diff --git a/src/oss/langgraph/agentic-rag.mdx b/src/oss/langgraph/agentic-rag.mdx
index 46ea6e1411..89c3531fc5 100644
--- a/src/oss/langgraph/agentic-rag.mdx
+++ b/src/oss/langgraph/agentic-rag.mdx
@@ -150,15 +150,17 @@ Now that we have our split documents, we can index them into a vector store that
   )
   retriever = vectorstore.as_retriever()
   ```
-2. Create a retriever tool using LangChain's prebuilt `create_retriever_tool`:
+2. Create a retriever tool using the `@tool` decorator:
   ```python
-  from langchain_classic.tools.retriever import create_retriever_tool
+  from langchain.tools import tool
 
-  retriever_tool = create_retriever_tool(
-      retriever,
-      "retrieve_blog_posts",
-      "Search and return information about Lilian Weng blog posts.",
-  )
+  @tool
+  def retrieve_blog_posts(query: str) -> str:
+      """Search and return information about Lilian Weng blog posts."""
+      docs = retriever.invoke(query)
+      return "\n\n".join([doc.page_content for doc in docs])
+
+  retriever_tool = retrieve_blog_posts
   ```
 3. Test the tool:
   ```python