Update app.py

app.py

@@ -58,6 +58,104 @@
 #     demo.launch()
 
 
+# import os
+# 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. "
+#     "based on their requirements."
+# )
+
+# def chat_function(message, history):
+
+#     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
+#                 })
+
+#         elif isinstance(item, (list, tuple)) and len(item) == 2:
+
+#             user_msg, assistant_msg = item
+
+#             if user_msg:
+#                 messages.append({
+#                     "role": "user",
+#                     "content": user_msg
+#                 })
+
+#             if assistant_msg:
+#                 messages.append({
+#                     "role": "assistant",
+#                     "content": assistant_msg
+#                 })
+
+#     messages.append({
+#         "role": "user",
+#         "content": message
+#     })
+
+#     try:
+
+#         completion = client.chat.completions.create(
+#             model="Qwen/Qwen2.5-Coder-7B-Instruct:nscale",
+#             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)}"
+
+# # Interface
+# demo = gr.ChatInterface(
+#     fn=chat_function,
+#     type="messages",
+#     title="AI Coding Assistant",
+#     description="A coding assistant powered by Qwen2.5-Coder."
+# )
+
+# # Launch
+# if __name__ == "__main__":
+#     demo.launch()
+
 import os
 import gradio as gr
 from dotenv import load_dotenv
@@ -71,9 +169,10 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 if not HF_TOKEN:
     raise ValueError("HF_TOKEN is missing.")
 
-# Initialize client
+# Initialize client with provider specified
 client = InferenceClient(
-    api_key=HF_TOKEN
+    api_key=HF_TOKEN,
+    provider="nscale",  # <-- explicitly set the provider here
 )
 
 # System prompt
@@ -86,59 +185,34 @@ 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:nscale",
+            model="Qwen/Qwen2.5-Coder-7B-Instruct",  # <-- remove ":nscale" suffix
             messages=messages,
             max_tokens=2048,
             temperature=0.7,
             top_p=0.95,
         )
-
         return completion.choices[0].message.content
 
     except Exception as e:
@@ -152,6 +226,5 @@ demo = gr.ChatInterface(
     description="A coding assistant powered by Qwen2.5-Coder."
 )
 
-# Launch
 if __name__ == "__main__":
     demo.launch()