Update run.py

run.py

@@ -183,7 +183,7 @@ def multimodalResponse(message,history,dropdown):
   str(context)
   print(system)
   formatted_prompt = format_prompt(system+"\n"+query, history)
-  stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+  stream = inferenceClient.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
   output = ""
   for response in stream:
     output += response.token.text