Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+
+def respond(
+    message,
+    history: list[dict[str, str]],
+    hf_token: gr.OAuthToken,
+):
+    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
+
+
+chatbot = gr.ChatInterface(
+    respond,
+    type="messages",
+    chatbot=gr.Chatbot(collapse_thinking=[("<thinking>", "</thinking>")])
+)
+
+with gr.Blocks() as demo:
+    with gr.Sidebar():
+        gr.LoginButton()
+    chatbot.render()
+
+
+if __name__ == "__main__":
+    demo.launch()