Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[文档] endpoint搭建方法参考 #978

Open
INSide-734 opened this issue Jun 21, 2023 · 21 comments
Open

[文档] endpoint搭建方法参考 #978

INSide-734 opened this issue Jun 21, 2023 · 21 comments
Labels
documentation Improvements or additions to documentation

Comments

@INSide-734
Copy link

INSide-734 commented Jun 21, 2023

browserless_endpoint搭建方式

注意:

如果搭建出错了请不要在此issue或者此项目下提新的issue,请到相应的项目下提issue

要求:

可以正常访问 chat.openai.com 且在被支持的国家或地区

使用的项目

go-chatgpt-api
ChatGPT-Proxy-V4

go-chatgpt-api

配置文件

根据你的网络环境不同,可以展开查看对应配置

直接利用现成的服务

服务器不定时维护,不保证高可用,利用这些服务导致的账号安全问题,与本项目无关

家庭网络
  go-chatgpt-api:
    container_name: go-chatgpt-api
    image: linweiyuan/go-chatgpt-api
    ports:
      - 8080:8080
    environment:
      - TZ=Asia/Shanghai
      - GO_CHATGPT_API_PROXY=
      - GO_CHATGPT_API_PANDORA=
      - GO_CHATGPT_API_ARKOSE_TOKEN_URL=
      - GO_CHATGPT_API_ARKOSE_PUID=
    restart: unless-stopped
服务器在直连或者通过网络代理的情况下可以正常访问 ChatGPT
  go-chatgpt-api:
    container_name: go-chatgpt-api
    image: linweiyuan/go-chatgpt-api
    ports:
      - 8080:8080
    environment:
      - TZ=Asia/Shanghai
      - GO_CHATGPT_API_PROXY=
      - GO_CHATGPT_API_PANDORA=
      - GO_CHATGPT_API_ARKOSE_TOKEN_URL=
      - GO_CHATGPT_API_ARKOSE_PUID=
    restart: unless-stopped
服务器访问 ChatGPT 提示 "Sorry, you have been blocked"

如何验证:curl https://chat.openai.com | grep '<p>' | awk '{$1=$1;print}'

  go-chatgpt-api:
    container_name: go-chatgpt-api
    image: linweiyuan/go-chatgpt-api
    ports:
      - 8080:8080
    environment:
      - TZ=Asia/Shanghai
      - GO_CHATGPT_API_PROXY=socks5://chatgpt-proxy-server-warp:65535
      - GO_CHATGPT_API_PANDORA=
      - GO_CHATGPT_API_ARKOSE_TOKEN_URL=
      - GO_CHATGPT_API_ARKOSE_PUID=
    depends_on:
      - chatgpt-proxy-server-warp
    restart: unless-stopped

  chatgpt-proxy-server-warp:
    container_name: chatgpt-proxy-server-warp
    image: linweiyuan/chatgpt-proxy-server-warp
    environment:
      - LOG_LEVEL=OFF
    restart: unless-stopped

设置代理

如需设置代理,可以设置环境变量 GO_CHATGPT_API_PROXY,比如 GO_CHATGPT_API_PROXY=http://127.0.0.1:20171
或者 GO_CHATGPT_API_PROXY=socks5://127.0.0.1:20170,注释掉或者留空则不启用

如果代理需账号密码验证,则 http://username:password@ip:port 或者 socks5://username:password@ip:port

如需配合 warp 使用:GO_CHATGPT_API_PROXY=socks5://chatgpt-proxy-server-warp:65535,因为需要设置 warp
的场景已经默认可以直接访问 ChatGPT 官网,因此共用一个变量不冲突(国内 VPS 不在讨论范围内,请自行配置网络环境,warp
服务在魔法环境下才能正常工作)

家庭网络无需跑 warp 服务,跑了也没用,会报错,仅在服务器需要

GPT-4 相关模型目前需要验证 arkose_token,如果配置 GO_CHATGPT_API_ARKOSE_TOKEN_URL 则使用在线服务获取 arkose_token
,不设置或者留空则由程序内部自己生成(推荐优先使用这种)

GO_CHATGPT_API_ARKOSE_TOKEN_URL 可选值:

如果用以上方法还是 403 并且你的 Plus
没有过期,则有一种可能就是你的账号被风控了,可以尝试用这个账号打开官网,看下会不会弹验证码,然后手动处理下,接着再回来看 go-chatgpt-api
还会不会 403


