Update app.py

app.py

@@ -1,10 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+from dotenv import load_dotenv
 
-"""
-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")
+# Load environment variables from a .env file if available
+load_dotenv()
+
+# Read your Hugging Face token from an environment variable
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+# Initialize client with token
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
 
 
 def respond(
@@ -35,13 +41,10 @@ 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
-"""
+
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +61,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()