Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import os
-import spaces
+import spaces  # <--- 1. Import Hugging Face ZeroGPU utilities
 from groq import Groq
 
 # Initialize the Groq client via Hugging Face Secrets
@@ -18,16 +18,9 @@ custom_css = """
 .sidebar-panel { background: #111827 !important; border: 1px solid #1f2937 !important; border-radius: 12px !important; }
 .chat-window { border: 1px solid #1f2937 !important; border-radius: 12px !important; background: #111827 !important; }
 """
-@spaces.GPU
-def chat_stream(message, history, model, system_prompt, temperature, max_tokens):
-    """
-    Handles streaming responses using the standard history list layout.
-    """
-    if not message.strip():
-        yield history
-        return
-        
 
+# 2. Add the ZeroGPU decorator here to make Hugging Face happy
+@spaces.GPU
 def chat_stream(message, history, model, system_prompt, temperature, max_tokens):
     """
     Handles streaming responses using the standard history list layout.
@@ -36,46 +29,37 @@ def chat_stream(message, history, model, system_prompt, temperature, max_tokens)
         yield history
         return
 
-    # 1. Initialize message list with system prompt
+    # Initialize message list with system prompt
     messages = [{"role": "system", "content": system_prompt}]
 
-    # 2. Add conversation history
+    # Add conversation history
     for turn in history:
-        # turn is typically [user_message, assistant_message]
         if turn[0]:
             messages.append({"role": "user", "content": turn[0]})
         if turn[1]:
             messages.append({"role": "assistant", "content": turn[1]})
 
-    # 3. Add the current user message
+    # Add the current user message
     messages.append({"role": "user", "content": message})
     
-    # 4. Append user message to history visually before generating
-    history.append(
-    {
-        "role": "assistant",
-        "content": response
-    }
-)
-
-return history
-
-
-# 5. Stream from Groq
-try:
-    stream = client.chat.completions.create(
-         model=model,
-         messages=messages,
-         temperature=temperature,
-         max_tokens=max_tokens,
-         stream=True,
+    # Append user message to history visually before generating
+    history.append([message, ""])
+    yield history
+
+    # Stream from Groq
+    try:
+        stream = client.chat.completions.create(
+            model=model,
+            messages=messages,
+            temperature=temperature,
+            max_tokens=max_tokens,
+            stream=True,
         )
 
         partial_response = ""
         for chunk in stream:
             if chunk.choices[0].delta.content:
                 partial_response += chunk.choices[0].delta.content
-                # Update the last assistant turn in history
                 history[-1][1] = partial_response
                 yield history
 
@@ -83,9 +67,8 @@ try:
         history[-1][1] = f"⚠️ Error connecting to Groq: {str(e)}"
         yield history
 
-# Build the layout manually without gr.ChatInterface macros
+# Build the layout manually
 with gr.Blocks() as demo:
-
     gr.Markdown("# 🚀 Personal AI ChatBot", elem_id="title-header")
     gr.Markdown("A fully customizable, hyper-fast LLM workspace.")
 
@@ -121,7 +104,7 @@ with gr.Blocks() as demo:
             )
 
             gr.Markdown("---")
-            gr.Markdown("**Status:** 🟢 Connected to Groq API")
+            gr.Markdown("**Status:** 🟢 Connected via ZeroGPU to Groq")
 
         # --- RIGHT COLUMN: CHAT INTERFACE ---
         with gr.Column(scale=3):
@@ -146,7 +129,6 @@ with gr.Blocks() as demo:
                 outputs=[msg_input]
             )
             
-            # Clear chat utility logic
             clear_btn.click(fn=lambda: [], inputs=None, outputs=[chatbot])
 
 if __name__ == "__main__":