Merge pull request #555 from utopeadia/main

Continue fixing Ollama embedding return issue

.github/FUNDING.yml

@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: ['https://afdian.com/a/new-api'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.gitignore

@@ -5,4 +5,5 @@ upload
 *.db
 build
 *.db-journal
-logs
+logs
+web/dist

README.md

@@ -1,16 +1,29 @@
+<div align="center">
+
+![new-api](/web/public/logo.png)
 
 # New API
 
-> [!NOTE]
-> 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发，感谢原作者的无私奉献。 
-> 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。
+<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
-> 本项目为个人学习使用，不保证稳定性，且不提供任何技术支持，使用者必须在遵循 OpenAI 的使用条款以及法律法规的情况下使用，不得用于非法用途。  
+</div>
+
+> [!NOTE]
+> 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发
+
+> [!IMPORTANT]
+> 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。
+> 本项目仅供个人学习使用，不保证稳定性，且不提供任何技术支持。
 > 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。
 
-> [!NOTE]
-> 最新版Docker镜像 calciumion/new-api:latest  
-> 更新指令 docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+> [!TIP]
+> 最新版Docker镜像：`calciumion/new-api:latest`  
+> 默认账号root 密码123456  
+> 更新指令：
+> ```
+> docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+> ```
+
 
 ## 主要变更
 此分叉版本的主要变更如下：
@@ -18,9 +31,9 @@
 1. 全新的UI界面（部分界面还待更新）
 2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
-   + [x] 易支付
+    + [x] 易支付
 4. 支持用key查询使用额度:
-   + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用
+    + 配合项目[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)可实现用key查询使用
 5. 渠道显示已使用额度，支持指定组织访问
 6. 分页支持选择每页显示数量
 7. 兼容原版One API的数据库，可直接使用原版数据库（one-api.db）
@@ -35,6 +48,7 @@
     4. Telegram Bot 名称是bot username 去掉@后的字符串
 13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
 14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
+15. **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道。
 
 ## 模型支持
 此版本额外支持以下模型：
@@ -48,35 +62,20 @@
 8. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
 9. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
 10. Dify
+11. Vertex AI，目前兼容Claude，Gemini，Llama3.1
 
