ci: fix Dockerfile & ci

- Add support for base64 encoded image in OpenAI's image_url

Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>

.github/workflows/linux-release.yml

@@ -7,6 +7,11 @@ on:
     tags:
       - '*'
       - '!*-alpha*'
+  workflow_dispatch:
+    inputs:
+      name:
+        description: 'reason'
+        required: false
 jobs:
   release:
     runs-on: ubuntu-latest
@@ -18,13 +23,13 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 16
-      - name: Build Frontend
+      - name: Build Frontend (theme default)
         env:
           CI: ""
         run: |
           cd web
-          npm install
-          REACT_APP_VERSION=$(git describe --tags) npm run build
+          git describe --tags > VERSION
+          REACT_APP_VERSION=$(git describe --tags) chmod u+x ./build.sh && ./build.sh
           cd ..
       - name: Set up Go
         uses: actions/setup-go@v3

.github/workflows/macos-release.yml

@@ -7,6 +7,11 @@ on:
     tags:
       - '*'
       - '!*-alpha*'
+  workflow_dispatch:
+    inputs:
+      name:
+        description: 'reason'
+        required: false
 jobs:
   release:
     runs-on: macos-latest
@@ -18,13 +23,13 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 16
-      - name: Build Frontend
+      - name: Build Frontend (theme default)
         env:
           CI: ""
         run: |
           cd web
-          npm install
-          REACT_APP_VERSION=$(git describe --tags) npm run build
+          git describe --tags > VERSION
+          REACT_APP_VERSION=$(git describe --tags) chmod u+x ./build.sh && ./build.sh
           cd ..
       - name: Set up Go
         uses: actions/setup-go@v3

.github/workflows/windows-release.yml

@@ -7,6 +7,11 @@ on:
     tags:
       - '*'
       - '!*-alpha*'
+  workflow_dispatch:
+    inputs:
+      name:
+        description: 'reason'
+        required: false
 jobs:
   release:
     runs-on: windows-latest
@@ -21,14 +26,14 @@ jobs:
       - uses: actions/setup-node@v3
         with:
           node-version: 16
-      - name: Build Frontend
+      - name: Build Frontend (theme default)
         env:
           CI: ""
         run: |
-          cd web
+          cd web/default
           npm install
           REACT_APP_VERSION=$(git describe --tags) npm run build
-          cd ..
+          cd ../..
       - name: Set up Go
         uses: actions/setup-go@v3
         with:

.gitignore

@@ -5,4 +5,5 @@ upload
 *.db
 build
 *.db-journal
-logs
+logs
+data

Dockerfile

@@ -1,11 +1,9 @@
 FROM node:16 as builder
 
 WORKDIR /build
-COPY web/package.json .
-RUN npm install
 COPY ./web .
 COPY ./VERSION .
-RUN DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build
+RUN chmod u+x ./build.sh && ./build.sh
 
 FROM golang AS builder2
 

README.en.md

@@ -60,7 +60,7 @@ _✨ Access all LLM through the standard OpenAI API format, easy to deploy & use
 1. Support for multiple large models:
    + [x] [OpenAI ChatGPT Series Models](https://platform.openai.com/docs/guides/gpt/chat-completions-api) (Supports [Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference))
    + [x] [Anthropic Claude Series Models](https://anthropic.com)
-   + [x] [Google PaLM2 Series Models](https://developers.generativeai.google)
+   + [x] [Google PaLM2 and Gemini Series Models](https://developers.generativeai.google)
    + [x] [Baidu Wenxin Yiyuan Series Models](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
    + [x] [Alibaba Tongyi Qianwen Series Models](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [Zhipu ChatGLM Series Models](https://bigmodel.cn)
@@ -189,6 +189,8 @@ If you encounter a blank page after deployment, refer to [#97](https://github.co
 
 > Zeabur's servers are located overseas, automatically solving network issues, and the free quota is sufficient for personal usage.
 
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/templates/7Q0KO3)
+
 1. First, fork the code.
 2. Go to [Zeabur](https://zeabur.com?referralCode=songquanpeng), log in, and enter the console.
 3. Create a new project. In Service -> Add Service, select Marketplace, and choose MySQL. Note down the connection parameters (username, password, address, and port).

README.ja.md

@@ -60,7 +60,7 @@ _✨ 標準的な OpenAI API フォーマットを通じてすべての LLM に
 1. 複数の大型モデルをサポート:
    + [x] [OpenAI ChatGPT シリーズモデル](https://platform.openai.com/docs/guides/gpt/chat-completions-api) ([Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference) をサポート)
    + [x] [Anthropic Claude シリーズモデル](https://anthropic.com)
-   + [x] [Google PaLM2 シリーズモデル](https://developers.generativeai.google)
+   + [x] [Google PaLM2/Gemini シリーズモデル](https://developers.generativeai.google)
    + [x] [Baidu Wenxin Yiyuan シリーズモデル](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
    + [x] [Alibaba Tongyi Qianwen シリーズモデル](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [Zhipu ChatGLM シリーズモデル](https://bigmodel.cn)
@@ -190,6 +190,8 @@ Please refer to the [environment variables](#environment-variables) section for
 
 > Zeabur のサーバーは海外にあるため、ネットワークの問題は自動的に解決されます。
 
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/templates/7Q0KO3)
+
 1. まず、コードをフォークする。
 2. [Zeabur](https://zeabur.com?referralCode=songquanpeng) にアクセスしてログインし、コンソールに入る。
 3. 新しいプロジェクトを作成します。Service -> Add ServiceでMarketplace を選択し、MySQL を選択する。接続パラメータ（ユーザー名、パスワード、アドレス、ポート）をメモします。

README.md

@@ -51,31 +51,29 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
   <a href="https://iamazing.cn/page/reward">赞赏支持</a>
 </p>
 
-> **Note**
+> [!NOTE]
 > 本项目为开源项目，使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
 > 
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
-> **Warning**
+> [!WARNING]
 > 使用 Docker 拉取的最新镜像可能是 `alpha` 版本，如果追求稳定性请手动指定版本。
 
+> [!WARNING]
+> 使用 root 用户初次登录系统后，务必修改默认密码 `123456`！
+
 ## 功能
 1. 支持多种大模型：
    + [x] [OpenAI ChatGPT 系列模型](https://platform.openai.com/docs/guides/gpt/chat-completions-api)（支持 [Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference)）
    + [x] [Anthropic Claude 系列模型](https://anthropic.com)
-   + [x] [Google PaLM2 系列模型](https://developers.generativeai.google)
+   + [x] [Google PaLM2/Gemini 系列模型](https://developers.generativeai.google)
    + [x] [百度文心一言系列模型](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
    + [x] [阿里通义千问系列模型](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [讯飞星火认知大模型](https://www.xfyun.cn/doc/spark/Web.html)
    + [x] [智谱 ChatGLM 系列模型](https://bigmodel.cn)
    + [x] [360 智脑](https://ai.360.cn)
-2. 支持配置镜像以及众多第三方代理服务：
-   + [x] [OpenAI-SB](https://openai-sb.com)
-   + [x] [CloseAI](https://console.closeai-asia.com/r/2412)
-   + [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] 自定义渠道：例如各种未收录的第三方代理服务
+   + [x] [腾讯混元大模型](https://cloud.tencent.com/document/product/1729)
+2. 支持配置镜像以及众多[第三方代理服务](https://iamazing.cn/page/openai-api-third-party-services)。
 3. 支持通过**负载均衡**的方式访问多个渠道。
 4. 支持 **stream 模式**，可以通过流式传输实现打字机效果。
 5. 支持**多机部署**，[详见此处](#多机部署)。
@@ -88,26 +86,34 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
 12. 支持**用户邀请奖励**。
 13. 支持以美元为单位显示额度。
 14. 支持发布公告，设置充值链接，设置新用户初始额度。
-15. 支持模型映射，重定向用户的请求模型。
+15. 支持模型映射，重定向用户的请求模型，如无必要请不要设置，设置之后会导致请求体被重新构造而非直接透传，会导致部分还未正式支持的字段无法传递成功。
 16. 支持失败自动重试。
 17. 支持绘图接口。
-18. 支持丰富的**自定义**设置，
+18. 支持 [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/providers/openai/)，渠道设置的代理部分填写 `https://gateway.ai.cloudflare.com/v1/ACCOUNT_TAG/GATEWAY/openai` 即可。
+19. 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。
-19. 支持通过系统访问令牌访问管理 API。
-20. 支持 Cloudflare Turnstile 用户校验。
-21. 支持用户管理，支持**多种用户登录注册方式**：
+20. 支持通过系统访问令牌访问管理 API（bearer token，用以替代 cookie，你可以自行抓包来查看 API 的用法）。
+21. 支持 Cloudflare Turnstile 用户校验。
+22. 支持用户管理，支持**多种用户登录注册方式**：
     + 邮箱登录注册（支持注册邮箱白名单）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)）。
+23. 支持主题切换，设置环境变量 `THEME` 即可，默认为 `default`，欢迎 PR 更多主题，具体参考[此处](./web/README.md)。
 
 ## 部署
 ### 基于 Docker 进行部署
-部署命令：`docker run --name one-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/one-api:/data justsong/one-api`
+```shell
+# 使用 SQLite 的部署命令：
+docker run --name one-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/one-api:/data justsong/one-api
+# 使用 MySQL 的部署命令，在上面的基础上添加 `-e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"`，请自行修改数据库连接参数，不清楚如何修改请参见下面环境变量一节。
+# 例如：
+docker run --name one-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/one-api:/data justsong/one-api
+```
 
 其中，`-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。
+数据和日志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。
 
 如果启动失败，请添加 `--privileged=true`，具体参考 https://github.com/songquanpeng/one-api/issues/482 。
 
@@ -149,6 +155,19 @@ sudo service nginx restart
 
 初始账号用户名为 `root`，密码为 `123456`。
 
+
+### 基于 Docker Compose 进行部署
+
+> 仅启动方式不同，参数设置不变，请参考基于 Docker 部署部分
+
+```shell
+# 目前支持 MySQL 启动，数据存储在 ./data/mysql 文件夹内
+docker-compose up -d
+
+# 查看部署状态
+docker-compose ps
+```
+
 ### 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：
    ```shell
@@ -236,7 +255,9 @@ docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://ope
 <summary><strong>部署到 Zeabur</strong></summary>
 <div>
 
-> Zeabur 的服务器在国外，自动解决了网络的问题，同时免费的额度也足够个人使用。
+> Zeabur 的服务器在国外，自动解决了网络的问题，同时免费的额度也足够个人使用
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/templates/7Q0KO3)
 
 1. 首先 fork 一份代码。
 2. 进入 [Zeabur](https://zeabur.com?referralCode=songquanpeng)，登录，进入控制台。
@@ -251,6 +272,17 @@ docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://ope
 </div>
 </details>
 
+<details>
+<summary><strong>部署到 Render</strong></summary>
+<div>
+
+> Render 提供免费额度，绑卡后可以进一步提升额度
+
+Render 可以直接部署 docker 镜像，不需要 fork 仓库：https://dashboard.render.com
+
+</div>
+</details>
+
 ## 配置
 系统本身开箱即用。
 
@@ -269,13 +301,20 @@ docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://ope
 
 注意，具体的 API Base 的格式取决于你所使用的客户端。
 
+例如对于 OpenAI 的官方库：
+```bash
+OPENAI_API_KEY="sk-xxxxxx"
+OPENAI_API_BASE="https://<HOST>:<PORT>/v1" 
+```
+
 ```mermaid
 graph LR
     A(用户)
-    A --->|请求| B(One API)
+    A --->|使用 One API 分发的 key 进行请求| B(One API)
     B -->|中继请求| C(OpenAI)
     B -->|中继请求| D(Azure)
-    B -->|中继请求| E(其他下游渠道)
+    B -->|中继请求| E(其他 OpenAI API 格式下游渠道)
+    B -->|中继并修改请求体和返回体| F(非 OpenAI API 格式下游渠道)
 ```
 
 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`。
@@ -303,24 +342,32 @@ graph LR
      + `SQL_CONN_MAX_LIFETIME`：连接的最大生命周期，默认为 `60`，单位分钟。
 4. `FRONTEND_BASE_URL`：设置之后将重定向页面请求到指定的地址，仅限从服务器设置。
    + 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。
+5. `MEMORY_CACHE_ENABLED`：启用内存缓存，会导致用户额度的更新存在一定的延迟，可选值为 `true` 和 `false`，未设置则默认为 `false`。
+   + 例子：`MEMORY_CACHE_ENABLED=true`
+6. `SYNC_FREQUENCY`：在启用缓存的情况下与数据库同步配置的频率，单位为秒，默认为 `600` 秒。
    + 例子：`SYNC_FREQUENCY=60`
-6. `NODE_TYPE`：设置之后将指定节点类型，可选值为 `master` 和 `slave`，未设置则默认为 `master`。
+7. `NODE_TYPE`：设置之后将指定节点类型，可选值为 `master` 和 `slave`，未设置则默认为 `master`。
    + 例子：`NODE_TYPE=slave`
-7. `CHANNEL_UPDATE_FREQUENCY`：设置之后将定期更新渠道余额，单位为分钟，未设置则不进行更新。
+8. `CHANNEL_UPDATE_FREQUENCY`：设置之后将定期更新渠道余额，单位为分钟，未设置则不进行更新。
    + 例子：`CHANNEL_UPDATE_FREQUENCY=1440`
-8. `CHANNEL_TEST_FREQUENCY`：设置之后将定期检查渠道，单位为分钟，未设置则不进行检查。
+9. `CHANNEL_TEST_FREQUENCY`：设置之后将定期检查渠道，单位为分钟，未设置则不进行检查。
    + 例子：`CHANNEL_TEST_FREQUENCY=1440`
-9. `POLLING_INTERVAL`：批量更新渠道余额以及测试可用性时的请求间隔，单位为秒，默认无间隔。
-   + 例子：`POLLING_INTERVAL=5`
-10. `BATCH_UPDATE_ENABLED`：启用数据库批量更新聚合，会导致用户额度的更新存在一定的延迟可选值为 `true` 和 `false`，未设置则默认为 `false`。
+10. `POLLING_INTERVAL`：批量更新渠道余额以及测试可用性时的请求间隔，单位为秒，默认无间隔。
+    + 例子：`POLLING_INTERVAL=5`
+11. `BATCH_UPDATE_ENABLED`：启用数据库批量更新聚合，会导致用户额度的更新存在一定的延迟可选值为 `true` 和 `false`，未设置则默认为 `false`。
     + 例子：`BATCH_UPDATE_ENABLED=true`
     + 如果你遇到了数据库连接数过多的问题，可以尝试启用该选项。
-11. `BATCH_UPDATE_INTERVAL=5`：批量更新聚合的时间间隔，单位为秒，默认为 `5`。
+12. `BATCH_UPDATE_INTERVAL=5`：批量更新聚合的时间间隔，单位为秒，默认为 `5`。
     + 例子：`BATCH_UPDATE_INTERVAL=5`
-12. 请求频率限制：
+13. 请求频率限制：
     + `GLOBAL_API_RATE_LIMIT`：全局 API 速率限制（除中继请求外），单 ip 三分钟内的最大请求数，默认为 `180`。
     + `GLOBAL_WEB_RATE_LIMIT`：全局 Web 速率限制，单 ip 三分钟内的最大请求数，默认为 `60`。
+14. 编码器缓存设置：
+    + `TIKTOKEN_CACHE_DIR`：默认程序启动时会联网下载一些通用的词元的编码，如：`gpt-3.5-turbo`，在一些网络环境不稳定，或者离线情况，可能会导致启动有问题，可以配置此目录缓存数据，可迁移到离线环境。
+    + `DATA_GYM_CACHE_DIR`：目前该配置作用与 `TIKTOKEN_CACHE_DIR` 一致，但是优先级没有它高。
+15. `RELAY_TIMEOUT`：中继超时设置，单位为秒，默认不设置超时时间。
+16. `SQLITE_BUSY_TIMEOUT`：SQLite 锁等待超时设置，单位为毫秒，默认 `3000`。
+17. `GEMINI_SAFETY_SETTING`：Gemini 的安全设置，默认 `BLOCK_NONE`。
 
 ### 命令行参数
 1. `--port <port_number>`: 指定服务器监听的端口号，默认为 `3000`。
@@ -360,6 +407,12 @@ https://openai.justsong.cn
    + 检查是否启用了 HTTPS，浏览器会拦截 HTTPS 域名下的 HTTP 请求。
 6. 报错：`当前分组负载已饱和，请稍后再试`
    + 上游通道 429 了。
+7. 升级之后我的数据会丢失吗？
+   + 如果使用 MySQL，不会。
+   + 如果使用 SQLite，需要按照我所给的部署命令挂载 volume 持久化 one-api.db 数据库文件，否则容器重启后数据会丢失。
+8. 升级之前数据库需要做变更吗？
+   + 一般情况下不需要，系统将在初始化的时候自动调整。
+   + 如果需要的话，我会在更新日志中说明，并给出脚本。
 
 ## 相关项目
 * [FastGPT](https://github.com/labring/FastGPT): 基于 LLM 大语言模型的知识库问答系统

common/constants.go

@@ -21,12 +21,9 @@ var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 
-var UsingSQLite = false
-
 // Any options with "Secret", "Token" in its key won't be return by GetOptions
 
 var SessionSecret = uuid.New().String()
-var SQLitePath = "one-api.db"
 
 var OptionMap map[string]string
 var OptionMapRWMutex sync.RWMutex
@@ -56,6 +53,7 @@ var EmailDomainWhitelist = []string{
 }
 
 var DebugEnabled = os.Getenv("DEBUG") == "true"
+var MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
 
 var LogConsumeEnabled = true
 
@@ -80,6 +78,7 @@ var QuotaForInviter = 0
 var QuotaForInvitee = 0
 var ChannelDisableThreshold = 5.0
 var AutomaticDisableChannelEnabled = false
+var AutomaticEnableChannelEnabled = false
 var QuotaRemindThreshold = 1000
 var PreConsumedQuota = 500
 var ApproximateTokenEnabled = false
@@ -92,11 +91,17 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = 10 * 60 // unit is second, will be overwritten by SYNC_FREQUENCY
+var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 10*60) // unit is second
 
 var BatchUpdateEnabled = false
 var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
 
+var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
+
+var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+
+var Theme = GetOrDefaultString("THEME", "default")
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )
@@ -155,9 +160,10 @@ const (
 )
 
 const (
-	ChannelStatusUnknown  = 0
-	ChannelStatusEnabled  = 1 // don't use 0, 0 is the default value!
-	ChannelStatusDisabled = 2 // also don't use 0
+	ChannelStatusUnknown          = 0
+	ChannelStatusEnabled          = 1 // don't use 0, 0 is the default value!
+	ChannelStatusManuallyDisabled = 2 // also don't use 0
+	ChannelStatusAutoDisabled     = 3
 )
 
 const (
@@ -184,30 +190,34 @@ const (
 	ChannelTypeOpenRouter     = 20
 	ChannelTypeAIProxyLibrary = 21
 	ChannelTypeFastGPT        = 22
+	ChannelTypeTencent        = 23
+	ChannelTypeGemini         = 24
 )
 
 var ChannelBaseURLs = []string{
-	"",                                // 0
-	"https://api.openai.com",          // 1
-	"https://oa.api2d.net",            // 2
-	"",                                // 3
-	"https://api.closeai-proxy.xyz",   // 4
-	"https://api.openai-sb.com",       // 5
-	"https://api.openaimax.com",       // 6
-	"https://api.ohmygpt.com",         // 7
-	"",                                // 8
-	"https://api.caipacity.com",       // 9
-	"https://api.aiproxy.io",          // 10
-	"",                                // 11
-	"https://api.api2gpt.com",         // 12
-	"https://api.aigc2d.com",          // 13
-	"https://api.anthropic.com",       // 14
-	"https://aip.baidubce.com",        // 15
-	"https://open.bigmodel.cn",        // 16
-	"https://dashscope.aliyuncs.com",  // 17
-	"",                                // 18
-	"https://ai.360.cn",               // 19
-	"https://openrouter.ai/api",       // 20
-	"https://api.aiproxy.io",          // 21
-	"https://fastgpt.run/api/openapi", // 22
+	"",                                  // 0
+	"https://api.openai.com",            // 1
+	"https://oa.api2d.net",              // 2
+	"",                                  // 3
+	"https://api.closeai-proxy.xyz",     // 4
+	"https://api.openai-sb.com",         // 5
+	"https://api.openaimax.com",         // 6
+	"https://api.ohmygpt.com",           // 7
+	"",                                  // 8
+	"https://api.caipacity.com",         // 9
+	"https://api.aiproxy.io",            // 10
+	"",                                  // 11
+	"https://api.api2gpt.com",           // 12
+	"https://api.aigc2d.com",            // 13
+	"https://api.anthropic.com",         // 14
+	"https://aip.baidubce.com",          // 15
+	"https://open.bigmodel.cn",          // 16
+	"https://dashscope.aliyuncs.com",    // 17
+	"",                                  // 18
+	"https://ai.360.cn",                 // 19
+	"https://openrouter.ai/api",         // 20
+	"https://api.aiproxy.io",            // 21
+	"https://fastgpt.run/api/openapi",   // 22
+	"https://hunyuan.cloud.tencent.com", //23
+	"",                                  //24
 }

common/database.go

@@ -0,0 +1,7 @@
+package common
+
+var UsingSQLite = false
+var UsingPostgreSQL = false
+
+var SQLitePath = "one-api.db"
+var SQLiteBusyTimeout = GetOrDefault("SQLITE_BUSY_TIMEOUT", 3000)

common/email.go

@@ -1,11 +1,13 @@
 package common
 
 import (
+	"crypto/rand"
 	"crypto/tls"
 	"encoding/base64"
 	"fmt"
 	"net/smtp"
 	"strings"
+	"time"
 )
 
 func SendEmail(subject string, receiver string, content string) error {
@@ -13,15 +15,32 @@ func SendEmail(subject string, receiver string, content string) error {
 		SMTPFrom = SMTPAccount
 	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
+
+	// Extract domain from SMTPFrom
+	parts := strings.Split(SMTPFrom, "@")
+	var domain string
+	if len(parts) > 1 {
+		domain = parts[1]
+	}
+	// Generate a unique Message-ID
+	buf := make([]byte, 16)
+	_, err := rand.Read(buf)
+	if err != nil {
+		return err
+	}
+	messageId := fmt.Sprintf("<%x@%s>", buf, domain)
+
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
+		"Message-ID: %s\r\n"+ // add Message-ID header to avoid being treated as spam, RFC 5322
+		"Date: %s\r\n"+
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, content))
+		receiver, SystemName, SMTPFrom, encodedSubject, messageId, time.Now().Format(time.RFC1123Z), content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
-	var err error
+
 	if SMTPPort == 465 {
 		tlsConfig := &tls.Config{
 			InsecureSkipVerify: true,

common/gin.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"github.com/gin-gonic/gin"
 	"io"
+	"strings"
 )
 
 func UnmarshalBodyReusable(c *gin.Context, v any) error {
@@ -16,7 +17,13 @@ func UnmarshalBodyReusable(c *gin.Context, v any) error {
 	if err != nil {
 		return err
 	}
-	err = json.Unmarshal(requestBody, &v)
+	contentType := c.Request.Header.Get("Content-Type")
+	if strings.HasPrefix(contentType, "application/json") {
+		err = json.Unmarshal(requestBody, &v)
+	} else {
+		// skip for now
+		// TODO: someday non json request have variant model, we will need to implementation this
+	}
 	if err != nil {
 		return err
 	}

common/image/image.go

@@ -0,0 +1,111 @@
+package image
+
+import (
+	"bytes"
+	"encoding/base64"
+	"image"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
+	"net/http"
+	"regexp"
+	"strings"
+	"sync"
+
+	_ "golang.org/x/image/webp"
+)
+
+// Regex to match data URL pattern
+var	dataURLPattern = regexp.MustCompile(`data:image/([^;]+);base64,(.*)`)
+
+func IsImageUrl(url string) (bool, error) {
+	resp, err := http.Head(url)
+	if err != nil {
+		return false, err
+	}
+	if !strings.HasPrefix(resp.Header.Get("Content-Type"), "image/") {
+		return false, nil
+	}
+	return true, nil
+}
+
+func GetImageSizeFromUrl(url string) (width int, height int, err error) {
+	isImage, err := IsImageUrl(url)
+	if !isImage {
+		return
+	}
+	resp, err := http.Get(url)
+	if err != nil {
+		return
+	}
+	defer resp.Body.Close()
+	img, _, err := image.DecodeConfig(resp.Body)
+	if err != nil {
+		return
+	}
+	return img.Width, img.Height, nil
+}
+
+func GetImageFromUrl(url string) (mimeType string, data string, err error) {
+	// Check if the URL is a data URL
+	matches := dataURLPattern.FindStringSubmatch(url)
+	if len(matches) == 3 {
+		// URL is a data URL
+		mimeType = "image/" + matches[1]
+		data = matches[2]
+		return
+	}
+
+	isImage, err := IsImageUrl(url)
+	if !isImage {
+		return
+	}
+	resp, err := http.Get(url)
+	if err != nil {
+		return
+	}
+	defer resp.Body.Close()
+	buffer := bytes.NewBuffer(nil)
+	_, err = buffer.ReadFrom(resp.Body)
+	if err != nil {
+		return
+	}
+	mimeType = resp.Header.Get("Content-Type")
+	data = base64.StdEncoding.EncodeToString(buffer.Bytes())
+	return
+}
+
+var (
+	reg = regexp.MustCompile(`data:image/([^;]+);base64,`)
+)
+
+var readerPool = sync.Pool{
+	New: func() interface{} {
+		return &bytes.Reader{}
+	},
+}
+
+func GetImageSizeFromBase64(encoded string) (width int, height int, err error) {
+	decoded, err := base64.StdEncoding.DecodeString(reg.ReplaceAllString(encoded, ""))
+	if err != nil {
+		return 0, 0, err
+	}
+
+	reader := readerPool.Get().(*bytes.Reader)
+	defer readerPool.Put(reader)
+	reader.Reset(decoded)
+
+	img, _, err := image.DecodeConfig(reader)
+	if err != nil {
+		return 0, 0, err
+	}
+
+	return img.Width, img.Height, nil
+}
+
+func GetImageSize(image string) (width int, height int, err error) {
+	if strings.HasPrefix(image, "data:image/") {
+		return GetImageSizeFromBase64(image)
+	}
+	return GetImageSizeFromUrl(image)
+}

