book

Generative AI with Python

Name: Generative AI with Python
ISBN: 9781807780210

by Rheinwerk Publishing, Inc, Bert Gollnick

April 2026

Intermediate

395 pages

13h 22m

English

Packt Publishing

Read now

Unlock full access

Notes on Usage
Table of Contents
Preface
Objective of This Book Target Audience Prerequisites: What You Should Already Know Structure of This Book How to Use This Book Effectively Downloadable Code and Additional Materials System Setup Acknowledgments Conventions Used in This Book
1 Introduction to Generative AI
1.1 Introduction to Artificial Intelligence
1.2 Pillars of Generative AI Advancement
1.2.1 Computational Power1.2.2 Model and Data Size1.2.3 Investments1.2.4 Algorithmic Improvements
1.3 Deep Learning
1.4 Narrow AI and General AI
1.5 Natural Language Processing Models
1.5.1 NLP Tasks1.5.2 Architectures
1.6 Large Language Models
1.6.1 Training1.6.2 Use Cases1.6.3 Limitations
1.7 Large Multimodal Models

1.8 Generative AI Applications
1.8.1 Consumer1.8.2 Business1.8.3 Prosumer
1.9 Summary
2 Pretrained Models
2.1 Hugging Face
2.2 Coding: Text Summarization
2.3 Exercise: Translation
2.3.1 Task2.3.2 Solution
2.4 Coding: Zero-Shot Classification
2.5 Coding: Fill-Mask
2.6 Coding: Question Answering
2.7 Coding: Named Entity Recognition
2.8 Coding: Text-to-Image
2.9 Exercise: Text-to-Audio
2.9.1 Task2.9.2 Solution
2.10 Capstone Project: Customer Feedback Analysis
2.11 Summary
3 Large Language Models
3.1 Brief History of Language Models
3.2 Simple Use of LLMs via Python
3.2.1 Coding: Using OpenAI3.2.2 Coding: Using Groq3.2.3 Coding: Large Multimodal Models3.2.4 Coding: Running Local LLMs
3.3 Model Parameters
3.3.1 Model Temperature3.3.2 Top-p and Top-k
3.4 Model Selection
3.4.1 Performance3.4.2 Knowledge Cutoff Date3.4.3 On-Premise versus Cloud-Based Hosting3.4.4 Open-Source, Open-Weight, and Proprietary Models3.4.5 Price3.4.6 Context Window3.4.7 Latency
3.5 Messages
3.5.1 User3.5.2 System3.5.3 Assistant
3.6 Prompt Templates
3.6.1 Coding: ChatPromptTemplates3.6.2 Coding: Improve Prompts with LangChain Hub
3.7 Chains
3.7.1 Coding: Simple Sequential Chain3.7.2 Coding: Parallel Chain3.7.3 Coding: Router Chain3.7.4 Coding: Chain with Memory
3.8 Safety and Security
3.8.1 Security3.8.2 Safety3.8.3 Coding: Implementing LLM Safety and Security
3.9 Model Improvements
3.10 New Trends
3.10.1 Reasoning Models3.10.2 Small Language Models3.10.3 Test-Time Computation
3.11 Summary
4 Prompt Engineering
4.1 Prompt Basics4.1.1 Prompt Process4.1.2 Prompt Components4.1.3 Basic Principles
4.2 Coding: Few-Shot Prompting
4.3 Coding: Chain-of-Thought
4.4 Coding: Self-Consistency Chain-of-Thought
4.5 Coding: Prompt Chaining
4.6 Coding: Self-Feedback
4.7 Summary
5 Vector Databases
5.1 Introduction
5.2 Data Ingestion Process
5.3 Loading Documents
5.3.1 High-Level Overview5.3.2 Coding: Load a Single Text File5.3.3 Coding: Load Multiple Text Files5.3.4 Exercise: Load Multiple Wikipedia Articles5.3.5 Exercise: Loading Project Gutenberg Book
5.4 Splitting Documents
5.4.1 Coding: Fixed-Size Chunking5.4.2 Coding: Structure-Based Chunking5.4.3 Coding: Semantic Chunking5.4.4 Coding: Custom Chunking
5.5 Embeddings
5.5.1 Overview5.5.2 Coding: Word Embeddings5.5.3 Coding: Sentence Embeddings5.5.4 Coding: Create Embeddings with LangChain
5.6 Storing Data
5.6.1 Selection of a Vector Database5.6.2 Coding: File-Based Storage with a Chroma Database5.6.3 Coding: Web-Based Storage with Pinecone
5.7 Retrieving Data
