T4-R3 in five minutes
An embedding is a list of numbers that stands for a text.
Cosine similarity is a comparison, not an understanding.
Dense passage retrieval is a cited approach for finding passages this way.
A close vector can still be the wrong fact.
Lab 06 shows a naive neighbor search missing a keyword hit. Read that result as a lesson, not a universal law.
Keep a keyword path beside the vector path until you have measured both on your notes. The lab's ablation is one fixture, not every corpus.
Sources and go deeper
- Karpukhin and co-authors, Dense Passage Retrieval for Open-Domain Question Answering, 2020 paper last checked 2026-10
- Lewis and co-authors, Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, 2020 paper last checked 2026-10
- Word embedding — Wikipedia wikipedia last checked 2026-10
- Retrieval-augmented generation — Wikipedia wikipedia last checked 2026-10