common/image/image_test.go

@@ -0,0 +1,171 @@
+package image_test
+
+import (
+	"encoding/base64"
+	"image"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"testing"
+
+	img "one-api/common/image"
+
+	"github.com/stretchr/testify/assert"
+	_ "golang.org/x/image/webp"
+)
+
+type CountingReader struct {
+	reader    io.Reader
+	BytesRead int
+}
+
+func (r *CountingReader) Read(p []byte) (n int, err error) {
+	n, err = r.reader.Read(p)
+	r.BytesRead += n
+	return n, err
+}
+
+var (
+	cases = []struct {
+		url    string
+		format string
+		width  int
+		height int
+	}{
+		{"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", "jpeg", 2560, 1669},
+		{"https://upload.wikimedia.org/wikipedia/commons/9/97/Basshunter_live_performances.png", "png", 4500, 2592},
+		{"https://upload.wikimedia.org/wikipedia/commons/c/c6/TO_THE_ONE_SOMETHINGNESS.webp", "webp", 984, 985},
+		{"https://upload.wikimedia.org/wikipedia/commons/d/d0/01_Das_Sandberg-Modell.gif", "gif", 1917, 1533},
+		{"https://upload.wikimedia.org/wikipedia/commons/6/62/102Cervus.jpg", "jpeg", 270, 230},
+	}
+)
+
+func TestDecode(t *testing.T) {
+	// Bytes read: varies sometimes
+	// jpeg: 1063892
+	// png: 294462
+	// webp: 99529
+	// gif: 956153
+	// jpeg#01: 32805
+	for _, c := range cases {
+		t.Run("Decode:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			reader := &CountingReader{reader: resp.Body}
+			img, format, err := image.Decode(reader)
+			assert.NoError(t, err)
+			size := img.Bounds().Size()
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, size.X)
+			assert.Equal(t, c.height, size.Y)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+
+	// Bytes read:
+	// jpeg: 4096
+	// png: 4096
+	// webp: 4096
+	// gif: 4096
+	// jpeg#01: 4096
+	for _, c := range cases {
+		t.Run("DecodeConfig:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			reader := &CountingReader{reader: resp.Body}
+			config, format, err := image.DecodeConfig(reader)
+			assert.NoError(t, err)
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, config.Width)
+			assert.Equal(t, c.height, config.Height)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+}
+
+func TestBase64(t *testing.T) {
+	// Bytes read:
+	// jpeg: 1063892
+	// png: 294462
+	// webp: 99072
+	// gif: 953856
+	// jpeg#01: 32805
+	for _, c := range cases {
+		t.Run("Decode:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			data, err := io.ReadAll(resp.Body)
+			assert.NoError(t, err)
+			encoded := base64.StdEncoding.EncodeToString(data)
+			body := base64.NewDecoder(base64.StdEncoding, strings.NewReader(encoded))
+			reader := &CountingReader{reader: body}
+			img, format, err := image.Decode(reader)
+			assert.NoError(t, err)
+			size := img.Bounds().Size()
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, size.X)
+			assert.Equal(t, c.height, size.Y)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+
+	// Bytes read:
+	// jpeg: 1536
+	// png: 768
+	// webp: 768
+	// gif: 1536
+	// jpeg#01: 3840
+	for _, c := range cases {
+		t.Run("DecodeConfig:"+c.format, func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			data, err := io.ReadAll(resp.Body)
+			assert.NoError(t, err)
+			encoded := base64.StdEncoding.EncodeToString(data)
+			body := base64.NewDecoder(base64.StdEncoding, strings.NewReader(encoded))
+			reader := &CountingReader{reader: body}
+			config, format, err := image.DecodeConfig(reader)
+			assert.NoError(t, err)
+			assert.Equal(t, c.format, format)
+			assert.Equal(t, c.width, config.Width)
+			assert.Equal(t, c.height, config.Height)
+			t.Logf("Bytes read: %d", reader.BytesRead)
+		})
+	}
+}
+
+func TestGetImageSize(t *testing.T) {
+	for i, c := range cases {
+		t.Run("Decode:"+strconv.Itoa(i), func(t *testing.T) {
+			width, height, err := img.GetImageSize(c.url)
+			assert.NoError(t, err)
+			assert.Equal(t, c.width, width)
+			assert.Equal(t, c.height, height)
+		})
+	}
+}
+
+func TestGetImageSizeFromBase64(t *testing.T) {
+	for i, c := range cases {
+		t.Run("Decode:"+strconv.Itoa(i), func(t *testing.T) {
+			resp, err := http.Get(c.url)
+			assert.NoError(t, err)
+			defer resp.Body.Close()
+			data, err := io.ReadAll(resp.Body)
+			assert.NoError(t, err)
+			encoded := base64.StdEncoding.EncodeToString(data)
+			width, height, err := img.GetImageSizeFromBase64(encoded)
+			assert.NoError(t, err)
+			assert.Equal(t, c.width, width)
+			assert.Equal(t, c.height, height)
+		})
+	}
+}

common/init.go

@@ -36,7 +36,11 @@ func init() {
 	}
 
 	if os.Getenv("SESSION_SECRET") != "" {
-		SessionSecret = os.Getenv("SESSION_SECRET")
+		if os.Getenv("SESSION_SECRET") == "random_string" {
+			SysError("SESSION_SECRET is set to an example value, please change it to a random string.")
+		} else {
+			SessionSecret = os.Getenv("SESSION_SECRET")
+		}
 	}
 	if os.Getenv("SQLITE_PATH") != "" {
 		SQLitePath = os.Getenv("SQLITE_PATH")

common/model-ratio.go

@@ -3,8 +3,32 @@ package common
 import (
 	"encoding/json"
 	"strings"
+	"time"
 )
 
+var DalleSizeRatios = map[string]map[string]float64{
+	"dall-e-2": {
+		"256x256":   1,
+		"512x512":   1.125,
+		"1024x1024": 1.25,
+	},
+	"dall-e-3": {
+		"1024x1024": 1,
+		"1024x1792": 2,
+		"1792x1024": 2,
+	},
+}
+
+var DalleGenerationImageAmounts = map[string][2]int{
+	"dall-e-2": {1, 10},
+	"dall-e-3": {1, 1}, // OpenAI allows n=1 currently.
+}
+
+var DalleImagePromptLengthLimitations = map[string]int{
+	"dall-e-2": 1000,
+	"dall-e-3": 4000,
+}
+
 // ModelRatio
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
@@ -19,11 +43,17 @@ var ModelRatio = map[string]float64{
 	"gpt-4-32k":                 30,
 	"gpt-4-32k-0314":            30,
 	"gpt-4-32k-0613":            30,
+	"gpt-4-1106-preview":        5,    // $0.01 / 1K tokens
+	"gpt-4-vision-preview":      5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":             0.75, // $0.0015 / 1K tokens
 	"gpt-3.5-turbo-0301":        0.75,
 	"gpt-3.5-turbo-0613":        0.75,
 	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
 	"gpt-3.5-turbo-16k-0613":    1.5,
+	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":        0.5,  // $0.001 / 1K tokens
+	"davinci-002":               1,    // $0.002 / 1K tokens
+	"babbage-002":               0.2,  // $0.0004 / 1K tokens
 	"text-ada-001":              0.2,
 	"text-babbage-001":          0.25,
 	"text-curie-001":            1,
@@ -31,7 +61,11 @@ var ModelRatio = map[string]float64{
 	"text-davinci-003":          10,
 	"text-davinci-edit-001":     10,
 	"code-davinci-edit-001":     10,
-	"whisper-1":                 15, // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"whisper-1":                 15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"tts-1":                     7.5, // $0.015 / 1K characters
+	"tts-1-1106":                7.5,
+	"tts-1-hd":                  15, // $0.030 / 1K characters
+	"tts-1-hd-1106":             15,
 	"davinci":                   10,
 	"curie":                     10,
 	"babbage":                   10,
@@ -40,25 +74,34 @@ var ModelRatio = map[string]float64{
 	"text-search-ada-doc-001":   10,
 	"text-moderation-stable":    0.1,
 	"text-moderation-latest":    0.1,
-	"dall-e":                    8,
+	"dall-e-2":                  8,      // $0.016 - $0.020 / image
+	"dall-e-3":                  20,     // $0.040 - $0.120 / image
 	"claude-instant-1":          0.815,  // $1.63 / 1M tokens
 	"claude-2":                  5.51,   // $11.02 / 1M tokens
+	"claude-2.0":                5.51,   // $11.02 / 1M tokens
+	"claude-2.1":                5.51,   // $11.02 / 1M tokens
 	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
 	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
+	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
 	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                    1,
+	"gemini-pro":                1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-pro-vision":         1,      // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"qwen-v1":                   0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus-v1":              1,      // ￥0.014 / 1k tokens
+	"qwen-turbo":                0.5715, // ￥0.008 / 1k tokens  // https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
+	"qwen-plus":                 1.4286, // ￥0.02 / 1k tokens
+	"qwen-max":                  1.4286, // ￥0.02 / 1k tokens
+	"qwen-max-longcontext":      1.4286, // ￥0.02 / 1k tokens
 	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
 	"SparkDesk":                 1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
 	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
 	"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
-	"360GPT_S2_V9.4":            0.8572, // ¥0.012 / 1k tokens
+	"hunyuan":                   7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 }
 
 func ModelRatio2JSONString() string {
@@ -75,6 +118,9 @@ func UpdateModelRatioByJSONString(jsonStr string) error {
 }
 
 func GetModelRatio(name string) float64 {
+	if strings.HasPrefix(name, "qwen-") && strings.HasSuffix(name, "-internet") {
+		name = strings.TrimSuffix(name, "-internet")
+	}
 	ratio, ok := ModelRatio[name]
 	if !ok {
 		SysError("model ratio not found: " + name)
@@ -85,9 +131,24 @@ func GetModelRatio(name string) float64 {
 
 func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-3.5") {
+		if strings.HasSuffix(name, "1106") {
+			return 2
+		}
+		if name == "gpt-3.5-turbo" || name == "gpt-3.5-turbo-16k" {
+			// TODO: clear this after 2023-12-11
+			now := time.Now()
+			// https://platform.openai.com/docs/models/continuous-model-upgrades
+			// if after 2023-12-11, use 2
+			if now.After(time.Date(2023, 12, 11, 0, 0, 0, 0, time.UTC)) {
+				return 2
+			}
+		}
 		return 1.333333
 	}
 	if strings.HasPrefix(name, "gpt-4") {
+		if strings.HasSuffix(name, "preview") {
+			return 3
+		}
 		return 2
 	}
 	if strings.HasPrefix(name, "claude-instant-1") {

common/utils.go

@@ -196,6 +196,21 @@ func GetOrDefault(env string, defaultValue int) int {
 	return num
 }
 
+func GetOrDefaultString(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}
+
 func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }
+
+func String2Int(str string) int {
+	num, err := strconv.Atoi(str)
+	if err != nil {
+		return 0
+	}
+	return num
+}

controller/channel-billing.go

@@ -111,7 +111,7 @@ func GetResponseBody(method, url string, channel *model.Channel, headers http.He
 }
 
 func updateChannelCloseAIBalance(channel *model.Channel) (float64, error) {
-	url := fmt.Sprintf("%s/dashboard/billing/credit_grants", channel.BaseURL)
+	url := fmt.Sprintf("%s/dashboard/billing/credit_grants", channel.GetBaseURL())
 	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
 
 	if err != nil {
@@ -201,18 +201,18 @@ func updateChannelAIGC2DBalance(channel *model.Channel) (float64, error) {
 
 func updateChannelBalance(channel *model.Channel) (float64, error) {
 	baseURL := common.ChannelBaseURLs[channel.Type]
-	if channel.BaseURL == "" {
-		channel.BaseURL = baseURL
+	if channel.GetBaseURL() == "" {
+		channel.BaseURL = &baseURL
 	}
 	switch channel.Type {
 	case common.ChannelTypeOpenAI:
-		if channel.BaseURL != "" {
-			baseURL = channel.BaseURL
+		if channel.GetBaseURL() != "" {
+			baseURL = channel.GetBaseURL()
 		}
 	case common.ChannelTypeAzure:
 		return 0, errors.New("尚未实现")
 	case common.ChannelTypeCustom:
-		baseURL = channel.BaseURL
+		baseURL = channel.GetBaseURL()
 	case common.ChannelTypeCloseAI:
 		return updateChannelCloseAIBalance(channel)
 	case common.ChannelTypeOpenAISB:

controller/channel-test.go

@@ -5,19 +5,23 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
+	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
 	"sync"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
 func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
 	switch channel.Type {
 	case common.ChannelTypePaLM:
 		fallthrough
+	case common.ChannelTypeGemini:
+		fallthrough
 	case common.ChannelTypeAnthropic:
 		fallthrough
 	case common.ChannelTypeBaidu:
@@ -42,14 +46,14 @@ func testChannel(channel *model.Channel, request ChatRequest) (err error, openai
 	}
 	requestURL := common.ChannelBaseURLs[channel.Type]
 	if channel.Type == common.ChannelTypeAzure {
-		requestURL = fmt.Sprintf("%s/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", channel.BaseURL, request.Model)
+		requestURL = getFullRequestURL(channel.GetBaseURL(), fmt.Sprintf("/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", request.Model), channel.Type)
 	} else {
-		if channel.BaseURL != "" {
-			requestURL = channel.BaseURL
+		if baseURL := channel.GetBaseURL(); len(baseURL) > 0 {
+			requestURL = baseURL
 		}
-		requestURL += "/v1/chat/completions"
-	}
 
+		requestURL = getFullRequestURL(requestURL, "/v1/chat/completions", channel.Type)
+	}
 	jsonData, err := json.Marshal(request)
 	if err != nil {
 		return err, nil
@@ -70,11 +74,18 @@ func testChannel(channel *model.Channel, request ChatRequest) (err error, openai
 	}
 	defer resp.Body.Close()
 	var response TextResponse
-	err = json.NewDecoder(resp.Body).Decode(&response)
+	body, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return err, nil
 	}
+	err = json.Unmarshal(body, &response)
+	if err != nil {
+		return fmt.Errorf("Error: %s\nResp body: %s", err, body), nil
+	}
 	if response.Usage.CompletionTokens == 0 {
+		if response.Error.Message == "" {
+			response.Error.Message = "补全 tokens 非预期返回 0"
+		}
 		return errors.New(fmt.Sprintf("type %s, code %v, message %s", response.Error.Type, response.Error.Code, response.Error.Message)), &response.Error
 	}
 	return nil, nil
@@ -136,20 +147,32 @@ func TestChannel(c *gin.Context) {
 var testAllChannelsLock sync.Mutex
 var testAllChannelsRunning bool = false
 
-// disable & notify
-func disableChannel(channelId int, channelName string, reason string) {
+func notifyRootUser(subject string, content string) {
 	if common.RootUserEmail == "" {
 		common.RootUserEmail = model.GetRootUserEmail()
 	}
-	model.UpdateChannelStatusById(channelId, common.ChannelStatusDisabled)
-	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
-	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
 	err := common.SendEmail(subject, common.RootUserEmail, content)
 	if err != nil {
 		common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
 	}
 }
 
+// disable & notify
+func disableChannel(channelId int, channelName string, reason string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled)
+	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
+	notifyRootUser(subject, content)
+}
+
+// enable & notify
+func enableChannel(channelId int, channelName string) {
+	model.UpdateChannelStatusById(channelId, common.ChannelStatusEnabled)
+	subject := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	content := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
+	notifyRootUser(subject, content)
+}
+
 func testAllChannels(notify bool) error {
 	if common.RootUserEmail == "" {
 		common.RootUserEmail = model.GetRootUserEmail()
@@ -172,20 +195,21 @@ func testAllChannels(notify bool) error {
 	}
 	go func() {
 		for _, channel := range channels {
-			if channel.Status != common.ChannelStatusEnabled {
-				continue
-			}
+			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
 			err, openaiErr := testChannel(channel, *testRequest)
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
-			if milliseconds > disableThreshold {
+			if isChannelEnabled && milliseconds > disableThreshold {
 				err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if shouldDisableChannel(openaiErr, -1) {
+			if isChannelEnabled && shouldDisableChannel(openaiErr, -1) {
 				disableChannel(channel.Id, channel.Name, err.Error())
 			}
+			if !isChannelEnabled && shouldEnableChannel(err, openaiErr) {
+				enableChannel(channel.Id, channel.Name)
+			}
 			channel.UpdateResponseTime(milliseconds)
 			time.Sleep(common.RequestInterval)
 		}

controller/channel.go

@@ -127,6 +127,23 @@ func DeleteChannel(c *gin.Context) {
 	return
 }
 
+func DeleteDisabledChannel(c *gin.Context) {
+	rows, err := model.DeleteDisabledChannel()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    rows,
+	})
+	return
+}
+
 func UpdateChannel(c *gin.Context) {
 	channel := model.Channel{}
 	err := c.ShouldBindJSON(&channel)

controller/log.go

@@ -19,7 +19,8 @@ func GetAllLogs(c *gin.Context) {
 	username := c.Query("username")
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*common.ItemsPerPage, common.ItemsPerPage)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*common.ItemsPerPage, common.ItemsPerPage, channel)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -106,7 +107,8 @@ func GetLogsStat(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	username := c.Query("username")
 	modelName := c.Query("model_name")
-	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName, channel)
 	//tokenNum := model.SumUsedToken(logType, startTimestamp, endTimestamp, modelName, username, "")
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
@@ -126,7 +128,8 @@ func GetLogsSelfStat(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName, channel)
 	//tokenNum := model.SumUsedToken(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,

controller/model.go

@@ -55,12 +55,21 @@ func init() {
 	// https://platform.openai.com/docs/models/model-endpoint-compatibility
 	openAIModels = []OpenAIModels{
 		{
-			Id:         "dall-e",
+			Id:         "dall-e-2",
 			Object:     "model",
 			Created:    1677649963,
 			OwnedBy:    "openai",
 			Permission: permission,
-			Root:       "dall-e",
+			Root:       "dall-e-2",
+			Parent:     nil,
+		},
+		{
+			Id:         "dall-e-3",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "dall-e-3",
 			Parent:     nil,
 		},
 		{
@@ -72,6 +81,42 @@ func init() {
 			Root:       "whisper-1",
 			Parent:     nil,
 		},
+		{
+			Id:         "tts-1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "tts-1",
+			Parent:     nil,
+		},
+		{
+			Id:         "tts-1-1106",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "tts-1-1106",
+			Parent:     nil,
+		},
+		{
+			Id:         "tts-1-hd",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "tts-1-hd",
+			Parent:     nil,
+		},
+		{
+			Id:         "tts-1-hd-1106",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "tts-1-hd-1106",
+			Parent:     nil,
+		},
 		{
 			Id:         "gpt-3.5-turbo",
 			Object:     "model",
@@ -117,6 +162,24 @@ func init() {
 			Root:       "gpt-3.5-turbo-16k-0613",
 			Parent:     nil,
 		},
+		{
+			Id:         "gpt-3.5-turbo-1106",
+			Object:     "model",
+			Created:    1699593571,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "gpt-3.5-turbo-1106",
+			Parent:     nil,
+		},
+		{
+			Id:         "gpt-3.5-turbo-instruct",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "gpt-3.5-turbo-instruct",
+			Parent:     nil,
+		},
 		{
 			Id:         "gpt-4",
 			Object:     "model",
@@ -171,6 +234,24 @@ func init() {
 			Root:       "gpt-4-32k-0613",
 			Parent:     nil,
 		},
+		{
+			Id:         "gpt-4-1106-preview",
+			Object:     "model",
+			Created:    1699593571,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "gpt-4-1106-preview",
+			Parent:     nil,
+		},
+		{
+			Id:         "gpt-4-vision-preview",
+			Object:     "model",
+			Created:    1699593571,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "gpt-4-vision-preview",
+			Parent:     nil,
+		},
 		{
 			Id:         "text-embedding-ada-002",
 			Object:     "model",
@@ -261,11 +342,29 @@ func init() {
 			Root:       "code-davinci-edit-001",
 			Parent:     nil,
 		},
+		{
+			Id:         "davinci-002",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "davinci-002",
+			Parent:     nil,
+		},
+		{
+			Id:         "babbage-002",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "babbage-002",
+			Parent:     nil,
+		},
 		{
 			Id:         "claude-instant-1",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-instant-1",
 			Parent:     nil,
@@ -274,11 +373,29 @@ func init() {
 			Id:         "claude-2",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-2",
 			Parent:     nil,
 		},
+		{
+			Id:         "claude-2.1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "anthropic",
+			Permission: permission,
+			Root:       "claude-2.1",
+			Parent:     nil,
+		},
+		{
+			Id:         "claude-2.0",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "anthropic",
+			Permission: permission,
+			Root:       "claude-2.0",
+			Parent:     nil,
+		},
 		{
 			Id:         "ERNIE-Bot",
 			Object:     "model",
@@ -297,6 +414,15 @@ func init() {
 			Root:       "ERNIE-Bot-turbo",
 			Parent:     nil,
 		},
+		{
+			Id:         "ERNIE-Bot-4",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "baidu",
+			Permission: permission,
+			Root:       "ERNIE-Bot-4",
+			Parent:     nil,
+		},
 		{
 			Id:         "Embedding-V1",
 			Object:     "model",
@@ -315,6 +441,33 @@ func init() {
 			Root:       "PaLM-2",
 			Parent:     nil,
 		},
+		{
+			Id:         "gemini-pro",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "google",
+			Permission: permission,
+			Root:       "gemini-pro",
+			Parent:     nil,
+		},
+		{
+			Id:         "gemini-pro-vision",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "google",
+			Permission: permission,
+			Root:       "gemini-pro-vision",
+			Parent:     nil,
+		},
+		{
+			Id:         "chatglm_turbo",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "zhipu",
+			Permission: permission,
+			Root:       "chatglm_turbo",
+			Parent:     nil,
+		},
 		{
 			Id:         "chatglm_pro",
 			Object:     "model",
@@ -343,21 +496,39 @@ func init() {
 			Parent:     nil,
 		},
 		{
-			Id:         "qwen-v1",
+			Id:         "qwen-turbo",
 			Object:     "model",
 			Created:    1677649963,
 			OwnedBy:    "ali",
 			Permission: permission,
-			Root:       "qwen-v1",
+			Root:       "qwen-turbo",
 			Parent:     nil,
 		},
 		{
-			Id:         "qwen-plus-v1",
+			Id:         "qwen-plus",
 			Object:     "model",
 			Created:    1677649963,
 			OwnedBy:    "ali",
 			Permission: permission,
-			Root:       "qwen-plus-v1",
+			Root:       "qwen-plus",
+			Parent:     nil,
+		},
+		{
+			Id:         "qwen-max",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "ali",
+			Permission: permission,
+			Root:       "qwen-max",
+			Parent:     nil,
+		},
+		{
+			Id:         "qwen-max-longcontext",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "ali",
+			Permission: permission,
+			Root:       "qwen-max-longcontext",
 			Parent:     nil,
 		},
 		{
@@ -415,12 +586,12 @@ func init() {
 			Parent:     nil,
 		},
 		{
-			Id:         "360GPT_S2_V9.4",
+			Id:         "hunyuan",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "360",
+			OwnedBy:    "tencent",
 			Permission: permission,
-			Root:       "360GPT_S2_V9.4",
+			Root:       "hunyuan",
 			Parent:     nil,
 		},
 	}

controller/option.go

@@ -46,7 +46,7 @@ func UpdateOption(c *gin.Context) {
 		if option.Value == "true" && common.GitHubClientId == "" {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
-				"message": "无法启用 GitHub OAuth，请先填入 GitHub Client ID 以及 GitHub Client Secret！",
+				"message": "无法启用 GitHub OAuth，请先填入 GitHub Client Id 以及 GitHub Client Secret！",
 			})
 			return
 		}

controller/relay-aiproxy.go

@@ -48,7 +48,7 @@ type AIProxyLibraryStreamResponse struct {
 func requestOpenAI2AIProxyLibrary(request GeneralOpenAIRequest) *AIProxyLibraryRequest {
 	query := ""
 	if len(request.Messages) != 0 {
-		query = request.Messages[len(request.Messages)-1].Content
+		query = request.Messages[len(request.Messages)-1].StringContent()
 	}
 	return &AIProxyLibraryRequest{
 		Model:  request.Model,

controller/relay-ali.go

@@ -13,20 +13,21 @@ import (
 // https://help.aliyun.com/document_detail/613695.html?spm=a2c4g.2399480.0.0.1adb778fAdzP9w#341800c0f8w0r
 
 type AliMessage struct {
-	User string `json:"user"`
-	Bot  string `json:"bot"`
+	Content string `json:"content"`
+	Role    string `json:"role"`
 }
 
 type AliInput struct {
-	Prompt  string       `json:"prompt"`
-	History []AliMessage `json:"history"`
+	//Prompt   string       `json:"prompt"`
+	Messages []AliMessage `json:"messages"`
 }
 
 type AliParameters struct {
-	TopP         float64 `json:"top_p,omitempty"`
-	TopK         int     `json:"top_k,omitempty"`
-	Seed         uint64  `json:"seed,omitempty"`
-	EnableSearch bool    `json:"enable_search,omitempty"`
+	TopP              float64 `json:"top_p,omitempty"`
+	TopK              int     `json:"top_k,omitempty"`
+	Seed              uint64  `json:"seed,omitempty"`
+	EnableSearch      bool    `json:"enable_search,omitempty"`
+	IncrementalOutput bool    `json:"incremental_output,omitempty"`
 }
 
 type AliChatRequest struct {
@@ -81,41 +82,32 @@ type AliChatResponse struct {
 	AliError
 }
 
