OpenAI>=1.0.0中ChatCompletion无法使用，Mac环境下如何替换？

开发GPT内容生成系统，Mac环境下无法升级/降级OpenAI库，原代码调用openai.ChatCompletion.create接口报错，提示该接口在openai>=1.0.0版本中已不再支持，尝试pip升级、降级操作均无效，需替换ChatCompletion相关调用以适配当前OpenAI版本。

原代码 #

import os
import openai

# Set the API key from an environment variable
openai.api_key = os.environ.get("api key ")

# Prompt GPT for content generation
prompt = "Write a blog post introducing an automated marketing platform for small businesses."
response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "user", "content": prompt}
    ],
    max_tokens=500,
    temperature=0.7,
)

# Print the generated content
print(response.choices[0].message.content)

报错信息 #

Traceback (most recent call last):
  File "/Users/macbook/marketing-automation/gpt_content_generation.py", line 9, in <module>
    response = openai.ChatCompletion.create(
  File "/Users/macbook/marketing-automation/env/lib/python3.9/site-packages/openai/lib/_old_api.py", line 39, in __call__
    raise APIRemovedInV1(symbol=self._symbol)
openai.lib._old_api.APIRemovedInV1: 

You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0 - see the README at https://github.com/openai/openai-python for the API.

官方提示信息 #

You can run `openai migrate` to automatically upgrade your codebase to use the 1.0.0 interface. 

Alternatively, you can pin your installation to the old version, e.g. `pip install openai==0.28`

A detailed migration guide is available here: https://github.com/openai/openai-python/discussions/742

直接修改代码适配OpenAI 1.x版本的API即可，核心改动如下：

• 改用OpenAI客户端实例初始化
• 调用chat.completions.create替代旧的ChatCompletion.create
• 响应解析逻辑与旧版一致，无需额外调整

修改后的代码：

import os
from openai import OpenAI

# 初始化OpenAI客户端
client = OpenAI(api_key=os.environ.get("api key"))

prompt = "Write a blog post introducing an automated marketing platform for small businesses."
response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "user", "content": prompt}
    ],
    max_tokens=500,
    temperature=0.7,
)

# 打印生成内容
print(response.choices[0].message.content)

若环境变量读取API Key存在问题，可临时直接赋值（不推荐生产环境使用）：

client = OpenAI(api_key="your-actual-api-key")

内容的提问来源于stack exchange，提问作者Divine