To get the most out of this book

To maximize your learning experience, you are expected to have, at the very least, a foundational understanding of software development principles and practices. Familiarity with Python programming is particularly beneficial, as the book’s examples and code snippets are predominantly in Python. While prior experience with machine learning concepts is advantageous, it is not strictly necessary, as the book provides explanations for many fundamental AI and ML concepts. However, you should be comfortable with basic data structures, algorithms, and have some experience working with APIs and cloud services.

Familiarity with version control systems like Git is assumed, as this book has a GitHub repository for code examples. While this book is designed to be accessible to those who are new to AI and LLMs, if you have some background in these areas, you will find it easier to grasp the more advanced concepts and techniques we present.

Download the example code files

The code bundle for the book is hosted on GitHub at https://github.com/PacktPublishing/LLM-Engineers-Handbook. We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!

Download the color images

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. You can download it here: https://packt.link/gbp/9781836200079.

Conventions used

There are a number of text conventions used throughout this book.

CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. For example: “In the format_samples function, we apply the Alpaca chat template to each individual message.”

A block of code is set as follows:

def format_samples(example):
    example["prompt"] = alpaca_template.format(example["prompt"])
    example["chosen"] = example['chosen'] + EOS_TOKEN
    example["rejected"] = example['rejected'] + EOS_TOKEN
    return {"prompt": example["prompt"], "chosen": example["chosen"], "rejected": example["rejected"]}

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

def format_samples(example):
    example["prompt"] = alpaca_template.format(example["prompt"])
    example["chosen"] = example['chosen'] + EOS_TOKEN
    example["rejected"] = example['rejected'] + EOS_TOKEN
    return {"prompt": example["prompt"], "chosen": example["chosen"], "rejected": example["rejected"]}

Any command-line input or output is written as follows:

poetry install --without aws

Bold: Indicates a new term, an important word, or words that you see on the screen. For instance, words in menus or dialog boxes appear in the text like this. For example: “To do so, go to the Settings tab at the top of the forked repository in GitHub. In the left panel, in the Security section, click on the Secrets and Variables toggle and, finally, click on Actions.”

Warnings or important notes appear like this.

Tips and tricks appear like this.