Update main.py

main.py

@@ -594,18 +594,20 @@ async def followup_agent(query: FollowupQueryModel, background_tasks: Background
     limited_conversation = conversations[query.conversation_id]
 
     
-    def process_response():
+    async def process_response():
         yield "<followup-response>\n\n"
         full_response = ""
         for content in chat_with_llama_stream(limited_conversation, model=query.model_id):
             full_response += content
             yield content
-            
         yield "</followup-response>\n\n"
         
         logger.info(f"LLM RAW response for query: {query.query}: {full_response}")
-        response_content, interact,tools = parse_followup_and_tools(full_response)
         
+        # Add a slight delay after sending the full LLM response
+        await asyncio.sleep(0.001)
+        
+        response_content, interact, tools = parse_followup_and_tools(full_response)
         result = {
             "clarification": interact
         }
@@ -616,7 +618,6 @@ async def followup_agent(query: FollowupQueryModel, background_tasks: Background
         
         # Add the assistant's response to the conversation history
         conversations[query.conversation_id].append({"role": "assistant", "content": full_response})
-        
         background_tasks.add_task(update_db, query.user_id, query.conversation_id, query.query, full_response)
         logger.info(f"Completed followup agent response for query: {query.query}, send result: {result}")