Building AI Agents with LLMs, RAG, and Knowledge Graphs : A Practical Guide to Autonomous and Modern AI Agents.

Format:

Book

Author/Creator:

Raieli, Salvatore.

Contributor:

Iuculano, Gabriele.

Language:

English

Subjects (All):

Artificial intelligence--Computer programs.

Artificial intelligence.

Natural language processing (Computer science).

Physical Description:

1 online resource (560 pages)

Edition:

1st ed.

Place of Publication:

Birmingham : Packt Publishing, Limited, 2025.

Summary:

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 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 Purchase of the print or Kindle book includes a free PDF eBook Book Description This AI agents 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 deep 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 built on popular libraries, along with real-world case studies, reinforce each concept and show you how these techniques come together. By the end of this book, you'll be well-equipped to build intelligent AI agents that reason, retrieve, and interact dynamically, empowering you to deploy powerful AI solutions across industries. 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.

Contents:

Cover

Title Page

Copyright and Credits

Dedication

Disclaimer

Contributors

Table of Contents

Preface

Free Benefits with Your Book

Part 1: The AI Agent Engine: From Text to Large Language Models

Chapter 1: Analyzing Text Data with Deep Learning

Technical requirements

Representing text for AI

One-hot encoding

Bag-of-words

TF-IDF

Embedding, application, and representation

Word2vec

A notion of similarity for text

Properties of embeddings

RNNs, LSTMs, GRUs, and CNNs for text

RNNs

LSTMs

GRUs

CNNs for text

Performing sentiment analysis with embedding and deep learning

Summary

Chapter 2: The Transformer: The Model Behind the Modern AI Revolution

Exploring attention and self-attention

Introducing the transformer model

Training a transformer

Exploring masked language modeling

Visualizing internal mechanisms

Applying a transformer

Subscribe for a free eBook

Chapter 3: Exploring LLMs as a Powerful AI Engine

Discovering the evolution of LLMs

The scaling law

Emergent properties

Context length

Mixture of experts

Instruction tuning, fine-tuning, and alignment

Exploring smaller and more efficient LLMs

Exploring multimodal models

Understanding hallucinations and ethical and legal issues

Prompt engineering

Further reading

Part 2: AI Agents and Retrieval of Knowledge

Chapter 4: Building a Web Scraping Agent with an LLM

Understanding the brain, perception, and action paradigm

The brain

The perception

Action

Classifying AI agents

Understanding the abilities of single-agent and multiple-agent systems

Exploring the principal libraries

LangChain

Haystack

LlamaIndex

Semantic Kernel

AutoGen.

Choosing an LLM agent framework

Creating an agent to search the web

Chapter 5: Extending Your Agent with RAG to Prevent Hallucinations

Exploring naïve RAG

Retrieval, optimization, and augmentation

Chunking strategies

Embedding strategies

Embedding databases

Evaluating the output

Comparison between RAG and fine-tuning

Using RAG to build a movie recommendation agent

Chapter 6: Advanced RAG Techniques for Information Retrieval and Augmentation

Discussing naïve RAG issues

Exploring the advanced RAG pipeline

Hierarchical indexing

Hypothetical questions and HyDE

Context enrichment

Query transformation

Keyword-based search and hybrid search

Query routing

Reranking

Response optimization

Modular RAG and its integration with other systems

Training and training-free approaches

Implementing an advanced RAG pipeline

Understanding the scalability and performance of RAG

Data scalability, storage, and preprocessing

Parallel processing

Security and privacy

Open questions and future perspectives

Chapter 7: Creating and Connecting a Knowledge Graph to an AI Agent

Introduction to knowledge graphs

A formal definition of graphs and knowledge graphs

Taxonomies and ontologies

Creating a knowledge graph with your LLM

Knowledge creation

Creating a knowledge graph with an LLM

Knowledge assessment

Knowledge cleaning

Knowledge enrichment

Knowledge hosting and deployment

Retrieving information with a knowledge graph and an LLM

Graph-based indexing

Graph-guided retrieval

GraphRAG applications

Understanding graph reasoning.

Knowledge graph embeddings

Graph neural networks

LLMs reasoning on knowledge graphs

Ongoing challenges in knowledge graphs and GraphRAG

Chapter 8: Reinforcement Learning and AI Agents

Introduction to reinforcement learning

The multi-armed bandit problem

Markov decision processes

Deep reinforcement learning

Model-free versus model-based approaches

On-policy versus off-policy methods

Exploring deep RL in detail

Challenges and future direction for deep RL

Learning how to play a video game with reinforcement learning

LLM interactions with RL models

RL-enhanced LLMs

LLM-enhanced RL

Key takeaways

Part 3: Creating Sophisticated AI to Solve Complex Scenarios

Chapter 9: Creating Single- and Multi-Agent Systems

Introduction to autonomous agents

Toolformer

HuggingGPT

ChemCrow

SwiftDossier

ChemAgent

Multi-agent for law

Multi-agent for healthcare applications

Working with HuggingGPT

Using HuggingGPT locally

Using HuggingGPT on the web

Multi-agent system

SaaS, MaaS, DaaS, and RaaS

Software as a Service (SaaS)

Model as a Service (MaaS)

Data as a Service (DaaS)

Results as a Service (RaaS)

A comparison of the different paradigms

Chapter 10: Building an AI Agent Application

Introduction to Streamlit

Starting with Streamlit

Caching the results

Developing our frontend with Streamlit

Adding the text elements

Inserting images in a Streamlit app

Creating a dynamic app

Creating an application with Streamlit and AI agents

Machine learning operations and LLM operations

Model development

Model training

Model testing.

Inference optimization

Handling errors in production

Security considerations for production

Asynchronous programming

asyncio

Asynchronous programming and ML

Docker

Kubernetes

Docker with ML

Chapter 11: The Future Ahead

AI agents in healthcare

Biomedical AI agents

AI agents in other sectors

Physical agents

LLM agents for gaming

Web agents

Challenges and open questions

Challenges in human-agent communication

No clear superiority of multi-agents

Limits of reasoning

Creativity in LLM

Mechanistic interpretability

The road to artificial general intelligence

Ethical questions

Chapter 12: Unlock Your Exclusive Benefits

Index

About Packt

Other Books You May Enjoy.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

1-83508-038-3

OCLC:

1527710967

Publisher Number:

CIPO000229933