Update app.py

app.py

@@ -164,11 +164,70 @@ For more information on `huggingface_hub` Inference API support, please check th
 # if __name__ == "__main__":
 #     demo.launch()
 
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+
+# # 1. Instantiate with named model param
+# client = InferenceClient(model="Qwen/Qwen2.5-Coder-32B-Instruct")
+
+# def respond(message, history: list[tuple[str, str]]):
+#     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."
+#     )
+#     max_tokens = 2048
+#     temperature = 0.7
+#     top_p = 0.95
+
+#     # Build messages in OpenAI-compatible format
+#     messages = [{"role": "system", "content": system_message}]
+#     for user_msg, assistant_msg in history:
+#         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})
+
+#     response = ""
+#     # 2. Use named parameters and alias if desired
+#     for chunk in client.chat.completions.create(
+#         model="Qwen/Qwen2.5-Coder-32B-Instruct",
+#         messages=messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         # 3. Extract token content
+#         token = chunk.choices[0].delta.content or ""
+#         response += token
+#         yield response
+
+# # 4. Wire up Gradio chat interface
+# demo = gr.ChatInterface(respond, type="messages")
+
+# if __name__ == "__main__":
+#     demo.launch()
 import gradio as gr
 from huggingface_hub import InferenceClient
+from dotenv import load_dotenv
+import os
 
-# 1. Instantiate with named model param
-client = InferenceClient(model="Qwen/Qwen2.5-Coder-32B-Instruct")
+# Load environment variables from .env file
+load_dotenv()
+hf_token = os.getenv("HF_TOKEN")
+
+# Ensure token is available
+if hf_token is None:
+    raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set in .env file or environment.")
+
+# Instantiate Hugging Face Inference Client with token
+client = InferenceClient(
+    model="Qwen/Qwen2.5-Coder-32B-Instruct",
+    token=hf_token
+)
 
 def respond(message, history: list[tuple[str, str]]):
     system_message = (
@@ -181,7 +240,7 @@ def respond(message, history: list[tuple[str, str]]):
     temperature = 0.7
     top_p = 0.95
 
-    # Build messages in OpenAI-compatible format
+    # Build conversation history
     messages = [{"role": "system", "content": system_message}]
     for user_msg, assistant_msg in history:
         if user_msg:
@@ -191,7 +250,7 @@ def respond(message, history: list[tuple[str, str]]):
     messages.append({"role": "user", "content": message})
 
     response = ""
-    # 2. Use named parameters and alias if desired
+    # Stream the response from the model
     for chunk in client.chat.completions.create(
         model="Qwen/Qwen2.5-Coder-32B-Instruct",
         messages=messages,
@@ -200,12 +259,11 @@ def respond(message, history: list[tuple[str, str]]):
         temperature=temperature,
         top_p=top_p,
     ):
-        # 3. Extract token content
         token = chunk.choices[0].delta.content or ""
         response += token
         yield response
 
-# 4. Wire up Gradio chat interface
+# Gradio UI
 demo = gr.ChatInterface(respond, type="messages")
 
 if __name__ == "__main__":
@@ -215,3 +273,4 @@ if __name__ == "__main__":
 
 
 
+