From 24b8ff1507ede57c29e33332aea9f113418c9c95 Mon Sep 17 00:00:00 2001
From: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Date: Thu, 6 Feb 2025 13:46:09 -0500
Subject: [PATCH] Update
 _posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
---
 _posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md b/_posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md
index 625920c0a..8bfb3c478 100644
--- a/_posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md
+++ b/_posts/2025-02-03-Reduce-Cost-with-Disk-based-Vector-Search.md
@@ -257,7 +257,7 @@ Interestingly, for this dataset, the on-disk approach with rescoring produces si
 
 ## Learnings
 
-Our testing shows that the two-phase ANN approach performs effectively in low-memory environments, though results vary significantly by dataset. When running your own experiments, we recommend testing with the `index.knn.disk.vector.shard_level_rescoring_disabled` setting both enabled and disabled to measure the performance benefit for your use case. Additionally, with disk-based search, ensure that your secondary storage is optimized for high read traffic---we found that SSDs generally provide the best results.
+Our testing shows that the two-phase approximate nearest neighbor approach performs effectively in low-memory environments, though results vary significantly by dataset. When running your own experiments, we recommend testing with the `index.knn.disk.vector.shard_level_rescoring_disabled` setting both enabled and disabled to measure the performance benefit for your use case. Additionally, with disk-based search, ensure that your secondary storage is optimized for high read traffic---we found that SSDs generally provide the best results.
 
 ## What's next?