diff --git a/packages/create-llama/templates/types/simple/fastapi/app/api/routers/chat.py b/packages/create-llama/templates/types/simple/fastapi/app/api/routers/chat.py
index f6a246386a01579da33f13235685cfa99741e76c..d4b000fd8306e588f8fceaed0a8f22386a76ea77 100644
--- a/packages/create-llama/templates/types/simple/fastapi/app/api/routers/chat.py
+++ b/packages/create-llama/templates/types/simple/fastapi/app/api/routers/chat.py
@@ -50,7 +50,7 @@ async def chat(
     ]
 
     # query chat engine
-    response = chat_engine.chat(lastMessage.content, messages)
+    response = await chat_engine.achat(lastMessage.content, messages)
     return _Result(
         result=_Message(role=MessageRole.ASSISTANT, content=response.response)
     )
diff --git a/packages/create-llama/templates/types/streaming/fastapi/app/api/routers/chat.py b/packages/create-llama/templates/types/streaming/fastapi/app/api/routers/chat.py
index 9dd9eb6ed30544899a02c7eb3678239a5b94ea6d..26fd480dee6a01004b19e48b81205b7fc7e55b66 100644
--- a/packages/create-llama/templates/types/streaming/fastapi/app/api/routers/chat.py
+++ b/packages/create-llama/templates/types/streaming/fastapi/app/api/routers/chat.py
@@ -49,11 +49,11 @@ async def chat(
     ]
 
     # query chat engine
-    response = chat_engine.stream_chat(lastMessage.content, messages)
+    response = await chat_engine.astream_chat(lastMessage.content, messages)
 
     # stream response
     async def event_generator():
-        for token in response.response_gen:
+        async for token in response.async_response_gen():
             # If client closes connection, stop sending events
             if await request.is_disconnected():
                 break