Update app.py

app.py

@@ -74,10 +74,12 @@ def query_model(model_name: str, messages: List[Dict[str, str]]) -> str:
 def respond(message: str, history: List[List[str]]) -> str:
     """Handle sequential model responses with individual updates"""
     messages = [{"role": "user", "content": message}]
+    current_output = ""
     
     # Get first model's response
     response1 = query_model("Qwen2.5-Coder-32B-Instruct", messages)
-    yield f"**Qwen2.5-Coder-32B-Instruct**:\n{response1}"
+    current_output = f"**Qwen2.5-Coder-32B-Instruct**:\n{response1}"
+    yield current_output
     
     # Add first response to context
     messages.append({
@@ -87,7 +89,8 @@ def respond(message: str, history: List[List[str]]) -> str:
     
     # Get second model's response
     response2 = query_model("Qwen2.5-72B-Instruct", messages)
-    yield f"**Qwen2.5-72B-Instruct**:\n{response2}"
+    current_output = f"{current_output}\n\n**Qwen2.5-72B-Instruct**:\n{response2}"
+    yield current_output
     
     # Add second response to context
     messages.append({
@@ -97,7 +100,8 @@ def respond(message: str, history: List[List[str]]) -> str:
     
     # Get final model's response
     response3 = query_model("Llama3.3-70B-Instruct", messages)
-    yield f"**Llama3.3-70B-Instruct**:\n{response3}"
+    current_output = f"{current_output}\n\n**Llama3.3-70B-Instruct**:\n{response3}"
+    yield current_output
 
 # Create the Gradio interface
 chat_interface = gr.ChatInterface(