app.py

import os

from openai import OpenAI
import gradio as gr

api_key = os.environ.get('OPENAI_API_KEY')
client = OpenAI(api_key=api_key)

MODELS = [
    'gpt-4o',
    'gpt-4o-mini',
    'gpt-4',
    'gpt-4-turbo',
    'gpt-3.5-turbo',
]


def generate(message, history, model, temperature=1.0):
    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=model,
                                              messages=history_openai_format,
                                              temperature=temperature,
                                              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


chat_interface = gr.ChatInterface(
    title='Private ChatGPT',
    description='Chat with OpenAI models using their official API. OpenAI <a href="https://platform.openai.com/docs/concepts">promises</a> not to train on input or output of API calls.',
    fn=generate,
    additional_inputs=[
        gr.Dropdown(label='model',
                    choices=MODELS,
                    value=MODELS[0],
                    allow_custom_value=True),
        gr.Slider(label="Temperature",
                  minimum=0.,
                  maximum=1.2,
                  step=0.05,
                  value=1.0),
    ],
    analytics_enabled=False,
    show_progress='full',
)
chat_interface.launch(share=True)