diff --git a/changelog/10658.misc.md b/changelog/10658.misc.md
new file mode 100644
index 000000000000..f1762761993f
--- /dev/null
+++ b/changelog/10658.misc.md
@@ -0,0 +1 @@
+Added comment to DIET documentation that makes it clear DIET does not ship with pre-trained embeddings.
\ No newline at end of file
diff --git a/docs/docs/components.mdx b/docs/docs/components.mdx
index c00054ffd96d..b48efd247cc0 100644
--- a/docs/docs/components.mdx
+++ b/docs/docs/components.mdx
@@ -1246,7 +1246,8 @@ Intent classifiers assign one of the intents defined in the domain file to incom
   single semantic vector space. We use the dot-product loss to maximize the similarity with the target label and
   minimize similarities with negative samples.
 
-  If you want to learn more about the model, check out the
+  DIET does not provide pre-trained word embeddings or pre-trained language models but it is able to use these features if
+  they are added to the pipeline. If you want to learn more about the model, check out the
   [Algorithm Whiteboard](https://www.youtube.com/playlist?list=PL75e0qA87dlG-za8eLI6t0_Pbxafk-cxb) series on YouTube,
   where we explain the model architecture in detail.