机器人请求失败!!!

eryajf / chatgpt-dingtalk

🎒 钉钉 & 🤖 GPT-3.5 让你的工作效率直接起飞 🚀 私聊群聊方式、单聊串聊模式、角色扮演、图片创作 🚀

https://wiki.eryajf.net

MIT License

2.09k stars 388 forks source link

机器人请求失败!!! #153

Open hhfeng616 opened 1 year ago

hhfeng616 commented 1 year ago

部署的阿里云服务器,开启了sockes5代理端口是1080看看下面的错误是什么原因导致的!!! 请求openai失败了，错误信息：Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused

@Daryl

docker-compose.yml如下面所示

version: '3'

services:
  chatgpt:
    container_name: chatgpt
    image: dockerproxy.com/eryajf/chatgpt-dingtalk:latest
    restart: always
    environment:
      APIKEY: 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  # 你的 api_key
      BASE_URL: ""  # 如果你想指定请求url的地址，可通过这个参数进行配置，不需要再添加 /v1，如果留空则默认为官方地址，
      MODEL: "gpt-3.5-turbo" # 指定模型
      SESSION_TIMEOUT: 600 # 超时时间
      HTTP_PROXY: http://host.docker.internal:1080 # 配置代理，注意host.docker.internal会解析到容器所在的宿主机IP，因此只需要更改端口即可，另外如果服务器在国外，则这里留空即可
      DEFAULT_MODE: "单聊" # 聊天模式
      MAX_REQUEST: 0 # 单人单日请求次数限制，默认为0，即不限制
      PORT: 8090 # 指定服务启动端口，默认为 8090，容器化部署时，不需要调整
      SERVICE_URL: "http://121.196.237.40:8090"  # 指定服务的地址，就是钉钉机器人配置的回调地址，比如: http://chat.eryajf.net
    ports:
      - "8090:8090"
    extra_hosts:
      - host.docker.internal:host-gateway

开启代理是sockes5代理是没有问题的！！！

root@UnitServer:~/data/docker_data/chatgpt-dingtalk# export ALL_PROXY=socks5://127.0.0.1:1080
root@UnitServer:~/data/docker_data/chatgpt-dingtalk# curl http://ipinfo.io
{
  "ip": "194.146.25.114",
  "city": "London",
  "region": "England",
  "country": "GB",
  "loc": "51.5085,-0.1257",
  "org": "AS210329 Kamatera Inc",
  "postal": "EC1A",
  "timezone": "Europe/London",
  "readme": "https://ipinfo.io/missingauth"
}root@UnitServer:~/data/docker_data/chatgpt-dingtalk#

root@UnitServer:~/data/docker_data/chatgpt-dingtalk# curl --proxy socks5h://127.0.0.1:1080 https://api.openai.com/v1/models
{
  "error": {
    "message": "You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accesing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}
root@UnitServer:~/data/docker_data/chatgpt-dingtalk#

hhfeng616 commented 1 year ago

doucker容器的ifconfig输出结果如下

root@UnitServer:~/data/docker_data/chatgpt-dingtalk# ifconfig
br-f531dfb7219d: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
        inet 172.18.0.1  netmask 255.255.0.0  broadcast 172.18.255.255
        ether 02:42:56:31:ba:7d  txqueuelen 0  (Ethernet)
        RX packets 1099  bytes 77701 (75.8 KiB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 1179  bytes 181834 (177.5 KiB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

docker0: flags=4099<UP,BROADCAST,MULTICAST>  mtu 1500
        inet 172.17.0.1  netmask 255.255.0.0  broadcast 172.17.255.255
        ether 02:42:a0:fe:36:01  txqueuelen 0  (Ethernet)
        RX packets 0  bytes 0 (0.0 B)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 0  bytes 0 (0.0 B)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
        inet 172.23.221.210  netmask 255.255.240.0  broadcast 172.23.223.255
        ether 00:16:3e:08:88:be  txqueuelen 1000  (Ethernet)
        RX packets 309448  bytes 56717100 (54.0 MiB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 490256  bytes 120328815 (114.7 MiB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

