What is RAG?
Review note: The answer refers to the original author's CV or target job offer — adapt it to your own experience.
Answer out loud or in your head first, then compare.
Answer
RAG is a way of preparing a model's answer using materials retrieved beforehand. The app first finds matching documents or passages, then passes them to the model together with the question. That way the model works with specific sources, not only knowledge memorised during training.
Example: an employee asks about leave rules. The system retrieves the current company document and uses it to create an answer with a link. RAG doesn't automatically mean training the model on the documents. Nor does it guarantee correctness: you can find the wrong passage or use it badly. Access to the materials must be checked before passing them to the model.
Why it matters: One of the offer's main requirements, previously explained too late.
Possible follow-ups: What happens when search doesn't find the document with the answer?
How did it go? Be honest — “Not yet” puts the question on your review list.
Further reading
- Azure AI Search: Hybrid search overview(opens in a new tab)Docs; accessed 22.10.2026. Vectors plus full text, with rankings merged by RRF.