Any Python project needs three fundamental tools: the Python interpreter, dependency management, and a task execution tool. The Python interpreter executes your Python project as expected. All the code within the book is tested with Python 3.11.8. You can download the Python interpreter from here: https://www.python.org/downloads/. We recommend installing the exact Python version (Python 3.11.8) to run the LLM Twin project using pyenv, making the installation process straightforward.

Instead of installing multiple global Python versions, we recommend managing them using pyenv, a Python version management tool that lets you manage multiple Python versions between projects. You can install it using this link: https://github.com/pyenv/pyenv?tab=readme-ov-file#installation.

After you have installed pyenv, you can install the latest version of Python 3.11, using pyenv, as follows:

pyenv install 3.11.8

Now list all installed Python...

This section will quickly present all the MLOps and LLMOps tools we will use throughout the book and their role in building ML systems using MLOps best practices. At this point in the book, we don’t aim to detail all the MLOps components we will use to implement the LLM Twin use case, such as model registries and orchestrators, but only provide a quick idea of what they are and how to use them. As we develop the LLM Twin project throughout the book, you will see hands-on examples of how we use all these tools. In Chapter 11, we will dive deeply into the theory of MLOps and LLMOps and connect all the dots. As the MLOps and LLMOps fields are highly practical, we will leave the theory of these aspects to the end, as it will be much easier to understand it after you go through the LLM Twin use case implementation.

Also, this section is not dedicated to showing you how to set up each tool. It focuses primarily on what each tool is used for and highlights...

We also want to present the NoSQL and vector databases we will use within our examples. When working locally, they are already integrated through Docker. Thus, when running poetry poe local-infrastructure-up, as instructed a few sections above, local images of Docker for both databases will be pulled and run on your machine. Also, when deploying the project, we will show you how to use their serverless option and integrate it with the rest of the LLM Twin project.

MongoDB: NoSQL database

MongoDB is one of today’s most popular, robust, fast, and feature-rich NoSQL databases. It integrates well with most cloud ecosystems, such as AWS, Google Cloud, Azure, and Databricks. Thus, using MongoDB as our NoSQL database was a no-brainer.

When we wrote this book, MongoDB was used by big players such as Novo Nordisk, Delivery Hero, Okta, and Volvo. This widespread adoption suggests that MongoDB will remain a leading NoSQL database...

This last part of the chapter will focus on setting up an AWS account (if you don’t already have one), an AWS access key, and the CLI. Also, we will look into what SageMaker is and why we use it.

We picked AWS as our cloud provider because it’s the most popular out there and the cloud in which we (the writers) have the most experience. The reality is that other big cloud providers, such as GCP or Azure, offer similar services. Thus, depending on your specific application, there is always a trade-off between development time (in which you have the most experience), features, and costs. But for our MVP, AWS, it’s the perfect option as it provides robust features for everything we need, such as S3 (object storage), ECR (container registry), and SageMaker (compute for training and inference).

Setting up an AWS account, an access key, and the CLI

As AWS could change its UI/UX, the best way to instruct you on how to create an AWS account...

In this chapter, we reviewed the core tools used across the book. First, we understood how to install the correct version of Python that supports our repository. Then, we looked over how to create a virtual environment and install all the dependencies using Poetry. Finally, we understood how to use a task execution tool like Poe the Poet to aggregate all the commands required to run the application.

The next step was to review all the tools used to ensure MLOps best practices, such as a model registry to share our models, an experiment tracker to manage our training experiments, an orchestrator to manage all our ML pipelines and artifacts, and metadata to manage all our files and datasets. We also understood what type of databases we need to implement the LLM Twin use case. Finally, we explored the process of setting up an AWS account, generating an access key, and configuring the AWS CLI for programmatic access to the AWS cloud. We also gained a deep understanding of...

• Acsany, P. (2024, February 19). Dependency Management With Python Poetry. https://realpython.com/dependency-management-python-poetry/
• Comet.ml. (n.d.). comet-ml/opik: Open-source end-to-end LLM Development Platform. GitHub. https://github.com/comet-ml/opik
• Czakon, J. (2024, September 25). ML Experiment Tracking: What It Is, Why It Matters, and How to Implement It. neptune.ai. https://neptune.ai/blog/ml-experiment-tracking
• Hopsworks. (n.d.). ML Artifacts (ML Assets)? Hopsworks. https://www.hopsworks.ai/dictionary/ml-artifacts
• Introduction | Documentation | Poetry – Python dependency management and packaging made easy. (n.d.). https://python-poetry.org/docs
• Jones, L. (2024, March 21). Managing Multiple Python Versions With pyenv. https://realpython.com/intro-to-pyenv/
• Kaewsanmua, K. (2024, January 3). Best Machine Learning Workflow and Pipeline Orchestration Tools. neptune.ai. https://neptune.ai/blog/best-workflow-and-pipeline...