报错解决：APIConnectionError 调用异常处理 (openAI api)

1. 报错

raise error.APIConnectionError(
openai.error.APIConnectionError: Error communicating with OpenAI: HTTPSConnectionPool(host=‘api.openai.com’, port=443): Max retries exceeded with url: /v1/audio/transcriptions (Caused by SSLError(“Can’t connect to HTTPS URL because the SSL module is not available.”))

2. 解决方法

• 文件路径：./envs/虚拟环境名称/Lib/site-packages/openai/api_requestor.py（openai库路径）
• 找到if not hasattr(_thread_context, "session"):方法，加入代理：

proxy = {
        'http': 'http://localhost:7890',
        'https': 'http://localhost:7890'
        }

• 在result = _thread_context.session.request(中加入代理：

	proxies=proxy,
	

• 主文件中配置环境

import os
 
os.environ["http_proxy"] = "http://localhost:7890"
os.environ["https_proxy"] = "http://localhost:7890"

3. 测试案例

import os
 
os.environ["http_proxy"] = "http://localhost:7890"
os.environ["https_proxy"] = "http://localhost:7890"

import openai
from langchain.llms import OpenAI

llm = OpenAI(temperature=0.9)

text = "Who won the world series in 2020?"
print(llm(text))

参考：openai-chatGPT的API调用异常处理