5.7.1 Similarity Calculation5.7.2 Coding: Retrieve Data from Chroma Database5.7.3 Coding: Retrieve Data from Pinecone
5.8 Capstone Project
5.8.1 Features5.8.2 Dataset5.8.3 Preparing the Vector Database5.8.4 Exercise: Get All Genres from the Vector Database5.8.5 App Development
5.9 Summary
6 Retrieval-Augmented Generation
6.1 Introduction
6.2 Coding: Simple Retrieval-Augmented Generation
6.2.1 Knowledge Source Setup6.2.2 Retrieval6.2.3 Augmentation6.2.4 Generation6.2.5 RAG Function Creation
6.3 Advanced Techniques
6.3.1 Advanced Preretrieval Techniques6.3.2 Advanced Retrieval Techniques6.3.3 Advanced Postretrieval Techniques
6.4 Coding: Prompt Caching
6.5 Evaluation
6.5.1 Challenges in RAG Evaluation6.5.2 Metrics6.5.3 Coding: Metrics
6.6 Summary
7 Agentic Systems
7.1 Introduction to AI Agents
7.2 Available Frameworks
7.3 Simple Agent
7.3.1 Agentic RAG7.3.2 ReAct
7.4 Agentic Framework: LangGraph
7.4.1 Simple Graph: Assistant7.4.2 Router Graph7.4.3 Graph with Tools
7.5 Agentic Framework: AG2
7.5.1 Two Agent Conversations7.5.2 Human in the Loop7.5.3 Agents Using Tools
7.6 Agentic Framework: CrewAI
7.6.1 Introduction7.6.2 First Crew: News Analysis Crew7.6.3 Exercise: AI Security Crew
7.7 Agentic Framework: OpenAI Agents
7.7.1 Getting Started with a Single Agent7.7.2 Working with Multiple Agents7.7.3 Agent with Search and Retrieval Functionality
7.8 Agentic Framework: Pydantic AI
7.9 Monitoring Agentic Systems
7.9.1 AgentOps7.9.2 Logfire
7.10 Summary
8 Deployment
8.1 Deployment Architecture
8.2 Deployment Strategy
8.2.1 REST API Development8.2.2 Deployment Priorities8.2.3 Coding: Local Deployment
8.3 Self-Contained App Development
8.4 Deployment to Heroku
8.4.1 Create a New App8.4.2 Download and Configure CLI8.4.3 Create app.py File8.4.4 Procfile Setup8.4.5 Environment Variables8.4.6 Python Environment8.4.7 Check the Result Locally8.4.8 Deployment to Heroku8.4.9 Stop Your App
8.5 Deployment to Streamlit
8.5.1 GitHub Repository8.5.2 Creating a New App
8.6 Deployment with Render
8.7 Summary
9 Outlook
9.1 Advances in Model Architecture
9.2 Limitations and Issues of LLMs
9.2.1 Hallucinations9.2.2 Biases9.2.3 Misinformation9.2.4 Intellectual Property9.2.5 Interpretability and Transparency9.2.6 Jailbreaking LLMs
9.3 Regulatory Developments
9.4 Artificial General Intelligence and Artificial Superintelligence
9.5 AI Systems in the Near Term
9.6 Useful Resources
9.7 Summary
The Author
Index
Service Pages
Legal Notes

Content preview from Generative AI with Python

3.8 Safety and Security

When working with LLMs, you must consider safety and security before you can deploy any system to production. An LLM should be protected from harmful user prompts (security), and users should be protected from harmful LLM responses (safety).

Figure 3.14 shows the pipeline from a user prompt that is first passed to an input firewall that checks for prompt security. Then, the prompt is further processed by the LLM before the output firewall checks whether the model response is safe and can thus be provided to the user.

Figure 3.14 LLM Safety and Security

Let’s study both aspects in more detail, starting with the input ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Generative AI with LangChain - Second Edition

Publisher Resources

ISBN: 9781807780210

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Generative AI with Python

by Rheinwerk Publishing, Inc, Bert Gollnick

3.8 Safety and Security

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.