lo: flags=73<UP,LOOPBACK,RUNNING>  mtu 65536
        inet 127.0.0.1  netmask 255.0.0.0
        loop  txqueuelen 1000  (Local Loopback)
        RX packets 1063  bytes 205363 (200.5 KiB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 1063  bytes 205363 (200.5 KiB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

vethf42c7da: flags=4163<UP,BROADCAST,RUNNING,MULTICAST>  mtu 1500
        ether 66:f4:f8:a5:2a:dc  txqueuelen 0  (Ethernet)
        RX packets 86  bytes 7745 (7.5 KiB)
        RX errors 0  dropped 0  overruns 0  frame 0
        TX packets 86  bytes 15855 (15.4 KiB)
        TX errors 0  dropped 0 overruns 0  carrier 0  collisions 0

root@UnitServer:~/data/docker_data/chatgpt-dingtalk#

hhfeng616 commented 1 year ago

时时运行输出的日志如下所示

| INFO [dingtalk callback parameters: dingbot.ReceiveMsg{ConversationID:"cidtVeI5kNf+DHSYfxLy/Pw3g==", AtUsers:[]struct { DingtalkID string "json:\"dingtalkId\"" }{struct { DingtalkID string "json:\"dingtalkId\"" }{DingtalkID:"$:LWCP_v1:$A8rRtZ2X/++mm8UpJJOEFHm+HTLnF90R"}}, ChatbotUserID:"$:LWCP_v1:$A8rRtZ2X/++mm8UpJJOEFHm+HTLnF90R", MsgID:"msgZjq1f8YZcfIvTi/upOfDfg==", SenderNick:"Daryl", IsAdmin:true, SenderStaffId:"manager957", SessionWebhookExpiredTime:1680362551853, CreateAt:1680357151704, ConversationType:"2", SenderID:"$:LWCP_v1:$7c8lREFsakUhrmjbv+Sn6onKL27nc1Am", ConversationTitle:"未来可期", IsInAtList:true, SessionWebhook:"https://oapi.dingtalk.com/robot/sendBySession?session=c7047ff966b9195044053ed012fd10d1", Text:dingbot.Text{Content:" lot"}, RobotCode:"ding6ze1fukrrr8p7kwk", Msgtype:"text"}]
chatgpt    | INFO [after generate prompt: "lot"]
chatgpt    | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]
chatgpt    | WARN [get gpt result falied: <nil>]

感觉问题就出在请求api.openai.com接口不通？服务器用的国内阿里云,端口都开放了，挂的梯子是SSR开的socks5代理 export ALL_PROXY=socks5://127.0.0.1:1080设置之后可以通过curl --proxy socks5h://127.0.0.1:1080 https://api.openai.com/v1/chat/completions访问到接口，就是不知道需要改哪里的设置才可以，是docker-compose中的 HTTP_PROXY: http://host.docker.internal:1080 # 这行代码要修改吗？

WinMin commented 1 year ago

chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看这个报错 chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看起来是你容器连不到你容器外的代理端口

hhfeng616 commented 1 year ago

chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看这个报错 chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看起来是你容器连不到你容器外的代理端口

HTTP_PROXY="socks5h://host.docker.internal:1080"改成这样吗

WinMin commented 1 year ago

chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看这个报错 chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused] 看起来是你容器连不到你容器外的代理端口

HTTP_PROXY="socks5h://host.docker.internal:1080"改成这样吗

你这代理不支持 http 代理吗？

hhfeng616 commented 1 year ago

chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看这个报错 chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused] 看起来是你容器连不到你容器外的代理端口

HTTP_PROXY="socks5h://host.docker.internal:1080"改成这样吗

你这代理不支持 http 代理吗？

买的梯子应该支持就是不知道怎么弄，新手一个搞了几天了还是不行，阿里云服务器上面用的shadowsocks-cli代理的

hhfeng616 commented 1 year ago

chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused]

