Your own AI, running on your own computer. No account. No monthly bill. Nothing leaves your PC.

In this hands-on project you install Ollama, download a small AI model, chat with it, and then build a real tool with it: a Python script that summarises any text file into three bullet points.

What you’ll build

• Ollama installed and working, with a small model (llama3.2:3b) ready to chat
• summarize.py: point it at any .txt file, get a 3-point summary
• ask.py: ask your local AI a question from a script

What you’ll learn

• What an AI model is, what “pull” means, and how much space and memory it needs
• How programs talk to Ollama (the same idea as any API)
• Reading and changing a real AI script
• Fixing the usual problems (Ollama not running, model not downloaded, file errors)

What you get

• A 13-lesson step-by-step course with real screenshots
• The finished scripts, a sample article, and a README

You need: Windows or Mac, about 3 GB of free disk space, 8 GB of RAM or more, and the free lessons What is the terminal?, What is Python? and What is a virtual environment? (links inside).

Time: about 30 minutes, most of it the one-time model download.