+const AliEnableSearchModelSuffix = "-internet"
+
 func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
 	messages := make([]AliMessage, 0, len(request.Messages))
-	prompt := ""
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
-		if message.Role == "system" {
-			messages = append(messages, AliMessage{
-				User: message.Content,
-				Bot:  "Okay",
-			})
-			continue
-		} else {
-			if i == len(request.Messages)-1 {
-				prompt = message.Content
-				break
-			}
-			messages = append(messages, AliMessage{
-				User: message.Content,
-				Bot:  request.Messages[i+1].Content,
-			})
-			i++
-		}
+		messages = append(messages, AliMessage{
+			Content: message.StringContent(),
+			Role:    strings.ToLower(message.Role),
+		})
+	}
+	enableSearch := false
+	aliModel := request.Model
+	if strings.HasSuffix(aliModel, AliEnableSearchModelSuffix) {
+		enableSearch = true
+		aliModel = strings.TrimSuffix(aliModel, AliEnableSearchModelSuffix)
 	}
 	return &AliChatRequest{
-		Model: request.Model,
+		Model: aliModel,
 		Input: AliInput{
-			Prompt:  prompt,
-			History: messages,
+			Messages: messages,
+		},
+		Parameters: AliParameters{
+			EnableSearch:      enableSearch,
+			IncrementalOutput: request.Stream,
 		},
-		//Parameters: AliParameters{  // ChatGPT's parameters are not compatible with Ali's
-		//	TopP: request.TopP,
-		//	TopK: 50,
-		//	//Seed:         0,
-		//	//EnableSearch: false,
-		//},
 	}
 }
 
@@ -217,7 +209,7 @@ func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *ChatCompletionsStre
 		Id:      aliResponse.RequestId,
 		Object:  "chat.completion.chunk",
 		Created: common.GetTimestamp(),
-		Model:   "ernie-bot",
+		Model:   "qwen",
 		Choices: []ChatCompletionsStreamResponseChoice{choice},
 	}
 	return &response
@@ -255,7 +247,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 		stopChan <- true
 	}()
 	setEventStreamHeaders(c)
-	lastResponseText := ""
+	//lastResponseText := ""
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
@@ -271,8 +263,8 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStat
 				usage.TotalTokens = aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
 			}
 			response := streamResponseAli2OpenAI(&aliResponse)
-			response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
-			lastResponseText = aliResponse.Output.Text
+			//response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
+			//lastResponseText = aliResponse.Output.Text
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {
 				common.SysError("error marshalling stream response: " + err.Error())
@@ -318,6 +310,7 @@ func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode
 		}, nil
 	}
 	fullTextResponse := responseAli2OpenAI(&aliResponse)
+	fullTextResponse.Model = "qwen"
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
 		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil

controller/relay-audio.go

@@ -1,16 +1,18 @@
 package controller
 
 import (
+	"bufio"
 	"bytes"
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
-
-	"github.com/gin-gonic/gin"
+	"strings"
 )
 
 func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
@@ -18,18 +20,47 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
 	group := c.GetString("group")
+	tokenName := c.GetString("token_name")
+
+	var ttsRequest TextToSpeechRequest
+	if relayMode == RelayModeAudioSpeech {
+		// Read JSON
+		err := common.UnmarshalBodyReusable(c, &ttsRequest)
+		// Check if JSON is valid
+		if err != nil {
+			return errorWrapper(err, "invalid_json", http.StatusBadRequest)
+		}
+		audioModel = ttsRequest.Model
+		// Check if text is too long 4096
+		if len(ttsRequest.Input) > 4096 {
+			return errorWrapper(errors.New("input is too long (over 4096 characters)"), "text_too_long", http.StatusBadRequest)
+		}
+	}
 
-	preConsumedTokens := common.PreConsumedQuota
 	modelRatio := common.GetModelRatio(audioModel)
 	groupRatio := common.GetGroupRatio(group)
 	ratio := modelRatio * groupRatio
-	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
+	var quota int
+	var preConsumedQuota int
+	switch relayMode {
+	case RelayModeAudioSpeech:
+		preConsumedQuota = int(float64(len(ttsRequest.Input)) * ratio)
+		quota = preConsumedQuota
+	default:
+		preConsumedQuota = int(float64(common.PreConsumedQuota) * ratio)
+	}
 	userQuota, err := model.CacheGetUserQuota(userId)
 	if err != nil {
 		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
+
+	// Check if user quota is enough
+	if userQuota-preConsumedQuota < 0 {
+		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+	}
 	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
 	if err != nil {
 		return errorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
@@ -61,19 +92,39 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
-
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
 
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
-	requestBody := c.Request.Body
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
+	if relayMode == RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		apiVersion := GetAPIVersion(c)
+		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/audio/transcriptions?api-version=%s", baseURL, audioModel, apiVersion)
+	}
+
+	requestBody := &bytes.Buffer{}
+	_, err = io.Copy(requestBody, c.Request.Body)
+	if err != nil {
+		return errorWrapper(err, "new_request_body_failed", http.StatusInternalServerError)
+	}
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody.Bytes()))
+	responseFormat := c.DefaultPostForm("response_format", "json")
 
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
 		return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+
+	if relayMode == RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		apiKey := c.Request.Header.Get("Authorization")
+		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+		req.Header.Set("api-key", apiKey)
+		req.ContentLength = c.Request.ContentLength
+	} else {
+		req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+	}
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
 
@@ -90,47 +141,65 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	if err != nil {
 		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}
-	var audioResponse AudioResponse
 
+	if relayMode != RelayModeAudioSpeech {
+		responseBody, err := io.ReadAll(resp.Body)
+		if err != nil {
+			return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		}
+		err = resp.Body.Close()
+		if err != nil {
+			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+		}
+
+		var openAIErr TextResponse
+		if err = json.Unmarshal(responseBody, &openAIErr); err == nil {
+			if openAIErr.Error.Message != "" {
+				return errorWrapper(fmt.Errorf("type %s, code %v, message %s", openAIErr.Error.Type, openAIErr.Error.Code, openAIErr.Error.Message), "request_error", http.StatusInternalServerError)
+			}
+		}
+
+		var text string
+		switch responseFormat {
+		case "json":
+			text, err = getTextFromJSON(responseBody)
+		case "text":
+			text, err = getTextFromText(responseBody)
+		case "srt":
+			text, err = getTextFromSRT(responseBody)
+		case "verbose_json":
+			text, err = getTextFromVerboseJSON(responseBody)
+		case "vtt":
+			text, err = getTextFromVTT(responseBody)
+		default:
+			return errorWrapper(errors.New("unexpected_response_format"), "unexpected_response_format", http.StatusInternalServerError)
+		}
+		if err != nil {
+			return errorWrapper(err, "get_text_from_body_err", http.StatusInternalServerError)
+		}
+		quota = countTokenText(text, audioModel)
+		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	}
+	if resp.StatusCode != http.StatusOK {
+		if preConsumedQuota > 0 {
+			// we need to roll back the pre-consumed quota
+			defer func(ctx context.Context) {
+				go func() {
+					// negative means add quota back for token & user
+					err := model.PostConsumeTokenQuota(tokenId, -preConsumedQuota)
+					if err != nil {
+						common.LogError(ctx, fmt.Sprintf("error rollback pre-consumed quota: %s", err.Error()))
+					}
+				}()
+			}(c.Request.Context())
+		}
+		return relayErrorHandler(resp)
+	}
+	quotaDelta := quota - preConsumedQuota
 	defer func(ctx context.Context) {
-		go func() {
-			quota := countTokenText(audioResponse.Text, audioModel)
-			quotaDelta := quota - preConsumedQuota
-			err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
-			if err != nil {
-				common.SysError("error consuming token remain quota: " + err.Error())
-			}
-			err = model.CacheUpdateUserQuota(userId)
-			if err != nil {
-				common.SysError("error update user quota cache: " + err.Error())
-			}
-			if quota != 0 {
-				tokenName := c.GetString("token_name")
-				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, 0, 0, audioModel, tokenName, quota, logContent)
-				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				channelId := c.GetInt("channel_id")
-				model.UpdateChannelUsedQuota(channelId, quota)
-			}
-		}()
+		go postConsumeQuota(ctx, tokenId, quotaDelta, quota, userId, channelId, modelRatio, groupRatio, audioModel, tokenName)
 	}(c.Request.Context())
 
-	responseBody, err := io.ReadAll(resp.Body)
-
-	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-	}
-	err = json.Unmarshal(responseBody, &audioResponse)
-	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
-	}
-
-	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
-
 	for k, v := range resp.Header {
 		c.Writer.Header().Set(k, v[0])
 	}
@@ -146,3 +215,48 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	}
 	return nil
 }
+
+func getTextFromVTT(body []byte) (string, error) {
+	return getTextFromSRT(body)
+}
+
+func getTextFromVerboseJSON(body []byte) (string, error) {
+	var whisperResponse WhisperVerboseJSONResponse
+	if err := json.Unmarshal(body, &whisperResponse); err != nil {
+		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+	}
+	return whisperResponse.Text, nil
+}
+
+func getTextFromSRT(body []byte) (string, error) {
+	scanner := bufio.NewScanner(strings.NewReader(string(body)))
+	var builder strings.Builder
+	var textLine bool
+	for scanner.Scan() {
+		line := scanner.Text()
+		if textLine {
+			builder.WriteString(line)
+			textLine = false
+			continue
+		} else if strings.Contains(line, "-->") {
+			textLine = true
+			continue
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		return "", err
+	}
+	return builder.String(), nil
+}
+
+func getTextFromText(body []byte) (string, error) {
+	return strings.TrimSuffix(string(body), "\n"), nil
+}
+
+func getTextFromJSON(body []byte) (string, error) {
+	var whisperResponse WhisperJSONResponse
+	if err := json.Unmarshal(body, &whisperResponse); err != nil {
+		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+	}
+	return whisperResponse.Text, nil
+}

controller/relay-baidu.go

@@ -89,7 +89,7 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 		if message.Role == "system" {
 			messages = append(messages, BaiduMessage{
 				Role:    "user",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, BaiduMessage{
 				Role:    "assistant",
@@ -98,7 +98,7 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 		} else {
 			messages = append(messages, BaiduMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -255,6 +255,7 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 		}, nil
 	}
 	fullTextResponse := responseBaidu2OpenAI(&baiduResponse)
+	fullTextResponse.Model = "ernie-bot"
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
 		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil

controller/relay-claude.go

@@ -70,7 +70,9 @@ func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
 		} else if message.Role == "assistant" {
 			prompt += fmt.Sprintf("\n\nAssistant: %s", message.Content)
 		} else if message.Role == "system" {
-			prompt += fmt.Sprintf("\n\nSystem: %s", message.Content)
+			if prompt == "" {
+				prompt = message.StringContent()
+			}
 		}
 	}
 	prompt += "\n\nAssistant:"
@@ -202,6 +204,7 @@ func claudeHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 		}, nil
 	}
 	fullTextResponse := responseClaude2OpenAI(&claudeResponse)
+	fullTextResponse.Model = model
 	completionTokens := countTokenText(claudeResponse.Completion, model)
 	usage := Usage{
 		PromptTokens:     promptTokens,

controller/relay-gemini.go

@@ -0,0 +1,337 @@
+package controller
+
+import (
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/common/image"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+)
+
+// https://ai.google.dev/docs/gemini_api_overview?hl=zh-cn
+
+const (
+	GeminiVisionMaxImageNum = 16
+)
+
+type GeminiChatRequest struct {
+	Contents         []GeminiChatContent        `json:"contents"`
+	SafetySettings   []GeminiChatSafetySettings `json:"safety_settings,omitempty"`
+	GenerationConfig GeminiChatGenerationConfig `json:"generation_config,omitempty"`
+	Tools            []GeminiChatTools          `json:"tools,omitempty"`
+}
+
+type GeminiInlineData struct {
+	MimeType string `json:"mimeType"`
+	Data     string `json:"data"`
+}
+
+type GeminiPart struct {
+	Text       string            `json:"text,omitempty"`
+	InlineData *GeminiInlineData `json:"inlineData,omitempty"`
+}
+
+type GeminiChatContent struct {
+	Role  string       `json:"role,omitempty"`
+	Parts []GeminiPart `json:"parts"`
+}
+
+type GeminiChatSafetySettings struct {
+	Category  string `json:"category"`
+	Threshold string `json:"threshold"`
+}
+
+type GeminiChatTools struct {
+	FunctionDeclarations any `json:"functionDeclarations,omitempty"`
+}
+
+type GeminiChatGenerationConfig struct {
+	Temperature     float64  `json:"temperature,omitempty"`
+	TopP            float64  `json:"topP,omitempty"`
+	TopK            float64  `json:"topK,omitempty"`
+	MaxOutputTokens int      `json:"maxOutputTokens,omitempty"`
+	CandidateCount  int      `json:"candidateCount,omitempty"`
+	StopSequences   []string `json:"stopSequences,omitempty"`
+}
+
+// Setting safety to the lowest possible values since Gemini is already powerless enough
+func requestOpenAI2Gemini(textRequest GeneralOpenAIRequest) *GeminiChatRequest {
+	geminiRequest := GeminiChatRequest{
+		Contents: make([]GeminiChatContent, 0, len(textRequest.Messages)),
+		SafetySettings: []GeminiChatSafetySettings{
+			{
+				Category:  "HARM_CATEGORY_HARASSMENT",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_HATE_SPEECH",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+				Threshold: common.GeminiSafetySetting,
+			},
+			{
+				Category:  "HARM_CATEGORY_DANGEROUS_CONTENT",
+				Threshold: common.GeminiSafetySetting,
+			},
+		},
+		GenerationConfig: GeminiChatGenerationConfig{
+			Temperature:     textRequest.Temperature,
+			TopP:            textRequest.TopP,
+			MaxOutputTokens: textRequest.MaxTokens,
+		},
+	}
+	if textRequest.Functions != nil {
+		geminiRequest.Tools = []GeminiChatTools{
+			{
+				FunctionDeclarations: textRequest.Functions,
+			},
+		}
+	}
+	shouldAddDummyModelMessage := false
+	for _, message := range textRequest.Messages {
+		content := GeminiChatContent{
+			Role: message.Role,
+			Parts: []GeminiPart{
+				{
+					Text: message.StringContent(),
+				},
+			},
+		}
+		openaiContent := message.ParseContent()
+		var parts []GeminiPart
+		imageNum := 0
+		for _, part := range openaiContent {
+			if part.Type == ContentTypeText {
+				parts = append(parts, GeminiPart{
+					Text: part.Text,
+				})
+			} else if part.Type == ContentTypeImageURL {
+				imageNum += 1
+				if imageNum > GeminiVisionMaxImageNum {
+					continue
+				}
+				mimeType, data, _ := image.GetImageFromUrl(part.ImageURL.Url)
+				parts = append(parts, GeminiPart{
+					InlineData: &GeminiInlineData{
+						MimeType: mimeType,
+						Data:     data,
+					},
+				})
+			}
+		}
+		content.Parts = parts
+
+		// there's no assistant role in gemini and API shall vomit if Role is not user or model
+		if content.Role == "assistant" {
+			content.Role = "model"
+		}
+		// Converting system prompt to prompt from user for the same reason
+		if content.Role == "system" {
+			content.Role = "user"
+			shouldAddDummyModelMessage = true
+		}
+		geminiRequest.Contents = append(geminiRequest.Contents, content)
+
+		// If a system message is the last message, we need to add a dummy model message to make gemini happy
+		if shouldAddDummyModelMessage {
+			geminiRequest.Contents = append(geminiRequest.Contents, GeminiChatContent{
+				Role: "model",
+				Parts: []GeminiPart{
+					{
+						Text: "Okay",
+					},
+				},
+			})
+			shouldAddDummyModelMessage = false
+		}
+	}
+
+	return &geminiRequest
+}
+
+type GeminiChatResponse struct {
+	Candidates     []GeminiChatCandidate    `json:"candidates"`
+	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
+}
+
+func (g *GeminiChatResponse) GetResponseText() string {
+	if g == nil {
+		return ""
+	}
+	if len(g.Candidates) > 0 && len(g.Candidates[0].Content.Parts) > 0 {
+		return g.Candidates[0].Content.Parts[0].Text
+	}
+	return ""
+}
+
+type GeminiChatCandidate struct {
+	Content       GeminiChatContent        `json:"content"`
+	FinishReason  string                   `json:"finishReason"`
+	Index         int64                    `json:"index"`
+	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+}
+
+type GeminiChatSafetyRating struct {
+	Category    string `json:"category"`
+	Probability string `json:"probability"`
+}
+
+type GeminiChatPromptFeedback struct {
+	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+}
+
+func responseGeminiChat2OpenAI(response *GeminiChatResponse) *OpenAITextResponse {
+	fullTextResponse := OpenAITextResponse{
+		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Choices: make([]OpenAITextResponseChoice, 0, len(response.Candidates)),
+	}
+	for i, candidate := range response.Candidates {
+		choice := OpenAITextResponseChoice{
+			Index: i,
+			Message: Message{
+				Role:    "assistant",
+				Content: "",
+			},
+			FinishReason: stopFinishReason,
+		}
+		if len(candidate.Content.Parts) > 0 {
+			choice.Message.Content = candidate.Content.Parts[0].Text
+		}
+		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	}
+	return &fullTextResponse
+}
+
+func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *ChatCompletionsStreamResponse {
+	var choice ChatCompletionsStreamResponseChoice
+	choice.Delta.Content = geminiResponse.GetResponseText()
+	choice.FinishReason = &stopFinishReason
+	var response ChatCompletionsStreamResponse
+	response.Object = "chat.completion.chunk"
+	response.Model = "gemini"
+	response.Choices = []ChatCompletionsStreamResponseChoice{choice}
+	return &response
+}
+
+func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+	responseText := ""
+	dataChan := make(chan string)
+	stopChan := make(chan bool)
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
+		if atEOF && len(data) == 0 {
+			return 0, nil, nil
+		}
+		if i := strings.Index(string(data), "\n"); i >= 0 {
+			return i + 1, data[0:i], nil
+		}
+		if atEOF {
+			return len(data), data, nil
+		}
+		return 0, nil, nil
+	})
+	go func() {
+		for scanner.Scan() {
+			data := scanner.Text()
+			data = strings.TrimSpace(data)
+			if !strings.HasPrefix(data, "\"text\": \"") {
+				continue
+			}
+			data = strings.TrimPrefix(data, "\"text\": \"")
+			data = strings.TrimSuffix(data, "\"")
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	setEventStreamHeaders(c)
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			// this is used to prevent annoying \ related format bug
+			data = fmt.Sprintf("{\"content\": \"%s\"}", data)
+			type dummyStruct struct {
+				Content string `json:"content"`
+			}
+			var dummy dummyStruct
+			err := json.Unmarshal([]byte(data), &dummy)
+			responseText += dummy.Content
+			var choice ChatCompletionsStreamResponseChoice
+			choice.Delta.Content = dummy.Content
+			response := ChatCompletionsStreamResponse{
+				Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+				Object:  "chat.completion.chunk",
+				Created: common.GetTimestamp(),
+				Model:   "gemini-pro",
+				Choices: []ChatCompletionsStreamResponseChoice{choice},
+			}
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	err := resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+	}
+	return nil, responseText
+}
+
+func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var geminiResponse GeminiChatResponse
+	err = json.Unmarshal(responseBody, &geminiResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if len(geminiResponse.Candidates) == 0 {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: OpenAIError{
+				Message: "No candidates returned",
+				Type:    "server_error",
+				Param:   "",
+				Code:    500,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
+	fullTextResponse.Model = model
+	completionTokens := countTokenText(geminiResponse.GetResponseText(), model)
+	usage := Usage{
+		PromptTokens:     promptTokens,
+		CompletionTokens: completionTokens,
+		TotalTokens:      promptTokens + completionTokens,
+	}
+	fullTextResponse.Usage = usage
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}

controller/relay-image.go

@@ -10,40 +10,82 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strings"
 
 	"github.com/gin-gonic/gin"
 )
 
+func isWithinRange(element string, value int) bool {
+	if _, ok := common.DalleGenerationImageAmounts[element]; !ok {
+		return false
+	}
+	min := common.DalleGenerationImageAmounts[element][0]
+	max := common.DalleGenerationImageAmounts[element][1]
+
+	return value >= min && value <= max
+}
+
 func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
-	imageModel := "dall-e"
+	imageModel := "dall-e-2"
+	imageSize := "1024x1024"
 
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
-	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 
 	var imageRequest ImageRequest
-	if consumeQuota {
-		err := common.UnmarshalBodyReusable(c, &imageRequest)
-		if err != nil {
-			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+	err := common.UnmarshalBodyReusable(c, &imageRequest)
+	if err != nil {
+		return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+	}
+
+	if imageRequest.N == 0 {
+		imageRequest.N = 1
+	}
+
+	// Size validation
+	if imageRequest.Size != "" {
+		imageSize = imageRequest.Size
+	}
+
+	// Model validation
+	if imageRequest.Model != "" {
+		imageModel = imageRequest.Model
+	}
+
+	imageCostRatio, hasValidSize := common.DalleSizeRatios[imageModel][imageSize]
+
+	// Check if model is supported
+	if hasValidSize {
+		if imageRequest.Quality == "hd" && imageModel == "dall-e-3" {
+			if imageSize == "1024x1024" {
+				imageCostRatio *= 2
+			} else {
+				imageCostRatio *= 1.5
+			}
 		}
+	} else {
+		return errorWrapper(errors.New("size not supported for this image model"), "size_not_supported", http.StatusBadRequest)
 	}
 
 	// Prompt validation
 	if imageRequest.Prompt == "" {
-		return errorWrapper(errors.New("prompt is required"), "required_field_missing", http.StatusBadRequest)
+		return errorWrapper(errors.New("prompt is required"), "prompt_missing", http.StatusBadRequest)
 	}
 
-	// Not "256x256", "512x512", or "1024x1024"
-	if imageRequest.Size != "" && imageRequest.Size != "256x256" && imageRequest.Size != "512x512" && imageRequest.Size != "1024x1024" {
-		return errorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024"), "invalid_field_value", http.StatusBadRequest)
+	// Check prompt length
+	if len(imageRequest.Prompt) > common.DalleImagePromptLengthLimitations[imageModel] {
+		return errorWrapper(errors.New("prompt is too long"), "prompt_too_long", http.StatusBadRequest)
 	}
 
-	// N should between 1 and 10
-	if imageRequest.N != 0 && (imageRequest.N < 1 || imageRequest.N > 10) {
-		return errorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
+	// Number of generated images validation
+	if isWithinRange(imageModel, imageRequest.N) == false {
+		// channel not azure
+		if channelType != common.ChannelTypeAzure {
+			return errorWrapper(errors.New("invalid value of n"), "n_not_within_range", http.StatusBadRequest)
+		}
 	}
 
