Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletter Hub
Free Learning
Arrow right icon
timer SALE ENDS IN
0 Days
:
00 Hours
:
00 Minutes
:
00 Seconds
Arrow up icon
GO TO TOP
Building AI Agents with LLMs, RAG, and Knowledge Graphs

You're reading from   Building AI Agents with LLMs, RAG, and Knowledge Graphs A practical guide to autonomous and modern AI agents

Arrow left icon
Product type Paperback
Published in Jul 2025
Publisher Packt
ISBN-13 9781835087060
Length 560 pages
Edition 1st Edition
Concepts
Arrow right icon
Authors (2):
Arrow left icon
Salvatore Raieli Salvatore Raieli
Author Profile Icon Salvatore Raieli
Salvatore Raieli
Gabriele Iuculano Gabriele Iuculano
Author Profile Icon Gabriele Iuculano
Gabriele Iuculano
Arrow right icon
View More author details
Toc

Table of Contents (17) Chapters Close

Preface 1. Part 1: The AI Agent Engine: From Text to Large Language Models
2. Chapter 1: Analyzing Text Data with Deep Learning FREE CHAPTER 3. Chapter 2: The Transformer: The Model Behind the Modern AI Revolution 4. Chapter 3: Exploring LLMs as a Powerful AI Engine 5. Part 2: AI Agents and Retrieval of Knowledge
6. Chapter 4: Building a Web Scraping Agent with an LLM 7. Chapter 5: Extending Your Agent with RAG to Prevent Hallucinations 8. Chapter 6: Advanced RAG Techniques for Information Retrieval and Augmentation 9. Chapter 7: Creating and Connecting a Knowledge Graph to an AI Agent 10. Chapter 8: Reinforcement Learning and AI Agents 11. Part 3: Creating Sophisticated AI to Solve Complex Scenarios
12. Chapter 9: Creating Single- and Multi-Agent Systems 13. Chapter 10: Building an AI Agent Application 14. Chapter 11: The Future Ahead 15. Index 16. Other Books You May Enjoy

Summary

This chapter focused on an important aspect of how we plan a multi-agent system. Whatever form our system takes, it must eventually go into production and be used by users. The experience for users is pivotal to whatever project we have in mind. That is why we started by using Streamlit, a framework that allows us to experiment quickly and get an initial proof of concept. Being able to get a prototype of our system allows us to understand both strengths and weaknesses before investing large resources in scaling. The advantage of Streamlit is that it allows us to analyze both the backend and the frontend, enabling us to interact with an application as if we were one of the users. Streamlit allows us to test what a complete product may look like before we conduct scaling and system optimization.

Obviously, an application will then have to pass this prototype stage to enter production. This step requires that we conduct scaling of our application. LLMs are complex products...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime