Update app.py

app.py

@@ -1,9 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
 
 
@@ -15,6 +13,7 @@ def respond(
     temperature,
     top_p,
 ):
+    # Prepare messages for the API
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -25,8 +24,10 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
+    # Initialize response variable
     response = ""
 
+    # Call the InferenceClient with chat_completion
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,14 +36,11 @@ def respond(
         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
-"""
+# Create the Gradio ChatInterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +57,8 @@ demo = gr.ChatInterface(
     ],
 )
 
-
+# Launch the Gradio app and print the URL
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch(share=True)  # Set to True to share on Hugging Face Spaces
+    # Print the URL for the Hugging Face Space
+    print(f"Your Hugging Face Space is live at: {os.environ['SPACE_URL']}")