RE
RAG Explainer Search — Similarity Rank
[06/08] Search — Similarity Rank

Rank every chunk by meaning

Your question is already a fingerprint (previous step). Now compare it against 8 mock chunks from the insurance PDF — see which bubble up.

How it works

  1. Cosine compares the question fingerprint with every chunk’s.
  2. Scores run 0.00 (unrelated) to 1.00 (same meaning).
  3. Sort all scores, keep only the Top-K, drop the rest.
Threshold: show only > 0.30

Top-K chunks are the only ones sent to the LLM. Others are ignored — like discarding 40 pages of legal fluff. Wondering why keywords aren’t enough? Try Keyword vs Vector →

For Builders — cosine

cosine = dot(a,b) for normalized vectors. Here Top-K=4. Real DBs use ANN for 10k+ vectors.