Update app.py

app.py

@@ -27,55 +27,48 @@ def auto_update():
 threading.Thread(target=auto_update, daemon=True).start()
 
 # Chatbot response function using the InferenceClient
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     # Prepare the message history for the model
     messages = [{"role": "system", "content": system_message}]
+    
     for val in history:
-        if val[0]:
+        if val[0]:  # User's message
             messages.append({"role": "user", "content": val[0]})
-        if val[1]:
+        if val[1]:  # Assistant's response
             messages.append({"role": "assistant", "content": val[1]})
-
+    
+    # Add the new user message
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
+    # Generate the response using the model
+    for msg in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
+        token = msg.choices[0].delta.content
         response += token
-        yield response
+        yield response  # Streaming response
 
 # Gradio 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"),
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="User Message"),
+        gr.State(),  # Gradio State to store the conversation history
+        gr.Textbox(value="You are a helpful chatbot.", label="System Message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
+    outputs=gr.Chatbot(),  # Gradio chatbot output
+    live=True  # Enable live responses
 )
 
 # Launch the interface
 if __name__ == "__main__":
     demo.launch()
-