Update app.py

app.py

@@ -1,52 +1,81 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+DEFAULT_MODEL = "openai/gpt-oss-20b"
+DEFAULT_SYSTEM_MESSAGE = "You are a friendly Chatbot."
+
 
 def respond(
-    message,
+    message: str,
     history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
     hf_token: gr.OAuthToken,
 ):
     """
-    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
+    Chat completion handler with streaming, safe auth checks,
+    and graceful error handling.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    # --- Auth guard ---------------------------------------------------------
+    if hf_token is None or not hf_token.token:
+        yield "🔒 **Authentication required.** Please log in using the sidebar button."
+        return
+
+    if not message or not message.strip():
+        yield "⚠️ Please enter a message before sending."
+        return
 
-    messages = [{"role": "system", "content": system_message}]
+    # --- Build messages -----------------------------------------------------
+    messages = []
+    if system_message and system_message.strip():
+        messages.append({"role": "system", "content": system_message})
 
-    messages.extend(history)
+    for entry in history or []:
+        # Defensive normalisation: handle both dict and legacy tuple formats.
+        if isinstance(entry, dict) and "role" in entry and "content" in entry:
+            messages.append(entry)
+        elif isinstance(entry, (list, tuple)) and len(entry) >= 2:
+            user_msg, assistant_msg = str(entry[0]), str(entry[1])
+            messages.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                messages.append({"role": "assistant", "content": assistant_msg})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # --- Stream inference ---------------------------------------------------
+    try:
+        client = InferenceClient(token=hf_token.token, model=DEFAULT_MODEL)
+        stream = client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        )
 
-    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 = ""
+        for chunk in stream:
+            choices = chunk.choices
+            if choices and choices[0].delta and choices[0].delta.content:
+                response += choices[0].delta.content
+                yield response
 
-        response += token
-        yield response
+    except Exception as e:
+        yield f"❌ **Inference error:** `{type(e).__name__}: {e}`"
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# --- UI -------------------------------------------------------------------
 chatbot = gr.ChatInterface(
     respond,
+    type="messages",  # Enforce the new {role, content} format
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(
+            value=DEFAULT_SYSTEM_MESSAGE,
+            label="System message",
+            placeholder="You are a helpful assistant...",
+        ),
         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(
@@ -61,9 +90,11 @@ chatbot = gr.ChatInterface(
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
+        gr.Markdown("## 🔐 Authentication")
         gr.LoginButton()
-    chatbot.render()
+        gr.LogoutButton()
 
+    chatbot.render()
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue(default_concurrency_limit=20).launch()