看这个报错 chatgpt | INFO [gpt request error: Post "https://api.openai.com/v1/chat/completions": proxyconnect tcp: dial tcp 172.17.0.1:1080: connect: connection refused] 看起来是你容器连不到你容器外的代理端口

HTTP_PROXY="socks5h://host.docker.internal:1080"改成这样吗

你这代理不支持 http 代理吗？

买的梯子应该支持就是不知道怎么弄，新手一个搞了几天了还是不行，阿里云服务器上面用的shadowsocks-cli代理的 HTTP_PROXY="socks5h://host.docker.internal:1080"这样还是不行感觉还是设置有问题host.docker.internal这个是127.0.0.1么还是我阿里云服务器的外网IP，宿主的所有请求必须类似这样的curl --proxy socks5h://127.0.0.1:1080 https://api.openai.com/v1/models.... docker里面的chatgpt-dingtalk直接访问不行需要用到外面的代理才可以？

baby9 commented 1 year ago

看起来你的阿里云服务器买的是国内的吧，你需要在服务器上开启代理你需要把代理端口监听在docker0网卡上，listen 172.17.0.1:1080，最好是以http协议，作者的项目没有提到对socks的支持 docker run时设置环境变量 -e HTTP_PROXY=“http://172.17.0.1:1080”

baby9 commented 1 year ago

看起来你的阿里云服务器买的是国内的吧，你需要在服务器上开启代理你需要把代理端口监听在docker0网卡上，listen 172.17.0.1:1080，最好是以http协议，作者的项目没有提到对socks的支持 docker run时设置环境变量 -e HTTP_PROXY=“http://172.17.0.1:1080”

以docker网桥模式启动，--add-host="host.docker.internal:host-gateway"这一步就不需要了

eryajf commented 1 year ago

看起来你的阿里云服务器买的是国内的吧，你需要在服务器上开启代理你需要把代理端口监听在docker0网卡上，listen 172.17.0.1:1080，最好是以http协议，作者的项目没有提到对socks的支持 docker run时设置环境变量 -e HTTP_PROXY=“http://172.17.0.1:1080”

最新的readme已做了说明：

hhfeng616 commented 1 year ago

172.17.0.1

docker run -itd --name chatgpt -p 8090:8090 -e APIKEY=sk-Sq5Iys65nLi6ECu72C44T3BlbkFJw4****="" -e MODEL="gpt-3.5-turbo" -e SESSION_TIMEOUT=600 -e HTTP_PROXY="socks5h://172.17.0.1:1080" -e DEFAULT_MODE="单聊" -e MAX_REQUEST=0 -e PORT=8090 -e SERVICE_URL="http://121.196.237.40:8090" -e CHAT_TYPE="0" --restart=always dockerproxy.com/eryajf/chatgpt-dingtalk:latest 改成这样了没有以前的错误了现在是其他的错误 {"log":"\u001b]10;?\u001b\\\u001b[6n\u001b]11;?\u001b\\\u001b[6n2023/04/02 19:58:41.966931 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 1\r\n","stream":"stdout","time":"2023-04-02T11:58:41.967225611Z"} {"log":"2023/04/02 19:58:53.975368 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 2\r\n","stream":"stdout","time":"2023-04-02T11:58:53.975628212Z"} {"log":"2023/04/02 19:59:05.983170 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 3\r\n","stream":"stdout","time":"2023-04-02T11:59:05.983409096Z"} {"log":"2023/04/02 19:59:17.991794 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 4\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992280844Z"} {"log":"INFO [🚀 The HTTP Server is running on :8090]\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992325647Z"} {"log":"INFO [dingtalk callback parameters: dingbot.ReceiveMsg{ConversationID:\"cidYO9AWtiXFrRV3bPQZa2Adft8hORVjGtTzKW4dtmDcDQ=\", AtUsers:[]struct { DingtalkID string \"json:\\\"dingtalkId\\\"\" }(nil), ChatbotUserID:\"$:LWCP_v1:$8Hd7LMU13qGG9ubDeFng2dLtq+1Rv5d1\", MsgID:\"msg1WKzHtRixA3p36ELftWgpw==\", SenderNick:\"Daryl\", IsAdmin:true, SenderStaffId:\"manager957\", SessionWebhookExpiredTime:1680442169550, CreateAt:1680436769303, ConversationType:\"1\", SenderID:\"$:LWCP_v1:$7c8lREFsakUhrmjbv+Sn6onKL27nc1Am\", ConversationTitle:\"\", IsInAtList:false, SessionWebhook:\"https://oapi.dingtalk.com/robot/sendBySession?session=ef79c594cd20f349791be88fa07f3d2b\", Text:dingbot.Text{Content:\"@44\"}, RobotCode:\"ding6ze1fukrrr8p7kwk\", Msgtype:\"text\"}]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659340235Z"} {"log":"INFO [after generate prompt: \"@44\"]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659378478Z"}

