Update app.py

app.py

@@ -1,10 +1,16 @@
 import gradio as gr
+import os
 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("HuggingFaceH4/zephyr-7b-beta")
+HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
+
+
+def respond(message):
+    for response in client.chat_completion(messages=[{"role": "user", "content": message}]):
+        yield response["choices"][0]["message"]["content"]
+
 
 
 def respond(