 	// map model name
@@ -60,18 +102,21 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			isModelMapped = true
 		}
 	}
-
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
-
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
-
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
+	if channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/dall-e-quickstart?tabs=dalle3%2Ccommand-line&pivots=rest-api
+		apiVersion := GetAPIVersion(c)
+		// https://{resource_name}.openai.azure.com/openai/deployments/dall-e-3/images/generations?api-version=2023-06-01-preview
+		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/images/generations?api-version=%s", baseURL, imageModel, apiVersion)
+	}
 
 	var requestBody io.Reader
-	if isModelMapped {
+	if isModelMapped || channelType == common.ChannelTypeAzure { // make Azure channel request body
 		jsonStr, err := json.Marshal(imageRequest)
 		if err != nil {
 			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
@@ -86,26 +131,23 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	ratio := modelRatio * groupRatio
 	userQuota, err := model.CacheGetUserQuota(userId)
 
-	sizeRatio := 1.0
-	// Size
-	if imageRequest.Size == "256x256" {
-		sizeRatio = 1
-	} else if imageRequest.Size == "512x512" {
-		sizeRatio = 1.125
-	} else if imageRequest.Size == "1024x1024" {
-		sizeRatio = 1.25
-	}
-	quota := int(ratio*sizeRatio*1000) * imageRequest.N
+	quota := int(ratio*imageCostRatio*1000) * imageRequest.N
 
-	if consumeQuota && userQuota-quota < 0 {
-		return errorWrapper(err, "insufficient_user_quota", http.StatusForbidden)
+	if userQuota-quota < 0 {
+		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
 		return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+	token := c.Request.Header.Get("Authorization")
+	if channelType == common.ChannelTypeAzure { // Azure authentication
+		token = strings.TrimPrefix(token, "Bearer ")
+		req.Header.Set("api-key", token)
+	} else {
+		req.Header.Set("Authorization", token)
+	}
 
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
@@ -126,43 +168,42 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	var textResponse ImageResponse
 
 	defer func(ctx context.Context) {
-		if consumeQuota {
-			err := model.PostConsumeTokenQuota(tokenId, quota)
-			if err != nil {
-				common.SysError("error consuming token remain quota: " + err.Error())
-			}
-			err = model.CacheUpdateUserQuota(userId)
-			if err != nil {
-				common.SysError("error update user quota cache: " + err.Error())
-			}
-			if quota != 0 {
-				tokenName := c.GetString("token_name")
-				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, 0, 0, imageModel, tokenName, quota, logContent)
-				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				channelId := c.GetInt("channel_id")
-				model.UpdateChannelUsedQuota(channelId, quota)
-			}
+		if resp.StatusCode != http.StatusOK {
+			return
+		}
+		err := model.PostConsumeTokenQuota(tokenId, quota)
+		if err != nil {
+			common.SysError("error consuming token remain quota: " + err.Error())
+		}
+		err = model.CacheUpdateUserQuota(userId)
+		if err != nil {
+			common.SysError("error update user quota cache: " + err.Error())
+		}
+		if quota != 0 {
+			tokenName := c.GetString("token_name")
+			logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
+			model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent)
+			model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+			channelId := c.GetInt("channel_id")
+			model.UpdateChannelUsedQuota(channelId, quota)
 		}
 	}(c.Request.Context())
 
-	if consumeQuota {
-		responseBody, err := io.ReadAll(resp.Body)
+	responseBody, err := io.ReadAll(resp.Body)
 
-		if err != nil {
-			return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
-		}
-		err = resp.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-		}
-		err = json.Unmarshal(responseBody, &textResponse)
-		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
-		}
-
-		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
 	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+	}
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+	}
+
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 
 	for k, v := range resp.Header {
 		c.Writer.Header().Set(k, v[0])

controller/relay-openai.go

@@ -88,30 +88,29 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 	return nil, responseText
 }
 
-func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
 	var textResponse TextResponse
-	if consumeQuota {
-		responseBody, err := io.ReadAll(resp.Body)
-		if err != nil {
-			return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
-		}
-		err = resp.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-		}
-		err = json.Unmarshal(responseBody, &textResponse)
-		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-		}
-		if textResponse.Error.Type != "" {
-			return &OpenAIErrorWithStatusCode{
-				OpenAIError: textResponse.Error,
-				StatusCode:  resp.StatusCode,
-			}, nil
-		}
-		// Reset response body
-		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if textResponse.Error.Type != "" {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: textResponse.Error,
+			StatusCode:  resp.StatusCode,
+		}, nil
+	}
+	// Reset response body
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+
 	// We shouldn't set the header before we parse the response body, because the parse part may fail.
 	// And then we will have to send an error response, but in this case, the header has already been set.
 	// So the httpClient will be confused by the response.
@@ -120,7 +119,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 		c.Writer.Header().Set(k, v[0])
 	}
 	c.Writer.WriteHeader(resp.StatusCode)
-	_, err := io.Copy(c.Writer, resp.Body)
+	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
 		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 	}
@@ -132,7 +131,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 	if textResponse.Usage.TotalTokens == 0 {
 		completionTokens := 0
 		for _, choice := range textResponse.Choices {
-			completionTokens += countTokenText(choice.Message.Content, model)
+			completionTokens += countTokenText(choice.Message.StringContent(), model)
 		}
 		textResponse.Usage = Usage{
 			PromptTokens:     promptTokens,

controller/relay-palm.go

@@ -59,7 +59,7 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 	}
 	for _, message := range textRequest.Messages {
 		palmMessage := PaLMChatMessage{
-			Content: message.Content,
+			Content: message.StringContent(),
 		}
 		if message.Role == "user" {
 			palmMessage.Author = "0"
@@ -187,6 +187,7 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
+	fullTextResponse.Model = model
 	completionTokens := countTokenText(palmResponse.Candidates[0].Content, model)
 	usage := Usage{
 		PromptTokens:     promptTokens,

controller/relay-tencent.go

@@ -0,0 +1,288 @@
+package controller
+
+import (
+	"bufio"
+	"crypto/hmac"
+	"crypto/sha1"
+	"encoding/base64"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"sort"
+	"strconv"
+	"strings"
+)
+
+// https://cloud.tencent.com/document/product/1729/97732
+
+type TencentMessage struct {
+	Role    string `json:"role"`
+	Content string `json:"content"`
+}
+
+type TencentChatRequest struct {
+	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
+	SecretId string `json:"secret_id"` // 官网 SecretId
+	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
+	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
+	Timestamp int64 `json:"timestamp"`
+	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
+	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
+	Expired int64  `json:"expired"`
+	QueryID string `json:"query_id"` //请求 Id，用于问题排查
+	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
+	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
+	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
+	Temperature float64 `json:"temperature"`
+	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
+	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
+	// 建议该参数和 temperature 只设置1个，不要同时更改
+	TopP float64 `json:"top_p"`
+	// Stream 0：同步，1：流式 （默认，协议：SSE)
+	// 同步请求超时：60s，如果内容较长建议使用流式
+	Stream int `json:"stream"`
+	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
+	// 输入 content 总数最大支持 3000 token。
+	Messages []TencentMessage `json:"messages"`
+}
+
+type TencentError struct {
+	Code    int    `json:"code"`
+	Message string `json:"message"`
+}
+
+type TencentUsage struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+	TotalTokens  int `json:"total_tokens"`
+}
+
+type TencentResponseChoices struct {
+	FinishReason string         `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     TencentMessage `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        TencentMessage `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+}
+
+type TencentChatResponse struct {
+	Choices []TencentResponseChoices `json:"choices,omitempty"` // 结果
+	Created string                   `json:"created,omitempty"` // unix 时间戳的字符串
+	Id      string                   `json:"id,omitempty"`      // 会话 id
+	Usage   Usage                    `json:"usage,omitempty"`   // token 数量
+	Error   TencentError             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string                   `json:"note,omitempty"`    // 注释
+	ReqID   string                   `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+}
+
+func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
+	messages := make([]TencentMessage, 0, len(request.Messages))
+	for i := 0; i < len(request.Messages); i++ {
+		message := request.Messages[i]
+		if message.Role == "system" {
+			messages = append(messages, TencentMessage{
+				Role:    "user",
+				Content: message.StringContent(),
+			})
+			messages = append(messages, TencentMessage{
+				Role:    "assistant",
+				Content: "Okay",
+			})
+			continue
+		}
+		messages = append(messages, TencentMessage{
+			Content: message.StringContent(),
+			Role:    message.Role,
+		})
+	}
+	stream := 0
+	if request.Stream {
+		stream = 1
+	}
+	return &TencentChatRequest{
+		Timestamp:   common.GetTimestamp(),
+		Expired:     common.GetTimestamp() + 24*60*60,
+		QueryID:     common.GetUUID(),
+		Temperature: request.Temperature,
+		TopP:        request.TopP,
+		Stream:      stream,
+		Messages:    messages,
+	}
+}
+
+func responseTencent2OpenAI(response *TencentChatResponse) *OpenAITextResponse {
+	fullTextResponse := OpenAITextResponse{
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Usage:   response.Usage,
+	}
+	if len(response.Choices) > 0 {
+		choice := OpenAITextResponseChoice{
+			Index: 0,
+			Message: Message{
+				Role:    "assistant",
+				Content: response.Choices[0].Messages.Content,
+			},
+			FinishReason: response.Choices[0].FinishReason,
+		}
+		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	}
+	return &fullTextResponse
+}
+
+func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *ChatCompletionsStreamResponse {
+	response := ChatCompletionsStreamResponse{
+		Object:  "chat.completion.chunk",
+		Created: common.GetTimestamp(),
+		Model:   "tencent-hunyuan",
+	}
+	if len(TencentResponse.Choices) > 0 {
+		var choice ChatCompletionsStreamResponseChoice
+		choice.Delta.Content = TencentResponse.Choices[0].Delta.Content
+		if TencentResponse.Choices[0].FinishReason == "stop" {
+			choice.FinishReason = &stopFinishReason
+		}
+		response.Choices = append(response.Choices, choice)
+	}
+	return &response
+}
+
+func tencentStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, string) {
+	var responseText string
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
+		if atEOF && len(data) == 0 {
+			return 0, nil, nil
+		}
+		if i := strings.Index(string(data), "\n"); i >= 0 {
+			return i + 1, data[0:i], nil
+		}
+		if atEOF {
+			return len(data), data, nil
+		}
+		return 0, nil, nil
+	})
+	dataChan := make(chan string)
+	stopChan := make(chan bool)
+	go func() {
+		for scanner.Scan() {
+			data := scanner.Text()
+			if len(data) < 5 { // ignore blank line or wrong format
+				continue
+			}
+			if data[:5] != "data:" {
+				continue
+			}
+			data = data[5:]
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	setEventStreamHeaders(c)
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			var TencentResponse TencentChatResponse
+			err := json.Unmarshal([]byte(data), &TencentResponse)
+			if err != nil {
+				common.SysError("error unmarshalling stream response: " + err.Error())
+				return true
+			}
+			response := streamResponseTencent2OpenAI(&TencentResponse)
+			if len(response.Choices) != 0 {
+				responseText += response.Choices[0].Delta.Content
+			}
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	err := resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+	}
+	return nil, responseText
+}
+
+func tencentHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+	var TencentResponse TencentChatResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &TencentResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if TencentResponse.Error.Code != 0 {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: OpenAIError{
+				Message: TencentResponse.Error.Message,
+				Code:    TencentResponse.Error.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := responseTencent2OpenAI(&TencentResponse)
+	fullTextResponse.Model = "hunyuan"
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}
+
+func parseTencentConfig(config string) (appId int64, secretId string, secretKey string, err error) {
+	parts := strings.Split(config, "|")
+	if len(parts) != 3 {
+		err = errors.New("invalid tencent config")
+		return
+	}
+	appId, err = strconv.ParseInt(parts[0], 10, 64)
+	secretId = parts[1]
+	secretKey = parts[2]
+	return
+}
+
+func getTencentSign(req TencentChatRequest, secretKey string) string {
+	params := make([]string, 0)
+	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
+	params = append(params, "secret_id="+req.SecretId)
+	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
+	params = append(params, "query_id="+req.QueryID)
+	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
+	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
+	params = append(params, "stream="+strconv.Itoa(req.Stream))
+	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
+
+	var messageStr string
+	for _, msg := range req.Messages {
+		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
+	}
+	messageStr = strings.TrimSuffix(messageStr, ",")
+	params = append(params, "messages=["+messageStr+"]")
+
+	sort.Sort(sort.StringSlice(params))
+	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
+	mac := hmac.New(sha1.New, []byte(secretKey))
+	signURL := url
+	mac.Write([]byte(signURL))
+	sign := mac.Sum([]byte(nil))
+	return base64.StdEncoding.EncodeToString(sign)
+}

controller/relay-text.go

@@ -6,13 +6,15 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strings"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -24,13 +26,22 @@ const (
 	APITypeAli
 	APITypeXunfei
 	APITypeAIProxyLibrary
+	APITypeTencent
+	APITypeGemini
 )
 
 var httpClient *http.Client
 var impatientHTTPClient *http.Client
 
 func init() {
-	httpClient = &http.Client{}
+	if common.RelayTimeout == 0 {
+		httpClient = &http.Client{}
+	} else {
+		httpClient = &http.Client{
+			Timeout: time.Duration(common.RelayTimeout) * time.Second,
+		}
+	}
+
 	impatientHTTPClient = &http.Client{
 		Timeout: 5 * time.Second,
 	}
@@ -38,16 +49,17 @@ func init() {
 
 func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	tokenId := c.GetInt("token_id")
 	userId := c.GetInt("id")
-	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 	var textRequest GeneralOpenAIRequest
-	if consumeQuota || channelType == common.ChannelTypeAzure || channelType == common.ChannelTypePaLM {
-		err := common.UnmarshalBodyReusable(c, &textRequest)
-		if err != nil {
-			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
-		}
+	err := common.UnmarshalBodyReusable(c, &textRequest)
+	if err != nil {
+		return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+	}
+	if textRequest.MaxTokens < 0 || textRequest.MaxTokens > math.MaxInt32/2 {
+		return errorWrapper(errors.New("max_tokens is invalid"), "invalid_max_tokens", http.StatusBadRequest)
 	}
 	if relayMode == RelayModeModerations && textRequest.Model == "" {
 		textRequest.Model = "text-moderation-latest"
@@ -108,22 +120,22 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		apiType = APITypeXunfei
 	case common.ChannelTypeAIProxyLibrary:
 		apiType = APITypeAIProxyLibrary
+	case common.ChannelTypeTencent:
+		apiType = APITypeTencent
+	case common.ChannelTypeGemini:
+		apiType = APITypeGemini
 	}
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
 	switch apiType {
 	case APITypeOpenAI:
 		if channelType == common.ChannelTypeAzure {
 			// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
-			query := c.Request.URL.Query()
-			apiVersion := query.Get("api-version")
-			if apiVersion == "" {
-				apiVersion = c.GetString("api_version")
-			}
+			apiVersion := GetAPIVersion(c)
 			requestURL := strings.Split(requestURL, "?")[0]
 			requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
 			baseURL = c.GetString("base_url")
@@ -134,7 +146,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			model_ = strings.TrimSuffix(model_, "-0301")
 			model_ = strings.TrimSuffix(model_, "-0314")
 			model_ = strings.TrimSuffix(model_, "-0613")
-			fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/%s", baseURL, model_, task)
+
+			requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
+			fullRequestURL = getFullRequestURL(baseURL, requestURL, channelType)
 		}
 	case APITypeClaude:
 		fullRequestURL = "https://api.anthropic.com/v1/complete"
@@ -147,6 +161,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
 		case "ERNIE-Bot-turbo":
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
+		case "ERNIE-Bot-4":
+			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
 		case "BLOOMZ-7B":
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
 		case "Embedding-V1":
@@ -164,9 +180,20 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		if baseURL != "" {
 			fullRequestURL = fmt.Sprintf("%s/v1beta2/models/chat-bison-001:generateMessage", baseURL)
 		}
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		fullRequestURL += "?key=" + apiKey
+	case APITypeGemini:
+		requestBaseURL := "https://generativelanguage.googleapis.com"
+		if baseURL != "" {
+			requestBaseURL = baseURL
+		}
+		version := "v1"
+		if c.GetString("api_version") != "" {
+			version = c.GetString("api_version")
+		}
+		action := "generateContent"
+		if textRequest.Stream {
+			action = "streamGenerateContent"
+		}
+		fullRequestURL = fmt.Sprintf("%s/%s/models/%s:%s", requestBaseURL, version, textRequest.Model, action)
 	case APITypeZhipu:
 		method := "invoke"
 		if textRequest.Stream {
@@ -178,6 +205,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		if relayMode == RelayModeEmbeddings {
 			fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/embeddings/text-embedding/text-embedding"
 		}
+	case APITypeTencent:
+		fullRequestURL = "https://hunyuan.cloud.tencent.com/hyllm/v1/chat/completions"
 	case APITypeAIProxyLibrary:
 		fullRequestURL = fmt.Sprintf("%s/api/library/ask", baseURL)
 	}
@@ -203,6 +232,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	if err != nil {
 		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
+	if userQuota-preConsumedQuota < 0 {
+		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+	}
 	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
 	if err != nil {
 		return errorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
@@ -213,7 +245,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		preConsumedQuota = 0
 		common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d has enough quota %d, trusted and no need to pre-consume", userId, userQuota))
 	}
-	if consumeQuota && preConsumedQuota > 0 {
+	if preConsumedQuota > 0 {
 		err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
 			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
@@ -259,6 +291,13 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
 		}
 		requestBody = bytes.NewBuffer(jsonStr)
+	case APITypeGemini:
+		geminiChatRequest := requestOpenAI2Gemini(textRequest)
+		jsonStr, err := json.Marshal(geminiChatRequest)
+		if err != nil {
+			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
+		}
+		requestBody = bytes.NewBuffer(jsonStr)
 	case APITypeZhipu:
 		zhipuRequest := requestOpenAI2Zhipu(textRequest)
 		jsonStr, err := json.Marshal(zhipuRequest)
@@ -281,6 +320,23 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
 		}
 		requestBody = bytes.NewBuffer(jsonStr)
+	case APITypeTencent:
+		apiKey := c.Request.Header.Get("Authorization")
+		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+		appId, secretId, secretKey, err := parseTencentConfig(apiKey)
+		if err != nil {
+			return errorWrapper(err, "invalid_tencent_config", http.StatusInternalServerError)
+		}
+		tencentRequest := requestOpenAI2Tencent(textRequest)
+		tencentRequest.AppId = appId
+		tencentRequest.SecretId = secretId
+		jsonStr, err := json.Marshal(tencentRequest)
+		if err != nil {
+			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
+		}
+		sign := getTencentSign(*tencentRequest, secretKey)
+		c.Request.Header.Set("Authorization", sign)
+		requestBody = bytes.NewBuffer(jsonStr)
 	case APITypeAIProxyLibrary:
 		aiProxyLibraryRequest := requestOpenAI2AIProxyLibrary(textRequest)
 		aiProxyLibraryRequest.LibraryId = c.GetString("library_id")
@@ -328,11 +384,23 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			if textRequest.Stream {
 				req.Header.Set("X-DashScope-SSE", "enable")
 			}
+			if c.GetString("plugin") != "" {
+				req.Header.Set("X-DashScope-Plugin", c.GetString("plugin"))
+			}
+		case APITypeTencent:
+			req.Header.Set("Authorization", apiKey)
+		case APITypePaLM:
+			req.Header.Set("x-goog-api-key", apiKey)
+		case APITypeGemini:
+			req.Header.Set("x-goog-api-key", apiKey)
 		default:
 			req.Header.Set("Authorization", "Bearer "+apiKey)
 		}
 		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		if isStream && c.Request.Header.Get("Accept") == "" {
+			req.Header.Set("Accept", "text/event-stream")
+		}
 		//req.Header.Set("Connection", c.Request.Header.Get("Connection"))
 		resp, err = httpClient.Do(req)
 		if err != nil {
@@ -364,44 +432,40 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 
 	var textResponse TextResponse
 	tokenName := c.GetString("token_name")
-	channelId := c.GetInt("channel_id")
 
 	defer func(ctx context.Context) {
 		// c.Writer.Flush()
 		go func() {
-			if consumeQuota {
-				quota := 0
-				completionRatio := common.GetCompletionRatio(textRequest.Model)
-				promptTokens = textResponse.Usage.PromptTokens
-				completionTokens = textResponse.Usage.CompletionTokens
-
-				quota = promptTokens + int(float64(completionTokens)*completionRatio)
-				quota = int(float64(quota) * ratio)
-				if ratio != 0 && quota <= 0 {
-					quota = 1
-				}
-				totalTokens := promptTokens + completionTokens
-				if totalTokens == 0 {
-					// in this case, must be some error happened
-					// we cannot just return, because we may have to return the pre-consumed quota
-					quota = 0
-				}
-				quotaDelta := quota - preConsumedQuota
-				err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
-				if err != nil {
-					common.LogError(ctx, "error consuming token remain quota: "+err.Error())
-				}
-				err = model.CacheUpdateUserQuota(userId)
-				if err != nil {
-					common.LogError(ctx, "error update user quota cache: "+err.Error())
-				}
-				if quota != 0 {
-					logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-					model.RecordConsumeLog(ctx, userId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
-					model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-					model.UpdateChannelUsedQuota(channelId, quota)
-				}
+			quota := 0
+			completionRatio := common.GetCompletionRatio(textRequest.Model)
+			promptTokens = textResponse.Usage.PromptTokens
+			completionTokens = textResponse.Usage.CompletionTokens
+			quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
+			if ratio != 0 && quota <= 0 {
+				quota = 1
 			}
+			totalTokens := promptTokens + completionTokens
+			if totalTokens == 0 {
+				// in this case, must be some error happened
+				// we cannot just return, because we may have to return the pre-consumed quota
+				quota = 0
+			}
+			quotaDelta := quota - preConsumedQuota
+			err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
+			if err != nil {
+				common.LogError(ctx, "error consuming token remain quota: "+err.Error())
+			}
+			err = model.CacheUpdateUserQuota(userId)
+			if err != nil {
+				common.LogError(ctx, "error update user quota cache: "+err.Error())
+			}
+			if quota != 0 {
+				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
+				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
+				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+				model.UpdateChannelUsedQuota(channelId, quota)
+			}
+
 		}()
 	}(c.Request.Context())
 	switch apiType {
@@ -415,7 +479,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
 			return nil
 		} else {
-			err, usage := openaiHandler(c, resp, consumeQuota, promptTokens, textRequest.Model)
+			err, usage := openaiHandler(c, resp, promptTokens, textRequest.Model)
 			if err != nil {
 				return err
 			}
@@ -489,6 +553,25 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			}
 			return nil
 		}
+	case APITypeGemini:
+		if textRequest.Stream {
+			err, responseText := geminiChatStreamHandler(c, resp)
+			if err != nil {
+				return err
+			}
+			textResponse.Usage.PromptTokens = promptTokens
+			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
+			return nil
+		} else {
+			err, usage := geminiChatHandler(c, resp, promptTokens, textRequest.Model)
+			if err != nil {
+				return err
+			}
+			if usage != nil {
+				textResponse.Usage = *usage
+			}
+			return nil
+		}
 	case APITypeZhipu:
 		if isStream {
 			err, usage := zhipuStreamHandler(c, resp)
@@ -541,24 +624,26 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return nil
 		}
 	case APITypeXunfei:
-		if isStream {
-			auth := c.Request.Header.Get("Authorization")
-			auth = strings.TrimPrefix(auth, "Bearer ")
-			splits := strings.Split(auth, "|")
-			if len(splits) != 3 {
-				return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
-			}
-			err, usage := xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		} else {
-			return errorWrapper(errors.New("xunfei api does not support non-stream mode"), "invalid_api_type", http.StatusBadRequest)
+		auth := c.Request.Header.Get("Authorization")
+		auth = strings.TrimPrefix(auth, "Bearer ")
+		splits := strings.Split(auth, "|")
+		if len(splits) != 3 {
+			return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
 		}
+		var err *OpenAIErrorWithStatusCode
+		var usage *Usage
+		if isStream {
+			err, usage = xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
+		} else {
+			err, usage = xunfeiHandler(c, textRequest, splits[0], splits[1], splits[2])
+		}
+		if err != nil {
+			return err
+		}
+		if usage != nil {
+			textResponse.Usage = *usage
+		}
+		return nil
 	case APITypeAIProxyLibrary:
 		if isStream {
 			err, usage := aiProxyLibraryStreamHandler(c, resp)
@@ -579,6 +664,25 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			}
 			return nil
 		}
+	case APITypeTencent:
+		if isStream {
+			err, responseText := tencentStreamHandler(c, resp)
+			if err != nil {
+				return err
+			}
+			textResponse.Usage.PromptTokens = promptTokens
+			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
+			return nil
+		} else {
+			err, usage := tencentHandler(c, resp)
+			if err != nil {
+				return err
+			}
+			if usage != nil {
+				textResponse.Usage = *usage
+			}
+			return nil
+		}
 	default:
 		return errorWrapper(errors.New("unknown api type"), "unknown_api_type", http.StatusInternalServerError)
 	}

controller/relay-utils.go

@@ -1,52 +1,67 @@
 package controller
 
 import (
+	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
-	"github.com/pkoukk/tiktoken-go"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
+	"one-api/common/image"
+	"one-api/model"
 	"strconv"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkoukk/tiktoken-go"
 )
 
 var stopFinishReason = "stop"
 