baby9 commented 1 year ago

172.17.0.1

docker run -itd --name chatgpt -p 8090:8090 -e APIKEY=sk-Sq5Iys65nLi6ECu72C44T3BlbkFJw4****="" -e MODEL="gpt-3.5-turbo" -e SESSION_TIMEOUT=600 -e HTTP_PROXY="socks5h://172.17.0.1:1080" -e DEFAULT_MODE="单聊" -e MAX_REQUEST=0 -e PORT=8090 -e SERVICE_URL="http://121.196.237.40:8090" -e CHAT_TYPE="0" --restart=always dockerproxy.com/eryajf/chatgpt-dingtalk:latest 改成这样了没有以前的错误了现在是其他的错误 {"log":"\u001b]10;?\u001b\\\u001b[6n\u001b]11;?\u001b\\\u001b[6n2023/04/02 19:58:41.966931 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 1\r\n","stream":"stdout","time":"2023-04-02T11:58:41.967225611Z"} {"log":"2023/04/02 19:58:53.975368 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 2\r\n","stream":"stdout","time":"2023-04-02T11:58:53.975628212Z"} {"log":"2023/04/02 19:59:05.983170 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 3\r\n","stream":"stdout","time":"2023-04-02T11:59:05.983409096Z"} {"log":"2023/04/02 19:59:17.991794 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 4\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992280844Z"} {"log":"INFO [🚀 The HTTP Server is running on :8090]\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992325647Z"} {"log":"INFO [dingtalk callback parameters: dingbot.ReceiveMsg{ConversationID:\"cidYO9AWtiXFrRV3bPQZa2Adft8hORVjGtTzKW4dtmDcDQ=\", AtUsers:[]struct { DingtalkID string \"json:\\\"dingtalkId\\\"\" }(nil), ChatbotUserID:\"$:LWCP_v1:$8Hd7LMU13qGG9ubDeFng2dLtq+1Rv5d1\", MsgID:\"msg1WKzHtRixA3p36ELftWgpw==\", SenderNick:\"Daryl\", IsAdmin:true, SenderStaffId:\"manager957\", SessionWebhookExpiredTime:1680442169550, CreateAt:1680436769303, ConversationType:\"1\", SenderID:\"$:LWCP_v1:$7c8lREFsakUhrmjbv+Sn6onKL27nc1Am\", ConversationTitle:\"\", IsInAtList:false, SessionWebhook:\"https://oapi.dingtalk.com/robot/sendBySession?session=ef79c594cd20f349791be88fa07f3d2b\", Text:dingbot.Text{Content:\"@44\"}, RobotCode:\"ding6ze1fukrrr8p7kwk\", Msgtype:\"text\"}]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659340235Z"} {"log":"INFO [after generate prompt: \"@44\"]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659378478Z"}

