Update app.py

app.py

@@ -72,27 +72,30 @@ def query_model(model_name: str, messages: List[Dict[str, str]]) -> str:
         return f"{model_name} error: {str(e)}"
 
 def respond(message: str, history: List[List[str]]) -> str:
-    """Handle continuous contextual conversations"""
-    # Build full message history from previous interactions
-    messages = []
-    for user_msg, bot_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": bot_msg})
+    """Handle sequential model responses with individual updates"""
+    messages = [{"role": "user", "content": message}]
     
-    # Add new user message
-    messages.append({"role": "user", "content": message})
-    
-    # First model sees current prompt + full history
+    # Get first model's response
     response1 = query_model("Qwen2.5-Coder-32B-Instruct", messages)
     yield f"**Qwen2.5-Coder-32B-Instruct**:\n{response1}"
     
-    # Second model sees current prompt + history + first response
-    messages.append({"role": "assistant", "content": response1})
+    # Add first response to context
+    messages.append({
+        "role": "assistant",
+        "content": f"Previous response: {response1}"
+    })
+    
+    # Get second model's response
     response2 = query_model("Qwen2.5-72B-Instruct", messages)
     yield f"**Qwen2.5-72B-Instruct**:\n{response2}"
     
-    # Third model sees current prompt + history + both responses
-    messages.append({"role": "assistant", "content": response2})
+    # Add second response to context
+    messages.append({
+        "role": "assistant",
+        "content": f"Previous responses: {response1}\n{response2}"
+    })
+    
+    # Get final model's response
     response3 = query_model("Llama3.3-70B-Instruct", messages)
     yield f"**Llama3.3-70B-Instruct**:\n{response3}"