up a

app.py

@@ -1,10 +1,14 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+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(model="meta-llama/Meta-Llama-3.1-405B-Instruct-FP8")
+
+TOKEN = os.getenv("HF_TOKEN")
+
+client = OpenAI(
+    base_url="https://api-inference.huggingface.co/v1/",
+    api_key=TOKEN,
+)
 
 def respond(
     message,
@@ -25,22 +29,20 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    
+    for message in  client.chat.completions.create(
+        model="meta-llama/Meta-Llama-3.1-405B-Instruct-FP8",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        messages=messages,
     ):
         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=[
@@ -57,5 +59,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()