Note and solve: Rate Limit openai gpt-3.5-turbo

[threeColorFr]

"error-stage1:Rate limit reached for default-gpt-3.5-turbo in organization org-NATszHOraQIVn1LhMbHGpI3Q on requests per min. Limit: 3 / min. Please try again in 20s. Contact support@openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method."

openai官方对请求速率限制一分钟3个，在此提醒一下。
因为是多轮框架，所以一个实例中间可能会断，影响结果。
Solve：TODO

[threeColorFr]

如果有多个账号的话，可以对api进行封装，实现超limit换key

# 封装openai Create,实现换key功能
with open("tokens.txt", "r") as f:
    keys = f.readlines()
    keys = [key.strip() for key in keys]

all_keys = itertools.cycle(keys)

def create(**args):
    global all_keys
    openai.api_key = next(all_keys)
    try:
        result = openai.ChatCompletion.create(**args)
    except openai.error.RateLimitError:
        result = create(**args)
    return result

[threeColorFr]

see code access.py for details