Part 3 of 8 · 1 min read
Vector search
Search by meaning, and what it can miss.
Module 2 covered it. It finds passages whose meaning is near the query's, so it handles paraphrase, but it can miss exact tokens and it always returns something, even when nothing is relevant. In the example, Dense(DOCS).rank("my money back for the yearly subscription")[0] is the refund passage, which BM25 missed.