Update app.py

app.py

@@ -3,32 +3,26 @@ from huggingface_hub import InferenceClient
 from dotenv import load_dotenv
 import os
 
-# Load environment variables from .env file
 load_dotenv()
 
-# Get the system message from environment variables
 system_message = os.getenv("SYSTEM_MESSAGE")
 
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
 def respond(message, history, max_tokens, temperature, top_p):
-    # Prepare the initial message list with the system message
+    
     messages = [{"role": "system", "content": system_message}]
 
-    # Add the conversation history to the messages list
     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})
 
-    # Add the latest user message to the messages list
     messages.append({"role": "user", "content": message})
 
-    # Initialize an empty response string
     response = ""
 
-    # Generate the response using the Hugging Face InferenceClient
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -40,7 +34,6 @@ def respond(message, history, max_tokens, temperature, top_p):
         response += token
         yield response
 
-# Define the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -50,6 +43,5 @@ demo = gr.ChatInterface(
     ]
 )
 
-# Launch the Gradio app
 if __name__ == "__main__":
     demo.launch()