Update app.py

app.py

@@ -1,26 +1,33 @@
 import gradio as gr
+import os
 from huggingface_hub import InferenceClient
 
-# Using Qwen 2.5 Coder
 model_id = "Qwen/Qwen2.5-Coder-32B-Instruct"
 
-def respond(message, history, system_message, temperature):
-    # Initialize the client
-    client = InferenceClient(model_id)
+def respond(message, history, system_message, temperature, request: gr.Request):
+    # 1. Try to get the user's token (if they logged in via the button)
+    token = None
+    if request:
+        token = request.token
     
-    # 1. Start with the System Message
-    messages = [{"role": "system", "content": system_message}]
+    # 2. If no user token, fall back to the Space's secret token (HF_TOKEN)
+    if token is None:
+        token = os.getenv("HF_TOKEN")
+
+    if token is None:
+        yield "Error: No authentication token found. Please add 'HF_TOKEN' to Space Secrets."
+        return
+
+    # Initialize client with the found token
+    client = InferenceClient(model_id, token=token)
     
-    # 2. Add the history
+    messages = [{"role": "system", "content": system_message}]
     for user_msg, bot_msg in history:
         messages.append({"role": "user", "content": user_msg})
         messages.append({"role": "assistant", "content": bot_msg})
     
-    # 3. Add the current user message
     messages.append({"role": "user", "content": message})
 
-    # Generate response
-    response_text = ""
     try:
         stream = client.chat_completion(
             messages, 
@@ -29,38 +36,27 @@ def respond(message, history, system_message, temperature):
             temperature=temperature,
             top_p=0.9
         )
+        response_text = ""
         for chunk in stream:
             content = chunk.choices[0].delta.content
             if content:
                 response_text += content
                 yield response_text
     except Exception as e:
-        yield f"Error: {str(e)}. The model might be busy."
+        yield f"Error: {str(e)}"
 
-# Build the UI
 with gr.Blocks(fill_height=True) as demo:
     with gr.Sidebar():
         gr.Markdown("# AI Coding Assistant")
         gr.Markdown(f"Running **{model_id}**")
+        # This button allows users to use their OWN token if they want
         gr.LoginButton("Sign in")
     
     gr.ChatInterface(
         respond,
         additional_inputs=[
-            # System Message Input
-            gr.Textbox(
-                value="You are a helpful assistant.", 
-                label="System Instruction",
-                lines=2
-            ),
-            # Temperature Slider
-            gr.Slider(
-                minimum=0.1, 
-                maximum=2.0, 
-                value=0.7, 
-                step=0.1, 
-                label="Temperature"
-            )
+            gr.Textbox(value="You are a helpful assistant.", label="System Instruction", lines=2),
+            gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature")
         ]
     )