Update app.py

app.py

@@ -8,7 +8,7 @@ from optillm.mcts import chat_with_mcts
 from optillm.bon import best_of_n_sampling
 from optillm.cot_reflection import cot_reflection
 
-API_KEY = os.environ.get("HF_TOKEN")
+API_KEY = os.environ.get("OPENROUTER_API_KEY")
 
 def respond(
     message,
@@ -20,7 +20,7 @@ def respond(
     temperature,
     top_p,
 ):
-    client = OpenAI(api_key=API_KEY, base_url="https://api-inference.huggingface.co/models/"+model+"/v1")
+    client = OpenAI(api_key=API_KEY, base_url="https://openrouter.ai/api/v1")
     
     messages = [{"role": "system", "content": system_message}]
 
@@ -34,7 +34,7 @@ def respond(
 
     # response = ""
 
-    final_response = cot_reflection(system_message, message, client, model)
+    final_response = mixture_of_agents(system_message, message, client, model)
     return final_response
 
     # for message in client.chat_completion(
@@ -56,11 +56,12 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Dropdown(
-            ["meta-llama/Meta-Llama-3.1-70B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct", "HuggingFaceH4/zephyr-7b-beta"], 
-            value="meta-llama/Meta-Llama-3.1-70B-Instruct", label="Model", info="Choose the base model"
+            ["nousresearch/hermes-3-llama-3.1-405b:free", "meta-llama/llama-3.1-8b-instruct:free", "qwen/qwen-2-7b-instruct:free",
+            "google/gemma-2-9b-it:free", "mistralai/mistral-7b-instruct:free", ], 
+            value="nousresearch/hermes-3-llama-3.1-405b:free", label="Model", info="Choose the base model"
         ),
         gr.Dropdown(
-            ["bon", "mcts", "moa"], value="moa", label="Approach", info="Choose the approach"
+            ["bon", "mcts", "moa", "cot_reflection"], value="moa", label="Approach", info="Choose the approach"
         ),
         gr.Textbox(value="", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),