From 1e18e19496f553101299f188e4c0068f465ee6af Mon Sep 17 00:00:00 2001 From: Andrew Kane Date: Mon, 28 Aug 2023 15:25:11 -0700 Subject: [PATCH] Updated readme [skip ci] --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index b43374c..9f2a1a4 100644 --- a/README.md +++ b/README.md @@ -166,7 +166,7 @@ Supported index types are: ## IVFFlat -An IVFFlat index divides vectors into lists, and then searches a subset of those lists. It has faster build times and uses less memory than HNSW, but has lower query performance. +An IVFFlat index divides vectors into lists, and then searches a subset of those lists. It has faster build times and uses less memory than HNSW, but has lower query performance (in terms of speed-recall tradeoff). Three keys to achieving good recall are: @@ -217,7 +217,7 @@ COMMIT; ## HNSW -An HNSW index creates a multilayer graph. It has slower build times and uses more memory than IVFFlat, but has better query performance. There’s no training step like IVFFlat, so the index can be created without any data in the table. +An HNSW index creates a multilayer graph. It has slower build times and uses more memory than IVFFlat, but has better query performance (in terms of speed-recall tradeoff). There’s no training step like IVFFlat, so the index can be created without any data in the table. Add an index for each distance function you want to use.