Update app.py

app.py

@@ -1,67 +1,45 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import time
 
+# Public model (fast + free)
+client = InferenceClient(model="google/gemma-2b-it")
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+SYSTEM_PROMPT = "You are a friendly AI assistant."
+
+def respond(message, history):
     """
-    Public inference (no login required)
+    Respond function for Gradio ChatInterface.
+    History is a list of (user, assistant) tuples.
     """
-    client = InferenceClient(model="google/gemma-2b-it")
-
-    messages = [{"role": "system", "content": system_message}]
-    messages.extend(history)
-    messages.append({"role": "user", "content": message})
-
-    response = ""
+    prompt = SYSTEM_PROMPT + "\n"
+    for u, a in history:
+        prompt += f"User: {u}\nAssistant: {a}\n"
+    prompt += f"User: {message}\nAssistant:"
 
     try:
-        # Use text_generation since chat_completion is not supported
-        prompt = system_message + "\n"
-        for msg in history:
-            prompt += f"{msg['role'].capitalize()}: {msg['content']}\n"
-        prompt += f"User: {message}\nAssistant:"
-
-        gen = client.text_generation(
+        # Generate response
+        response = client.text_generation(
             prompt=prompt,
-            max_new_tokens=max_tokens,
-            temperature=temperature,
-            top_p=top_p,
+            max_new_tokens=150,
+            temperature=0.7,
+            top_p=0.9,
         )
-        response += gen
         yield response
     except:
-        yield "Server busy. Please try again."
-
+        # If server busy
+        yield "AI is waking up… Please wait a few seconds"
 
+# Gradio ChatInterface
 chatbot = gr.ChatInterface(
     respond,
-    type="messages",
-    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)",
-        ),
-    ],
+    title="AI Assistant",
+    description="Public AI chatbot (free)",
 )
 
 with gr.Blocks() as demo:
-    # Removed login button to make it public
     chatbot.render()
 
-
 if __name__ == "__main__":
-    demo.queue()  # optional, helps with multiple users
+    demo.queue()  # handles multiple users
     demo.launch()