try simply changing invoke to stream

app.py

@@ -145,7 +145,7 @@ def chain_call(history):
     # search_result = vector_store.similarity_search(query=st.session_state["messages"][-1]["content"], k=5)
     # chat_completion = search_result # TODO update this after we implement our chain
     # chat_completion = chain.invoke(input_example) # *** TODO here we will pass only the chat history, the chain handles the system prompt
-    chat_completion = chain.invoke(input)
+    chat_completion = chain.stream(input)
     return chat_completion
 
 def write_response():