Update app.py

app.py

@@ -1,4 +1,9 @@
 import gradio as gr
+import json
+import requests
+import openai
+
+
 
 def response_print(model_list, response_list):
     answer = ""
@@ -8,12 +13,34 @@ def response_print(model_list, response_list):
         answer = answer + f"# {model_list[idx]}'s response: {cot if response_list else none}\n"
     return answer
 
-demo = gr.Interface(
-    response_print,
-    [
+TITLE = """<h1 align="center">LLM Agora 🗣️🏦</h1>"""
+
+INTRODUCTION_TEXT = """
+The **LLM Agora 🗣️🏦** aims to improve the quality of open-source LMs' responses through debate & revision introduced in [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://arxiv.org/abs/2305.14325).
+
+Do you know that? 🤔 **LLMs can also improve their responses by debating with other LLMs**! 😮 We applied this concept to several open-source LMs to verify that the open-source model, not the proprietary one, can sufficiently improve the response through discussion. 🤗
+For more details, please refer to the GitHub Repository below.
+
+You can use LLM Agora with your own questions if the response of open-source LM is not satisfactory and you want to improve the quality!
+The Math, GSM8K, and MMLU Tabs show the results of the experiment, and for inference, please use the 'Inference' tab.
+
+Please check the more specific information in [GitHub Repository](https://github.com/gauss5930/LLM-Agora)!
+"""
+
+with gr.Blocks() as demo:
+    gr.HTML(TITLE)
+    gr.Markdown(INTRODUCTION_TEXT)
+
+    with gr.Tab("Inference"):
         gr.CheckboxGroup(["Llama2", "Alpaca", "Vicuna", "Koala", "Falcon", "Baize", "WizardLM", "Orca", "phi-1.5"], label="Model Selection", info="Choose 3 LMs to participate in LLM Agora."),
         gr.Checkbox(label="CoT", info="Do you want to use CoT for inference?")
-    ],
-    "text",
-)
+    
+    with gr.Tab("Math"):
+        text
+    
+    with gr.Tab("GSM8K"):
+
+    with gr.Tab("MMLU"):
+
+
 demo.launch()