GPT模型调用时抛出openai.error.RateLimitError

Question

最近想在python里调用gpt模型的api来实现一个聊天机器人。但是在运行代码时会报错：

Traceback (most recent call last):
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\tenacity\__init__.py", line 382, in __call__
    result = fn(*args, **kwargs)
  File "d:\编程资料\编程语言\python\我的程序\ChatGPT.py", line 11, in completion_with_backoff
    return openai.Completion.create(**kwargs)
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\openai\api_resources\completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\openai\api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\openai\api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "C:\Users\王铭瑄\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\openai\api_requestor.py", line 763, in _interpret_response_line
    raise self.handle_error_response(
openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

这个错误是因为调用gpt-3.5-torbo频率超过限制造成的，但是程序调用频率没超过openai的官方文档里说的。代码：

import openai
import os
from tenacity import (
    retry,
    stop_after_attempt,
    wait_random_exponential,
)
 
@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
def completion_with_backoff(**kwargs):
    return openai.Completion.create(**kwargs)



ENCRYPTED_OPENAI_API_KEY = "..."
openai.api_key = ENCRYPTED_OPENAI_API_KEY



while True:
    q = input("问题：")
    # res=openai.ChatCompletion.create(
    #     model="gpt-3.5-turbo",
    #     messages=[
    #         {"role":"user","content":q}
    #     ]
    # )
    res = completion_with_backoff(model="gpt-3.5-turbo",
                                   messages=[
                                       {"role": "user", "content": q}
                                   ]
                                   )
    print(res["choices"][0]["message"]["content"])

(运行此代码时开了代理)
请问大家为什么会抛出openai.error.RateLimitError以及如何解决？

Answer 1

这个报错是说，你的api额度用完了，现在没有钱了，需要充值。。。你还用的是3.5的apikey吗，那个免费的额度是有有效期的，你看看
是不是额度已经过期了。
查看额度的链接是这个：
https://platform.openai.com/account/usage