作者刚才更新了，重新拉取镜像部署

eryajf commented 1 year ago

172.17.0.1

docker run -itd --name chatgpt -p 8090:8090 -e APIKEY=sk-Sq5Iys65nLi6ECu72C44T3BlbkFJw4****="" -e MODEL="gpt-3.5-turbo" -e SESSION_TIMEOUT=600 -e HTTP_PROXY="socks5h://172.17.0.1:1080" -e DEFAULT_MODE="单聊" -e MAX_REQUEST=0 -e PORT=8090 -e SERVICE_URL="http://121.196.237.40:8090" -e CHAT_TYPE="0" --restart=always dockerproxy.com/eryajf/chatgpt-dingtalk:latest 改成这样了没有以前的错误了现在是其他的错误 {"log":"\u001b]10;?\u001b\\\u001b[6n\u001b]11;?\u001b\\\u001b[6n2023/04/02 19:58:41.966931 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 1\r\n","stream":"stdout","time":"2023-04-02T11:58:41.967225611Z"} {"log":"2023/04/02 19:58:53.975368 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 2\r\n","stream":"stdout","time":"2023-04-02T11:58:53.975628212Z"} {"log":"2023/04/02 19:59:05.983170 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 3\r\n","stream":"stdout","time":"2023-04-02T11:59:05.983409096Z"} {"log":"2023/04/02 19:59:17.991794 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 4\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992280844Z"} {"log":"INFO [🚀 The HTTP Server is running on :8090]\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992325647Z"} {"log":"INFO [dingtalk callback parameters: dingbot.ReceiveMsg{ConversationID:\"cidYO9AWtiXFrRV3bPQZa2Adft8hORVjGtTzKW4dtmDcDQ=\", AtUsers:[]struct { DingtalkID string \"json:\\\"dingtalkId\\\"\" }(nil), ChatbotUserID:\"$:LWCP_v1:$8Hd7LMU13qGG9ubDeFng2dLtq+1Rv5d1\", MsgID:\"msg1WKzHtRixA3p36ELftWgpw==\", SenderNick:\"Daryl\", IsAdmin:true, SenderStaffId:\"manager957\", SessionWebhookExpiredTime:1680442169550, CreateAt:1680436769303, ConversationType:\"1\", SenderID:\"$:LWCP_v1:$7c8lREFsakUhrmjbv+Sn6onKL27nc1Am\", ConversationTitle:\"\", IsInAtList:false, SessionWebhook:\"https://oapi.dingtalk.com/robot/sendBySession?session=ef79c594cd20f349791be88fa07f3d2b\", Text:dingbot.Text{Content:\"@44\"}, RobotCode:\"ding6ze1fukrrr8p7kwk\", Msgtype:\"text\"}]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659340235Z"} {"log":"INFO [after generate prompt: \"@44\"]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659378478Z"}

作者刚才更新了，重新拉取镜像部署

再拉取下最新镜像，另外注意看下readme的启动命令说明，最新版本添加了几个环境变量

hhfeng616 commented 1 year ago

172.17.0.1

docker run -itd --name chatgpt -p 8090:8090 -e APIKEY=sk-Sq5Iys65nLi6ECu72C44T3BlbkFJw4****="" -e MODEL="gpt-3.5-turbo" -e SESSION_TIMEOUT=600 -e HTTP_PROXY="socks5h://172.17.0.1:1080" -e DEFAULT_MODE="单聊" -e MAX_REQUEST=0 -e PORT=8090 -e SERVICE_URL="http://121.196.237.40:8090" -e CHAT_TYPE="0" --restart=always dockerproxy.com/eryajf/chatgpt-dingtalk:latest 改成这样了没有以前的错误了现在是其他的错误 {"log":"\u001b]10;?\u001b\\\u001b[6n\u001b]11;?\u001b\\\u001b[6n2023/04/02 19:58:41.966931 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 1\r\n","stream":"stdout","time":"2023-04-02T11:58:41.967225611Z"} {"log":"2023/04/02 19:58:53.975368 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 2\r\n","stream":"stdout","time":"2023-04-02T11:58:53.975628212Z"} {"log":"2023/04/02 19:59:05.983170 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 3\r\n","stream":"stdout","time":"2023-04-02T11:59:05.983409096Z"} {"log":"2023/04/02 19:59:17.991794 ERROR RESTY Get \"https://api.openai.com/dashboard/billing/credit_grants\": context deadline exceeded (Client.Timeout exceeded while awaiting headers), Attempt 4\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992280844Z"} {"log":"INFO [🚀 The HTTP Server is running on :8090]\r\n","stream":"stdout","time":"2023-04-02T11:59:17.992325647Z"} {"log":"INFO [dingtalk callback parameters: dingbot.ReceiveMsg{ConversationID:\"cidYO9AWtiXFrRV3bPQZa2Adft8hORVjGtTzKW4dtmDcDQ=\", AtUsers:[]struct { DingtalkID string \"json:\\\"dingtalkId\\\"\" }(nil), ChatbotUserID:\"$:LWCP_v1:$8Hd7LMU13qGG9ubDeFng2dLtq+1Rv5d1\", MsgID:\"msg1WKzHtRixA3p36ELftWgpw==\", SenderNick:\"Daryl\", IsAdmin:true, SenderStaffId:\"manager957\", SessionWebhookExpiredTime:1680442169550, CreateAt:1680436769303, ConversationType:\"1\", SenderID:\"$:LWCP_v1:$7c8lREFsakUhrmjbv+Sn6onKL27nc1Am\", ConversationTitle:\"\", IsInAtList:false, SessionWebhook:\"https://oapi.dingtalk.com/robot/sendBySession?session=ef79c594cd20f349791be88fa07f3d2b\", Text:dingbot.Text{Content:\"@44\"}, RobotCode:\"ding6ze1fukrrr8p7kwk\", Msgtype:\"text\"}]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659340235Z"} {"log":"INFO [after generate prompt: \"@44\"]\r\n","stream":"stdout","time":"2023-04-02T11:59:29.659378478Z"}

