Update app.py

app.py

@@ -1,6 +1,10 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+# Initialize the client for a HF-hosted model
+# No token needed when running inside a Space owned by a Team org
+client = InferenceClient(model="meta-llama/Llama-3.1-8B-Instruct")
+
 
 def respond(
     message,
@@ -9,41 +13,32 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    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
+    Generate responses using HF-hosted Llama 3.1 model.
+    This version avoids Novita/Groq routing and does not require tokens.
     """
-    # client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")   # bills personal account
-    client = InferenceClient(model="meta-llama/Llama-3.1-8B-Instruct")       # models that HF hosts natively can be used without token
-
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    # Stream responses using the new chat.completions API
+    for message_chunk in client.chat.completions.create(
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
+        delta = message_chunk.choices[0].delta
+        if delta and delta.content:
+            token = delta.content
+            response += token
+            yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Define the Gradio Chat Interface
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -61,11 +56,11 @@ chatbot = gr.ChatInterface(
     ],
 )
 
+# Build the Gradio Blocks interface with optional login button
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()