Update app.py

app.py

@@ -1,10 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
 
 from optillm.moa import mixture_of_agents 
 from optillm.mcts import chat_with_mcts
 from optillm.bon import best_of_n_sampling
 
+API_KEY = os.environ.get("HF_TOKEN")
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,7 +17,7 @@ def respond(
     temperature,
     top_p,
 ):
-    client = InferenceClient(model)
+    client = OpenAI(api_key=API_KEY, base_url="https://api-inference.huggingface.co/models/"+model+"/v1")
     
     messages = [{"role": "system", "content": system_message}]