generate_response.py

def generate_response(history, model ):
        global messages, cost

        response = openai.ChatCompletion.create(
            model = model,
            messages=messages,
            temperature=0.2,
        )

        response_msg = response.choices[0].message.content
        cost = cost + (response.usage['total_tokens'])*(0.002/1000)
        messages = messages + [{"role":'assistant', 'content': response_msg}]

        for char in response_msg:

            history[-1][1] += char
            #time.sleep(0.05)
            yield history