Update app.py

app.py

@@ -21,6 +21,8 @@ def respond(
     temperature,
     top_p,
 ):
+    messages = []
+    
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -32,12 +34,7 @@ def respond(
     response = ""
 
     stream = client.chat.completions.create(
-        messages=[
-            {
-                "role": "user",
-                "content": "Why is fast inference important?",
-            }
-        ],
+        messages=messages,
         model=model_id,
         max_tokens=max_tokens,
         temperature=temperature,
@@ -52,6 +49,7 @@ def respond(
 
 chatbot = gr.ChatInterface(
     respond,
+    chatbot=gr.Chatbot(height=500),
     additional_inputs=[
         gr.Dropdown(
             ["llama3.1-8b", "llama3.1-70b"],