Update app.py

app.py

@@ -169,10 +169,10 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 if not HF_TOKEN:
     raise ValueError("HF_TOKEN is missing.")
 
-# Initialize client with provider specified
+# Initialize client with nscale router
 client = InferenceClient(
+    base_url="https://router.huggingface.co/nscale/v1",
     api_key=HF_TOKEN,
-    provider="nscale",  # <-- explicitly set the provider here
 )
 
 # System prompt
@@ -185,29 +185,47 @@ system_message = (
 
 def chat_function(message, history):
 
-    messages = [{"role": "system", "content": system_message}]
+    messages = [
+        {
+            "role": "system",
+            "content": system_message
+        }
+    ]
 
     history = history or []
 
     for item in history:
+
         if isinstance(item, dict):
             role = item.get("role")
             content = item.get("content", "")
             if role in ["user", "assistant"]:
-                messages.append({"role": role, "content": content})
+                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
+                })
 
-    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",  # <-- remove ":nscale" suffix
+            model="Qwen/Qwen2.5-Coder-7B-Instruct",
             messages=messages,
             max_tokens=2048,
             temperature=0.7,