book

AI-Assisted Coding

Name: AI-Assisted Coding
ISBN: 9781807787714

by Rheinwerk Publishing, Inc, Michael Kofler, Bernd Öggl, Sebastian Springer

April 2026

Intermediate

399 pages

11h 38m

English

Packt Publishing

Read now

Unlock full access

Notes on Usage
Table of Contents
Preface
Local Execution of Language Models Coding with AI Support for Advanced Users AI Makes Mistakes and Hallucinates The Three Stages of Using AI There’s No Getting around AI Tools
Part I Coding with AI Support
1 Introduction
1.1 Coding via Chat1.1.1 Password Generator1.1.2 Python: Searching and Replacing Dates1.1.3 SQL: Analysis of a Table1.1.4 PHP: Bearer Token Authentication1.1.5 Porting a Bash Script for PowerShell1.1.6 Paid ChatGPT Offers1.1.7 Anthropic Claude
1.2 The Art of Prompting
1.2.1 Prompt Frameworks1.2.2 A Question of Context1.2.3 Custom GPTs1.2.4 Comparing Custom GPTs, Fine-Tuning, and Retrieval-Augmented Generation
1.3 Code Wizards
1.3.1 Installing GitHub Copilot1.3.2 First Steps with Visual Studio Code and GitHub Copilot1.3.3 Switching between Code Suggestions1.3.4 Tips and Tricks1.3.5 Chat Mode with Additional Keywords1.3.6 Chat Examples1.3.7 Alternatives to the Chat Sidebar1.3.8 Other Functions1.3.9 Security and Data Protection1.3.10 Trouble in Remote Mode
1.4 Chat or Wizard?
1.5 Basic Principles of Large Language Models
1.5.1 From the Human Brain to Neural Networks1.5.2 Machine Learning through Backpropagation1.5.3 Large Language Models1.5.4 The Transformer Model1.5.5 Generative Pretrained Transformer (GPT)1.5.6 Training: From Training Material to Language Model1.5.7 Large Language Model Application: From Prompt to Response1.5.8 The Limits of Linguistic “Intelligence”1.5.9 The Size of the Context Window1.5.10 The Fill-in-the-Middle Approach
2 Pair Programming
2.1 Structuring Code into Functions2.1.1 Defining Functions Yourself2.1.2 Defining Functions and Parameters2.1.3 Detailed Questions about Functions and Parameters2.1.4 Code Optimization2.1.5 Code Reuse2.1.6 Splitting Code across Multiple Files

