Update app.py

app.py

@@ -37,11 +37,11 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 # Define Gradio respond function for chatbot
 def respond(
     message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    history,
+    system_message="You are a helpful assistant.",
+    max_tokens=512,
+    temperature=0.7,
+    top_p=0.95,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -63,25 +63,20 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
 # Create Gradio chat interface
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="User Input", placeholder="Type your message here..."),
+        gr.State(),
+    ],
+    outputs=[
+        gr.Chatbot(),
     ],
+    live=True
 )
 
 # Flask routes