import zhipuai.openai_bridge as openai
openai.api_key = "65ff******.s******Z"

completion = openai.ChatCompletion.create(
  model="chatglm_pro",
  messages=[{"role": "user", "content": "你好，请自我介绍并说明你能给我提供的帮助"}]
)

print(completion)
# {
#   "code": 200,
#   "msg": "\u64cd\u4f5c\u6210\u529f",
#   "success": true,
#   "request_id": "789********",
#   "choices": [
#     {
#       "message": {
#         "role": "assistant",
#         "content": "\" \u4f60\u597d\uff01\u6211\u662f ChatGLM\uff0c\u662f\u6e05\u534e\u5927\u5b66 KEG \u5b9e\u9a8c\u5ba4\u548c\u667a\u8c31 AI \u516c\u53f8\u5171\u540c\u8bad\u7ec3\u7684\u8bed\u8a00\u6a21\u578b\u3002\u6211\u7684\u76ee\u6807\u662f\u901a\u8fc7\u56de\u7b54\u7528\u6237\u63d0\u51fa\u7684\u95ee\u9898\u6765\u5e2e\u52a9\u4ed6\u4eec\u89e3\u51b3\u95ee\u9898\u3002\u6211\u53ef\u4ee5\u56de\u7b54\u5404\u79cd\u5404\u6837\u7684\u95ee\u9898\uff0c\u5305\u62ec\u4f46\u4e0d\u9650\u4e8e\u79d1\u5b66\u3001\u6280\u672f\u3001\u5386\u53f2\u3001\u6587\u5316\u3001\u5065\u5eb7\u3001\u6cd5\u5f8b\u7b49\u7b49\u3002\u5982\u679c\u6709\u4efb\u4f55\u95ee\u9898\u9700\u8981\u5e2e\u52a9\uff0c\u8bf7\u968f\u65f6\u5411\u6211\u63d0\u95ee\u3002\""
#       },
#       "finish_reason": "stop",
#       "index": 0
#     }
#   ]
# }

print(completion.choices[0].message.content)
# " 你好！我是 ChatGLM，是清华大学 KEG 实验室和智谱 AI 公司共同训练的语言模型。我的目标是通过回答用户提出的问题来帮助他们解决问题。我可以回答各种各样的问题，包括但不限于科学、技术、历史、文化、健康、法律等等。如果有任何问题需要帮助，请随时向我提问。"

import importhook

# Setup hook to be called any time the `openai` module is imported and loaded into module cache
@importhook.on_import('openai')
def on_openai_import(socket):
    import openai
    new_openai = importhook.copy_module(openai)
    setattr(new_openai, 'ChatCompletion', ZPChatCompletion)
    return new_openai

# 然后引入其他依赖 openai 的库
# eg in LangChain: import openai