try making the output stream go to screen

app.py

@@ -183,19 +183,25 @@ async def main(message: cl.Message):
     # )
     
     runnable_chain = prompt | model | parser
-    output_chunks = runnable_chain.invoke({})
-    print(''.join(output_chunks))
-    print("output chunks")
+    # output_chunks = runnable_chain.invoke({})
+    # print(''.join(output_chunks))
+    # print("output chunks")
 
 
-    print([m.to_openai() for m in prompt.messages])
+    # print([m.to_openai() for m in prompt.messages])
 
     msg = cl.Message(content="")
 
+    output_stream = runnable_chain.astream({})
+
+    async for chunk in output_stream:
+        print(chunk, sep='', flush=True)
+
     # Call OpenAI
-    async for stream_resp in await client.chat.completions.create(
-        messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
-    ):
+    # async for stream_resp in await client.chat.completions.create(
+    #     messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
+    # ):
+    async for stream_resp in output_stream:
         token = stream_resp.choices[0].delta.content
         if not token:
             token = ""