 您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
-## 渠道重试
-渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
-如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。  
-### 缓存设置方法
-1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
-    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
-2. `MEMORY_CACHE_ENABLED`：启用内存缓存（如果设置了`REDIS_CONN_STRING`，则无需手动设置），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`
-### 为什么有的时候没有重试
-这些错误码不会重试：400，504，524
-### 我想让400也重试
-在`渠道->编辑`中，将`状态码复写`改为
-```json
-{
-  "400": "500"
-}
-```
-可以实现400错误转为500错误，从而重试
-
 ## 比原版One API多出的配置
-- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒
-- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`
-- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`
-- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用，
-- `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`
-- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度
+- `GENERATE_DEFAULT_TOKEN`：是否为新注册用户生成初始令牌，默认为 `false`。
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒。
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`。
+- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`，建议开启，不影响客户端传入stream_options参数返回结果。
+- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
+- `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
+- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
+- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置
+- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`，`STRICT`，默认为 `NONE`。
 ## 部署
 ### 部署要求
 - 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）
@@ -99,8 +98,25 @@ docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(宝塔的服务器地址:宝塔数据库端口)/宝塔数据库名称" -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
 # 注意：数据库要开启远程访问，并且只允许服务器IP访问
 ```
-### 默认账号密码
-默认账号root 密码123456
+
+## 渠道重试
+渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
+如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。
+### 缓存设置方法
+1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
+    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
+2. `MEMORY_CACHE_ENABLED`：启用内存缓存（如果设置了`REDIS_CONN_STRING`，则无需手动设置），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`
+### 为什么有的时候没有重试
+这些错误码不会重试：400，504，524
+### 我想让400也重试
+在`渠道->编辑`中，将`状态码复写`改为
+```json
+{
+  "400": "500"
+}
+```
+可以实现400错误转为500错误，从而重试
 
 ## Midjourney接口设置文档
 [对接文档](Midjourney.md)
@@ -108,24 +124,19 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ## Suno接口设置文档
 [对接文档](Suno.md)
 
-## 交流群
-<img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="300">
-
 ## 界面截图
+![796df8d287b7b7bd7853b2497e7df511](https://github.com/user-attachments/assets/255b5e97-2d3a-4434-b4fa-e922ad88ff5a)
+
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/ad0e7aae-0203-471c-9716-2d83768927d4)
 
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/d1ac216e-0804-4105-9fdc-66b35022d861)
-
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)  
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/f4f40ed4-8ccb-43d7-a580-90677827646d)  
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/90d7d763-6a77-4b36-9f76-2bb30f18583d)
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/e414228a-3c35-429a-b298-6451d76d9032)
+![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)
 夜间模式  
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/1c66b593-bb9e-4757-9720-ff2759539242)
-
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/5b3228e8-2556-44f7-97d6-4f8d8ee6effa)  
 ![image](https://github.com/Calcium-Ion/new-api/assets/61247483/af9a07ee-5101-4b3d-8bd9-ae21a4fd7e9e)
 
+## 交流群
+<img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="200">
+
 ## 相关项目
 - [One API](https://github.com/songquanpeng/one-api)：原版项目
 - [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)：Midjourney接口支持

common/constants.go

@@ -112,6 +112,9 @@ var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
 var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
+// https://docs.cohere.com/docs/safety-modes Type; NONE/CONTEXTUAL/STRICT
+var CohereSafetySetting = GetEnvOrDefaultString("COHERE_SAFETY_SETTING", "NONE")
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )
@@ -123,6 +126,10 @@ const (
 	RoleRootUser   = 100
 )
 
+func IsValidateRole(role int) bool {
+	return role == RoleGuestUser || role == RoleCommonUser || role == RoleAdminUser || role == RoleRootUser
+}
+
 var (
 	FileUploadPermission    = RoleGuestUser
 	FileDownloadPermission  = RoleGuestUser
@@ -213,6 +220,9 @@ const (
 	ChannelTypeDify           = 37
 	ChannelTypeJina           = 38
 	ChannelCloudflare         = 39
+	ChannelTypeSiliconFlow    = 40
+	ChannelTypeVertexAi       = 41
+	ChannelTypeMistral        = 42
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
 
@@ -259,4 +269,7 @@ var ChannelBaseURLs = []string{
 	"",                                          //37
 	"https://api.jina.ai",                       //38
 	"https://api.cloudflare.com",                //39
+	"https://api.siliconflow.cn",                //40
+	"",                                          //41
+	"https://api.mistral.ai",                    //42
 }

common/email-outlook-auth.go

@@ -0,0 +1,40 @@
+package common
+
+import (
+	"errors"
+	"net/smtp"
+	"strings"
+)
+
+type outlookAuth struct {
+	username, password string
+}
+
+func LoginAuth(username, password string) smtp.Auth {
+	return &outlookAuth{username, password}
+}
+
+func (a *outlookAuth) Start(_ *smtp.ServerInfo) (string, []byte, error) {
+	return "LOGIN", []byte{}, nil
+}
+
+func (a *outlookAuth) Next(fromServer []byte, more bool) ([]byte, error) {
+	if more {
+		switch string(fromServer) {
+		case "Username:":
+			return []byte(a.username), nil
+		case "Password:":
+			return []byte(a.password), nil
+		default:
+			return nil, errors.New("unknown fromServer")
+		}
+	}
+	return nil, nil
+}
+
+func isOutlookServer(server string) bool {
+	// 兼容多地区的outlook邮箱和ofb邮箱
+	// 其实应该加一个Option来区分是否用LOGIN的方式登录
+	// 先临时兼容一下
+	return strings.Contains(server, "outlook") || strings.Contains(server, "onmicrosoft")
+}

common/email.go

@@ -9,17 +9,26 @@ import (
