配置OpenAI客户端遇openai.OpenAIError，按文档操作仍未解决

• 问题根源：OpenAI Python SDK v1.x版本中，api_key需要传递给客户端实例，类属性OpenAI.api_key的设置方式已不再生效。

• 解决方案1：实例化时直接传入api_key
  修改代码如下：

from openai import OpenAI

client = OpenAI(
  api_key="MY_API_KEY_HERE",  # 在此位置传入api_key
  organization='org-w3VLIwcgMFnrEX2R8tyPwGuA',
  project='$PROJECT_ID',
)

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

• 解决方案2：使用环境变量（推荐）

1. 删除代码中OpenAI.api_key = "MY_API_KEY_HERE"这一行
2. 设置系统环境变量：
   • Windows命令行：set OPENAI_API_KEY=MY_API_KEY_HERE
   • Linux/macOS终端：export OPENAI_API_KEY=MY_API_KEY_HERE
3. 实例化客户端时无需手动传入api_key：

from openai import OpenAI

client = OpenAI(
  organization='org-w3VLIwcgMFnrEX2R8tyPwGuA',
  project='$PROJECT_ID',
)

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

内容的提问来源于stack exchange，提问作者Python Nerd