diff --git a/pages/generative-apis/how-to/query-language-models.mdx b/pages/generative-apis/how-to/query-language-models.mdx
index ea5239835e..47a4cab1e5 100644
--- a/pages/generative-apis/how-to/query-language-models.mdx
+++ b/pages/generative-apis/how-to/query-language-models.mdx
@@ -212,7 +212,7 @@ The service also supports asynchronous mode for any chat completion.
   )
 
   async def main():
-      stream = client.chat.completions.create(
+      stream = await client.chat.completions.create(
           model="llama-3.1-8b-instruct",
           messages=[{
           "role": "user",
@@ -250,7 +250,7 @@ The service also supports asynchronous mode for any chat completion.
           if event.type == "response.output_text.delta":
               print(event.delta, end="")
           elif event.type == "response.completed":
-              break
+              continue
 
   asyncio.run(main())
   ```