added introductory prompt

backend.py

@@ -12,7 +12,8 @@ from huggingface_hub import login
 from llama_index.core.memory import ChatMemoryBuffer
 from typing import Iterator, List, Any
 from llama_index.core.chat_engine import CondensePlusContextChatEngine
-from llama_index.core.llms import ChatMessage, MessageRole
+from llama_index.core.llms import ChatMessage, MessageRole , CompletionResponse
+
 
 
 
@@ -143,7 +144,9 @@ def handle_query(query_str: str,
                 
                 outputs.append(token)
                 print(f"Generated token: {token}")
-                yield "".join(outputs)
+                
+                streamed_response = "".join(outputs)
+                yield CompletionResponse(text=streamed_response, delta=token)
 
         """if sources:
             sources_str = ", ".join(sources)