Leanpub Header

Skip to main content
Go to Leanpub.com

Gerbil Scheme in Action

AI Applications, Network Programming, and Utilities

Gerbil Scheme in Action
This book is 100% completeLast updated on 2026-11-12
+17,478 words in the last 30 days
Mark Watson

Lisp languages are a secret weapon! Use the modern Gerbil Scheme for AI and other applications.

Minimum price

Free!

$10.00

You pay

Author earns

$

Also available for 1 book credit with a Reader Membership

PDF
EPUB
WEB
APP
About

About

About the Book

Gerbil Scheme is a practical modern Lisp language that is used in this book for Large Language Model (LLMs) and other AI projects, network programming, and for writing utilities.

Share this book

Feedback

Contact the author

Author

About the Author

Mark Watson

Mark Watson is a consultant specializing in LLMs, deep learning, machine learning, knowledge graphs, and general artificial intelligence software development. He uses Common Lisp, Clojure, Python, Java, Haskell, and Ruby for development.

He is the author of 20+ published books on Artificial Intelligence, Deep Learning, Java, Ruby, Machine Learning, Common LISP, Clojure, JavaScript, Semantic Web, NLP, C++, Linux, and Scheme. He has 55 US Patents.

Mark's consulting customer list includes: Google, Capital One, Olive AI, CompassLabs, Disney, Sitescout.com, Embed.ly, and Webmind Corporation.

Mark wrote ten traditional published books for McGraw Hill, Springer Verlag, J Wiley, and Morgan Kaufman publishers before adopting the LeanPub self-publishing platform.

The Leanpub Podcast

Podcast

Podcast Episode

Contents

Table of Contents

Preface

  1. New Material Added in Latest Edition
  2. A Comment on Licenses
  3. Running Gerbil Scheme on macOS and Linux
  4. History and Background to the Gerbil Scheme Project
  5. Core Gerbil Toolkits Used in this Book: :std/net/request and :std/text/json

Setting Up Gerbil Scheme Development Environment

  1. Verifying Your Installation with Hello World
  2. The Gerbil Workflow: Modules, Packages, and Build Tools
  3. Editor Setup
  4. Gerbil for Schemers: Quick Language Primer

Introduction To Writing Command Line Utilities

  1. Overview of the Command Line Utilities Project Structure and Build System
  2. Simple Structure for Command Line Utilities
  3. A More Flexible Structure for Command Line Utilities
  4. Wrap Up for Writing Command Line Utilities in Gerbil Scheme and Notes On User Built Libraries
  5. Optional Practice Problems

Web Scraping in Gerbil Scheme

  1. What We Will Build
  2. Why Regular Expressions and Not a Real Parser
  3. Project Structure
  4. The Library: webscrape.ss
  5. The Test Program: test_webscrape.ss
  6. Running the Test Driver
  7. Interpreting the Output
  8. Design Choices and Limitations
  9. Wrap Up
  10. Optional Practice Problems

Google Gemini API

  1. Example Code
  2. Example Output
  3. Optional Practice Problems

Ollama

  1. Example Code
  2. Install Ollama and Pull a Model to Experiment With
  3. Example Output
  4. Tool/Function Calling with Ollama
  5. Defining Tools: example_tools.ss
  6. The Agent Loop: use_tools.ss
  7. Tool Calling Example Output
  8. Building Your Own Tools
  9. Optional Practice Problems

OpenAI API

  1. Example Code
  2. Example Output
  3. Optional Practice Problems

Inexpensive and Fast LLM Inference Using the Groq Service

  1. Structure of Project and Build Instructions
  2. groq_inference.ss Utility
  3. Example script: gpt-oss-120b.ss
  4. Optional Practice Problems

Building a Personal AI Assistant CLI with Gerbil Scheme

  1. The Idea: Your Own AI Terminal Companion
  2. Theory: Grounding, RAG, and the Context Window
  3. Project Structure
  4. The Cache Module
  5. The Main REPL Module
  6. Building and Running
  7. Sample Session
  8. Interpreting the Results
  9. Wrap Up
  10. Optional Practice Problems

AI-Driven Text Adventure Game in Gerbil Scheme

  1. The Architecture of an LLM Game Master
  2. Defining the Adventure World (story.txt)
  3. Implementing the Game Loop (game.ss)
  4. The Automated Smoke Test (test.ss)
  5. Running the Game and Sample Session
  6. Interpreting the Results
  7. Wrap Up
  8. Optional Practice Problems

Building an Autonomous LLM Coding Harness

  1. The Architecture of an Agentic Harness
  2. The Delimiter Scanner (parens.ss)
  3. Generating Unified Diffs and Human Approval (approval.ss)
  4. The Verification Gate (checker.ss)
  5. Running the Coding Harness
  6. Interpreting the Results
  7. Wrap Up
  8. Optional Practice Problems

