Update app.py

app.py

@@ -63,105 +63,61 @@ import gradio as gr
 from dotenv import load_dotenv
 from huggingface_hub import InferenceClient
 
-# Load environment variables
 load_dotenv()
 
 HF_TOKEN = os.getenv("HF_TOKEN")
-
 if not HF_TOKEN:
     raise ValueError("HF_TOKEN is missing.")
 
-# Initialize client
-client = InferenceClient(
-    api_key=HF_TOKEN,
-)
-
-# System prompt
 system_message = (
     "You are a helpful and experienced coding assistant specialized in web development. "
     "Help the user by generating complete and functional code for building websites. "
-    "You can provide HTML, CSS, JavaScript, and backend code like Flask, Node.js, etc. "
+    "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) "
     "based on their requirements."
 )
 
-# Chat function
-def chat_function(message, history):
+client = InferenceClient(
+    provider="nscale",
+    api_key=HF_TOKEN,
+)
 
-    messages = [
-        {
-            "role": "system",
-            "content": system_message
-        }
-    ]
+def chat_function(message, history):
+    messages = [{"role": "system", "content": system_message}]
 
     history = history or []
-
-    # Handle Gradio history properly
     for item in history:
-
-        # Messages format
         if isinstance(item, dict):
-
             role = item.get("role")
             content = item.get("content", "")
-
-            if role in ["user", "assistant"]:
-                messages.append({
-                    "role": role,
-                    "content": content
-                })
-
-        # Tuple fallback
+            if role in ("user", "assistant"):
+                messages.append({"role": role, "content": content})
         elif isinstance(item, (list, tuple)) and len(item) == 2:
-
             user_msg, assistant_msg = item
-
             if user_msg:
-                messages.append({
-                    "role": "user",
-                    "content": user_msg
-                })
-
+                messages.append({"role": "user", "content": user_msg})
             if assistant_msg:
-                messages.append({
-                    "role": "assistant",
-                    "content": assistant_msg
-                })
+                messages.append({"role": "assistant", "content": assistant_msg})
 
-    # Add latest user message
-    messages.append({
-        "role": "user",
-        "content": message
-    })
+    messages.append({"role": "user", "content": message})
 
     try:
-
         completion = client.chat.completions.create(
-            model="Qwen/Qwen2.5-Coder-7B-Instruct:nscale",
+            model="Qwen/Qwen2.5-Coder-7B-Instruct",
             messages=messages,
             max_tokens=2048,
             temperature=0.7,
             top_p=0.95,
         )
-
         return completion.choices[0].message.content
-
     except Exception as e:
         return f"Error: {str(e)}"
 
-# UI
 demo = gr.ChatInterface(
     fn=chat_function,
     type="messages",
     title="AI Coding Assistant",
     description="A coding assistant powered by Qwen2.5-Coder.",
-    examples=[
-        "Create a responsive landing page.",
-        "Build a Flask authentication API.",
-        "Make a Node.js CRUD app."
-    ]
 )
 
-# Launch
 if __name__ == "__main__":
     demo.launch()