+// tokenEncoderMap won't grow after initialization
 var tokenEncoderMap = map[string]*tiktoken.Tiktoken{}
+var defaultTokenEncoder *tiktoken.Tiktoken
 
 func InitTokenEncoders() {
 	common.SysLog("initializing token encoders")
-	fallbackTokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
+	gpt35TokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
 	if err != nil {
-		common.FatalLog(fmt.Sprintf("failed to get fallback token encoder: %s", err.Error()))
+		common.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
+	}
+	defaultTokenEncoder = gpt35TokenEncoder
+	gpt4TokenEncoder, err := tiktoken.EncodingForModel("gpt-4")
+	if err != nil {
+		common.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
 	}
 	for model, _ := range common.ModelRatio {
-		tokenEncoder, err := tiktoken.EncodingForModel(model)
-		if err != nil {
-			common.SysError(fmt.Sprintf("using fallback encoder for model %s", model))
-			tokenEncoderMap[model] = fallbackTokenEncoder
-			continue
+		if strings.HasPrefix(model, "gpt-3.5") {
+			tokenEncoderMap[model] = gpt35TokenEncoder
+		} else if strings.HasPrefix(model, "gpt-4") {
+			tokenEncoderMap[model] = gpt4TokenEncoder
+		} else {
+			tokenEncoderMap[model] = nil
 		}
-		tokenEncoderMap[model] = tokenEncoder
 	}
 	common.SysLog("token encoders initialized")
 }
 
 func getTokenEncoder(model string) *tiktoken.Tiktoken {
-	if tokenEncoder, ok := tokenEncoderMap[model]; ok {
+	tokenEncoder, ok := tokenEncoderMap[model]
+	if ok && tokenEncoder != nil {
 		return tokenEncoder
 	}
-	tokenEncoder, err := tiktoken.EncodingForModel(model)
-	if err != nil {
-		common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
-		tokenEncoder, err = tiktoken.EncodingForModel("gpt-3.5-turbo")
+	if ok {
+		tokenEncoder, err := tiktoken.EncodingForModel(model)
 		if err != nil {
-			common.FatalLog(fmt.Sprintf("failed to get token encoder for model gpt-3.5-turbo: %s", err.Error()))
+			common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
+			tokenEncoder = defaultTokenEncoder
 		}
+		tokenEncoderMap[model] = tokenEncoder
+		return tokenEncoder
 	}
-	tokenEncoderMap[model] = tokenEncoder
-	return tokenEncoder
+	return defaultTokenEncoder
 }
 
 func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
@@ -75,7 +90,33 @@ func countTokenMessages(messages []Message, model string) int {
 	tokenNum := 0
 	for _, message := range messages {
 		tokenNum += tokensPerMessage
-		tokenNum += getTokenNum(tokenEncoder, message.Content)
+		switch v := message.Content.(type) {
+		case string:
+			tokenNum += getTokenNum(tokenEncoder, v)
+		case []any:
+			for _, it := range v {
+				m := it.(map[string]any)
+				switch m["type"] {
+				case "text":
+					tokenNum += getTokenNum(tokenEncoder, m["text"].(string))
+				case "image_url":
+					imageUrl, ok := m["image_url"].(map[string]any)
+					if ok {
+						url := imageUrl["url"].(string)
+						detail := ""
+						if imageUrl["detail"] != nil {
+							detail = imageUrl["detail"].(string)
+						}
+						imageTokens, err := countImageTokens(url, detail)
+						if err != nil {
+							common.SysError("error counting image tokens: " + err.Error())
+						} else {
+							tokenNum += imageTokens
+						}
+					}
+				}
+			}
+		}
 		tokenNum += getTokenNum(tokenEncoder, message.Role)
 		if message.Name != nil {
 			tokenNum += tokensPerName
@@ -86,13 +127,81 @@ func countTokenMessages(messages []Message, model string) int {
 	return tokenNum
 }
 
+const (
+	lowDetailCost         = 85
+	highDetailCostPerTile = 170
+	additionalCost        = 85
+)
+
+// https://platform.openai.com/docs/guides/vision/calculating-costs
+// https://github.com/openai/openai-cookbook/blob/05e3f9be4c7a2ae7ecf029a7c32065b024730ebe/examples/How_to_count_tokens_with_tiktoken.ipynb
+func countImageTokens(url string, detail string) (_ int, err error) {
+	var fetchSize = true
+	var width, height int
+	// Reference: https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding
+	// detail == "auto" is undocumented on how it works, it just said the model will use the auto setting which will look at the image input size and decide if it should use the low or high setting.
+	// According to the official guide, "low" disable the high-res model,
+	// and only receive low-res 512px x 512px version of the image, indicating
+	// that image is treated as low-res when size is smaller than 512px x 512px,
+	// then we can assume that image size larger than 512px x 512px is treated
+	// as high-res. Then we have the following logic:
+	// if detail == "" || detail == "auto" {
+	// 	width, height, err = image.GetImageSize(url)
+	// 	if err != nil {
+	// 		return 0, err
+	// 	}
+	// 	fetchSize = false
+	// 	// not sure if this is correct
+	// 	if width > 512 || height > 512 {
+	// 		detail = "high"
+	// 	} else {
+	// 		detail = "low"
+	// 	}
+	// }
+
+	// However, in my test, it seems to be always the same as "high".
+	// The following image, which is 125x50, is still treated as high-res, taken
+	// 255 tokens in the response of non-stream chat completion api.
+	// https://upload.wikimedia.org/wikipedia/commons/1/10/18_Infantry_Division_Messina.jpg
+	if detail == "" || detail == "auto" {
+		// assume by test, not sure if this is correct
+		detail = "high"
+	}
+	switch detail {
+	case "low":
+		return lowDetailCost, nil
+	case "high":
+		if fetchSize {
+			width, height, err = image.GetImageSize(url)
+			if err != nil {
+				return 0, err
+			}
+		}
+		if width > 2048 || height > 2048 { // max(width, height) > 2048
+			ratio := float64(2048) / math.Max(float64(width), float64(height))
+			width = int(float64(width) * ratio)
+			height = int(float64(height) * ratio)
+		}
+		if width > 768 && height > 768 { // min(width, height) > 768
+			ratio := float64(768) / math.Min(float64(width), float64(height))
+			width = int(float64(width) * ratio)
+			height = int(float64(height) * ratio)
+		}
+		numSquares := int(math.Ceil(float64(width)/512) * math.Ceil(float64(height)/512))
+		result := numSquares*highDetailCostPerTile + additionalCost
+		return result, nil
+	default:
+		return 0, errors.New("invalid detail option")
+	}
+}
+
 func countTokenInput(input any, model string) int {
-	switch input.(type) {
+	switch v := input.(type) {
 	case string:
-		return countTokenText(input.(string), model)
+		return countTokenText(v, model)
 	case []string:
 		text := ""
-		for _, s := range input.([]string) {
+		for _, s := range v {
 			text += s
 		}
 		return countTokenText(text, model)
@@ -133,6 +242,19 @@ func shouldDisableChannel(err *OpenAIError, statusCode int) bool {
 	return false
 }
 
+func shouldEnableChannel(err error, openAIErr *OpenAIError) bool {
+	if !common.AutomaticEnableChannelEnabled {
+		return false
+	}
+	if err != nil {
+		return false
+	}
+	if openAIErr != nil {
+		return false
+	}
+	return true
+}
+
 func setEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("Content-Type", "text/event-stream")
 	c.Writer.Header().Set("Cache-Control", "no-cache")
@@ -141,11 +263,52 @@ func setEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("X-Accel-Buffering", "no")
 }
 
+type GeneralErrorResponse struct {
+	Error    OpenAIError `json:"error"`
+	Message  string      `json:"message"`
+	Msg      string      `json:"msg"`
+	Err      string      `json:"err"`
+	ErrorMsg string      `json:"error_msg"`
+	Header   struct {
+		Message string `json:"message"`
+	} `json:"header"`
+	Response struct {
+		Error struct {
+			Message string `json:"message"`
+		} `json:"error"`
+	} `json:"response"`
+}
+
+func (e GeneralErrorResponse) ToMessage() string {
+	if e.Error.Message != "" {
+		return e.Error.Message
+	}
+	if e.Message != "" {
+		return e.Message
+	}
+	if e.Msg != "" {
+		return e.Msg
+	}
+	if e.Err != "" {
+		return e.Err
+	}
+	if e.ErrorMsg != "" {
+		return e.ErrorMsg
+	}
+	if e.Header.Message != "" {
+		return e.Header.Message
+	}
+	if e.Response.Error.Message != "" {
+		return e.Response.Error.Message
+	}
+	return ""
+}
+
 func relayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *OpenAIErrorWithStatusCode) {
 	openAIErrorWithStatusCode = &OpenAIErrorWithStatusCode{
 		StatusCode: resp.StatusCode,
 		OpenAIError: OpenAIError{
-			Message: fmt.Sprintf("bad response status code %d", resp.StatusCode),
+			Message: "",
 			Type:    "upstream_error",
 			Code:    "bad_response_status_code",
 			Param:   strconv.Itoa(resp.StatusCode),
@@ -159,11 +322,64 @@ func relayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *OpenAIEr
 	if err != nil {
 		return
 	}
-	var textResponse TextResponse
-	err = json.Unmarshal(responseBody, &textResponse)
+	var errResponse GeneralErrorResponse
+	err = json.Unmarshal(responseBody, &errResponse)
 	if err != nil {
 		return
 	}
-	openAIErrorWithStatusCode.OpenAIError = textResponse.Error
+	if errResponse.Error.Message != "" {
+		// OpenAI format error, so we override the default one
+		openAIErrorWithStatusCode.OpenAIError = errResponse.Error
+	} else {
+		openAIErrorWithStatusCode.OpenAIError.Message = errResponse.ToMessage()
+	}
+	if openAIErrorWithStatusCode.OpenAIError.Message == "" {
+		openAIErrorWithStatusCode.OpenAIError.Message = fmt.Sprintf("bad response status code %d", resp.StatusCode)
+	}
 	return
 }
+
+func getFullRequestURL(baseURL string, requestURL string, channelType int) string {
+	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
+
+	if strings.HasPrefix(baseURL, "https://gateway.ai.cloudflare.com") {
+		switch channelType {
+		case common.ChannelTypeOpenAI:
+			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/v1"))
+		case common.ChannelTypeAzure:
+			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/openai/deployments"))
+		}
+	}
+	return fullRequestURL
+}
+
+func postConsumeQuota(ctx context.Context, tokenId int, quotaDelta int, totalQuota int, userId int, channelId int, modelRatio float64, groupRatio float64, modelName string, tokenName string) {
+	// quotaDelta is remaining quota to be consumed
+	err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
+	if err != nil {
+		common.SysError("error consuming token remain quota: " + err.Error())
+	}
+	err = model.CacheUpdateUserQuota(userId)
+	if err != nil {
+		common.SysError("error update user quota cache: " + err.Error())
+	}
+	// totalQuota is total quota consumed
+	if totalQuota != 0 {
+		logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
+		model.RecordConsumeLog(ctx, userId, channelId, totalQuota, 0, modelName, tokenName, totalQuota, logContent)
+		model.UpdateUserUsedQuotaAndRequestCount(userId, totalQuota)
+		model.UpdateChannelUsedQuota(channelId, totalQuota)
+	}
+	if totalQuota <= 0 {
+		common.LogError(ctx, fmt.Sprintf("totalQuota consumed is %d, something is wrong", totalQuota))
+	}
+}
+
+func GetAPIVersion(c *gin.Context) string {
+	query := c.Request.URL.Query()
+	apiVersion := query.Get("api-version")
+	if apiVersion == "" {
+		apiVersion = c.GetString("api_version")
+	}
+	return apiVersion
+}

controller/relay-xunfei.go

@@ -81,7 +81,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 		if message.Role == "system" {
 			messages = append(messages, XunfeiMessage{
 				Role:    "user",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, XunfeiMessage{
 				Role:    "assistant",
@@ -90,7 +90,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 		} else {
 			messages = append(messages, XunfeiMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -118,6 +118,7 @@ func responseXunfei2OpenAI(response *XunfeiChatResponse) *OpenAITextResponse {
 			Role:    "assistant",
 			Content: response.Payload.Choices.Text[0].Content,
 		},
+		FinishReason: stopFinishReason,
 	}
 	fullTextResponse := OpenAITextResponse{
 		Object:  "chat.completion",
@@ -177,33 +178,91 @@ func buildXunfeiAuthUrl(hostUrl string, apiKey, apiSecret string) string {
 }
 
 func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
+	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
+	if err != nil {
+		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
+	}
+	setEventStreamHeaders(c)
 	var usage Usage
-	query := c.Request.URL.Query()
-	apiVersion := query.Get("api-version")
-	if apiVersion == "" {
-		apiVersion = c.GetString("api_version")
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case xunfeiResponse := <-dataChan:
+			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
+			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
+			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
+			response := streamResponseXunfei2OpenAI(&xunfeiResponse)
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	return nil, &usage
+}
+
+func xunfeiHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
+	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
+	if err != nil {
+		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
 	}
-	if apiVersion == "" {
-		apiVersion = "v1.1"
-		common.SysLog("api_version not found, use default: " + apiVersion)
+	var usage Usage
+	var content string
+	var xunfeiResponse XunfeiChatResponse
+	stop := false
+	for !stop {
+		select {
+		case xunfeiResponse = <-dataChan:
+			if len(xunfeiResponse.Payload.Choices.Text) == 0 {
+				continue
+			}
+			content += xunfeiResponse.Payload.Choices.Text[0].Content
+			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
+			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
+			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
+		case stop = <-stopChan:
+		}
 	}
-	domain := "general"
-	if apiVersion == "v2.1" {
-		domain = "generalv2"
+	if len(xunfeiResponse.Payload.Choices.Text) == 0 {
+		xunfeiResponse.Payload.Choices.Text = []XunfeiChatResponseTextItem{
+			{
+				Content: "",
+			},
+		}
 	}
-	hostUrl := fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion)
+	xunfeiResponse.Payload.Choices.Text[0].Content = content
+
+	response := responseXunfei2OpenAI(&xunfeiResponse)
+	jsonResponse, err := json.Marshal(response)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	_, _ = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}
+
+func xunfeiMakeRequest(textRequest GeneralOpenAIRequest, domain, authUrl, appId string) (chan XunfeiChatResponse, chan bool, error) {
 	d := websocket.Dialer{
 		HandshakeTimeout: 5 * time.Second,
 	}
-	conn, resp, err := d.Dial(buildXunfeiAuthUrl(hostUrl, apiKey, apiSecret), nil)
+	conn, resp, err := d.Dial(authUrl, nil)
 	if err != nil || resp.StatusCode != 101 {
-		return errorWrapper(err, "dial_failed", http.StatusInternalServerError), nil
+		return nil, nil, err
 	}
 	data := requestOpenAI2Xunfei(textRequest, appId, domain)
 	err = conn.WriteJSON(data)
 	if err != nil {
-		return errorWrapper(err, "write_json_failed", http.StatusInternalServerError), nil
+		return nil, nil, err
 	}
+
 	dataChan := make(chan XunfeiChatResponse)
 	stopChan := make(chan bool)
 	go func() {
@@ -230,61 +289,24 @@ func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case xunfeiResponse := <-dataChan:
-			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
-			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
-			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
-			response := streamResponseXunfei2OpenAI(&xunfeiResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
-		}
-	})
-	return nil, &usage
+
+	return dataChan, stopChan, nil
 }
 
-func xunfeiHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var xunfeiResponse XunfeiChatResponse
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+func getXunfeiAuthUrl(c *gin.Context, apiKey string, apiSecret string) (string, string) {
+	query := c.Request.URL.Query()
+	apiVersion := query.Get("api-version")
+	if apiVersion == "" {
+		apiVersion = c.GetString("api_version")
 	}
-	err = resp.Body.Close()
-	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	if apiVersion == "" {
+		apiVersion = "v1.1"
+		common.SysLog("api_version not found, use default: " + apiVersion)
 	}
-	err = json.Unmarshal(responseBody, &xunfeiResponse)
-	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	domain := "general"
+	if apiVersion != "v1.1" {
+		domain += strings.Split(apiVersion, ".")[0]
 	}
-	if xunfeiResponse.Header.Code != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
-				Message: xunfeiResponse.Header.Message,
-				Type:    "xunfei_error",
-				Param:   "",
-				Code:    xunfeiResponse.Header.Code,
-			},
-			StatusCode: resp.StatusCode,
-		}, nil
-	}
-	fullTextResponse := responseXunfei2OpenAI(&xunfeiResponse)
-	jsonResponse, err := json.Marshal(fullTextResponse)
-	if err != nil {
-		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-	c.Writer.Header().Set("Content-Type", "application/json")
-	c.Writer.WriteHeader(resp.StatusCode)
-	_, err = c.Writer.Write(jsonResponse)
-	return nil, &fullTextResponse.Usage
+	authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
+	return domain, authUrl
 }

controller/relay-zhipu.go

@@ -114,7 +114,7 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 		if message.Role == "system" {
 			messages = append(messages, ZhipuMessage{
 				Role:    "system",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, ZhipuMessage{
 				Role:    "user",
@@ -123,7 +123,7 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 		} else {
 			messages = append(messages, ZhipuMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}
@@ -290,6 +290,7 @@ func zhipuHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 		}, nil
 	}
 	fullTextResponse := responseZhipu2OpenAI(&zhipuResponse)
+	fullTextResponse.Model = "chatglm"
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
 		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil

controller/relay.go

@@ -12,10 +12,106 @@ import (
 
 type Message struct {
 	Role    string  `json:"role"`
-	Content string  `json:"content"`
+	Content any     `json:"content"`
 	Name    *string `json:"name,omitempty"`
 }
 
+type ImageURL struct {
+	Url    string `json:"url,omitempty"`
+	Detail string `json:"detail,omitempty"`
+}
+
+type TextContent struct {
+	Type string `json:"type,omitempty"`
+	Text string `json:"text,omitempty"`
+}
+
+type ImageContent struct {
+	Type     string    `json:"type,omitempty"`
+	ImageURL *ImageURL `json:"image_url,omitempty"`
+}
+
+const (
+	ContentTypeText     = "text"
+	ContentTypeImageURL = "image_url"
+)
+
+type OpenAIMessageContent struct {
+	Type     string    `json:"type,omitempty"`
+	Text     string    `json:"text"`
+	ImageURL *ImageURL `json:"image_url,omitempty"`
+}
+
+func (m Message) IsStringContent() bool {
+	_, ok := m.Content.(string)
+	return ok
+}
+
+func (m Message) StringContent() string {
+	content, ok := m.Content.(string)
+	if ok {
+		return content
+	}
+	contentList, ok := m.Content.([]any)
+	if ok {
+		var contentStr string
+		for _, contentItem := range contentList {
+			contentMap, ok := contentItem.(map[string]any)
+			if !ok {
+				continue
+			}
+			if contentMap["type"] == ContentTypeText {
+				if subStr, ok := contentMap["text"].(string); ok {
+					contentStr += subStr
+				}
+			}
+		}
+		return contentStr
+	}
+	return ""
+}
+
+func (m Message) ParseContent() []OpenAIMessageContent {
+	var contentList []OpenAIMessageContent
+	content, ok := m.Content.(string)
+	if ok {
+		contentList = append(contentList, OpenAIMessageContent{
+			Type: ContentTypeText,
+			Text: content,
+		})
+		return contentList
+	}
+	anyList, ok := m.Content.([]any)
+	if ok {
+		for _, contentItem := range anyList {
+			contentMap, ok := contentItem.(map[string]any)
+			if !ok {
+				continue
+			}
+			switch contentMap["type"] {
+			case ContentTypeText:
+				if subStr, ok := contentMap["text"].(string); ok {
+					contentList = append(contentList, OpenAIMessageContent{
+						Type: ContentTypeText,
+						Text: subStr,
+					})
+				}
+			case ContentTypeImageURL:
+				if subObj, ok := contentMap["image_url"].(map[string]any); ok {
+					contentList = append(contentList, OpenAIMessageContent{
+						Type: ContentTypeImageURL,
+						ImageURL: &ImageURL{
+							Url: subObj["url"].(string),
+						},
+					})
+				}
+			}
+		}
+		return contentList
+	}
+	return nil
+}
+
 const (
 	RelayModeUnknown = iota
 	RelayModeChatCompletions
@@ -24,24 +120,37 @@ const (
 	RelayModeModerations
 	RelayModeImagesGenerations
 	RelayModeEdits
-	RelayModeAudio
+	RelayModeAudioSpeech
+	RelayModeAudioTranscription
+	RelayModeAudioTranslation
 )
 
 // https://platform.openai.com/docs/api-reference/chat
 
+type ResponseFormat struct {
+	Type string `json:"type,omitempty"`
+}
+
 type GeneralOpenAIRequest struct {
-	Model       string    `json:"model,omitempty"`
-	Messages    []Message `json:"messages,omitempty"`
-	Prompt      any       `json:"prompt,omitempty"`
-	Stream      bool      `json:"stream,omitempty"`
-	MaxTokens   int       `json:"max_tokens,omitempty"`
-	Temperature float64   `json:"temperature,omitempty"`
-	TopP        float64   `json:"top_p,omitempty"`
-	N           int       `json:"n,omitempty"`
-	Input       any       `json:"input,omitempty"`
-	Instruction string    `json:"instruction,omitempty"`
-	Size        string    `json:"size,omitempty"`
-	Functions   any       `json:"functions,omitempty"`
+	Model            string          `json:"model,omitempty"`
+	Messages         []Message       `json:"messages,omitempty"`
+	Prompt           any             `json:"prompt,omitempty"`
+	Stream           bool            `json:"stream,omitempty"`
+	MaxTokens        int             `json:"max_tokens,omitempty"`
+	Temperature      float64         `json:"temperature,omitempty"`
+	TopP             float64         `json:"top_p,omitempty"`
+	N                int             `json:"n,omitempty"`
+	Input            any             `json:"input,omitempty"`
+	Instruction      string          `json:"instruction,omitempty"`
+	Size             string          `json:"size,omitempty"`
+	Functions        any             `json:"functions,omitempty"`
+	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
+	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
+	Seed             float64         `json:"seed,omitempty"`
+	Tools            any             `json:"tools,omitempty"`
+	ToolChoice       any             `json:"tool_choice,omitempty"`
+	User             string          `json:"user,omitempty"`
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {
@@ -77,16 +186,51 @@ type TextRequest struct {
 	//Stream   bool      `json:"stream"`
 }
 
+// ImageRequest docs: https://platform.openai.com/docs/api-reference/images/create
 type ImageRequest struct {
-	Prompt string `json:"prompt"`
-	N      int    `json:"n"`
-	Size   string `json:"size"`
+	Model          string `json:"model"`
+	Prompt         string `json:"prompt" binding:"required"`
+	N              int    `json:"n,omitempty"`
+	Size           string `json:"size,omitempty"`
+	Quality        string `json:"quality,omitempty"`
+	ResponseFormat string `json:"response_format,omitempty"`
+	Style          string `json:"style,omitempty"`
+	User           string `json:"user,omitempty"`
 }
 
-type AudioResponse struct {
+type WhisperJSONResponse struct {
 	Text string `json:"text,omitempty"`
 }
 
