app.py

import os
import gradio as gr

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]],
    model,
    approach,
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    client = OpenAI(api_key=API_KEY, base_url="https://api-inference.huggingface.co/models/"+model+"/v1")
    
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    # response = ""

    final_response = mixture_of_agents(system_message, message, client, model)
    return final_response

    # for message in client.chat_completion(
    #     messages,
    #     max_tokens=max_tokens,
    #     stream=True,
    #     temperature=temperature,
    #     top_p=top_p,
    # ):
    #     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=[
        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"
        ),
        gr.Dropdown(
            ["bon", "mcts", "moa"], 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"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()