diff --git a/doc/website/blog/2025-02-12-rag-with-ent-atlas-pgvector.mdx b/doc/website/blog/2025-02-12-rag-with-ent-atlas-pgvector.mdx
index 5f02ba732..86d2cd8fd 100644
--- a/doc/website/blog/2025-02-12-rag-with-ent-atlas-pgvector.mdx
+++ b/doc/website/blog/2025-02-12-rag-with-ent-atlas-pgvector.mdx
@@ -182,7 +182,18 @@ using the statements in [this file](https://github.com/rotemtam/entrag/blob/e917
 
 :::
 
-Now, let's create our Atlas configuration which composes the `base.pg.hcl` file with the Ent schema:
+Now, let's create our base configuration `base.pg.hcl` which provides the vector extension for the public schema:
+
+```hcl title="base.pg.hcl"
+schema "public" {
+}
+
+extension "vector" {
+  schema = schema.public
+}
+```
+
+Now, let's create our Atlas configuration which composes the base.pg.hcl file with the Ent schema:
 
 ```hcl title="atlas.hcl"
 data "composite_schema" "schema" {
@@ -817,4 +828,4 @@ managing and modifying the query execution process.
 
 In this blog post, we explored how to build a RAG system using Ent, Atlas, and pgvector. Special thanks to
 [Eli Bendersky](https://eli.thegreenplace.net/2023/retrieval-augmented-generation-in-go/) for the informative
-blog post and for his great Go writing over the years!
\ No newline at end of file
+blog post and for his great Go writing over the years!