Exercise 2 — A text-to-SQL agent with a validator

Guided practice6 min
Time
30-40 min
You need
the kit, the venv, python data/make_dataset.py done, Ollama running with llama3.2, Exercise 1 finished
Deliverable
the five Q: blocks of your Step 6, with their try lines

The lab kit of the course: https://github.com/hrhouma2/aiopsatlas-ml-data-diagnostics-labs-en

Goal

Supervisors at NorthPeak ask questions in English. You will build an agent that turns each question into SQL, checks the SQL, runs it on a read-only copy of diagnostics.sqlite, and shows the rows. The model is small, so some of its queries are wrong. You will see one fail three times in a row and still end right, because your loop feeds the errors back.

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.

Sign inNo account yet? Create one
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
Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one