2.2 Example: IBAN Validation
2.2.1 Start2.2.2 Checking the IBAN Length2.2.3 Troubleshooting2.2.4 Test2.2.5 Removing Spaces from the IBAN2.2.6 Checksum Test2.2.7 Trouble with the Test Data2.2.8 Code Optimization
2.3 Object-Oriented Programming
2.3.1 Example: User Account Class2.3.2 Output of the Object2.3.3 JSON Export and Constructor2.3.4 Example: Bank Account2.3.5 Example: Sorting Photos Based on EXIF Data2.3.6 Example: Dealing with Singletons
2.4 Example: Quiz
2.4.1 Class Design2.4.2 Implementing the Question Class2.4.3 A Pool of Questions for Testing2.4.4 Methods for the Question Class2.4.5 UML Diagram2.4.6 AI Bot or Code Wizard?
2.5 Example: Solving Sudoku
2.5.1 Class Setup2.5.2 Detaching Individual Fields in Rows2.5.3 Solving Individual Fields in Columns and in Blocks2.5.4 Test Code and Issues with the Test Data2.5.5 Brainstorming2.5.6 Storing Solution Candidates per Field2.5.7 Filling in Fields Where Only One Solution Number Is Possible2.5.8 Personal Conclusion2.5.9 Alternative Procedure2.5.10 Prompting Correctly
3 Debugging
3.1 Web Applications3.1.1 CSS Fixes3.1.2 iCal Download in the Browser3.1.3 Backend Frontend without a Proxy Server3.1.4 JavaScript Fetch with the Wrong Content Type3.1.5 JamGPT
3.2 App Development
3.2.1 Flutter and Null Safety Values3.2.2 Layouts in Flutter
3.3 Developing on Raspberry Pi
3.3.1 Step-by-Step Debugging on a Raspberry Pi3.3.2 Help for Creating Log Entries
3.4 Visual Studio and Visual Studio Code
3.4.1 Missing Python Modules in VS Code3.4.2 Visual Studio Exception Debugging
3.5 Conclusion
4 Refactoring
4.1 Introduction to Refactoring4.1.1 Objectives of Refactoring
4.2 Refactoring Using AI Tools
4.2.1 Recognizing the Need for Refactoring
4.3 Best Practices
4.3.1 Only the Internal Structure May Be Changed4.3.2 Small-Step Approach4.3.3 Test-Driven Refactoring4.3.4 Defining Clear Goals
4.4 Conclusion
5 Testing Software
5.1 Generating Test Data
5.2 AI-Supported Test Automation
5.2.1 Creating AI-Supported Unit Tests
5.3 Test-Driven Development with AI
5.3.1 Implementing the First Test5.3.2 The Second Test5.3.3 The Third Test5.3.4 Generating Test Data
5.4 Using Dependencies
5.5 Optimizing Tests
5.5.1 Optimizing Test Code5.5.2 Writing Missing Tests
5.6 End-to-End Tests
5.6.1 Generating an End-to-End Test5.6.2 Creating a Page Object
5.7 Conclusion
6 Documenting Software
6.1 Challenges with Documentation
6.2 Inline Documentation
6.2.1 Sample Inline Documentation
6.3 Function and Class Documentation
6.3.1 Benefits and Drawbacks of Function and Class Documentation6.3.2 Sample Function and Class Documentation
6.4 API Documentation
6.4.1 Sample API Documentation
6.5 Outdated Documentation
6.6 Conclusion
7 Databases
7.1 Database Design7.1.1 Example: Database for an Online Store7.1.2 Database Management System Selection7.1.3 Example: Cloud Shopping List7.1.4 Changing the Database Schema
7.2 SQL Commands
7.2.1 Date Calculation7.2.2 Troubleshooting7.2.3 WordPress Image Search7.2.4 Complex Query with Subquery or Self Join7.2.5 Formatting an SQL Command
7.3 Administration
7.3.1 PostgreSQL: User Administration7.3.2 SQL Server: Automated Backup7.3.3 Determining the Schema of a Database7.3.4 MariaDB Tuning
7.4 Client Programming
8 Scripting and System Administration
8.1 Scripting8.1.1 Bash: Loop Over a Text File8.1.2 PowerShell: Sorting Photos8.1.3 Python: SQLite Application8.1.4 Bash Troubleshooting8.1.5 Python: Recursive Search for Files8.1.6 Other Prompt Examples
8.2 Example: Converting a Python Script to PHP Code
8.2.1 Conclusion
8.3 Regular Expressions
8.3.1 Searching and Replacing Dates8.3.2 File Search Using grep
8.4 System Administration
8.4.1 SSH Authentication by Key8.4.2 Docker Setup8.4.3 Proxy Server8.4.4 Fixing Network Issues in a Virtual Machine with a Web Server8.4.5 Linux Server Setup8.4.6 Additional Prompts
8.5 Example: “wget” Script Plus “tmpfs” Configuration
8.5.1 Developing a “wget” Script8.5.2 Linux Server Configuration with “tmpfs”8.5.3 Conclusion
8.6 Calling GitHub Copilot and ChatGPT in the Terminal
8.6.1 GitHub Command-Line Interface (“gh”)8.6.2 Shell-GPT (“sgpt”)8.6.3 Using Language Models in the Terminal (“llm”)
Part II Local Language Models and Advanced AI Tools
