From 73b356a55f0f706d7dcf71c1c6cb569534c2c54b Mon Sep 17 00:00:00 2001 From: zeelkalariya <134590969+zeelkalariya@users.noreply.github.com> Date: Fri, 26 May 2023 19:51:09 +0530 Subject: [PATCH] Update README.md --- README.md | 191 ++++++++++++++++++++++++++---------------------------- 1 file changed, 93 insertions(+), 98 deletions(-) diff --git a/README.md b/README.md index c972c600..82d94b55 100644 --- a/README.md +++ b/README.md @@ -6,8 +6,7 @@ # One API -_✨ All in one 的 OpenAI 接口,整合各种 API 访问方式,开箱即用✨_ - +_✨ All in one 的 OpenAIInterface, integrating various API access methods, out of the box ✨_
@@ -29,68 +28,65 @@ _✨ All in one 的 OpenAI 接口,整合各种 API 访问方式,开箱即用
- 程序下载 + program download · - 部署教程 + Deployment Tutorial · - 意见反馈 + Feedback · - 截图展示 + screenshot display · - 在线演示 + online demo · - 常见问题 + common problem
-> **Warning**:从 `v0.2` 版本升级到 `v0.3` 版本需要手动迁移数据库,请手动执行[数据库迁移脚本](./bin/migration_v0.2-v0.3.sql)。 +> **Warning**:Upgrading from `v0.2` to `v0.3` requires manual database migration, please manually execute [database migration script](./bin/migration_v0.2-v0.3.sql). - -## 功能 -1. 支持多种 API 访问渠道,欢迎 PR 或提 issue 添加更多渠道: - + [x] OpenAI 官方通道 +## Function +1. Multiple API access channels are supported. PRs or issues are welcome to add more channels: + + [x] OpenAI official channel + [x] **Azure OpenAI API** + [x] [API2D](https://api2d.com/r/197971) + [x] [OhMyGPT](https://aigptx.top?aff=uFpUl2Kf) - + [x] [AI Proxy](https://aiproxy.io/?i=OneAPI) (邀请码:`OneAPI`) + + [x] [AI Proxy](https://aiproxy.io/?i=OneAPI) (Invitation code:`OneAPI`) + [x] [AI.LS](https://ai.ls) + [x] [OpenAI Max](https://openaimax.com) + [x] [OpenAI-SB](https://openai-sb.com) + [x] [CloseAI](https://console.openai-asia.com/r/2412) - + [x] 自定义渠道:例如使用自行搭建的 OpenAI 代理 -2. 支持通过**负载均衡**的方式访问多个渠道。 -3. 支持 **stream 模式**,可以通过流式传输实现打字机效果。 -4. 支持**多机部署**,[详见此处](#多机部署)。 -5. 支持**令牌管理**,设置令牌的过期时间和使用次数。 -6. 支持**兑换码管理**,支持批量生成和导出兑换码,可使用兑换码为账户进行充值。 -7. 支持**通道管理**,批量创建通道。 -8. 支持发布公告,设置充值链接,设置新用户初始额度。 -9. 支持丰富的**自定义**设置, - 1. 支持自定义系统名称,logo 以及页脚。 - 2. 支持自定义首页和关于页面,可以选择使用 HTML & Markdown 代码进行自定义,或者使用一个单独的网页通过 iframe 嵌入。 -10. 支持通过系统访问令牌访问管理 API。 -11. 支持用户管理,支持**多种用户登录注册方式**: - + 邮箱登录注册以及通过邮箱进行密码重置。 - + [GitHub 开放授权](https://github.com/settings/applications/new)。 - + 微信公众号授权(需要额外部署 [WeChat Server](https://github.com/songquanpeng/wechat-server))。 -12. 未来其他大模型开放 API 后,将第一时间支持,并将其封装成同样的 API 访问方式。 + + [x]Custom channels: such as using a self-built OpenAI agent +2. Support access to multiple channels through **load balancing**. +3.Support **stream mode**, you can achieve typewriter effect through streaming. +4. Support **multi-machine deployment**, [see here for details](#multi-machine deployment). +5. Support **token management**, set the expiration time and usage times of the token. +6. Supports **redemption code management**, supports batch generation and export of redemption codes, and can use redemption codes to recharge accounts. +7.Support **channel management**, create channels in batches. +8. Support for publishing announcements, setting recharge links, and setting new user initial quotas。 +9. Support rich **custom** settings, + 1. Support custom system name, logo and footer. + 2. Support custom homepage and about page, you can choose to use HTML & Markdown code to customize, or use a separate webpage to embed through iframe. +10. Support for accessing the management API through system access tokens. +11.Support user management, support **multiple user login and registration methods**: + + Email login registration and password reset through email. + + [GitHub Open License](https://github.com/settings/applications/new). + + WeChat official account authorization (requires additional deployment of [WeChat Server](https://github.com/songquanpeng/wechat-server)). +12. In the future, after other large models open APIs, they will be supported as soon as possible and encapsulated into the same API access method. -## 部署 -### 基于 Docker 进行部署 -执行:`docker run -d --restart always -p 3000:3000 -v /home/ubuntu/data/one-api:/data justsong/one-api` +## deployment +### Deploy based on Docker +implement:`docker run -d --restart always -p 3000:3000 -v /home/ubuntu/data/one-api:/data justsong/one-api` -`-p 3000:3000` 中的第一个 `3000` 是宿主机的端口,可以根据需要进行修改。 - -数据将会保存在宿主机的 `/home/ubuntu/data/one-api` 目录,请确保该目录存在且具有写入权限,或者更改为合适的目录。 - -Nginx 的参考配置: +`-p 3000:3000` The first `3000` in is the host port, which can be modified as needed. +The data will be saved in the `/home/ubuntu/data/one-api` directory of the host machine, please make sure the directory exists and has write permission, or change to a suitable directory. +Nginx The reference configuration: ``` server{ - server_name openai.justsong.cn; # 请根据实际情况修改你的域名 + server_name openai.justsong.cn; #Please modify your domain name according to the actual situation location / { client_max_body_size 64m; proxy_http_version 1.1; - proxy_pass http://localhost:3000; # 请根据实际情况修改你的端口 + proxy_pass http://localhost:3000; # Please modify your port according to the actual situation proxy_set_header Host $host; proxy_set_header X-Forwarded-For $remote_addr; proxy_cache_bypass $http_upgrade; @@ -99,99 +95,98 @@ server{ } ``` -之后使用 Let's Encrypt 的 certbot 配置 HTTPS: +Then configure HTTPS with Let's Encrypt's certbot: ```bash -# Ubuntu 安装 certbot: +# Ubuntu Install certbot: sudo snap install --classic certbot sudo ln -s /snap/bin/certbot /usr/bin/certbot -# 生成证书 & 修改 Nginx 配置 +#Generate certificate & modify Nginx configuration sudo certbot --nginx -# 根据指示进行操作 -# 重启 Nginx +#follow instructions +# restart nginx sudo service nginx restart ``` -### 手动部署 -1. 从 [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) 下载可执行文件或者从源码编译: +### Manual deployment +1. 从 [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) Download the executable or compile from source: ```shell git clone https://github.com/songquanpeng/one-api.git - # 构建前端 + # Build the front end cd one-api/web npm install npm run build - # 构建后端 + # build backend cd .. go mod download go build -ldflags "-s -w" -o one-api ```` -2. 运行: +2. run: ```shell chmod u+x one-api ./one-api --port 3000 --log-dir ./logs ``` -3. 访问 [http://localhost:3000/](http://localhost:3000/) 并登录。初始账号用户名为 `root`,密码为 `123456`。 +3. Visit [http://localhost:3000/](http://localhost:3000/) and log in. The initial account username is `root`, and the password is `123456`. -更加详细的部署教程[参见此处](https://iamazing.cn/page/how-to-deploy-a-website)。 +A more detailed deployment tutorial [see here](https://iamazing.cn/page/how-to-deploy-a-website). +### Multi-machine deployment +1. All servers `SESSION_SECRET` set the same value. +2. `SQL_DSN` must be set, use the MySQL database instead of SQLite, please configure the synchronization of the main and standby databases by yourself. +3. All slave servers must set `SYNC_FREQUENCY` to periodically synchronize configuration from the database. +4. The slave server can optionally set `FRONTEND_BASE_URL` to redirect page requests to the master server. -### 多机部署 -1. 所有服务器 `SESSION_SECRET` 设置一样的值。 -2. 必须设置 `SQL_DSN`,使用 MySQL 数据库而非 SQLite,请自行配置主备数据库同步。 -3. 所有从服务器必须设置 `SYNC_FREQUENCY`,以定期从数据库同步配置。 -4. 从服务器可以选择设置 `FRONTEND_BASE_URL`,以重定向页面请求到主服务器。 +For details on how to use environment variables, see [here](#environment variables). -环境变量的具体使用方法详见[此处](#环境变量)。 +## configuration +The system itself works out of the box. -## 配置 -系统本身开箱即用。 +You can configure it by setting environment variables or command line parameters. -你可以通过设置环境变量或者命令行参数进行配置。 +After the system starts, use `root` user to log in to the system and do further configuration. -等到系统启动后,使用 `root` 用户登录系统并做进一步的配置。 +## How to use +Add your API Key in the `Channels` page, and then add an access token in the `Tokens` page. -## 使用方式 -在`渠道`页面中添加你的 API Key,之后在`令牌`页面中新增一个访问令牌。 +Then you can use your token to access the One API in the same way as [OpenAI API](https://platform.openai.com/docs/api-reference/introduction). -之后就可以使用你的令牌访问 One API 了,使用方式与 [OpenAI API](https://platform.openai.com/docs/api-reference/introduction) 一致。 +You can specify which channel to use to process this request by adding the channel ID after the token, for example: `Authorization: Bearer ONE_API_KEY-CHANNEL_ID`. +Note that a token created by an admin user is required to specify a channel ID. -可以通过在令牌后面添加渠道 ID 的方式指定使用哪一个渠道处理本次请求,例如:`Authorization: Bearer ONE_API_KEY-CHANNEL_ID`。 -注意,需要是管理员用户创建的令牌才能指定渠道 ID。 +If not added, multiple channels will be used in a load balancing manner. -不加的话将会使用负载均衡的方式使用多个渠道。 +### Environment variables +1. `REDIS_CONN_STRING`: After setting, Redis will be used as the storage for request frequency limit instead of memory storage. + + Example: `REDIS_CONN_STRING=redis://default:redispw@localhost:49153` +2. `SESSION_SECRET`: After setting, a fixed session key will be used, so that the logged-in user's cookie will still be valid after the system restarts. + + Example: `SESSION_SECRET=random_string` +3. `SQL_DSN`: After setting, the specified database will be used instead of SQLite. + + Example: `SQL_DSN=root:123456@tcp(localhost:3306)/one-api` +4. `FRONTEND_BASE_URL`: After setting, the specified front-end address will be used instead of the back-end address. + + Example: `FRONTEND_BASE_URL=https://openai.justsong.cn` +5. `SYNC_FREQUENCY`: After setting, the configuration will be periodically synchronized with the database, in seconds, if not set, no synchronization will be performed. + + Example: `SYNC_FREQUENCY=60` -### 环境变量 -1. `REDIS_CONN_STRING`:设置之后将使用 Redis 作为请求频率限制的存储,而非使用内存存储。 - + 例子:`REDIS_CONN_STRING=redis://default:redispw@localhost:49153` -2. `SESSION_SECRET`:设置之后将使用固定的会话密钥,这样系统重新启动后已登录用户的 cookie 将依旧有效。 - + 例子:`SESSION_SECRET=random_string` -3. `SQL_DSN`:设置之后将使用指定数据库而非 SQLite。 - + 例子:`SQL_DSN=root:123456@tcp(localhost:3306)/one-api` -4. `FRONTEND_BASE_URL`:设置之后将使用指定的前端地址,而非后端地址。 - + 例子:`FRONTEND_BASE_URL=https://openai.justsong.cn` -5. `SYNC_FREQUENCY`:设置之后将定期与数据库同步配置,单位为秒,未设置则不进行同步。 - + 例子:`SYNC_FREQUENCY=60` +### Command Line Arguments +1. `--port