作者刚才更新了，重新拉取镜像部署

再拉取下最新镜像，另外注意看下readme的启动命令说明，最新版本添加了几个环境变量

折腾了这么久用的二进制包部署成功了！！！！

sscoo commented 1 year ago

@daryl

docker-compose.yml如下面所示

version: '3'

services:
  chatgpt:
    container_name: chatgpt
    image: dockerproxy.com/eryajf/chatgpt-dingtalk:latest
    restart: always
    environment:
      APIKEY: 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  # 你的 api_key
      BASE_URL: ""  # 如果你想指定请求url的地址，可通过这个参数进行配置，不需要再添加 /v1，如果留空则默认为官方地址，
      MODEL: "gpt-3.5-turbo" # 指定模型
      SESSION_TIMEOUT: 600 # 超时时间
      HTTP_PROXY: http://host.docker.internal:1080 # 配置代理，注意host.docker.internal会解析到容器所在的宿主机IP，因此只需要更改端口即可，另外如果服务器在国外，则这里留空即可
      DEFAULT_MODE: "单聊" # 聊天模式
      MAX_REQUEST: 0 # 单人单日请求次数限制，默认为0，即不限制
      PORT: 8090 # 指定服务启动端口，默认为 8090，容器化部署时，不需要调整
      SERVICE_URL: "http://121.196.237.40:8090"  # 指定服务的地址，就是钉钉机器人配置的回调地址，比如: http://chat.eryajf.net
    ports:
      - "8090:8090"
    extra_hosts:
      - host.docker.internal:host-gateway

开启代理是sockes5代理是没有问题的！！！

root@UnitServer:~/data/docker_data/chatgpt-dingtalk# export ALL_PROXY=socks5://127.0.0.1:1080
root@UnitServer:~/data/docker_data/chatgpt-dingtalk# curl http://ipinfo.io
{
  "ip": "194.146.25.114",
  "city": "London",
  "region": "England",
  "country": "GB",
  "loc": "51.5085,-0.1257",
  "org": "AS210329 Kamatera Inc",
  "postal": "EC1A",
  "timezone": "Europe/London",
  "readme": "https://ipinfo.io/missingauth"
}root@UnitServer:~/data/docker_data/chatgpt-dingtalk#

root@UnitServer:~/data/docker_data/chatgpt-dingtalk# curl --proxy socks5h://127.0.0.1:1080 https://api.openai.com/v1/models
{
  "error": {
    "message": "You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accesing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}
root@UnitServer:~/data/docker_data/chatgpt-dingtalk#

key不要用明文写出来啊