Update app.py

app.py

@@ -1,3 +1,4 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
@@ -9,45 +10,58 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
+    hf_token: gr.OAuthToken | None,
 ):
     """
-    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 handler for Hugging Face Inference API.
+    Works with both HF Spaces (OAuth) and local execution (HF_TOKEN env var).
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
-    messages = [{"role": "system", "content": system_message}]
+    # ✅ Get token from Spaces OAuth or local env
+    token = None
+    if hf_token and getattr(hf_token, "token", None):
+        token = hf_token.token
+    else:
+        token = os.getenv("HF_TOKEN")
 
-    messages.extend(history)
+    if not token:
+        yield "❌ No Hugging Face token found. Please log in or set HF_TOKEN."
+        return
+
+    # ✅ Choose a model that supports Inference API
+    model_id = "mistralai/Mistral-7B-Instruct-v0.2"  # change if needed
+    client = InferenceClient(token=token, model=model_id)
 
+    # ✅ Build messages list
+    messages = [{"role": "system", "content": system_message}]
+    messages.extend(history)
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
+    # ✅ Streaming response
+    for message_chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = message_chunk.choices
         token = ""
-        if len(choices) and choices[0].delta.content:
+        if len(choices) and choices[0].delta and choices[0].delta.content:
             token = choices[0].delta.content
 
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# ✅ Gradio UI
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful research assistant.", 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(
@@ -63,8 +77,10 @@ chatbot = gr.ChatInterface(
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
+        gr.Markdown("🔑 Log in with your Hugging Face account to run the model.")
     chatbot.render()
 
 
 if __name__ == "__main__":
-    demo.launch()
+    # ✅ share=True → generates public link when running locally
+    demo.launch(share=True)