Improved chat mode

main.py

@@ -4,9 +4,13 @@ from llama_index.node_parser import SimpleNodeParser
 from llama_index import VectorStoreIndex
 from llama_index.llms import OpenAI, ChatMessage, MessageRole
 from llama_index.prompts import ChatPromptTemplate
+from llama_index import set_global_handler
+from llama_index.chat_engine.types import ChatMode
 import os
 import re
 
+#set_global_handler("simple")
+
 llm = OpenAI(model="gpt-4", temperature=0, max_tokens=256)
 service_context = ServiceContext.from_defaults(llm=llm)
 set_global_service_context(service_context)
@@ -90,16 +94,13 @@ refine_template = ChatPromptTemplate(chat_refine_msgs)
 
 chat_engine = index.as_chat_engine(
     text_qa_template=text_qa_template,
-    refine_template=refine_template
+    refine_template=refine_template,
+    chat_mode=ChatMode.OPENAI
 )
 
 while True:
     try:
-        user_prompt = input("Prompt: ")
-        streaming_response = chat_engine.stream_chat(user_prompt)
-        for token in streaming_response.response_gen:
-            print(token, end="")
-        print("\n")
+        chat_engine.chat_repl()
     except KeyboardInterrupt:
         break