added streaming

app.py

@@ -6,6 +6,8 @@ from llama_index.llms import OpenAI
 from llama_index.text_splitter import TokenTextSplitter
 
 from theme import CustomTheme
+import time
+import asyncio
 
 # create storage context
 storage_context = StorageContext.from_defaults(persist_dir="modulhandbuch")
@@ -67,12 +69,23 @@ submit_button = gr.Button(
 def response(message, history):
     if message == "":
         answer = default_text
-    else:
-        answer = str(query_engine.chat(message, chat_history=query_engine.chat_history))
-    print("message", message)
-    print("answer", answer)
-    print("history", history)
-    return answer
+        return answer
+
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    
+    answer = query_engine.stream_chat(message, chat_history=query_engine.chat_history)
+
+    text = ""
+    for token in answer.response_gen:
+        time.sleep(0.1)
+        text += token
+
+        yield text
+    #print("message", message)
+    #print("answer", answer)
+    #print("history", history)
+    #return answer
 
 
 def main():