app.py

import os
from openai import OpenAI
import gradio as gr

api_key = os.environ.get("OPENAI_API_KEY")
base_url = os.environ.get("OPENAI_API_BASE")
client = OpenAI(api_key=api_key, base_url=base_url)

def predict(message, history):
    history_openai_format = []
    for human, assistant in history:
        history_openai_format.append({"role": "user", "content": human })
        history_openai_format.append({"role": "assistant", "content":assistant})
    history_openai_format.append({"role": "user", "content": message})
  
    response = client.chat.completions.create(model='Llama-3-8B-UltraMedical',
    messages= history_openai_format,
    temperature=1.0,
    stop=["<|eot_id|>"],
    stream=True)

    partial_message = ""
    for chunk in response:
        if chunk.choices[0].delta.content is not None:
              partial_message = partial_message + chunk.choices[0].delta.content
              yield partial_message

gr.ChatInterface(predict).launch()