A Simple In-Memory RDF Store and Query Language in Gerbil Scheme

  1. Introduction to RDF and the Goal of This Chapter
  2. Data Model: Triples and the Store
  3. Parsing SPARQL Queries
  4. Query Evaluation: Pattern Matching and Joining
  5. Gerbil RDF Implementation
  6. Running the Demo and Using the Code
  7. Summary and Further Directions
  8. Optional Practice Problems

Wikidata API Using SPARQL Queries

  1. Example Code
  2. Example Output
  3. Optional Practice Problems

Code for Natural Language Processing (NLP)

  1. Structure of Project and Build Instructions
  2. Top Level Project Code
  3. Other Source Files
  4. Test Run
  5. Building and Running the Command Line Tool
  6. Optional Practice Problems

Command Line Applications For NLP

  1. Re-using the NLP Library For a Command Line Utility to Identify Categories or Topics in Input Text
  2. Using OpenAI’s GPT-5 model To Summarize Input Text
  3. Optional Practice Problems

AutoContext: Hybrid Retrieval-Augmented Generation (RAG)

  1. Theoretical Foundations of Hybrid Retrieval
  2. Input Data Representation
  3. Implementing BM25 Okapi in Gerbil Scheme
  4. Implementing Vector-Space TF-IDF in Gerbil Scheme
  5. Orchestrating the AutoContext Pipeline
  6. Test Suite and Verification
  7. Running the Code and Expected Output
  8. Interpreting the Results
  9. Wrap Up
  10. Optional Practice Problems

Gerbil Scheme FFI Example Using the C Language Raptor RDF Library

  1. Implementation of a FFI Bridge Library for Raptor
  2. Test Code
  3. Build System
  4. Optional Practice Problems

Complete FFI Example: C Language Wrapper for Rasqal SPARQL Library and Sord RDF Datastore Library

  1. Library Selection
  2. Overview of the Project Structure and Build System
  3. Implementation of the C Language Wrapper
  4. A Gerbil Scheme Shim to Call The C Language Wrapper Code
  5. Gerbil Scheme Main Program for this Example
  6. Example Output
  7. Optional Practice Problems

WebKit Applications - macOS Only

  1. Architecture Overview
  2. Prerequisites and Building
  3. Project Structure
  4. The C Shim
  5. Gambit FFI Bindings
  6. The Bridge: JS to Scheme Communication
  7. High-Level API
  8. Example 1: Hello World
  9. Example 2: Counter App with Bridge
  10. Example 3: Markdown File Viewer
  11. The Build System
  12. Comparing Common Lisp and Gerbil Versions
  13. API Reference Summary
  14. Key Takeaways
  15. Optional Practice Problems

Symbolic Mathematics: Polynomial Differentiation and Integration

  1. Theoretical Foundations
  2. The Data Layer (data.ss)
  3. Symbolic Differentiation (differentiation.ss)
  4. Symbolic Integration (integration.ss)
  5. Complete Test Suite (test.ss)
  6. Running the Code and Expected Output
  7. Interpreting the Results
  8. Wrap Up
  9. Optional Practice Problems

Probability: Bayesian and Frequentist Reasoning

  1. Theoretical Foundations
  2. The Bayesian Engine (bayes.ss)
  3. Correlation Analysis (correlation.ss)
  4. The Frequentist Toolkit (frequentist.ss)
  5. The Medical Screening Example (medical.ss)
  6. The Frequentist Trial Simulation (frequentist-demo.ss)
  7. Running the Code and Expected Output
  8. Interpreting the Results
  9. Wrap Up
  10. Optional Practice Problems

Gaussian Anomaly Detection

  1. Theoretical Background
  2. The Dataset
  3. Project Structure
  4. The Detector Module: detector.ss
  5. The Demo Program: wisconsin_demo.ss
  6. Running the Demo
  7. Interpreting the Results
  8. Wrap Up
  9. Optional Practice Problems

K-means Clustering

  1. Theoretical Background
  2. The Dataset
  3. Project Structure
  4. The K-means Library: kmeans-lib.ss
  5. The Demo Program: test.ss
  6. Running the Demo
  7. Interpreting the Results
  8. Wrap Up
  9. Optional Practice Problems

microGPT: A Complete Transformer and Autograd Engine from Scratch

  1. Theoretical Foundations
  2. Input Data Sample (names.txt)
  3. Complete Source Code (microgpt.ss)
  4. Running the Code and Expected Output
  5. Interpreting the Results
  6. Wrap Up
  7. Optional Practice Problems

Reinforcement Learning: Value Iteration and Q-Learning

  1. Theoretical Background
  2. Project Structure
  3. Example 1: Value Iteration on a 3×3 Grid World
  4. Example 2: Q-Learning on FrozenLake
  5. Wrap Up
  6. Optional Practice Problems

Building a Chess Engine and AI Bot

  1. Theoretical Background
  2. Project Structure
  3. The Engine Module: engine.ss
  4. The AI Module: ai.ss
  5. The CLI Module: cli.ss
  6. The Perft Module: perft.ss
  7. Running the Code
  8. Interpreting the Output
  9. Wrap Up
  10. Optional Practice Problems

Also by the Author

Also by the Author

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub