AI Workflows Course — Preparation Instructions

ℹ️ Read carefully!

During the course for practical exercises, you'll need to use your own computer in combination with cloud resources. Please, install the recommended tools, prepare the required accounts, and make sure that you pass the self-check tests.

Tools

Any operating system is allowed, but some installation variations may apply. The following software needs to be installed locally on your computer:

Git

Available through package managers or Git for Windows installer.

ℹ️ If you never used Git before, it is recommended to watch the introductory videos: Git for poets.

Python

3.11+

Download from the official website or install via a package manager.

ℹ️ On MacOS, it is recommended to use Homebrew: brew install python. On Windows, you can also install Python from the Microsoft Store.

Node.js

20+

Download from the official website or install via a package manager.

→ Installation guide

ℹ️ It is recommended to use a version manager like nvm (MacOS/Linux) or nvm-windows.

Docker

27.+

Available through package managers or Docker Desktop for MacOS and Windows.

ℹ️ Docker is used to run n8n, Ollama, and vector databases locally during the exercises.

Ollama

Download from ollama.com — used for running local LLM models.

ℹ️ After installation, pull a small model to verify it works: ollama pull llama3.2

⚠️ Ollama requires at least 8 GB of RAM. If your machine doesn't meet this requirement, cloud-hosted alternatives will be provided during the course.

VS Code

(recommended) Visual Studio Code — lightweight code editor with great extension support for Python and JavaScript.

Accounts & API Keys

You will need access to the following services. Please create accounts and obtain API keys before the course:

OpenAI

Create an account at platform.openai.com and generate an API key.

ℹ️ You'll need to add a small amount of credit (e.g. $5–10) to cover API usage during the exercises.

LangSmith

(optional) Create a free account at smith.langchain.com — used for tracing and evaluating LLM applications.

Self-check

Essential tools

Check that Git is working from your command line, and you can clone a project from GitLab e.g.:

git --version
git clone https://gitlab.com/gitlab-org/examples/npm-install

Python & Node.js

Check that Python and Node.js are installed and working from your command line:

python3 --version
pip3 --version
node --version
npm --version

Docker & Ollama

Check that Docker and Ollama are installed and working:

docker version
ollama --version

OpenAI API key

Verify your OpenAI API key works by running the following command (replace YOUR_API_KEY with your actual key):

curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

You should receive a JSON response with a list of available models.