目前 warp 容器检测到流量超过 1G 会自动重启,如果你知道什么是 teams-enroll-token
(不知道就跳过),可以通过环境变量 TEAMS_ENROLL_TOKEN
设置它的值,然后利用这条命令来检查是否生效

docker-compose exec chatgpt-proxy-server-warp warp-cli --accept-tos account | awk 'NR==1'

Account type: Free (没有生效)

Account type: Team (设置正常)

填写接入点地址

接下来就可以在chatgpt-mirai-qq-bot的config.cfg中填写browserless_endpoint了,示例:

[openai]
# 网页版 ChatGPT 接入点,欢迎在交流群中分享你的接入点
browserless_endpoint = "http(s)://127.0.0.1:8080/chat/"

ChatGPT-Proxy-V4

由于作者没有提供docker镜像,所以需要自己手动构建镜像运行或者从Release下载可执行文件

注意,有一个基于IP的速率限制。需要设置一个PUID环境变量来解决这个问题 export PUID="user-... " 这需要ChatGPT Plus帐户

以下是docker运行方式

# clone 至本地
git clone https://github.com/acheong08/ChatGPT-Proxy-V4.git
# cd 至目录
cd ChatGPT-Proxy-V4
# docker构建镜像
docker build -t chatgpt-proxy-v4 .

docker-compose.yml示例

version: '3.3'
services:
    chatgpt-proxy:
        image: chatgpt-proxy-v4
        container_name: chatgpt-proxy-v4
        ports:
            - '8080:8080'
        env_file:
        - .env

接下来就可以在chatgpt-mirai-qq-bot的config.cfg中填写browserless_endpoint了,示例:

[openai]
# 网页版 ChatGPT 接入点,欢迎在交流群中分享你的接入点
browserless_endpoint = "http(s)://127.0.0.1:8080/api/"
@INSide-734 INSide-734 changed the title web_api搭建方法参考 endpoint搭建方法参考 Jun 22, 2023
@joep1000
Copy link

我在建立chatgpt代理时得到了以下错误:
chatgpt-qq-chatgpt-1 | │ │ │ └ <class 'httpcore.ReadError'>
chatgpt-qq-chatgpt-1 | │ │ └ <method 'throw' of 'generator' objects>
chatgpt-qq-chatgpt-1 | │ └ <generator object map_httpcore_exceptions at 0x7f5e742c9f40>
chatgpt-qq-chatgpt-1 | └ <contextlib._GeneratorContextManager object at 0x7f5e5f384f50>
chatgpt-qq-chatgpt-1 | File "/usr/local/lib/python3.11/site-packages/httpx/_transports/default.py", line 77, in map_httpcore_exceptions
chatgpt-qq-chatgpt-1 | raise mapped_exc(message) from exc
chatgpt-qq-chatgpt-1 | │ └ ''
chatgpt-qq-chatgpt-1 | └ <class 'httpx.ReadError'>
chatgpt-qq-chatgpt-1 |

@joep1000
Copy link

我正在使用chatgpt-proxy-v4

@INSide-734
Copy link
Author

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

@joep1000
Copy link

joep1000 commented Jun 23, 2023

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"

按照教程中的指示

我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

@INSide-734
Copy link
Author

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"

按照教程中的指示

我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

ChatGPT-proxy-V4 是否有错误的日志?

@joep1000
Copy link

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"
按照教程中的指示
我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

ChatGPT-proxy-V4 是否有错误的日志?

我没有看到,chatgpt-proxy-v4似乎按预期运行。这是我运行docker-compose日志时得到的结果:

chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main.main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

@INSide-734
Copy link
Author

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"
按照教程中的指示
我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

ChatGPT-proxy-V4 是否有错误的日志?

我没有看到,chatgpt-proxy-v4似乎按预期运行。这是我运行docker-compose日志时得到的结果:

chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main.main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot貌似没有连接到ChatGPT-proxy-V4,请尝试将

主机IP:5600/api

或者

容器IP:5600/api

填写至你的config.cfg内

@joep1000
Copy link

joep1000 commented Jun 23, 2023

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"
按照教程中的指示
我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

ChatGPT-proxy-V4 是否有错误的日志?

我没有看到,chatgpt-proxy-v4似乎按预期运行。这是我运行docker-compose日志时得到的结果:
chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main.main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot貌似没有连接到ChatGPT-proxy-V4,请尝试将

主机IP:5600/api

或者

容器IP:5600/api

填写至你的config.cfg内

非常感谢您的帮助! 我想现在已经接近工作了。我已经把配置文件中的ip地址改成了docker的ip地址,但现在我遇到了这个错误:

manager.bot:login_openai:348 - 登录失败! 连接 OpenAI 服务器失败,请更换代理节点重试!

