Update app.py

app.py

@@ -1,45 +1,70 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import time
 
-# Public model (fast + free)
-client = InferenceClient(model="google/gemma-2b-it")
 
-SYSTEM_PROMPT = "You are a friendly AI assistant."
-
-def respond(message, history):
+def respond(
+    message,
+    history: list[dict[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+    hf_token: gr.OAuthToken,
+):
     """
-    Respond function for Gradio ChatInterface.
-    History is a list of (user, assistant) tuples.
+    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-    prompt = SYSTEM_PROMPT + "\n"
-    for u, a in history:
-        prompt += f"User: {u}\nAssistant: {a}\n"
-    prompt += f"User: {message}\nAssistant:"
-
-    try:
-        # Generate response
-        response = client.text_generation(
-            prompt=prompt,
-            max_new_tokens=150,
-            temperature=0.7,
-            top_p=0.9,
-        )
+    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+
+    messages = [{"role": "system", "content": system_message}]
+
+    messages.extend(history)
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        choices = message.choices
+        token = ""
+        if len(choices) and choices[0].delta.content:
+            token = choices[0].delta.content
+
+        response += token
         yield response
-    except:
-        # If server busy
-        yield "AI is waking up… Please wait a few seconds"
 
-# Gradio ChatInterface
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 chatbot = gr.ChatInterface(
     respond,
-    title="AI Assistant",
-    description="Public AI chatbot (free)",
+    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)",
+        ),
+    ],
 )
 
 with gr.Blocks() as demo:
+    with gr.Sidebar():
+        gr.LoginButton()
     chatbot.render()
 
+
 if __name__ == "__main__":
-    demo.queue()  # handles multiple users
-    demo.launch()
+    demo.launch()