Exercise 2 — Keyword search vs vector search

Guided practice5 min

Time: 25-35 min
You need: the kit, the venv, Ollama running, the Chroma store of Exercise 1 in data/chroma/
Deliverable: the five-row table of Step 4 and the hybrid top-3 of Step 5, pasted in a text file

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

Goal

Two technicians disagree. One says "just search the words". The other says "use the embeddings". You will settle it with numbers. For five real questions, you will rank the 31 chunks with TF-IDF and with Chroma, compare the top hit of each, and then merge both rankings with reciprocal rank fusion.

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 9 — Retrieval and vector databases” 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