9 Executing Language Models Locally
9.1 Spoiled for Choice of Large Language Model9.1.1 Which Models Solve Which Problems?9.1.2 Hardware Requirements9.1.3 Alternatives to the Local Execution of Models
9.2 GPT4All
9.2.1 Installation and Use9.2.2 Chat with Your Files9.2.3 Conclusion
9.3 Ollama
9.3.1 Benefits of Ollama9.3.2 General Structure of Ollama9.3.3 Local Installation and Execution9.3.4 Running Ollama in a Docker Container
9.4 Open WebUI for Ollama
9.4.1 Installing Open WebUI9.4.2 Using Custom Documents in Open WebUI9.4.3 Custom Workspace Models
9.5 Continue
9.5.1 Installation9.5.2 Usage
9.6 Ollama API
9.6.1 Ollama REST API9.6.2 Libraries for Accessing the Ollama API
9.7 Tabby
9.7.1 Installing the Tabby Server and the Plug-In9.7.2 Usage
9.8 Conclusion
10 Automated Code Processing
10.1 OpenAI API10.1.1 Setting Up an API Account10.1.2 Hello, World!10.1.3 Formulating the Prompt10.1.4 Chat System10.1.5 Processing the Response10.1.6 Uploading and Downloading Files10.1.7 Uploads for Special Applications10.1.8 Playground
10.2 Ollama API
10.2.1 Manipulating Code
10.3 Groq API
10.4 Example: Automated Commenting of Code
10.4.1 Real-Life Experience10.4.2 Extracting Code from the Response10.4.3 Genuine Errors10.4.4 Trouble with Large Code Files10.4.5 Translating Existing Comments10.4.6 Conclusion
10.5 Example: From Python 2 to Python 3
10.5.1 Real-Life Experience
11 Level 3 Tools: OpenHands and Aider
11.1 OpenHands11.1.1 Installation11.1.2 The Web Interface
11.2 Using OpenHands
11.2.1 Not Too Much at Once!11.2.2 Conclusion
11.3 Aider
11.3.1 Installation11.3.2 Start11.3.3 Aider Commands11.3.4 Multiline Prompts11.3.5 Coding Rules and Conventions11.3.6 Aider in the Web Browser
11.4 Using Aider
11.4.1 Example 1: Sorting Photos11.4.2 Example 2: Web Scraping11.4.3 Example 3: Implementing Changes in a Large Project11.4.4 More Prompting Examples and Video Tips
12 Retrieval-Augmented Generation and Text-to-SQL
12.1 RAG Quick Start
12.2 The Viel-Falter (Many Butterflies) Project
12.3 Loading Documents
12.3.1 SimpleDirectoryReader and SimpleWebPageReader
12.4 Creating an Index
12.4.1 The Embedding Model
12.5 Vector Store Databases
12.6 RAG Queries
12.6.1 Source Code12.6.2 Conclusion
12.7 Text-to-SQL
12.7.1 Database Export from MongoDB to SQLite12.7.2 Text-to-SQL with LlamaIndex12.7.3 Sample Queries12.7.4 Conclusion
13 Risks and Outlook
13.1 Issues and Limitations of Using AI Tools13.1.1 Old, Cumbersome Code13.1.2 The Question of Maintainability13.1.3 Privacy13.1.4 A New Kind of Dependency13.1.5 Learning to Program in the Age of AI
13.2 Exemplary AI Failure
13.2.1 Outdated Information13.2.2 Hallucinations13.2.3 Logic Errors13.2.4 Security Issues13.2.5 Less Than Ideal Solutions
13.3 Ethical Issues
13.3.1 The Origin of AI Knowledge13.3.2 Jobless IT Experts13.3.3 Unlimited Energy Consumption
13.4 Conclusions and Outlook
13.4.1 Better Results with More Prior Knowledge and Experience13.4.2 Cloud or Local AI?13.4.3 Quality Enhancement through Training with AI-Generated Code13.4.4 The Coming Few Years13.4.5 Conclusion
The Authors
Index
Service Pages
Legal Notes

Content preview from AI-Assisted Coding

12.6 RAG Queries

For our question to lead to a meaningful answer, several steps are executed in succession by the LlamaIndex library:

The question in natural language is converted into vectors. For this purpose, the same embedding model must be used as when creating VectorStoreIndex.
The system searches for similar vectors in the database.
The content of the LlamaIndex nodes found is redirected to an LLM as a context with the question.
The LLM formulates an answer in natural language from the data.

Having dealt with the embedding model so far, this is the first time we’ve come into contact with the LLM. But that’s not quite true: in Section 12.4, TitleExtractor used an LLM to create a summary from the split documents. Which LLM ...

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

Publisher Resources

ISBN: 9781807787714

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

AI-Assisted Coding

by Rheinwerk Publishing, Inc, Michael Kofler, Bernd Öggl, Sebastian Springer

12.6 RAG Queries

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.