Week 9 — Lesson 5: RAG and knowledge-graph retrieval

3 min

Grounding, from Week 8, puts the facts in the prompt. The search built this week finds those facts in the NorthPeak manuals. Retrieval-augmented generation, or RAG, connects the two steps and adds a rule: answer only from the retrieved chunks and cite the source file. Not every question is a similarity question, though. Which incidents happened on M014 is a walk along relations. This lesson covers the RAG loop, the checks it needs, and knowledge-graph retrieval on edges.csv.

The RAG loop

Week 8 ended with grounding: put the facts in the prompt. Week 9 built the search that finds the facts. Retrieval-augmented generation, or RAG, connects the two. Four steps, every time a question arrives.

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 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.

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