@INSide-734
Copy link
Author

我正在使用chatgpt-proxy-v4

config.cfg内容中browserless_endpoint的内容是什么?

browserless_endpoint = "http://127.0.0.1:5600/api/"
按照教程中的指示
我没有使用8080端口,因为它已经被用于一个不同的docker-compose语句。ChatGPT-proxy-V4也被配置在5600端口上,为了确定,我在路由器上打开了这个端口。

ChatGPT-proxy-V4 是否有错误的日志?

我没有看到,chatgpt-proxy-v4似乎按预期运行。这是我运行docker-compose日志时得到的结果:
chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main.main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot貌似没有连接到ChatGPT-proxy-V4,请尝试将

主机IP:5600/api

或者

容器IP:5600/api

填写至你的config.cfg内

非常感谢您的帮助! 我想现在已经接近工作了。我已经把配置文件中的ip地址改成了docker的ip地址,但现在我遇到了这个错误:

manager.bot:login_openai:348 - 登录失败! 连接 OpenAI 服务器失败,请更换代理节点重试!

很明显,你的网络环境无法访问openai,请检查你的代理,和ChatGPT-proxy-V4的代理,我目前没有找到设置ChatGPT-proxy-V4代理的方法,你可以尝试使用go-chatgpt-api,这个项目可以使用代理

@joep1000
Copy link

I am using chatgpt-proxy-v4

What is the content of browserless_endpoint in config.cfg content?

browserless_endpoint = " http://127.0.0.1:5600/api/ "
as instructed in the tutorial
I am not using port 8080 as it is already used for a different docker-compose statement. ChatGPT-proxy-V4 is also configured on port 5600. To be sure, I opened this port on the router.

Does ChatGPT-proxy-V4 have error logs?

I don't see that, chatgpt-proxy-v4 seems to work as expected. This is what I get when I run the docker-compose log:
chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main. main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/ password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot does not seem to be connected to ChatGPT-proxy-V4, please try to

主机IP:5600/api

or

容器IP:5600/api

Fill in your config.cfg

Thanks a lot for your help! I think it's close to working now. I've changed the ip address in the config file to docker's ip address, but now I'm getting this error:
manager.bot:login_openai:348 - Login failed! Failed to connect to the OpenAI server, please replace the proxy node and try again!

Obviously, your network environment cannot access openai, please check your proxy, and the proxy of ChatGPT-proxy-V4, I have not found a way to set the proxy of ChatGPT-proxy-V4, you can try to use go-chatgpt- api , This project can use proxy

即使使用go-chatgpt-api,仍然得到这个错误。

登录失败! 连接OpenAI服务器失败,请使用不同的代理节点重试!

我在docker-compose.yml中的go-chatgpt-api文件是这样的:

go-chatgpt-api-:
container_name: go-chatgpt-api
image: linweiyuan/go-chatgpt-api
ports:
- 5500:5500
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
environment:
- GO_CHATGPT_API_PROXY=socks5://chatgpt-proxy-server-warp:65535
depends_on:
- chatgpt-proxy-server-warp
restart: unless-stopped

chatgpt-proxy-server-warp:
container_name: chatgpt-proxy-server-warp
image: linweiyuan/chatgpt-proxy-server-warp
environment:
- LOG_LEVEL=OFF
restart: unless-stopped

@INSide-734
Copy link
Author

I am using chatgpt-proxy-v4

What is the content of browserless_endpoint in config.cfg content?

browserless_endpoint = " http://127.0.0.1:5600/api/ "
as instructed in the tutorial
I am not using port 8080 as it is already used for a different docker-compose statement. ChatGPT-proxy-V4 is also configured on port 5600. To be sure, I opened this port on the router.

Does ChatGPT-proxy-V4 have error logs?

I don't see that, chatgpt-proxy-v4 seems to work as expected. This is what I get when I run the docker-compose log:
chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main. main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/ password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot does not seem to be connected to ChatGPT-proxy-V4, please try to

主机IP:5600/api

or

容器IP:5600/api

Fill in your config.cfg

Thanks a lot for your help! I think it's close to working now. I've changed the ip address in the config file to docker's ip address, but now I'm getting this error:
manager.bot:login_openai:348 - Login failed! Failed to connect to the OpenAI server, please replace the proxy node and try again!

