Week 11 — Lesson 1: Tool calling: the model asks, your code runs

2 min

In Week 1 you made a tool call by hand: you asked for JSON, parsed it, checked the name, ran the function. llama3.2 was trained to do the JSON part itself. For NorthPeak this means a question about machine M014 can reach diagnostics.sqlite through a function that your code controls. This lesson shows the tools argument of ollama.chat, the tool_calls that come back, and the tool role that carries the result to the model.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

This lesson is part of the “Week 11 — LLM tools and database querying” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Back to the outline