Email sign-up and proof of purchase required

What you will learn

• Learn how LLMs work, their structure, uses, and limits, and design RAG pipelines to link them to external data
• Build and query knowledge graphs for structured context and factual grounding
• Develop AI agents that plan, reason, and use tools to complete tasks
• Integrate LLMs with external APIs and databases to incorporate live data
• Apply techniques to minimize hallucinations and ensure accurate outputs
• Orchestrate multiple agents to solve complex, multi-step problems
• Optimize prompts, memory, and context handling for long-running tasks
• Deploy and monitor AI agents in production environments

Who this book is for

If you are a data scientist or researcher who wants to learn how to create and deploy an AI agent to solve limitless tasks, this book is for you. To get the most out of this book, you should have basic knowledge of Python and Gen AI. This book is also excellent for experienced data scientists who want to explore state-of-the-art developments in LLM and LLM-based applications.

Table of Contents

1. Analyzing Text Data with Deep Learning
2. The Transformer: The Model Behind the Modern AI Revolution
3. Exploring LLMs as a Powerful AI Engine
4. Building a Web Scraping Agent with an LLM
5. Extending Your Agent with RAG to Prevent Hallucinations
6. Advanced RAG Techniques for Information Retrieval and Augmentation
7. Creating and Connecting a Knowledge Graph to an AI Agent
8. Reinforcement Learning and AI Agents
9. Creating Single- and Multi-Agent Systems
10. Building an AI Agent Application
11. The Future Ahead

Salvatore Raieli is a senior data scientist in a pharmaceutical company with a focus on using AI for drug discovery against cancer. He has led different multidisciplinary projects with LLMs, agents, NLP, and other AI techniques. He has an MSc in AI and a PhD in immunology and has experience in building neural networks to solve complex problems with large datasets. He enjoys building AI applications for concrete challenges that can lead to societal benefits. In his spare time, he writes on his popularization blog on AI (on Medium).

Gabriele Iuculano boasts extensive expertise in embedded systems and AI. Leading a team as the test platform architect, Gabriele has been instrumental in architecting a sophisticated simulation system that underpins a cutting-edge test automation platform. He is committed to integrating AI-driven solutions, focusing on predictive maintenance systems to anticipate needs and prevent downtimes. He obtained his MSc in AI from the University of Leeds, demonstrating expertise in leveraging AI for system efficiencies. Gabriele aims to revolutionize current business through the power of new disruptive technologies such as AI.