Obviously, your network environment cannot access openai, please check your proxy, and the proxy of ChatGPT-proxy-V4, I have not found a way to set the proxy of ChatGPT-proxy-V4, you can try to use go-chatgpt- api , This project can use proxy

即使使用go-chatgpt-api,仍然得到这个错误。

登录失败! 连接OpenAI服务器失败,请使用不同的代理节点重试!

我在docker-compose.yml中的go-chatgpt-api文件是这样的:

go-chatgpt-api-:
container_name: go-chatgpt-api
image: linweiyuan/go-chatgpt-api
ports:
- 5500:5500
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
environment:
- GO_CHATGPT_API_PROXY=socks5://chatgpt-proxy-server-warp:65535
depends_on:
- chatgpt-proxy-server-warp
restart: unless-stopped

chatgpt-proxy-server-warp:
container_name: chatgpt-proxy-server-warp
image: linweiyuan/chatgpt-proxy-server-warp
environment:
- LOG_LEVEL=OFF
restart: unless-stopped

请不要使用warp,请将docker-compose中的warp内容删除,将go-chatgpt-api中的GO_CHATGPT_API_PROXY变量更改为你的代理地址,注意,你的代理地址为你的主机地址

@joep1000
Copy link

I am using chatgpt-proxy-v4

What is the content of browserless_endpoint in config.cfg content?

browserless_endpoint = " http://127.0.0.1:5600/api/ "
as instructed in the tutorial
I am not using port 8080 as it is already used for a different docker-compose statement. ChatGPT-proxy-V4 is also configured on port 5600. To be sure, I opened this port on the router.

Does ChatGPT-proxy-V4 have error logs?

I don't see that, chatgpt-proxy-v4 seems to work as expected. This is what I get when I run the docker-compose log:
chatgpt-proxy-v4 | [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
chatgpt-proxy-v4 | - using env: export GIN_MODE=release
chatgpt-proxy-v4 | - using code: gin.SetMode(gin.ReleaseMode)
chatgpt-proxy-v4 |
chatgpt-proxy-v4 | [GIN-debug] GET /ping --> main. main.func1 (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/puid --> main.main.func2 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/ password --> main.main.func3 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /admin/openai --> main.main.func4 (4 handlers)
chatgpt-proxy-v4 | [GIN-debug] GET /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] POST /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PUT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] PATCH /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] HEAD /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] OPTIONS /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] DELETE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] CONNECT /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | [GIN-debug] TRACE /api/*path --> main.proxy (3 handlers)
chatgpt-proxy-v4 | 2023/06/23 09:04:30 1 :9090

chatgpt-mirai-qq-bot does not seem to be connected to ChatGPT-proxy-V4, please try to

主机IP:5600/api

or

容器IP:5600/api

Fill in your config.cfg

Thanks a lot for your help! I think it's close to working now. I've changed the ip address in the config file to docker's ip address, but now I'm getting this error:
manager.bot:login_openai:348 - Login failed! Failed to connect to the OpenAI server, please replace the proxy node and try again!

Obviously, your network environment cannot access openai, please check your proxy, and the proxy of ChatGPT-proxy-V4, I have not found a way to set the proxy of ChatGPT-proxy-V4, you can try to use go-chatgpt- api , This project can use proxy

即使使用go-chatgpt-api,仍然得到这个错误。
登录失败! 连接OpenAI服务器失败,请使用不同的代理节点重试!
我在docker-compose.yml中的go-chatgpt-api文件是这样的:
go-chatgpt-api-:
container_name: go-chatgpt-api
image: linweiyuan/go-chatgpt-api
ports:

  • 5500:5500
    volumes:
  • /var/run/docker.sock:/var/run/docker.sock:ro
    environment:
  • GO_CHATGPT_API_PROXY=socks5://chatgpt-proxy-server-warp:65535
    depends_on:
  • chatgpt-proxy-server-warp
    restart: unless-stopped
    chatgpt-proxy-server-warp:
    container_name: chatgpt-proxy-server-warp
    image: linweiyuan/chatgpt-proxy-server-warp
    environment:
  • LOG_LEVEL=OFF
    restart: unless-stopped

请不要使用warp,请将docker-compose中的warp内容删除,将go-chatgpt-api中的GO_CHATGPT_API_PROXY变量更改为你的代理地址,注意,你的代理地址为你的主机地址

再次感谢您的帮助。我删除了docker-compose文件中的warp内容,并将代理链接到我的本地地址(代理的ip adress:port),但不管怎样,我还是得到同样的错误:

manager.bot:__V1_check_auth:461 - [ChatGPT-Web] - 的 access_token 还有 4 天过期

@INSide-734
Copy link
Author

INSide-734 commented Jun 23, 2023

这并不是报错,只是提示你token过期的时间😂😂😂

@joep1000
Copy link

这并不是报错,只是提升你token过期的时间😂😂😂

😂😂😅我的错,没注意! 这就是我所说的错误信息:

ERROR | manager.bot:login_openai:348 - 登录失败! 连接 OpenAI 服务器失败,请更换代理节点重试!

