Advanced RAG
Better answers.
Fix the query.↘
What does basic RAG get wrong often enough
that advanced RAG exists to fix?
Basic RAG does one similarity search on the user's raw question and hopes the top-k chunks are right. In practice the retrieval is what breaks: a question is worded nothing like the document that answers it, key facts get split across separate chunks, and a single search only ever asks once.
A great model handed the wrong passages still gives a wrong answer, so advanced RAG focuses almost entirely on getting the right text in front of the model.
fix it?”
→ No. A great model handed
the wrong passages still gives
a wrong answer.
How do query rewriting, multi-query, and HyDE each improve
the search before retrieval happens?
All three fix the query before searching. Rewriting rephrases a vague or messy question into something cleaner.
Multi-query turns one question into several rewordings, searches with each, and unions the results, so a single bad phrasing doesn't sink you. HyDE (Hypothetical Document Embeddings) goes further: the model drafts a fake answer to the question and searches with that, because an answer looks far more like the real document than a question does.
cleanly
rewordings
each
results
answer
the draft
the real doc
Why does HyDE search with a made-up answer
instead of the user's raw question?
Vector search returns whatever is nearest in meaning-space, and a question like "why is onboarding slow?" lands far from the paragraph that answers it. A drafted answer uses the same vocabulary and shape as the real document, so it sits right next to it, and the search then retrieves the true passages.
The draft doesn't have to be correct. It only has to be shaped like the target.
The risk is that on a niche topic the model can invent a wrong premise and steer the search off.
This is a small sample.
600+ interview questions live inside Skillumen.
Every concept card carries its own interview questions, graded as you answer.
Free to start.