[ERR]500 from chatgpt
fateNiu opened this issue · comments
{
"error": {
"code": "500",
"details": "....<p id="cf-spinner-please-wait">Please stand by, while we are checking your browser...
"message": "Unknown error",
"param": null,
"type": "internal_server_error"
}
}
hmm it seems like you run into Cloudflare, you must use reverse proxy then
same here
Embedded error: Get "https://chat.openai.com/api/auth/csrf": Proxy responded with non 200 code: 400 Bad Request
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.
...
2023/08/04 18:07:01 &{begin 403
I have tried to use proxy but with no luck
This happens with last night ChatGPT update, you can get pass it using reverse proxy
API_REVERSE_PROXY: https://bypass.churchless.tech/conversation
Give it a try with my repository oldweipro/ChatGPT-to-API and see if the fix-403
branch can solve your issue.
试一下我的仓库 oldweipro/ChatGPT-to-API fix-403
分支的是否可以解决你的问题
@oldweipro 感谢,但是 pro/ChatGPT-to-API 在我这里依旧 500。
@oldweipro 感谢,但是 pro/ChatGPT-to-API 在我这里依旧 500。
可以贴一下报错信息吗
$ ./freechatgpt
[GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.
[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
- using env: export GIN_MODE=release
- using code: gin.SetMode(gin.ReleaseMode)
[GIN-debug] GET /ping --> main.main.func1 (4 handlers)
[GIN-debug] PATCH /admin/password --> main.passwordHandler (5 handlers)
[GIN-debug] PATCH /admin/tokens --> main.tokensHandler (5 handlers)
[GIN-debug] PATCH /admin/puid --> main.puidHandler (5 handlers)
[GIN-debug] PATCH /admin/openai --> main.openaiHandler (5 handlers)
[GIN-debug] OPTIONS /v1/chat/completions --> main.optionsHandler (4 handlers)
[GIN-debug] POST /v1/chat/completions --> main.nightmare (5 handlers)
[GIN-debug] GET /v1/engines --> main.engines_handler (5 handlers)
[GIN-debug] GET /v1/models --> main.engines_handler (5 handlers)
2023/08/06 23:56:31 838493 127.0.0.1:8282
[GIN] 2023/08/06 - 23:56:38 | 500 | 217.771872ms | 127.0.0.1 | POST "/v1/chat/completions"
^C2023/08/06 23:58:19 838493 Received SIGINT.
2023/08/06 23:58:19 838493 Waiting for connections to finish...
2023/08/06 23:58:19 838493 Serve() returning...
Authenticator 会报错吗,先确认一下我修复的403错误是否有用
Authenticator 会报错吗,先确认一下我修复的403错误是否有用
我不是 plus,没有 puid,Aithenticator 部分我是自己用 playwright 做的自动化。没用过这个库里的 Authencator,这个库里的 Authencator 需要 puid?很久前用这个库不能自己生成 access_tokens.json
,就没再尝试。
go-chatgpt-api 这套代码在我这里,同 ip, access_token,不会 500 。估计是那个 id 要每次新生成了?跟 ua 之类的应该关系不大。
go-chatgpt-api 这套代码在我这里,同 ip, access_token,不会 500 。估计是那个 id 要每次新生成了?跟 ua 之类的应该关系不大。
我没有plus,puid这个我没测试过😂
go-chatgpt-api 这套代码在我这里,同 ip, access_token,不会 500 。估计是那个 id 要每次新生成了?跟 ua 之类的应该关系不大。
我没有plus,puid这个我没测试过joy
不是,我是指发给 ChatGPT 网页的conversation id,对应 https://github.com/linweiyuan/go-chatgpt-api/blob/main/api/imitate/api.go 这个文件里 89 行那个。