From 74034f434ba5554adcf357ef705b676636762896 Mon Sep 17 00:00:00 2001
From: DavIvek <david.ivekovic@memgraph.io>
Date: Tue, 7 Oct 2025 11:56:42 +0200
Subject: [PATCH 1/2] add cosine similarity function

---
 pages/querying/vector-search.mdx | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/pages/querying/vector-search.mdx b/pages/querying/vector-search.mdx
index 50ce52e36..26832d83a 100644
--- a/pages/querying/vector-search.mdx
+++ b/pages/querying/vector-search.mdx
@@ -160,6 +160,16 @@ for the metric is `l2sq` (squared Euclidean distance).
 | `sorensen`  | Sørensen-Dice coefficient                           |
 | `jaccard`   | Jaccard index                                       |
 
+### Cosine similarity function
+
+You can calculate cosine similarity directly in queries using the `vector_search.cosine_similarity` function. This is useful when you need to compute similarity between vectors without creating a vector index.
+
+{<h3 className="custom-header"> Usage: </h3>}
+
+```cypher
+RETURN vector_search.cosine_similarity([1.0, 2.0], [1.0, 3.0]) AS similarity;
+```
+
 ### Scalar type
 
 Properties are stored as 64-bit values in the property store. However, for efficiency, vector elements in the vector index are stored using 32-bit values by default. 

From 275de004fc45262b0451cd123cb525825cf55acb Mon Sep 17 00:00:00 2001
From: Matea Pesic <80577904+matea16@users.noreply.github.com>
Date: Tue, 7 Oct 2025 13:31:19 +0200
Subject: [PATCH 2/2] Apply suggestions from code review

---
 pages/querying/vector-search.mdx | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pages/querying/vector-search.mdx b/pages/querying/vector-search.mdx
index 26832d83a..1e5ab1c62 100644
--- a/pages/querying/vector-search.mdx
+++ b/pages/querying/vector-search.mdx
@@ -160,9 +160,9 @@ for the metric is `l2sq` (squared Euclidean distance).
 | `sorensen`  | Sørensen-Dice coefficient                           |
 | `jaccard`   | Jaccard index                                       |
 
-### Cosine similarity function
+### Cosine similarity
 
-You can calculate cosine similarity directly in queries using the `vector_search.cosine_similarity` function. This is useful when you need to compute similarity between vectors without creating a vector index.
+You can calculate cosine similarity directly in queries using the `vector_search.cosine_similarity()` function. This is useful when you need to compute similarity between vectors without creating a vector index.
 
 {<h3 className="custom-header"> Usage: </h3>}