diff --git a/README.md b/README.md
index 4898cf1..87b59f6 100644
--- a/README.md
+++ b/README.md
@@ -414,14 +414,6 @@ Yes, pgvector uses the write-ahead log (WAL), which allows for replication and p
 
 You’ll need to use [dimensionality reduction](https://en.wikipedia.org/wiki/Dimensionality_reduction) at the moment.
 
-#### Do indexes need to fit into memory?
-
-No, but as with other index types, you’ll likely see better performance if they do. You can get the size of an index with:
-
-```sql
-SELECT pg_size_pretty(pg_relation_size('index_name'));
-```
-
 #### Can I store vectors with different dimensions in the same column?
 
 You can use `vector` as the type (instead of `vector(3)`).
@@ -471,6 +463,14 @@ and query with:
 SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
 ```
 
+#### Do indexes need to fit into memory?
+
+No, but like other index types, you’ll likely see better performance if they do. You can get the size of an index with:
+
+```sql
+SELECT pg_size_pretty(pg_relation_size('index_name'));
+```
+
 ## Troubleshooting
 
 #### Why isn’t a query using an index?