TypeError: fetch failed (can't connect to OpenAI Api)

[sannyii]

加了key以后，一直connect error的错误。求救。。。

[sannyii]

状态码 500

[blkcor]

我也
https://api.openai.com/v1/chat/completions这个接口fetch不到
.env配置了HTTPS_PROXY为我的clash

[ddiu8081]

clash的话，可以先开启增强模式；HTTPS_PROXY 参数还没在这个 repo 实装

[mango2017]

error fetch failed
应该怎么改啊

[DanielFu12]

同样报错，有大神指导一下吗

[x-dr]

用cf_worker反代apenai api 替换掉https://api.openai.com
我自建了一个https://openai.1rmb.tk

自建

代码

const TELEGRAPH_URL = 'https://api.openai.com';

addEventListener('fetch', event => {
  event.respondWith(handleRequest(event.request))
})

async function handleRequest(request) {
  const url = new URL(request.url);
  url.host = TELEGRAPH_URL.replace(/^https?:\/\//, '');
  const modifiedRequest = new Request(url.toString(), {
    headers: request.headers,
    method: request.method,
    body: request.body,
    redirect: 'follow'
  });
  const response = await fetch(modifiedRequest);
  const modifiedResponse = new Response(response.body, response);
  // 添加允许跨域访问的响应头
  modifiedResponse.headers.set('Access-Control-Allow-Origin', '*');
  return modifiedResponse;
}

使用

curl --location 'https://openai.1rmb.tk/v1/chat/completions' \
--header 'Authorization: Bearer sk-xxxxxxxxxxxxxxx' \
--header 'Content-Type: application/json' \
--data '{
   "model": "gpt-3.5-turbo",
  "messages": [{"role": "user", "content": "Hello!"}]
 }'

[ddiu8081]

HTTPS_PROXY 已经支持，本地运行可配置一个 HTTP 代理。

[honestyallan]

部署到google云，访问api/generate接口， 报500异常