+type WhisperVerboseJSONResponse struct {
+	Task     string    `json:"task,omitempty"`
+	Language string    `json:"language,omitempty"`
+	Duration float64   `json:"duration,omitempty"`
+	Text     string    `json:"text,omitempty"`
+	Segments []Segment `json:"segments,omitempty"`
+}
+
+type Segment struct {
+	Id               int     `json:"id"`
+	Seek             int     `json:"seek"`
+	Start            float64 `json:"start"`
+	End              float64 `json:"end"`
+	Text             string  `json:"text"`
+	Tokens           []int   `json:"tokens"`
+	Temperature      float64 `json:"temperature"`
+	AvgLogprob       float64 `json:"avg_logprob"`
+	CompressionRatio float64 `json:"compression_ratio"`
+	NoSpeechProb     float64 `json:"no_speech_prob"`
+}
+
+type TextToSpeechRequest struct {
+	Model          string  `json:"model" binding:"required"`
+	Input          string  `json:"input" binding:"required"`
+	Voice          string  `json:"voice" binding:"required"`
+	Speed          float64 `json:"speed"`
+	ResponseFormat string  `json:"response_format"`
+}
+
 type Usage struct {
 	PromptTokens     int `json:"prompt_tokens"`
 	CompletionTokens int `json:"completion_tokens"`
@@ -119,6 +263,7 @@ type OpenAITextResponseChoice struct {
 
 type OpenAITextResponse struct {
 	Id      string                     `json:"id"`
+	Model   string                     `json:"model,omitempty"`
 	Object  string                     `json:"object"`
 	Created int64                      `json:"created"`
 	Choices []OpenAITextResponseChoice `json:"choices"`
@@ -149,7 +294,7 @@ type ChatCompletionsStreamResponseChoice struct {
 	Delta struct {
 		Content string `json:"content"`
 	} `json:"delta"`
-	FinishReason *string `json:"finish_reason"`
+	FinishReason *string `json:"finish_reason,omitempty"`
 }
 
 type ChatCompletionsStreamResponse struct {
@@ -183,14 +328,22 @@ func Relay(c *gin.Context) {
 		relayMode = RelayModeImagesGenerations
 	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/edits") {
 		relayMode = RelayModeEdits
-	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
-		relayMode = RelayModeAudio
+	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
+		relayMode = RelayModeAudioSpeech
+	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
+		relayMode = RelayModeAudioTranscription
+	} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/translations") {
+		relayMode = RelayModeAudioTranslation
 	}
 	var err *OpenAIErrorWithStatusCode
 	switch relayMode {
 	case RelayModeImagesGenerations:
 		err = relayImageHelper(c, relayMode)
-	case RelayModeAudio:
+	case RelayModeAudioSpeech:
+		fallthrough
+	case RelayModeAudioTranslation:
+		fallthrough
+	case RelayModeAudioTranscription:
 		err = relayAudioHelper(c, relayMode)
 	default:
 		err = relayTextHelper(c, relayMode)

docker-compose.yml

@@ -9,21 +9,21 @@ services:
     ports:
       - "3000:3000"
     volumes:
-      - ./data:/data
+      - ./data/oneapi:/data
       - ./logs:/app/logs
     environment:
-      - SQL_DSN=root:123456@tcp(host.docker.internal:3306)/one-api  # 修改此行，或注释掉以使用 SQLite 作为数据库
+      - SQL_DSN=oneapi:123456@tcp(db:3306)/one-api  # 修改此行，或注释掉以使用 SQLite 作为数据库
       - REDIS_CONN_STRING=redis://redis
       - SESSION_SECRET=random_string  # 修改为随机字符串
       - TZ=Asia/Shanghai
 #      - NODE_TYPE=slave  # 多机部署时从节点取消注释该行
 #      - SYNC_FREQUENCY=60  # 需要定期从数据库加载数据时取消注释该行
 #      - FRONTEND_BASE_URL=https://openai.justsong.cn  # 多机部署时从节点取消注释该行
-
     depends_on:
       - redis
+      - db
     healthcheck:
-      test: [ "CMD-SHELL", "curl -s http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk '{print $2}' | grep 'true'" ]
+      test: [ "CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $2}'" ]
       interval: 30s
       timeout: 10s
       retries: 3
@@ -32,3 +32,18 @@ services:
     image: redis:latest
     container_name: redis
     restart: always
+
+  db:
+    image: mysql:8.2.0
+    restart: always
+    container_name: mysql
+    volumes:
+      - ./data/mysql:/var/lib/mysql  # 挂载目录，持久化存储
+    ports:
+      - '3306:3306'
+    environment:
+      TZ: Asia/Shanghai   # 设置时区
+      MYSQL_ROOT_PASSWORD: 'OneAPI@justsong' # 设置 root 用户的密码
+      MYSQL_USER: oneapi   # 创建专用用户
+      MYSQL_PASSWORD: '123456'    # 设置专用用户密码
+      MYSQL_DATABASE: one-api   # 自动创建数据库

go.mod

@@ -15,8 +15,11 @@ require (
 	github.com/google/uuid v1.3.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/pkoukk/tiktoken-go v0.1.5
-	golang.org/x/crypto v0.9.0
+	github.com/stretchr/testify v1.8.3
+	golang.org/x/crypto v0.17.0
+	golang.org/x/image v0.14.0
 	gorm.io/driver/mysql v1.4.3
+	gorm.io/driver/postgres v1.5.2
 	gorm.io/driver/sqlite v1.4.3
 	gorm.io/gorm v1.25.0
 )
@@ -25,6 +28,7 @@ require (
 	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.10.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
@@ -49,13 +53,13 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.11 // indirect
 	golang.org/x/arch v0.3.0 // indirect
-	golang.org/x/net v0.10.0 // indirect
-	golang.org/x/sys v0.8.0 // indirect
-	golang.org/x/text v0.9.0 // indirect
+	golang.org/x/net v0.17.0 // indirect
+	golang.org/x/sys v0.15.0 // indirect
+	golang.org/x/text v0.14.0 // indirect
 	google.golang.org/protobuf v1.30.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	gorm.io/driver/postgres v1.5.2 // indirect
 )

go.sum

@@ -150,11 +150,13 @@ golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUu
 golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
 golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.9.0 h1:LF6fAI+IutBocDJ2OT0Q1g8plpYljMZ4+lty+dsqw3g=
-golang.org/x/crypto v0.9.0/go.mod h1:yrmDGqONDYtNj3tH8X9dzUun2m2lzPa9ngI6/RUPGR0=
+golang.org/x/crypto v0.17.0 h1:r8bRNjWL3GshPW3gkd+RpvzWrZAwPS49OmTGZ/uhM4k=
+golang.org/x/crypto v0.17.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
+golang.org/x/image v0.14.0 h1:tNgSxAFe3jC4uYqvZdTr84SZoM1KfwdC9SKIFrLjFn4=
+golang.org/x/image v0.14.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
-golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
+golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
+golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -162,14 +164,14 @@ golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.8.0 h1:EBmGv8NaZBZTWvrbjNoL6HVt+IVy3QDQpJs7VRIw3tU=
-golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.15.0 h1:h48lPFYpsTvQJZF4EKyI4aLHaev3CxivZmv7yZig9pc=
+golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.9.0 h1:2sjJmO8cDvYveuX97RDLsxlyUxLl+GHoLxBiRdHllBE=
-golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
+golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -198,7 +200,6 @@ gorm.io/driver/postgres v1.5.2/go.mod h1:fmpX0m2I1PKuR7mKZiEluwrP3hbs+ps7JIGMUBp
 gorm.io/driver/sqlite v1.4.3 h1:HBBcZSDnWi5BW3B3rwvVTc510KGkBkexlOg0QrmLUuU=
 gorm.io/driver/sqlite v1.4.3/go.mod h1:0Aq3iPO+v9ZKbcdiz8gLWRw5VOPcBOPUQJFLq5e2ecI=
 gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
-gorm.io/gorm v1.24.0 h1:j/CoiSm6xpRpmzbFJsQHYj+I8bGYWLXVHeYEyyKlF74=
 gorm.io/gorm v1.24.0/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
 gorm.io/gorm v1.25.0 h1:+KtYtb2roDz14EQe4bla8CbQlmb9dN3VejSai3lprfU=
 gorm.io/gorm v1.25.0/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=

i18n/en.json

@@ -119,6 +119,7 @@
   " 年 ": " y ",
   "未测试": "Not tested",
   "通道 ${name} 测试成功，耗时 ${time.toFixed(2)} 秒。": "Channel ${name} test succeeded, time consumed ${time.toFixed(2)} s.",
+  "已成功开始测试所有通道，请刷新页面查看结果。": "All channels have been successfully tested, please refresh the page to view the results.",
   "已成功开始测试所有已启用通道，请刷新页面查看结果。": "All enabled channels have been successfully tested, please refresh the page to view the results.",
   "通道 ${name} 余额更新成功！": "Channel ${name} balance updated successfully!",
   "已更新完毕所有已启用通道余额！": "The balance of all enabled channels has been updated!",
@@ -139,6 +140,7 @@
   "启用": "Enable",
   "编辑": "Edit",
   "添加新的渠道": "Add a new channel",
+  "测试所有通道": "Test all channels",
   "测试所有已启用通道": "Test all enabled channels",
   "更新所有已启用通道余额": "Update the balance of all enabled channels",
   "刷新": "Refresh",
@@ -456,6 +458,7 @@
   "使用明细（总消耗额度：{renderQuota(stat.quota)}）": "Usage Details (Total Consumption Quota: {renderQuota(stat.quota)})",
   "用户名称": "User Name",
   "令牌名称": "Token Name",
+  "默认令牌": "Default Token",
   "留空则查询全部用户": "Leave blank to query all users",
   "留空则查询全部令牌": "Leave blank to query all tokens",
   "模型名称": "Model Name",
@@ -524,5 +527,250 @@
   "模型版本": "Model version",
   "请输入星火大模型版本，注意是接口地址中的版本号，例如：v2.1": "Please enter the version of the Starfire model, note that it is the version number in the interface address, for example: v2.1",
   "点击查看": "click to view",
-  "请确保已在 Azure 上创建了 gpt-35-turbo 模型，并且 apiVersion 已正确填写！": "Please make sure that the gpt-35-turbo model has been created on Azure, and the apiVersion has been filled in correctly!"
+  "请确保已在 Azure 上创建了 gpt-35-turbo 模型，并且 apiVersion 已正确填写！": "Please make sure that the gpt-35-turbo model has been created on Azure, and the apiVersion has been filled in correctly!",
+  "处理中...": "Processing...",
+  "绑定成功！": "Binding successful!",
+  "登录成功！": "Login successful!",
+  "操作失败，重定向至登录界面中...": "Operation failed, redirecting to login screen...",
+  "出现错误，第 ${count} 次重试中...": "An error occurred, retrying ${count}...",
+  "首页": "Home",
+  "渠道": "Channel",
+  "令牌": "API Keys",
+  "兑换": "Redeem",
+  "充值": "Recharge",
+  "用户": "Users",
+  "日志": "Logs",
+  "设置": "Settings",
+  "关于": "About",
+  "聊天": "Chat",
+  "注销成功!": "Logout successful!",
+  "注销": "Log out",
+  "登录": "Log in",
+  "注册": "Sign up",
+  "加载{name}中...": "Loading {name}...",
+  "未登录或登录已过期，请重新登录！": "Not logged in or login has expired, please log in again!",
+  "请立刻修改默认密码！": "Please change the default password immediately!",
+  "欢迎回来": "Welcome back",
+  "没有账户？": "No account?",
+  "立刻注册": "Sign up now",
+  "用户名": "Username",
+  "密码": "Password",
+  "正在登录……": "Logging in...",
+  "忘记密码": "Forgot password",
+  "其他方式": "Other methods",
+  "微信扫码关注公众号，输入「验证码」获取验证码（三分钟内有效）": "Scan the QR code with WeChat, follow the official account and enter 'verification code' to get the verification code (valid within three minutes)",
+  "验证码": "Verification code",
+  "全部用户": "All users",
+  "当前用户": "Current user",
+  "全部": "All",
+  "消费": "Consumption",
+  "管理": "Management",
+  "系统": "System",
+  "未知": "Unknown",
+  "其他模型": "Other models",
+  "复制成功": "Copy successful",
+  "使用明细": "Usages",
+  "刷新": "Refresh",
+  "收起面板": "Collapse panel",
+  "展开面板": "Expand panel",
+  "显示查询选项": "Show search options",
+  "隐藏查询选项": "Hide search options",
+  "用户名称": "User name",
+  "可选值": "Optional values",
+  "渠道 ID": "Channel ID",
+  "令牌名称": "Key name",
+  "模型名称": "Model name",
+  "起始时间": "Start time",
+  "结束时间": "End time",
+  "查询": "Query",
+  "隐藏条形图": "Hide bar chart",
+  "显示条形图": "Show bar chart",
+  "折线条形图只展示最新50条数据": "Line and bar charts only show the latest 50 pieces of data",
+  "总消耗": "Total consumption",
+  "总共调用了 {payload[0].value} 次": "A total of {payload[0].value} calls were made",
+  "{model.name}: {model.value} 次": "{model.name}: {model.value} times",
+  "总共调用了 {payload[0].value} 次 {payload[0].name}": "A total of {payload[0].value} {payload[0].name} calls were made",
+  "总消耗额度": "Total consumption limit",
+  "暂无数据": "No data available",
+  "更多数据统计图形即将到来，敬请期待！": "More data statistics graphics are coming soon, stay tuned!",
+  "复制用户名": "Copy username",
+  "{`共 ${counts} 条数据`}": "{`A total of ${counts} pieces of data`}",
+  "共 0 条数据": "A total of 0 pieces of data",
+  "选择明细分类": "Select detail category",
+  "模型倍率": "model rate",
+  "分组倍率": "group rate",
+  "新密码已复制到剪贴板：": "New password has been copied to the clipboard:",
+  "密码重置确认": "Password reset confirmation",
+  "邮箱地址": "Email address",
+  "新密码": "New password",
+  "密码已复制到剪贴板：": "Password has been copied to the clipboard:",
+  "密码重置完成": "Password reset complete",
+  "提交": "Submit",
+  "返回登录": "Return to login",
+  "请稍后重试，浏览器环境检查未通过": "Please try again later, browser environment check failed",
+  "重置邮件发送成功，请检查邮箱！": "Reset email sent successfully, please check your email!",
+  "密码重置": "Password reset",
+  "重试": "Retry",
+  "组": "Group",
+  "令牌已重置并已复制到剪贴板": "Token has been reset and copied to the clipboard",
+  "邀请链接已复制到剪切板": "Invitation link has been copied to the clipboard",
+  "系统令牌已复制到剪切板": "System token has been copied to the clipboard",
+  "请输入你的账户名以确认删除！": "Please enter your account name to confirm deletion!",
+  "账户已删除！": "Account has been deleted!",
+  "微信账户绑定成功！": "WeChat account binding successful!",
+  "请稍后几秒重试，Turnstile 正在检查用户环境！": "Please try again in a few seconds, Turnstile is checking the user environment!",
+  "验证码发送成功，请检查邮箱！": "Verification code sent successfully, please check your email!",
+  "邮箱账户绑定成功！": "Email account binding successful!",
+  "个人信息": "Personal information",
+  "编辑个人信息": "Edit personal information",
+  "生成系统访问令牌": "Generate system access token",
+  "复制邀请链接": "Copy invitation link",
+  "删除个人帐户": "Delete personal account",
+  "普通用户": "Regular user",
+  "管理员": "Administrator",
+  "超级管理员": "Super administrator",
+  "显示名称": "Display name",
+  "GitHub 账号": "GitHub account",
+  "微信账号": "WeChat account",
+  "修改个人信息只允许在电脑端进行。生成的令牌用于系统管理，而非用于请求 OpenAI 相关的服务，请知悉。": "Modifying personal information is only allowed on a computer. The generated token is for system management, not for requesting OpenAI related services. Please be aware.",
+  "可用模型": "Available models",
+  "账号绑定": "Account binding",
+  "绑定微信": "Bind WeChat",
+  "绑定 GitHub": "Bind GitHub",
+  "绑定邮箱": "Bind Email",
+  "绑定": "Bind",
+  "绑定邮箱地址": "Bind email address",
+  "输入邮箱地址": "Enter email address",
+  "重新发送": "Resend",
+  "获取验证码": "Get verification code",
+  "确认绑定": "Confirm binding",
+  "取消": "Cancel",
+  "危险操作": "Dangerous operation",
+  "您正在删除自己的帐户，将清空所有数据且不可恢复": "You are deleting your own account, all data will be cleared and cannot be recovered",
+  "输入你的账户名": "Enter your account name",
+  "以确认删除": "To confirm deletion",
+  "确认删除": "Confirm deletion",
+  "未使用": "Not used",
+  "已禁用": "Disabled",
+  "已使用": "Used",
+  "未知状态": "Unknown status",
+  "操作成功完成！": "Operation successfully completed!",
+  "搜索兑换码的 ID 和名称 ...": "Search for the ID and name of the redemption code ...",
+  "名称": "Name",
+  "状态": "Status",
+  "额度": "Quota",
+  "创建时间": "Creation time",
+  "兑换时间": "Redemption time",
+  "操作": "Operation",
+  "尚未兑换": "Not yet redeemed",
+  "已复制到剪贴板！": "Copied to clipboard!",
+  "无法复制到剪贴板，请手动复制，已将兑换码填入搜索框。": "Unable to copy to clipboard, please copy manually. The redemption code has been filled in the search box.",
+  "复制": "Copy",
+  "删除": "Delete",
+  "禁用": "Disable",
+  "启用": "Enable",
+  "编辑": "Edit",
+  "添加新的兑换码": "Add new redemption code",
+  "密码长度不得小于 8 位！": "Password length must not be less than 8 characters!",
+  "两次输入的密码不一致": "The two passwords entered do not match",
+  "注册成功！": "Registration successful!",
+  "请填写注册邮箱！": "Please fill in the registration email!",
+  "请在${verificationTimeout}秒后再试": "Please try again after ${verificationTimeout} seconds",
+  "验证码发送成功，请检查你的邮箱！": "Verification code sent successfully, please check your email!",
+  "已有账户？": "Already have an account?",
+  "请输入用户名（最长 12 位）": "Please enter a username (up to 12 characters)",
+  "请输入密码（最短 8 位，最长 20 位）": "Please enter a password (minimum 8 characters, maximum 20 characters)",
+  "请再次输入密码": "Please enter the password again",
+  "请输入邮箱地址": "Please enter an email address",
+  "秒后可重发": "Can be resent after seconds",
+  "请输入邮箱验证码": "Please enter the email verification code",
+  "已过期": "Expired",
+  "已启用": "Enabled",
+  "已耗尽": "Exhausted",
+  "无": "None",
+  "令牌密钥": "API Key",
+  "令牌状态": "Key status",
+  "已用额度": "Used quota",
+  "剩余额度": "Remaining quota",
+  "过期时间": "Expiration time",
+  "你确定要删除这个令牌吗?": "Are you sure you want to delete this key?",
+  "无法复制到剪贴板，请手动复制，已将令牌密钥填入搜索框": "Unable to copy to clipboard, please copy manually. The key key has been filled in the search box.",
+  "无限制": "Unlimited",
+  "永不过期": "Never expires",
+  "使用 API 访问令牌进行服务鉴权和计费。": "Use API Key for service authentication and billing.",
+  "API 访问令牌关系到您的个人利益，请妥善留存，不要与其他人共享，也不要保存在客户端代码中。": "API Key is related to your personal interests. Please keep it properly. Do not share it with others or save it in client code.",
+  "创建令牌": "Create Key",
+  "什么都还没有，快去创建一个令牌开始使用吧！": "Nothing yet, go create a key to start using!",
+  "你确定要删除该令牌吗": "Are you sure you want to delete this key",
+  "导出令牌信息": "Export key information",
+  "错误：未登录或登录已过期，请重新登录！": "Error: Not logged in or login has expired, please log in again!",
+  "错误：请求次数过多，请稍后再试！": "Error: Too many requests, please try again later!",
+  "错误：服务器内部错误，请联系管理员！": "Error: Server internal error, please contact the online customer service!",
+  "本站仅作演示之用，无服务端！": "This site is for demonstration purposes only, no server!",
+  "错误：": "Error:",
+  "加载首页内容失败...": "Failed to load homepage content...",
+  "系统状况": "System status",
+  "系统信息": "System information",
+  "系统信息总览": "System information overview",
+  "名称：": "Name:",
+  "版本：": "Version:",
+  "源码：": "Source code:",
+  "启动时间：": "Startup time:",
+  "系统配置": "System configuration",
+  "系统配置总览": "System configuration overview",
+  "邮箱验证：": "Email verification:",
+  "未启用": "Not enabled",
+  "Turnstile 用户校验：": "Turnstile user verification:",
+  "页面不存在": "Page does not exist",
+  "请检查你的浏览器地址是否正确": "Please check if your browser address is correct",
+  "个人设置": "Personal settings",
+  "运营设置": "Operations settings",
+  "系统设置": "System settings",
+  "其他设置": "Other settings",
+  "默认令牌": "Default key",
+  "过期时间必须在当前时间之后！": "Expiration time must be after the current time!",
+  "额度必须大于等于 0！": "Quota must be greater than or equal to 0!",
+  "过期时间格式错误！": "Expiration time format error!",
+  "创建令牌数量必须大于等于 1！": "The number of keys to create must be greater than or equal to 1!",
+  "令牌修改成功": "API Key modification successful",
+  "令牌创建成功": "API Key creation successful",
+  "更新令牌信息": "Update key information",
+  "创建新的令牌": "Create a new key",
+  "请输入名称": "Please enter a name",
+  "请输入过期时间，格式为 yyyy-MM-dd HH:mm:ss，-1 表示无限制": "Please enter the expiration time, the format is yyyy-MM-dd HH:mm:ss, -1 means unlimited",
+  "无限额度": "Unlimited quota",
+  "注意：启用无限额度后，已用额度将不再进行计算。": "Note: After enabling unlimited quota, the used quota will no longer be calculated.",
+  "等于": "Equals",
+  "请输入额度（单位：token）": "Please enter the quota (unit: token)",
+  "创建令牌数量": "Create key quantity",
+  "请输入令牌数量": "Please enter the number of keys",
+  "注意：令牌的额度仅用于限制令牌本身的最大额度使用量，实际的使用受到账户的剩余额度限制。": "Note: The quota of the key is only used to limit the maximum quota usage of the key itself, and the actual usage is subject to the remaining quota of the account.",
+  "我的令牌": "My keys",
+  "请输入额度兑换码！": "Please enter the redeem code!",
+  "充值成功！": "Recharge successful!",
+  "请求失败": "Request failed",
+  "超级管理员未设置充值链接！": "The super administrator did not set a recharge link!",
+  "充值额度": "Recharge quota",
+  "兑换中...": "Redeeming...",
+  "请点击充值以获取额度兑换码。": "Please click recharge to get the quota redemption code.",
+  "用户信息更新成功！": "User information updated successfully!",
+  "更新用户信息": "Update user information",
+  "请输入新的用户名": "Please enter a new username",
+  "请输入新的密码，最短 8 位": "Please enter a new password, at least 8 characters",
+  "请输入新的显示名称": "Please enter a new display name",
+  "分组": "Group",
+  "请选择分组": "Please select a group",
+  "请在系统设置页面编辑分组倍率以添加新的分组：": "Please edit the group rate on the system settings page to add a new group:",
+  "请输入新的剩余额度": "Please enter a new remaining quota",
+  "已绑定的 GitHub 账户": "Bound GitHub account",
+  "此项只读，需要用户通过个人设置页面的相关绑定按钮进行绑定，不可直接修改": "This item is read-only, users need to bind through the relevant binding button on the personal settings page, cannot be directly modified",
+  "已绑定的微信账户": "Bound WeChat account",
+  "已绑定的邮箱账户": "Bound email account",
+  "新版本可用：${data.version}，请使用快捷键 Shift + F5 刷新页面": "New version available: ${data.version}, please refresh the page using the shortcut key Shift + F5",
+  "无法正常连接至服务器！": "Unable to connect to the server normally!",
+  "提示：": "Input:",
+  "补全：": "Output:",
+  "搜索令牌名称": "Search key name",
+  "测试所有渠道": "Test all channels",
+  "更新已启用渠道余额": "Update the balance of enabled channels"
 }

main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"embed"
+	"fmt"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
@@ -14,15 +15,12 @@ import (
 	"strconv"
 )
 
-//go:embed web/build
+//go:embed web/build/*
 var buildFS embed.FS
 
-//go:embed web/build/index.html
-var indexPage []byte
-
 func main() {
 	common.SetupLogger()
-	common.SysLog("One API " + common.Version + " started")
+	common.SysLog(fmt.Sprintf("One API %s started with theme %s", common.Version, common.Theme))
 	if os.Getenv("GIN_MODE") != "debug" {
 		gin.SetMode(gin.ReleaseMode)
 	}
@@ -50,18 +48,17 @@ func main() {
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {
+		// for compatibility with old versions
+		common.MemoryCacheEnabled = true
+	}
+	if common.MemoryCacheEnabled {
+		common.SysLog("memory cache enabled")
+		common.SysError(fmt.Sprintf("sync frequency: %d seconds", common.SyncFrequency))
 		model.InitChannelCache()
 	}
-	if os.Getenv("SYNC_FREQUENCY") != "" {
-		frequency, err := strconv.Atoi(os.Getenv("SYNC_FREQUENCY"))
-		if err != nil {
-			common.FatalLog("failed to parse SYNC_FREQUENCY: " + err.Error())
-		}
-		common.SyncFrequency = frequency
-		go model.SyncOptions(frequency)
-		if common.RedisEnabled {
-			go model.SyncChannelCache(frequency)
-		}
+	if common.MemoryCacheEnabled {
+		go model.SyncOptions(common.SyncFrequency)
+		go model.SyncChannelCache(common.SyncFrequency)
 	}
 	if os.Getenv("CHANNEL_UPDATE_FREQUENCY") != "" {
 		frequency, err := strconv.Atoi(os.Getenv("CHANNEL_UPDATE_FREQUENCY"))
@@ -95,7 +92,7 @@ func main() {
 	store := cookie.NewStore([]byte(common.SessionSecret))
 	server.Use(sessions.Sessions("session", store))
 
