####################################################
#Mit Streaming
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 = openai.ChatCompletion.create(
        model='gpt-3.5-turbo',
        messages= history_openai_format,
        temperature=1.0,
        stream=True
    )

    partial_message = ""
    for chunk in response:
        if len(chunk['choices'][0]['delta']) != 0:
            partial_message = partial_message + chunk['choices'][0]['delta']['content']
            yield partial_message

gr.ChatInterface(predict).queue().launch()

##########################################################
#OpenAI Chatinterface
from langchain.chat_models import ChatOpenAI
from langchain.schema import AIMessage, HumanMessage
import openai
import gradio as gr

os.environ["OPENAI_API_KEY"] = "sk-..."  # Replace with your key

llm = ChatOpenAI(temperature=1.0, model='gpt-3.5-turbo-0613')

def predict(message, history):
    history_langchain_format = []
    for human, ai in history:
        history_langchain_format.append(HumanMessage(content=human))
        history_langchain_format.append(AIMessage(content=ai))
    history_langchain_format.append(HumanMessage(content=message))
    gpt_response = llm(history_langchain_format)
    return gpt_response.content

gr.ChatInterface(predict).launch()