Unlocking Data with Generative AI and RAG : Learn AI Agent Fundamentals with RAG-Powered Memory, Graph-based RAG, and Intelligent Recall.

Format:

Book

Author/Creator:

Bourne, Keith.

Language:

English

Subjects (All):

Natural language generation (Computer science).

Artificial intelligence--Computer programs.

Artificial intelligence.

Physical Description:

1 online resource (606 p.)

Edition:

Second edition.

Place of Publication:

Birmingham : Packt Publishing, Limited, 2025.

Summary:

Design intelligent AI agents with retrieval-augmented generation, memory components, and graph-based context integrationFree with your book: DRM-free PDF version + access to Packt's next-gen Reader* Key Features Build next-gen AI systems using agent memory, semantic caches, and LangMem Implement graph-based retrieval pipelines with ontologies and...

Contents:

Cover

Title Page

Copyright

Dedication

Contributors

Table of Contents

Preface

Free Benefits with Your Book

Part 1: Introduction to Retrieval-Augmented Generation (RAG)

Chapter 1: What Is Retrieval-Augmented Generation?

Understanding RAG

basics and principles

Advantages of RAG

Challenges of RAG

RAG vocabulary

LLM

Prompting, prompt design, and prompt engineering

LangChain and LlamaIndex

Inference

AI agents and agent-related terminology

Context window

Fine-tuning

full-model fine-tuning and parameter-efficient fine-tuning

Vector store or vector database?

Vectors, vectors, vectors!

Understanding vectors

Implementing RAG in AI applications

Comparing RAG with conventional generative AI

Comparing RAG with model fine-tuning

The architecture and stages of RAG systems

Summary

Chapter 2: Code Lab: An Entire RAG Pipeline

Technical requirements

Setting up an LLM account with OpenAI

Code lab 2.1

building your first RAG pipeline

Step 1

installing dependencies

Step 2

imports

Step 3

OpenAI connection

Step 4

indexing

Web loading and crawling

Step 5

splitting

Step 6

embedding and indexing the chunks

Retrieval and generation

Step 7

prompt templates from LangChain Hub

Step 8

formatting a function so that it matches the next step's input

Step 9

defining your LLM

Step 10

setting up a LangChain chain using LCEL

Step 11

submitting a question for RAG

Final output

Chapter 3: Practical Applications of RAG

Customer support and chatbots with RAG

Technical support

Financial services

Healthcare

RAG for automated reporting

How RAG is utilized with automated reporting

Transforming unstructured data into actionable insights

Enhancing decision-making and strategic planning

E-commerce support

Dynamic online product descriptions

Product recommendations for e-commerce sites

Utilizing knowledge bases with RAG

Searchability and utility of internal knowledge bases

External knowledge retrieval: from compliance to competitive intelligence

Personalization and targeted recommendations

Training and education

Code lab 3.1

adding sources to your RAG

Chapter 4: Components of a RAG System

Technical requirements

Key component overview

Indexing

Retrieval-focused steps

The generation stage

Prompting

Defining your LLM

User interface or UI

Pre-processing

Post-processing

Output interface

Evaluation

Reference

Chapter 5: Managing Security in RAG Applications

How RAG can be leveraged as a security solution

Limiting data

Ensuring the reliability of generated content

Maintaining transparency

RAG security challenges

LLMs as black boxes

Privacy concerns and protecting user data

Hallucinations

Notes:

Description based upon print version of record.

Red teaming

OCLC-licensed vendor bibliographic record.

ISBN:

1-80638-165-6

OCLC:

1565283603