-	router.SetRouter(server, buildFS, indexPage)
+	router.SetRouter(server, buildFS)
 	var port = os.Getenv("PORT")
 	if port == "" {
 		port = strconv.Itoa(*common.Port)

middleware/auth.go

@@ -94,7 +94,7 @@ func TokenAuth() func(c *gin.Context) {
 			abortWithMessage(c, http.StatusUnauthorized, err.Error())
 			return
 		}
-		userEnabled, err := model.IsUserEnabled(token.UserId)
+		userEnabled, err := model.CacheIsUserEnabled(token.UserId)
 		if err != nil {
 			abortWithMessage(c, http.StatusInternalServerError, err.Error())
 			return
@@ -106,12 +106,6 @@ func TokenAuth() func(c *gin.Context) {
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
 		c.Set("token_name", token.Name)
-		requestURL := c.Request.URL.String()
-		consumeQuota := true
-		if strings.HasPrefix(requestURL, "/v1/models") {
-			consumeQuota = false
-		}
-		c.Set("consume_quota", consumeQuota)
 		if len(parts) > 1 {
 			if model.IsAdmin(token.UserId) {
 				c.Set("channelId", parts[1])

middleware/distributor.go

@@ -25,12 +25,12 @@ func Distribute() func(c *gin.Context) {
 		if ok {
 			id, err := strconv.Atoi(channelId.(string))
 			if err != nil {
-				abortWithMessage(c, http.StatusBadRequest, "无效的渠道 ID")
+				abortWithMessage(c, http.StatusBadRequest, "无效的渠道 Id")
 				return
 			}
 			channel, err = model.GetChannelById(id, true)
 			if err != nil {
-				abortWithMessage(c, http.StatusBadRequest, "无效的渠道 ID")
+				abortWithMessage(c, http.StatusBadRequest, "无效的渠道 Id")
 				return
 			}
 			if channel.Status != common.ChannelStatusEnabled {
@@ -40,10 +40,7 @@ func Distribute() func(c *gin.Context) {
 		} else {
 			// Select a channel for the user
 			var modelRequest ModelRequest
-			var err error
-			if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
-				err = common.UnmarshalBodyReusable(c, &modelRequest)
-			}
+			err := common.UnmarshalBodyReusable(c, &modelRequest)
 			if err != nil {
 				abortWithMessage(c, http.StatusBadRequest, "无效的请求")
 				return
@@ -60,10 +57,10 @@ func Distribute() func(c *gin.Context) {
 			}
 			if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
 				if modelRequest.Model == "" {
-					modelRequest.Model = "dall-e"
+					modelRequest.Model = "dall-e-2"
 				}
 			}
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
+			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") || strings.HasPrefix(c.Request.URL.Path, "/v1/audio/translations") {
 				if modelRequest.Model == "" {
 					modelRequest.Model = "whisper-1"
 				}
@@ -82,16 +79,20 @@ func Distribute() func(c *gin.Context) {
 		c.Set("channel", channel.Type)
 		c.Set("channel_id", channel.Id)
 		c.Set("channel_name", channel.Name)
-		c.Set("model_mapping", channel.ModelMapping)
+		c.Set("model_mapping", channel.GetModelMapping())
 		c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
-		c.Set("base_url", channel.BaseURL)
+		c.Set("base_url", channel.GetBaseURL())
 		switch channel.Type {
 		case common.ChannelTypeAzure:
 			c.Set("api_version", channel.Other)
 		case common.ChannelTypeXunfei:
 			c.Set("api_version", channel.Other)
+		case common.ChannelTypeGemini:
+			c.Set("api_version", channel.Other)
 		case common.ChannelTypeAIProxyLibrary:
 			c.Set("library_id", channel.Other)
+		case common.ChannelTypeAli:
+			c.Set("plugin", channel.Other)
 		}
 		c.Next()
 	}

middleware/recover.go

@@ -0,0 +1,28 @@
+package middleware
+
+import (
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"net/http"
+	"one-api/common"
+	"runtime/debug"
+)
+
+func RelayPanicRecover() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		defer func() {
+			if err := recover(); err != nil {
+				common.SysError(fmt.Sprintf("panic detected: %v", err))
+				common.SysError(fmt.Sprintf("stacktrace from panic: %s", string(debug.Stack())))
+				c.JSON(http.StatusInternalServerError, gin.H{
+					"error": gin.H{
+						"message": fmt.Sprintf("Panic detected, error: %v. Please submit a issue here: https://github.com/songquanpeng/one-api", err),
+						"type":    "one_api_panic",
+					},
+				})
+				c.Abort()
+			}
+		}()
+		c.Next()
+	}
+}

model/ability.go

@@ -10,15 +10,25 @@ type Ability struct {
 	Model     string `json:"model" gorm:"primaryKey;autoIncrement:false"`
 	ChannelId int    `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
 	Enabled   bool   `json:"enabled"`
+	Priority  *int64 `json:"priority" gorm:"bigint;default:0;index"`
 }
 
 func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 	ability := Ability{}
+	groupCol := "`group`"
+	trueVal := "1"
+	if common.UsingPostgreSQL {
+		groupCol = `"group"`
+		trueVal = "true"
+	}
+
 	var err error = nil
-	if common.UsingSQLite {
-		err = DB.Where("`group` = ? and model = ? and enabled = 1", group, model).Order("RANDOM()").Limit(1).First(&ability).Error
+	maxPrioritySubQuery := DB.Model(&Ability{}).Select("MAX(priority)").Where(groupCol+" = ? and model = ? and enabled = "+trueVal, group, model)
+	channelQuery := DB.Where(groupCol+" = ? and model = ? and enabled = "+trueVal+" and priority = (?)", group, model, maxPrioritySubQuery)
+	if common.UsingSQLite || common.UsingPostgreSQL {
+		err = channelQuery.Order("RANDOM()").First(&ability).Error
 	} else {
-		err = DB.Where("`group` = ? and model = ? and enabled = 1", group, model).Order("RAND()").Limit(1).First(&ability).Error
+		err = channelQuery.Order("RAND()").First(&ability).Error
 	}
 	if err != nil {
 		return nil, err
@@ -40,6 +50,7 @@ func (channel *Channel) AddAbilities() error {
 				Model:     model,
 				ChannelId: channel.Id,
 				Enabled:   channel.Status == common.ChannelStatusEnabled,
+				Priority:  channel.Priority,
 			}
 			abilities = append(abilities, ability)
 		}

model/cache.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"math/rand"
 	"one-api/common"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -20,14 +21,18 @@ var (
 )
 
 func CacheGetTokenByKey(key string) (*Token, error) {
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
 	var token Token
 	if !common.RedisEnabled {
-		err := DB.Where("`key` = ?", key).First(&token).Error
+		err := DB.Where(keyCol+" = ?", key).First(&token).Error
 		return &token, err
 	}
 	tokenObjectString, err := common.RedisGet(fmt.Sprintf("token:%s", key))
 	if err != nil {
-		err := DB.Where("`key` = ?", key).First(&token).Error
+		err := DB.Where(keyCol+" = ?", key).First(&token).Error
 		if err != nil {
 			return nil, err
 		}
@@ -159,6 +164,17 @@ func InitChannelCache() {
 			}
 		}
 	}
+
+	// sort by priority
+	for group, model2channels := range newGroup2model2channels {
+		for model, channels := range model2channels {
+			sort.Slice(channels, func(i, j int) bool {
+				return channels[i].GetPriority() > channels[j].GetPriority()
+			})
+			newGroup2model2channels[group][model] = channels
+		}
+	}
+
 	channelSyncLock.Lock()
 	group2model2channels = newGroup2model2channels
 	channelSyncLock.Unlock()
@@ -174,7 +190,7 @@ func SyncChannelCache(frequency int) {
 }
 
 func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
-	if !common.RedisEnabled {
+	if !common.MemoryCacheEnabled {
 		return GetRandomSatisfiedChannel(group, model)
 	}
 	channelSyncLock.RLock()
@@ -183,6 +199,17 @@ func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error
 	if len(channels) == 0 {
 		return nil, errors.New("channel not found")
 	}
-	idx := rand.Intn(len(channels))
+	endIdx := len(channels)
+	// choose by priority
+	firstChannel := channels[0]
+	if firstChannel.GetPriority() > 0 {
+		for i := range channels {
+			if channels[i].GetPriority() != firstChannel.GetPriority() {
+				endIdx = i
+				break
+			}
+		}
+	}
+	idx := rand.Intn(endIdx)
 	return channels[idx], nil
 }

model/channel.go

@@ -11,18 +11,19 @@ type Channel struct {
 	Key                string  `json:"key" gorm:"not null;index"`
 	Status             int     `json:"status" gorm:"default:1"`
 	Name               string  `json:"name" gorm:"index"`
-	Weight             int     `json:"weight"`
+	Weight             *uint   `json:"weight" gorm:"default:0"`
 	CreatedTime        int64   `json:"created_time" gorm:"bigint"`
 	TestTime           int64   `json:"test_time" gorm:"bigint"`
 	ResponseTime       int     `json:"response_time"` // in milliseconds
-	BaseURL            string  `json:"base_url" gorm:"column:base_url"`
+	BaseURL            *string `json:"base_url" gorm:"column:base_url;default:''"`
 	Other              string  `json:"other"`
 	Balance            float64 `json:"balance"` // in USD
 	BalanceUpdatedTime int64   `json:"balance_updated_time" gorm:"bigint"`
 	Models             string  `json:"models"`
 	Group              string  `json:"group" gorm:"type:varchar(32);default:'default'"`
 	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
-	ModelMapping       string  `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
+	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
+	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
 }
 
 func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
@@ -37,7 +38,11 @@ func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
 }
 
 func SearchChannels(keyword string) (channels []*Channel, err error) {
-	err = DB.Omit("key").Where("id = ? or name LIKE ? or `key` = ?", keyword, keyword+"%", keyword).Find(&channels).Error
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
+	err = DB.Omit("key").Where("id = ? or name LIKE ? or "+keyCol+" = ?", common.String2Int(keyword), keyword+"%", keyword).Find(&channels).Error
 	return channels, err
 }
 
@@ -52,17 +57,6 @@ func GetChannelById(id int, selectAll bool) (*Channel, error) {
 	return &channel, err
 }
 
-func GetRandomChannel() (*Channel, error) {
-	channel := Channel{}
-	var err error = nil
-	if common.UsingSQLite {
-		err = DB.Where("status = ? and `group` = ?", common.ChannelStatusEnabled, "default").Order("RANDOM()").Limit(1).First(&channel).Error
-	} else {
-		err = DB.Where("status = ? and `group` = ?", common.ChannelStatusEnabled, "default").Order("RAND()").Limit(1).First(&channel).Error
-	}
-	return &channel, err
-}
-
 func BatchInsertChannels(channels []Channel) error {
 	var err error
 	err = DB.Create(&channels).Error
@@ -78,6 +72,27 @@ func BatchInsertChannels(channels []Channel) error {
 	return nil
 }
 
+func (channel *Channel) GetPriority() int64 {
+	if channel.Priority == nil {
+		return 0
+	}
+	return *channel.Priority
+}
+
+func (channel *Channel) GetBaseURL() string {
+	if channel.BaseURL == nil {
+		return ""
+	}
+	return *channel.BaseURL
+}
+
+func (channel *Channel) GetModelMapping() string {
+	if channel.ModelMapping == nil {
+		return ""
+	}
+	return *channel.ModelMapping
+}
+
 func (channel *Channel) Insert() error {
 	var err error
 	err = DB.Create(channel).Error
@@ -154,3 +169,13 @@ func updateChannelUsedQuota(id int, quota int) {
 		common.SysError("failed to update channel used quota: " + err.Error())
 	}
 }
+
+func DeleteChannelByStatus(status int64) (int64, error) {
+	result := DB.Where("status = ?", status).Delete(&Channel{})
+	return result.RowsAffected, result.Error
+}
+
+func DeleteDisabledChannel() (int64, error) {
+	result := DB.Where("status = ? or status = ?", common.ChannelStatusAutoDisabled, common.ChannelStatusManuallyDisabled).Delete(&Channel{})
+	return result.RowsAffected, result.Error
+}

model/log.go

@@ -8,17 +8,18 @@ import (
 )
 
 type Log struct {
-	Id               int    `json:"id"`
-	UserId           int    `json:"user_id"`
-	CreatedAt        int64  `json:"created_at" gorm:"bigint;index"`
-	Type             int    `json:"type" gorm:"index"`
+	Id               int    `json:"id;index:idx_created_at_id,priority:1"`
+	UserId           int    `json:"user_id" gorm:"index"`
+	CreatedAt        int64  `json:"created_at" gorm:"bigint;index:idx_created_at_id,priority:2;index:idx_created_at_type"`
+	Type             int    `json:"type" gorm:"index:idx_created_at_type"`
 	Content          string `json:"content"`
-	Username         string `json:"username" gorm:"index;default:''"`
+	Username         string `json:"username" gorm:"index:index_username_model_name,priority:2;default:''"`
 	TokenName        string `json:"token_name" gorm:"index;default:''"`
-	ModelName        string `json:"model_name" gorm:"index;default:''"`
+	ModelName        string `json:"model_name" gorm:"index;index:index_username_model_name,priority:1;default:''"`
 	Quota            int    `json:"quota" gorm:"default:0"`
 	PromptTokens     int    `json:"prompt_tokens" gorm:"default:0"`
 	CompletionTokens int    `json:"completion_tokens" gorm:"default:0"`
+	ChannelId        int    `json:"channel" gorm:"index"`
 }
 
 const (
@@ -46,8 +47,8 @@ func RecordLog(userId int, logType int, content string) {
 	}
 }
 
-func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string) {
-	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, promptTokens, completionTokens, modelName, tokenName, quota, content))
+func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string) {
+	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
 	if !common.LogConsumeEnabled {
 		return
 	}
@@ -62,6 +63,7 @@ func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, complet
 		TokenName:        tokenName,
 		ModelName:        modelName,
 		Quota:            quota,
+		ChannelId:        channelId,
 	}
 	err := DB.Create(log).Error
 	if err != nil {
@@ -69,7 +71,7 @@ func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, complet
 	}
 }
 
-func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int) (logs []*Log, err error) {
+func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel int) (logs []*Log, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
 		tx = DB
@@ -91,6 +93,9 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if endTimestamp != 0 {
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
+	if channel != 0 {
+		tx = tx.Where("channel_id = ?", channel)
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
 	return logs, err
 }
@@ -128,8 +133,8 @@ func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
 	return logs, err
 }
 
-func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (quota int) {
-	tx := DB.Table("logs").Select("sum(quota)")
+func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (quota int) {
+	tx := DB.Table("logs").Select("ifnull(sum(quota),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -145,12 +150,15 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	if modelName != "" {
 		tx = tx.Where("model_name = ?", modelName)
 	}
+	if channel != 0 {
+		tx = tx.Where("channel_id = ?", channel)
+	}
 	tx.Where("type = ?", LogTypeConsume).Scan(&quota)
 	return quota
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := DB.Table("logs").Select("sum(prompt_tokens) + sum(completion_tokens)")
+	tx := DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}

model/main.go

@@ -1,6 +1,7 @@
 package model
 
 import (
+	"fmt"
 	"gorm.io/driver/mysql"
 	"gorm.io/driver/postgres"
 	"gorm.io/driver/sqlite"
@@ -42,6 +43,7 @@ func chooseDB() (*gorm.DB, error) {
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
 			common.SysLog("using PostgreSQL as database")
+			common.UsingPostgreSQL = true
 			return gorm.Open(postgres.New(postgres.Config{
 				DSN:                  dsn,
 				PreferSimpleProtocol: true, // disables implicit prepared statement usage
@@ -58,7 +60,8 @@ func chooseDB() (*gorm.DB, error) {
 	// Use SQLite
 	common.SysLog("SQL_DSN not set, using SQLite as database")
 	common.UsingSQLite = true
-	return gorm.Open(sqlite.Open(common.SQLitePath), &gorm.Config{
+	config := fmt.Sprintf("?_busy_timeout=%d", common.SQLiteBusyTimeout)
+	return gorm.Open(sqlite.Open(common.SQLitePath+config), &gorm.Config{
 		PrepareStmt: true, // precompile SQL
 	})
 }
@@ -81,6 +84,7 @@ func InitDB() (err error) {
 		if !common.IsMasterNode {
 			return nil
 		}
+		common.SysLog("database migration started")
 		err = db.AutoMigrate(&Channel{})
 		if err != nil {
 			return err

model/option.go

@@ -34,6 +34,7 @@ func InitOptionMap() {
 	common.OptionMap["TurnstileCheckEnabled"] = strconv.FormatBool(common.TurnstileCheckEnabled)
 	common.OptionMap["RegisterEnabled"] = strconv.FormatBool(common.RegisterEnabled)
 	common.OptionMap["AutomaticDisableChannelEnabled"] = strconv.FormatBool(common.AutomaticDisableChannelEnabled)
+	common.OptionMap["AutomaticEnableChannelEnabled"] = strconv.FormatBool(common.AutomaticEnableChannelEnabled)
 	common.OptionMap["ApproximateTokenEnabled"] = strconv.FormatBool(common.ApproximateTokenEnabled)
 	common.OptionMap["LogConsumeEnabled"] = strconv.FormatBool(common.LogConsumeEnabled)
 	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
@@ -147,6 +148,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.EmailDomainRestrictionEnabled = boolValue
 		case "AutomaticDisableChannelEnabled":
 			common.AutomaticDisableChannelEnabled = boolValue
+		case "AutomaticEnableChannelEnabled":
+			common.AutomaticEnableChannelEnabled = boolValue
 		case "ApproximateTokenEnabled":
 			common.ApproximateTokenEnabled = boolValue
 		case "LogConsumeEnabled":

model/redemption.go

@@ -50,8 +50,13 @@ func Redeem(key string, userId int) (quota int, err error) {
 	}
 	redemption := &Redemption{}
 
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
+
 	err = DB.Transaction(func(tx *gorm.DB) error {
-		err := tx.Set("gorm:query_option", "FOR UPDATE").Where("`key` = ?", key).First(redemption).Error
+		err := tx.Set("gorm:query_option", "FOR UPDATE").Where(keyCol+" = ?", key).First(redemption).Error
 		if err != nil {
 			return errors.New("无效的兑换码")
 		}

model/user.go

@@ -42,7 +42,11 @@ func GetAllUsers(startIdx int, num int) (users []*User, err error) {
 }
 
 func SearchUsers(keyword string) (users []*User, err error) {
-	err = DB.Omit("password").Where("id = ? or username LIKE ? or email LIKE ? or display_name LIKE ?", keyword, keyword+"%", keyword+"%", keyword+"%").Find(&users).Error
+	if !common.UsingPostgreSQL {
+		err = DB.Omit("password").Where("id = ? or username LIKE ? or email LIKE ? or display_name LIKE ?", keyword, keyword+"%", keyword+"%", keyword+"%").Find(&users).Error
+	} else {
+		err = DB.Omit("password").Where("username LIKE ? or email LIKE ? or display_name LIKE ?", keyword+"%", keyword+"%", keyword+"%").Find(&users).Error
+	}
 	return users, err
 }
 
@@ -266,7 +270,12 @@ func GetUserEmail(id int) (email string, err error) {
 }
 
 func GetUserGroup(id int) (group string, err error) {
-	err = DB.Model(&User{}).Where("id = ?", id).Select("`group`").Find(&group).Error
+	groupCol := "`group`"
+	if common.UsingPostgreSQL {
+		groupCol = `"group"`
+	}
+
+	err = DB.Model(&User{}).Where("id = ?", id).Select(groupCol).Find(&group).Error
 	return group, err
 }
 
@@ -309,7 +318,8 @@ func GetRootUserEmail() (email string) {
 
 func UpdateUserUsedQuotaAndRequestCount(id int, quota int) {
 	if common.BatchUpdateEnabled {
-		addNewRecord(BatchUpdateTypeUsedQuotaAndRequestCount, id, quota)
+		addNewRecord(BatchUpdateTypeUsedQuota, id, quota)
+		addNewRecord(BatchUpdateTypeRequestCount, id, 1)
 		return
 	}
 	updateUserUsedQuotaAndRequestCount(id, quota, 1)
@@ -327,6 +337,24 @@ func updateUserUsedQuotaAndRequestCount(id int, quota int, count int) {
 	}
 }
 
+func updateUserUsedQuota(id int, quota int) {
+	err := DB.Model(&User{}).Where("id = ?", id).Updates(
+		map[string]interface{}{
+			"used_quota": gorm.Expr("used_quota + ?", quota),
+		},
+	).Error
+	if err != nil {
+		common.SysError("failed to update user used quota: " + err.Error())
+	}
+}
+
+func updateUserRequestCount(id int, count int) {
+	err := DB.Model(&User{}).Where("id = ?", id).Update("request_count", gorm.Expr("request_count + ?", count)).Error
+	if err != nil {
+		common.SysError("failed to update user request count: " + err.Error())
+	}
+}
+
 func GetUsernameById(id int) (username string) {
 	DB.Model(&User{}).Where("id = ?", id).Select("username").Find(&username)
 	return username

model/utils.go

@@ -6,13 +6,13 @@ import (
 	"time"
 )
 
-const BatchUpdateTypeCount = 4 // if you add a new type, you need to add a new map and a new lock
-
 const (
 	BatchUpdateTypeUserQuota = iota
 	BatchUpdateTypeTokenQuota
-	BatchUpdateTypeUsedQuotaAndRequestCount
+	BatchUpdateTypeUsedQuota
 	BatchUpdateTypeChannelUsedQuota
+	BatchUpdateTypeRequestCount
+	BatchUpdateTypeCount // if you add a new type, you need to add a new map and a new lock
 )
 
 var batchUpdateStores []map[int]int
@@ -51,7 +51,7 @@ func batchUpdate() {
 		store := batchUpdateStores[i]
 		batchUpdateStores[i] = make(map[int]int)
 		batchUpdateLocks[i].Unlock()
-
+		// TODO: maybe we can combine updates with same key?
 		for key, value := range store {
 			switch i {
 			case BatchUpdateTypeUserQuota:
@@ -64,8 +64,10 @@ func batchUpdate() {
 				if err != nil {
 					common.SysError("failed to batch update token quota: " + err.Error())
 				}
-			case BatchUpdateTypeUsedQuotaAndRequestCount:
-				updateUserUsedQuotaAndRequestCount(key, value, 1) // TODO: count is incorrect
+			case BatchUpdateTypeUsedQuota:
+				updateUserUsedQuota(key, value)
+			case BatchUpdateTypeRequestCount:
+				updateUserRequestCount(key, value)
 			case BatchUpdateTypeChannelUsedQuota:
 				updateChannelUsedQuota(key, value)
 			}

pull_request_template.md

@@ -0,0 +1,9 @@
+[//]: # (请按照以下格式关联 issue)
+[//]: # (请在提交 PR 前确认所提交的功能可用，附上截图即可，这将有助于项目维护者 review & merge 该 PR，谢谢)
+[//]: # (项目维护者一般仅在周末处理 PR，因此如若未能及时回复希望能理解)
+[//]: # (开发者交流群：910657413)
+[//]: # (请在提交 PR 之前删除上面的注释)
+
+close #issue_number
+
+我已确认该 PR 已自测通过，相关截图如下：

router/api-router.go

@@ -74,6 +74,7 @@ func SetApiRouter(router *gin.Engine) {
 			channelRoute.GET("/update_balance/:id", controller.UpdateChannelBalance)
 			channelRoute.POST("/", controller.AddChannel)
 			channelRoute.PUT("/", controller.UpdateChannel)
+			channelRoute.DELETE("/disabled", controller.DeleteDisabledChannel)
 			channelRoute.DELETE("/:id", controller.DeleteChannel)
 		}
 		tokenRoute := apiRouter.Group("/token")

router/main.go

@@ -10,7 +10,7 @@ import (
 	"strings"
 )
 