@INSide-734
Copy link
Author

这并不是报错,只是提升你token过期的时间😂😂😂

😂😂😅我的错,没注意! 这就是我所说的错误信息:

ERROR | manager.bot:login_openai:348 - 登录失败! 连接 OpenAI 服务器失败,请更换代理节点重试!

chatgpt-mirai-qq-bot的config.cfg是否添加了代理呢
例如

[[openai.accounts]]
# 省略的账号信息
 
# 这里填写的内容由你的代理程序提供
proxy="http://127.0.0.1:1080"

@lss233 lss233 added the documentation Improvements or additions to documentation label Jun 24, 2023
@lss233 lss233 changed the title endpoint搭建方法参考 [文档] endpoint搭建方法参考 Jun 24, 2023
@glaw1984
Copy link

[root@ser603810133198 opt]# git clone https://github.com/acheong08/ChatGPT-Proxy-V4.git
正克隆到 'ChatGPT-Proxy-V4'...
remote: Enumerating objects: 302, done.
remote: Counting objects: 100% (205/205), done.
remote: Compressing objects: 100% (87/87), done.
remote: Total 302 (delta 127), reused 126 (delta 115), pack-reused 97
接收对象中: 100% (302/302), 69.28 KiB | 0 bytes/s, done.
处理 delta 中: 100% (187/187), done.
[root@ser603810133198 opt]# cd ChatGPT-Proxy-V4
[root@ser603810133198 ChatGPT-Proxy-V4]# docker build -t chatgpt-proxy-v4
ERROR: "docker buildx build" requires exactly 1 argument.
See 'docker buildx build --help'.

Usage: docker buildx build [OPTIONS] PATH | URL | -

这些是什么错误?

@Haibersut Haibersut pinned this issue Jul 5, 2023
@INSide-734
Copy link
Author

[root@ser603810133198 opt]# git clone https://github.com/acheong08/ChatGPT-Proxy-V4.git
正克隆到 'ChatGPT-Proxy-V4'...
remote: Enumerating objects: 302, done.
remote: Counting objects: 100% (205/205), done.
remote: Compressing objects: 100% (87/87), done.
remote: Total 302 (delta 127), reused 126 (delta 115), pack-reused 97
接收对象中: 100% (302/302), 69.28 KiB | 0 bytes/s, done.
处理 delta 中: 100% (187/187), done.
[root@ser603810133198 opt]# cd ChatGPT-Proxy-V4
[root@ser603810133198 ChatGPT-Proxy-V4]# docker build -t chatgpt-proxy-v4
ERROR: "docker buildx build" requires exactly 1 argument.
See 'docker buildx build --help'.

Usage: docker buildx build [OPTIONS] PATH | URL | -

这些是什么错误?

docker构建镜像失败,可以自行百度解决

@bengogozhou
Copy link

docker build -t chatgpt-proxy-v4 . <----最后面少了一个点。

@0x676e67
Copy link

这有个gpt4端点搭建方案:https://github.com/gngpp/ninja

@Creepender-Brine
Copy link

我是纯小白(提问错地方了告诉我我火速来删),想请问一下各位大佬,[go-chatgpt-api]和这个项目同时搭建,利用accesstoken模拟apikey这个功能,搭出来什么都连上了,但是每次只能问一个问题,再问就显示有人在等待,然后chatgptweb上就会出现很多newchat,这怎么办?我该去哪儿问?

@INSide-734
Copy link
Author

INSide-734 commented Jan 1, 2024

我是纯小白(提问错地方了告诉我我火速来删),想请问一下各位大佬,[go-chatgpt-api]和这个项目同时搭建,利用accesstoken模拟apikey这个功能,搭出来什么都连上了,但是每次只能问一个问题,再问就显示有人在等待,然后chatgptweb上就会出现很多newchat,这怎么办?我该去哪儿问?

这个问题我也不清楚,我刚看了一眼 go-chatgpt-api 已经归档了,尝试换一个项目搭建试试?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation
Projects
None yet
Development

No branches or pull requests

7 participants