from openai import OpenAI
import gradio as gr
import os
import dotenv

dotenv.load_dotenv()

OPENAI_API_KEY = os.environ['OPENAI_API_KEY']

print(OPENAI_API_KEY)

client = OpenAI(api_key=OPENAI_API_KEY)

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='gpt-3.5-turbo',
        # model="gpt-4-turbo",
        model="gpt-4o",
        messages= history_openai_format,
        temperature=1.0,
        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()