-func SetRouter(router *gin.Engine, buildFS embed.FS, indexPage []byte) {
+func SetRouter(router *gin.Engine, buildFS embed.FS) {
 	SetApiRouter(router)
 	SetDashboardRouter(router)
 	SetRelayRouter(router)
@@ -20,7 +20,7 @@ func SetRouter(router *gin.Engine, buildFS embed.FS, indexPage []byte) {
 		common.SysLog("FRONTEND_BASE_URL is ignored on master node")
 	}
 	if frontendBaseUrl == "" {
-		SetWebRouter(router, buildFS, indexPage)
+		SetWebRouter(router, buildFS)
 	} else {
 		frontendBaseUrl = strings.TrimSuffix(frontendBaseUrl, "/")
 		router.NoRoute(func(c *gin.Context) {

router/relay-router.go

@@ -17,7 +17,7 @@ func SetRelayRouter(router *gin.Engine) {
 		modelsRouter.GET("/:model", controller.RetrieveModel)
 	}
 	relayV1Router := router.Group("/v1")
-	relayV1Router.Use(middleware.TokenAuth(), middleware.Distribute())
+	relayV1Router.Use(middleware.RelayPanicRecover(), middleware.TokenAuth(), middleware.Distribute())
 	{
 		relayV1Router.POST("/completions", controller.Relay)
 		relayV1Router.POST("/chat/completions", controller.Relay)
@@ -29,17 +29,44 @@ func SetRelayRouter(router *gin.Engine) {
 		relayV1Router.POST("/engines/:model/embeddings", controller.Relay)
 		relayV1Router.POST("/audio/transcriptions", controller.Relay)
 		relayV1Router.POST("/audio/translations", controller.Relay)
+		relayV1Router.POST("/audio/speech", controller.Relay)
 		relayV1Router.GET("/files", controller.RelayNotImplemented)
 		relayV1Router.POST("/files", controller.RelayNotImplemented)
 		relayV1Router.DELETE("/files/:id", controller.RelayNotImplemented)
 		relayV1Router.GET("/files/:id", controller.RelayNotImplemented)
 		relayV1Router.GET("/files/:id/content", controller.RelayNotImplemented)
-		relayV1Router.POST("/fine-tunes", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes/:id", controller.RelayNotImplemented)
-		relayV1Router.POST("/fine-tunes/:id/cancel", controller.RelayNotImplemented)
-		relayV1Router.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
+		relayV1Router.POST("/fine_tuning/jobs", controller.RelayNotImplemented)
+		relayV1Router.GET("/fine_tuning/jobs", controller.RelayNotImplemented)
+		relayV1Router.GET("/fine_tuning/jobs/:id", controller.RelayNotImplemented)
+		relayV1Router.POST("/fine_tuning/jobs/:id/cancel", controller.RelayNotImplemented)
+		relayV1Router.GET("/fine_tuning/jobs/:id/events", controller.RelayNotImplemented)
 		relayV1Router.DELETE("/models/:model", controller.RelayNotImplemented)
 		relayV1Router.POST("/moderations", controller.Relay)
+		relayV1Router.POST("/assistants", controller.RelayNotImplemented)
+		relayV1Router.GET("/assistants/:id", controller.RelayNotImplemented)
+		relayV1Router.POST("/assistants/:id", controller.RelayNotImplemented)
+		relayV1Router.DELETE("/assistants/:id", controller.RelayNotImplemented)
+		relayV1Router.GET("/assistants", controller.RelayNotImplemented)
+		relayV1Router.POST("/assistants/:id/files", controller.RelayNotImplemented)
+		relayV1Router.GET("/assistants/:id/files/:fileId", controller.RelayNotImplemented)
+		relayV1Router.DELETE("/assistants/:id/files/:fileId", controller.RelayNotImplemented)
+		relayV1Router.GET("/assistants/:id/files", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id", controller.RelayNotImplemented)
+		relayV1Router.DELETE("/threads/:id", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/messages", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/messages/:messageId", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/messages/:messageId", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/messages/:messageId/files/:filesId", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/messages/:messageId/files", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/runs", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/runs/:runsId", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/runs/:runsId", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/runs", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/runs/:runsId/submit_tool_outputs", controller.RelayNotImplemented)
+		relayV1Router.POST("/threads/:id/runs/:runsId/cancel", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/runs/:runsId/steps/:stepId", controller.RelayNotImplemented)
+		relayV1Router.GET("/threads/:id/runs/:runsId/steps", controller.RelayNotImplemented)
 	}
 }

router/web-router.go

@@ -2,6 +2,7 @@ package router
 
 import (
 	"embed"
+	"fmt"
 	"github.com/gin-contrib/gzip"
 	"github.com/gin-contrib/static"
 	"github.com/gin-gonic/gin"
@@ -12,17 +13,22 @@ import (
 	"strings"
 )
 
-func SetWebRouter(router *gin.Engine, buildFS embed.FS, indexPage []byte) {
+func SetWebRouter(router *gin.Engine, buildFS embed.FS) {
 	router.Use(gzip.Gzip(gzip.DefaultCompression))
 	router.Use(middleware.GlobalWebRateLimit())
 	router.Use(middleware.Cache())
-	router.Use(static.Serve("/", common.EmbedFolder(buildFS, "web/build")))
+	router.Use(static.Serve("/", common.EmbedFolder(buildFS, fmt.Sprintf("web/build/%s", common.Theme))))
 	router.NoRoute(func(c *gin.Context) {
 		if strings.HasPrefix(c.Request.RequestURI, "/v1") || strings.HasPrefix(c.Request.RequestURI, "/api") {
 			controller.RelayNotFound(c)
 			return
 		}
 		c.Header("Cache-Control", "no-cache")
+		indexPage, err := buildFS.ReadFile(fmt.Sprintf("web/build/%s/index.html", common.Theme))
+		if err != nil {
+			controller.RelayNotFound(c)
+			return
+		}
 		c.Data(http.StatusOK, "text/html; charset=utf-8", indexPage)
 	})
 }

web/README.md

@@ -1,21 +1,11 @@
-# React Template
+# One API 的前端界面
+> 每个文件夹代表一个主题，欢迎提交你的主题
 
-## Basic Usages
+## 提交新的主题
+1. 在 `web` 文件夹下新建一个文件夹，文件夹名为主题名。
+2. 把你的主题文件放到这个文件夹下。
+3. 修改 `package.json` 文件，把 `build` 命令改为：`"build": "react-scripts build && mv build ../build/default"`，其中 `default` 为你的主题名。
 
-```shell
-# Runs the app in the development mode
-npm start
-
-# Builds the app for production to the `build` folder
-npm run build
-```
-
-If you want to change the default server, please set `REACT_APP_SERVER` environment variables before build,
-for example: `REACT_APP_SERVER=http://your.domain.com`.
-
-Before you start editing, make sure your `Actions on Save` options have `Optimize imports` & `Run Prettier` enabled.
-
-## Reference
-
-1. https://github.com/OIerDb-ng/OIerDb
-2. https://github.com/cornflourblue/react-hooks-redux-registration-login-example
+## 主题列表
+### default
+默认主题

web/THEMES

@@ -0,0 +1 @@
+default

web/build.sh

@@ -0,0 +1,13 @@
+#!/bin/sh
+
+version=$(cat VERSION)
+themes=$(cat THEMES)
+IFS=$'\n'
+
+for theme in $themes; do
+    echo "Building theme: $theme"
+    cd $theme
+    npm install
+    DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$version npm run build
+    cd ..
+done

web/default/README.md

@@ -0,0 +1,21 @@
+# React Template
+
+## Basic Usages
+
+```shell
+# Runs the app in the development mode
+npm start
+
+# Builds the app for production to the `build` folder
+npm run build
+```
+
+If you want to change the default server, please set `REACT_APP_SERVER` environment variables before build,
+for example: `REACT_APP_SERVER=http://your.domain.com`.
+
+Before you start editing, make sure your `Actions on Save` options have `Optimize imports` & `Run Prettier` enabled.
+
+## Reference
+
+1. https://github.com/OIerDb-ng/OIerDb
+2. https://github.com/cornflourblue/react-hooks-redux-registration-login-example

web/default/package.json

@@ -18,7 +18,7 @@
   },
   "scripts": {
     "start": "react-scripts start",
-    "build": "react-scripts build",
+    "build": "react-scripts build && mv build ../build/default",
     "test": "react-scripts test",
     "eject": "react-scripts eject"
   },

web/default/src/App.js

@@ -283,7 +283,9 @@ function App() {
           </Suspense>
         }
       />
-      <Route path='*' element={NotFound} />
+      <Route path='*' element={
+          <NotFound />
+      } />
     </Routes>
   );
 }

web/default/src/components/ChannelsTable.js

@@ -1,7 +1,7 @@
 import React, { useEffect, useState } from 'react';
-import { Button, Form, Label, Pagination, Popup, Table } from 'semantic-ui-react';
+import { Button, Form, Input, Label, Message, Pagination, Popup, Table } from 'semantic-ui-react';
 import { Link } from 'react-router-dom';
-import { API, showError, showInfo, showNotice, showSuccess, timestamp2string } from '../helpers';
+import { API, setPromptShown, shouldShowPrompt, showError, showInfo, showSuccess, timestamp2string } from '../helpers';
 
 import { CHANNEL_OPTIONS, ITEMS_PER_PAGE } from '../constants';
 import { renderGroup, renderNumber } from '../helpers/render';
@@ -24,7 +24,7 @@ function renderType(type) {
     }
     type2label[0] = { value: 0, text: '未知类型', color: 'grey' };
   }
-  return <Label basic color={type2label[type].color}>{type2label[type].text}</Label>;
+  return <Label basic color={type2label[type]?.color}>{type2label[type]?.text}</Label>;
 }
 
 function renderBalance(type, balance) {
@@ -55,6 +55,7 @@ const ChannelsTable = () => {
   const [searchKeyword, setSearchKeyword] = useState('');
   const [searching, setSearching] = useState(false);
   const [updatingBalance, setUpdatingBalance] = useState(false);
+  const [showPrompt, setShowPrompt] = useState(shouldShowPrompt("channel-test"));
 
   const loadChannels = async (startIdx) => {
     const res = await API.get(`/api/channel/?p=${startIdx}`);
@@ -96,7 +97,7 @@ const ChannelsTable = () => {
       });
   }, []);
 
-  const manageChannel = async (id, action, idx) => {
+  const manageChannel = async (id, action, idx, value) => {
     let data = { id };
     let res;
     switch (action) {
@@ -111,6 +112,23 @@ const ChannelsTable = () => {
         data.status = 2;
         res = await API.put('/api/channel/', data);
         break;
+      case 'priority':
+        if (value === '') {
+          return;
+        }
+        data.priority = parseInt(value);
+        res = await API.put('/api/channel/', data);
+        break;
+      case 'weight':
+        if (value === '') {
+          return;
+        }
+        data.weight = parseInt(value);
+        if (data.weight < 0) {
+          data.weight = 0;
+        }
+        res = await API.put('/api/channel/', data);
+        break;
     }
     const { success, message } = res.data;
     if (success) {
@@ -135,9 +153,23 @@ const ChannelsTable = () => {
         return <Label basic color='green'>已启用</Label>;
       case 2:
         return (
-          <Label basic color='red'>
-            已禁用
-          </Label>
+          <Popup
+            trigger={<Label basic color='red'>
+              已禁用
+            </Label>}
+            content='本渠道被手动禁用'
+            basic
+          />
+        );
+      case 3:
+        return (
+          <Popup
+            trigger={<Label basic color='yellow'>
+              已禁用
+            </Label>}
+            content='本渠道被程序自动禁用'
+            basic
+          />
         );
       default:
         return (
@@ -195,7 +227,6 @@ const ChannelsTable = () => {
       showInfo(`通道 ${name} 测试成功，耗时 ${time.toFixed(2)} 秒。`);
     } else {
       showError(message);
-      showNotice("当前版本测试是通过按照 OpenAI API 格式使用 gpt-3.5-turbo 模型进行非流式请求实现的，因此测试报错并不一定代表通道不可用，该功能后续会修复。")
     }
   };
 
@@ -203,7 +234,18 @@ const ChannelsTable = () => {
     const res = await API.get(`/api/channel/test`);
     const { success, message } = res.data;
     if (success) {
-      showInfo('已成功开始测试所有已启用通道，请刷新页面查看结果。');
+      showInfo('已成功开始测试所有通道，请刷新页面查看结果。');
+    } else {
+      showError(message);
+    }
+  };
+
+  const deleteAllDisabledChannels = async () => {
+    const res = await API.delete(`/api/channel/disabled`);
+    const { success, message, data } = res.data;
+    if (success) {
+      showSuccess(`已删除所有禁用渠道，共计 ${data} 个`);
+      await refresh();
     } else {
       showError(message);
     }
@@ -244,17 +286,15 @@ const ChannelsTable = () => {
     if (channels.length === 0) return;
     setLoading(true);
     let sortedChannels = [...channels];
-    if (typeof sortedChannels[0][key] === 'string') {
-      sortedChannels.sort((a, b) => {
+    sortedChannels.sort((a, b) => {
+      if (!isNaN(a[key])) {
+        // If the value is numeric, subtract to sort
+        return a[key] - b[key];
+      } else {
+        // If the value is not numeric, sort as strings
         return ('' + a[key]).localeCompare(b[key]);
-      });
-    } else {
-      sortedChannels.sort((a, b) => {
-        if (a[key] === b[key]) return 0;
-        if (a[key] > b[key]) return -1;
-        if (a[key] < b[key]) return 1;
-      });
-    }
+      }
+    });
     if (sortedChannels[0].id === channels[0].id) {
       sortedChannels.reverse();
     }
@@ -262,6 +302,7 @@ const ChannelsTable = () => {
     setLoading(false);
   };
 
+
   return (
     <>
       <Form onSubmit={searchChannels}>
@@ -275,7 +316,19 @@ const ChannelsTable = () => {
           onChange={handleKeywordChange}
         />
       </Form>
+      {
+        showPrompt && (
+          <Message onDismiss={() => {
+            setShowPrompt(false);
+            setPromptShown("channel-test");
+          }}>
+            当前版本测试是通过按照 OpenAI API 格式使用 gpt-3.5-turbo
+            模型进行非流式请求实现的，因此测试报错并不一定代表通道不可用，该功能后续会修复。
 
+            另外，OpenAI 渠道已经不再支持通过 key 获取余额，因此余额显示为 0。对于支持的渠道类型，请点击余额进行刷新。
+          </Message>
+        )
+      }
       <Table basic compact size='small'>
         <Table.Header>
           <Table.Row>
@@ -335,6 +388,14 @@ const ChannelsTable = () => {
             >
               余额
             </Table.HeaderCell>
+            <Table.HeaderCell
+              style={{ cursor: 'pointer' }}
+              onClick={() => {
+                sortChannel('priority');
+              }}
+            >
+              优先级
+            </Table.HeaderCell>
             <Table.HeaderCell>操作</Table.HeaderCell>
           </Table.Row>
         </Table.Header>
@@ -373,6 +434,22 @@ const ChannelsTable = () => {
                       basic
                     />
                   </Table.Cell>
+                  <Table.Cell>
+                    <Popup
+                      trigger={<Input type='number' defaultValue={channel.priority} onBlur={(event) => {
+                        manageChannel(
+                          channel.id,
+                          'priority',
+                          idx,
+                          event.target.value
+                        );
+                      }}>
+                        <input style={{ maxWidth: '60px' }} />
+                      </Input>}
+                      content='渠道选择优先级，越高越优先'
+                      basic
+                    />
+                  </Table.Cell>
                   <Table.Cell>
                     <div>
                       <Button
@@ -441,15 +518,29 @@ const ChannelsTable = () => {
 
         <Table.Footer>
           <Table.Row>
-            <Table.HeaderCell colSpan='8'>
+            <Table.HeaderCell colSpan='9'>
               <Button size='small' as={Link} to='/channel/add' loading={loading}>
                 添加新的渠道
               </Button>
               <Button size='small' loading={loading} onClick={testAllChannels}>
-                测试所有已启用通道
+                测试所有渠道
               </Button>
               <Button size='small' onClick={updateAllChannelsBalance}
-                      loading={loading || updatingBalance}>更新所有已启用通道余额</Button>
+                      loading={loading || updatingBalance}>更新已启用渠道余额</Button>
+              <Popup
+                trigger={
+                  <Button size='small' loading={loading}>
+                    删除禁用渠道
+                  </Button>
+                }
+                on='click'
+                flowing
+                hoverable
+              >
+                <Button size='small' loading={loading} negative onClick={deleteAllDisabledChannels}>
+                  确认删除
+                </Button>
+              </Popup>
               <Pagination
                 floated='right'
                 activePage={activePage}

web/default/src/components/LoginForm.js

@@ -2,8 +2,8 @@ import React, { useContext, useEffect, useState } from 'react';
 import { Button, Divider, Form, Grid, Header, Image, Message, Modal, Segment } from 'semantic-ui-react';
 import { Link, useNavigate, useSearchParams } from 'react-router-dom';
 import { UserContext } from '../context/User';
-import { API, getLogo, showError, showSuccess } from '../helpers';
-import { getOAuthState, onGitHubOAuthClicked } from './utils';
+import { API, getLogo, showError, showSuccess, showWarning } from '../helpers';
+import { onGitHubOAuthClicked } from './utils';
 
 const LoginForm = () => {
   const [inputs, setInputs] = useState({
@@ -68,8 +68,14 @@ const LoginForm = () => {
       if (success) {
         userDispatch({ type: 'login', payload: data });
         localStorage.setItem('user', JSON.stringify(data));
-        navigate('/');
-        showSuccess('登录成功！');
+        if (username === 'root' && password === '123456') {
+          navigate('/user/edit');
+          showSuccess('登录成功！');
+          showWarning('请立刻修改默认密码！');
+        } else {
+          navigate('/token');
+          showSuccess('登录成功！');
+        }
       } else {
         showError(message);
       }
@@ -126,7 +132,7 @@ const LoginForm = () => {
                 circular
                 color='black'
                 icon='github'
-                onClick={()=>onGitHubOAuthClicked(status.github_client_id)}
+                onClick={() => onGitHubOAuthClicked(status.github_client_id)}
               />
             ) : (
               <></>

web/default/src/components/LogsTable.js

@@ -56,9 +56,10 @@ const LogsTable = () => {
     token_name: '',
     model_name: '',
     start_timestamp: timestamp2string(0),
-    end_timestamp: timestamp2string(now.getTime() / 1000 + 3600)
+    end_timestamp: timestamp2string(now.getTime() / 1000 + 3600),
+    channel: ''
   });
-  const { username, token_name, model_name, start_timestamp, end_timestamp } = inputs;
+  const { username, token_name, model_name, start_timestamp, end_timestamp, channel } = inputs;
 
   const [stat, setStat] = useState({
     quota: 0,
@@ -84,7 +85,7 @@ const LogsTable = () => {
   const getLogStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
-    let res = await API.get(`/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`);
+    let res = await API.get(`/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`);
     const { success, message, data } = res.data;
     if (success) {
       setStat(data);
@@ -109,7 +110,7 @@ const LogsTable = () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
     if (isAdminUser) {
-      url = `/api/log/?p=${startIdx}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+      url = `/api/log/?p=${startIdx}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
     } else {
       url = `/api/log/self/?p=${startIdx}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
@@ -205,16 +206,9 @@ const LogsTable = () => {
         </Header>
         <Form>
           <Form.Group>
-            {
-              isAdminUser && (
-                <Form.Input fluid label={'用户名称'} width={2} value={username}
-                            placeholder={'可选值'} name='username'
-                            onChange={handleInputChange} />
-              )
-            }
-            <Form.Input fluid label={'令牌名称'} width={isAdminUser ? 2 : 3} value={token_name}
+            <Form.Input fluid label={'令牌名称'} width={3} value={token_name}
                         placeholder={'可选值'} name='token_name' onChange={handleInputChange} />
-            <Form.Input fluid label='模型名称' width={isAdminUser ? 2 : 3} value={model_name} placeholder='可选值'
+            <Form.Input fluid label='模型名称' width={3} value={model_name} placeholder='可选值'
                         name='model_name'
                         onChange={handleInputChange} />
             <Form.Input fluid label='起始时间' width={4} value={start_timestamp} type='datetime-local'
@@ -225,6 +219,19 @@ const LogsTable = () => {
                         onChange={handleInputChange} />
             <Form.Button fluid label='操作' width={2} onClick={refresh}>查询</Form.Button>
           </Form.Group>
+          {
+            isAdminUser && <>
+              <Form.Group>
+                <Form.Input fluid label={'渠道 ID'} width={3} value={channel}
+                            placeholder='可选值' name='channel'
+                            onChange={handleInputChange} />
+                <Form.Input fluid label={'用户名称'} width={3} value={username}
+                            placeholder={'可选值'} name='username'
+                            onChange={handleInputChange} />
+
+              </Form.Group>
+            </>
+          }
         </Form>
         <Table basic compact size='small'>
           <Table.Header>
@@ -238,6 +245,17 @@ const LogsTable = () => {
               >
                 时间
               </Table.HeaderCell>
+              {
+                isAdminUser && <Table.HeaderCell
+                  style={{ cursor: 'pointer' }}
+                  onClick={() => {
+                    sortLog('channel');
+                  }}
+                  width={1}
+                >
+                  渠道
+                </Table.HeaderCell>
+              }
               {
                 isAdminUser && <Table.HeaderCell
                   style={{ cursor: 'pointer' }}
@@ -299,16 +317,16 @@ const LogsTable = () => {
                 onClick={() => {
                   sortLog('quota');
                 }}
-                width={2}
+                width={1}
               >
-                消耗额度
+                额度
               </Table.HeaderCell>
               <Table.HeaderCell
                 style={{ cursor: 'pointer' }}
                 onClick={() => {
                   sortLog('content');
                 }}
-                width={isAdminUser ? 4 : 5}
+                width={isAdminUser ? 4 : 6}
               >
                 详情
               </Table.HeaderCell>
@@ -326,6 +344,11 @@ const LogsTable = () => {
                 return (
                   <Table.Row key={log.id}>
                     <Table.Cell>{renderTimestamp(log.created_at)}</Table.Cell>
+                    {
+                      isAdminUser && (
+                        <Table.Cell>{log.channel ? <Label basic>{log.channel}</Label> : ''}</Table.Cell>
+                      )
+                    }
                     {
                       isAdminUser && (
                         <Table.Cell>{log.username ? <Label>{log.username}</Label> : ''}</Table.Cell>
@@ -345,7 +368,7 @@ const LogsTable = () => {
 
           <Table.Footer>
             <Table.Row>
-              <Table.HeaderCell colSpan={'9'}>
+              <Table.HeaderCell colSpan={'10'}>
                 <Select
                   placeholder='选择明细分类'
                   options={LOG_OPTIONS}

web/default/src/components/OperationSetting.js

@@ -16,6 +16,7 @@ const OperationSetting = () => {
     ChatLink: '',
     QuotaPerUnit: 0,
     AutomaticDisableChannelEnabled: '',
+    AutomaticEnableChannelEnabled: '',
     ChannelDisableThreshold: 0,
     LogConsumeEnabled: '',
     DisplayInCurrencyEnabled: '',
@@ -269,6 +270,12 @@ const OperationSetting = () => {
               name='AutomaticDisableChannelEnabled'
               onChange={handleInputChange}
             />
+            <Form.Checkbox
+                checked={inputs.AutomaticEnableChannelEnabled === 'true'}
+                label='成功时自动启用通道'
+                name='AutomaticEnableChannelEnabled'
+                onChange={handleInputChange}
+            />
           </Form.Group>
           <Form.Button onClick={() => {
             submitConfig('monitor').then();

web/default/src/components/RedemptionsTable.js

@@ -130,7 +130,13 @@ const RedemptionsTable = () => {
     setLoading(true);
     let sortedRedemptions = [...redemptions];
     sortedRedemptions.sort((a, b) => {
-      return ('' + a[key]).localeCompare(b[key]);
+      if (!isNaN(a[key])) {
+        // If the value is numeric, subtract to sort
+        return a[key] - b[key];
+      } else {
+        // If the value is not numeric, sort as strings
+        return ('' + a[key]).localeCompare(b[key]);
+      }
     });
     if (sortedRedemptions[0].id === redemptions[0].id) {
       sortedRedemptions.reverse();

web/default/src/components/TokensTable.js

@@ -138,7 +138,7 @@ const TokensTable = () => {
     let defaultUrl;
   
     if (chatLink) {
-      defaultUrl = chatLink + `/#/?settings={"key":"sk-${key}"}`;
+      defaultUrl = chatLink + `/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
     } else {
       defaultUrl = `https://chat.oneapi.pro/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
     }
@@ -228,7 +228,13 @@ const TokensTable = () => {
     setLoading(true);
     let sortedTokens = [...tokens];
     sortedTokens.sort((a, b) => {
-      return ('' + a[key]).localeCompare(b[key]);
+      if (!isNaN(a[key])) {
+        // If the value is numeric, subtract to sort
+        return a[key] - b[key];
+      } else {
+        // If the value is not numeric, sort as strings
+        return ('' + a[key]).localeCompare(b[key]);
+      }
     });
     if (sortedTokens[0].id === tokens[0].id) {
       sortedTokens.reverse();

web/default/src/components/UsersTable.js

@@ -133,7 +133,13 @@ const UsersTable = () => {
     setLoading(true);
     let sortedUsers = [...users];
     sortedUsers.sort((a, b) => {
-      return ('' + a[key]).localeCompare(b[key]);
+      if (!isNaN(a[key])) {
+        // If the value is numeric, subtract to sort
+        return a[key] - b[key];
+      } else {
+        // If the value is not numeric, sort as strings
+        return ('' + a[key]).localeCompare(b[key]);
+      }
     });
     if (sortedUsers[0].id === users[0].id) {
       sortedUsers.reverse();

web/default/src/constants/channel.constants.js

@@ -3,11 +3,13 @@ export const CHANNEL_OPTIONS = [
   { key: 14, text: 'Anthropic Claude', value: 14, color: 'black' },
   { key: 3, text: 'Azure OpenAI', value: 3, color: 'olive' },
   { key: 11, text: 'Google PaLM2', value: 11, color: 'orange' },
+  { key: 24, text: 'Google Gemini', value: 24, color: 'orange' },
   { key: 15, text: '百度文心千帆', value: 15, color: 'blue' },
   { key: 17, text: '阿里通义千问', value: 17, color: 'orange' },
   { key: 18, text: '讯飞星火认知', value: 18, color: 'blue' },
   { key: 16, text: '智谱 ChatGLM', value: 16, color: 'violet' },
   { key: 19, text: '360 智脑', value: 19, color: 'blue' },
+  { key: 23, text: '腾讯混元', value: 23, color: 'teal' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
   { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
   { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },