Why Your B-tree Index Is Useless for Semantic Search — And What HNSW Does Instead
For software engineers who know what an index is and what an embedding is. Start Here: A Question You Think You Already Know the Answer To You have a chunks table with 50,000 rows. Each row has a text column and a vector column — a list of 1536 floating point numbers representing the semantic meaning of that text. A user query arrives. You embed it into another 1536-dimensional vector. Now you want the most semantically similar chunks. ...