Update app.py

app.py

@@ -113,53 +113,100 @@ 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
+
+# """
+# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# """
+# client = InferenceClient("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. "
+#         "Break down the tasks clearly if needed, and be friendly and supportive in your responses."
+#     )
+#     max_tokens = 2048
+#     temperature = 0.7
+#     top_p = 0.95
+
+#     messages = [{"role": "system", "content": system_message}]
+
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+
+#     for message in client.chat_completion(
+#         messages,
+#         max_tokens=max_tokens,
+#         stream=True,
+#         temperature=temperature,
+#         top_p=top_p,
+#     ):
+#         token = message.choices[0].delta.content
+
+#         response += token
+#         yield response
+
+# """
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# """
+# demo = gr.ChatInterface(respond)
+
+# if __name__ == "__main__":
+#     demo.launch()
+
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
+# 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. "
-        "Break down the tasks clearly if needed, and be friendly and supportive in your responses."
+        "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 val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
+    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 = ""
-
-    for message in client.chat_completion(
-        messages,
+    # 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,
     ):
-        token = message.choices[0].delta.content
-
+        # 3. Extract token content
+        token = chunk.choices[0].delta.content or ""
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(respond)
+# 4. Wire up Gradio chat interface
+demo = gr.ChatInterface(respond, type="messages")
 
 if __name__ == "__main__":
     demo.launch()
@@ -167,3 +214,4 @@ if __name__ == "__main__":
 
 
 
+