 	"time"
 )
 
+func generateMessageID() string {
+	domain := strings.Split(SMTPAccount, "@")[1]
+	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain)
+}
+
 func SendEmail(subject string, receiver string, content string) error {
 	if SMTPFrom == "" { // for compatibility
 		SMTPFrom = SMTPAccount
 	}
+	if SMTPServer == "" && SMTPAccount == "" {
+		return fmt.Errorf("SMTP 服务器未配置")
+	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
 		"Date: %s\r\n"+
+		"Message-ID: %s\r\n"+ // 添加 Message-ID 头
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), content))
+		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), generateMessageID(), content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
@@ -62,6 +71,9 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err != nil {
 			return err
 		}
+	} else if isOutlookServer(SMTPAccount) {
+		auth = LoginAuth(SMTPAccount, SMTPToken)
+		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	} else {
 		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	}

common/model-ratio.go

@@ -3,6 +3,7 @@ package common
 import (
 	"encoding/json"
 	"strings"
+	"sync"
 )
 
 // from songquanpeng/one-api
@@ -22,27 +23,36 @@ const (
 
 var defaultModelRatio = map[string]float64{
 	//"midjourney":                50,
-	"gpt-4-gizmo-*": 15,
-	"gpt-4-all":     15,
-	"gpt-4o-all":    15,
-	"gpt-4":         15,
+	"gpt-4-gizmo-*":  15,
+	"gpt-4o-gizmo-*": 2.5,
+	"gpt-4-all":      15,
+	"gpt-4o-all":     15,
+	"gpt-4":          15,
 	//"gpt-4-0314":                   15, //deprecated
 	"gpt-4-0613": 15,
 	"gpt-4-32k":  30,
 	//"gpt-4-32k-0314":               30, //deprecated
-	"gpt-4-32k-0613":            30,
-	"gpt-4-1106-preview":        5,   // $0.01 / 1K tokens
-	"gpt-4-0125-preview":        5,   // $0.01 / 1K tokens
-	"gpt-4-turbo-preview":       5,   // $0.01 / 1K tokens
-	"gpt-4-vision-preview":      5,   // $0.01 / 1K tokens
-	"gpt-4-1106-vision-preview": 5,   // $0.01 / 1K tokens
-	"gpt-4o":                    2.5, // $0.01 / 1K tokens
-	"gpt-4o-2024-05-13":         2.5, // $0.01 / 1K tokens
-	"gpt-4o-mini":               0.7,
-	"gpt-4o-mini-2024-07-18":    0.7,
-	"gpt-4-turbo":               5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":    5,    // $0.01 / 1K tokens
-	"gpt-3.5-turbo":             0.25, // $0.0015 / 1K tokens
+	"gpt-4-32k-0613":                  30,
+	"gpt-4-1106-preview":              5,    // $0.01 / 1K tokens
+	"gpt-4-0125-preview":              5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-preview":             5,    // $0.01 / 1K tokens
+	"gpt-4-vision-preview":            5,    // $0.01 / 1K tokens
+	"gpt-4-1106-vision-preview":       5,    // $0.01 / 1K tokens
+	"chatgpt-4o-latest":               2.5,  // $0.01 / 1K tokens
+	"gpt-4o":                          1.25, // $0.01 / 1K tokens
+	"gpt-4o-audio-preview":            1.25, // $0.0015 / 1K tokens
+	"gpt-4o-audio-preview-2024-10-01": 1.25, // $0.0015 / 1K tokens
+	"gpt-4o-2024-08-06":               1.25, // $0.01 / 1K tokens
+	"gpt-4o-2024-05-13":               2.5,
+	"gpt-4o-realtime-preview":         2.5,
+	"o1-preview":                      7.5,
+	"o1-preview-2024-09-12":           7.5,
+	"o1-mini":                         1.5,
+	"o1-mini-2024-09-12":              1.5,
+	"gpt-4o-mini":                     0.075,
+	"gpt-4o-mini-2024-07-18":          0.075,
+	"gpt-4-turbo":                     5, // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":          5, // $0.01 / 1K tokens
 	//"gpt-3.5-turbo-0301":           0.75, //deprecated
 	"gpt-3.5-turbo-0613":     0.75,
 	"gpt-3.5-turbo-16k":      1.5, // $0.003 / 1K tokens
@@ -78,8 +88,10 @@ var defaultModelRatio = map[string]float64{
 	"claude-2.0":                     4,     // $8 / 1M tokens
 	"claude-2.1":                     4,     // $8 / 1M tokens
 	"claude-3-haiku-20240307":        0.125, // $0.25 / 1M tokens
+	"claude-3-5-haiku-20241022":      0.5,   // $1 / 1M tokens
 	"claude-3-sonnet-20240229":       1.5,   // $3 / 1M tokens
 	"claude-3-5-sonnet-20240620":     1.5,
+	"claude-3-5-sonnet-20241022":     1.5,
 	"claude-3-opus-20240229":         7.5, // $15 / 1M tokens
 	"ERNIE-4.0-8K":                   0.120 * RMB,
 	"ERNIE-3.5-8K":                   0.012 * RMB,
@@ -102,8 +114,10 @@ var defaultModelRatio = map[string]float64{
 	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"gemini-1.0-pro-vision-001":      1,
 	"gemini-1.0-pro-001":             1,
-	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-pro-latest":          1.75, // $3.5 / 1M tokens
+	"gemini-1.5-pro-exp-0827":        1.75, // $3.5 / 1M tokens
 	"gemini-1.5-flash-latest":        1,
+	"gemini-1.5-flash-exp-0827":      1,
 	"gemini-1.0-pro-latest":          1,
 	"gemini-1.0-pro-vision-latest":   1,
 	"gemini-ultra":                   1,
@@ -115,6 +129,13 @@ var defaultModelRatio = map[string]float64{
 	"glm-4v":                         0.05 * RMB, // ￥0.05 / 1k tokens
 	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
 	"glm-3-turbo":                    0.3572,
+	"glm-4-plus":                     0.05 * RMB,
+	"glm-4-0520":                     0.1 * RMB,
+	"glm-4-air":                      0.001 * RMB,
+	"glm-4-airx":                     0.01 * RMB,
+	"glm-4-long":                     0.001 * RMB,
+	"glm-4-flash":                    0,
+	"glm-4v-plus":                    0.01 * RMB,
 	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
 	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
 	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
@@ -133,26 +154,28 @@ var defaultModelRatio = map[string]float64{
 	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
-	"yi-34b-chat-0205":      0.18,
-	"yi-34b-chat-200k":      0.864,
-	"yi-vl-plus":            0.432,
-	"yi-large":              20.0 / 1000 * RMB,
-	"yi-medium":             2.5 / 1000 * RMB,
-	"yi-vision":             6.0 / 1000 * RMB,
-	"yi-medium-200k":        12.0 / 1000 * RMB,
-	"yi-spark":              1.0 / 1000 * RMB,
-	"yi-large-rag":          25.0 / 1000 * RMB,
-	"yi-large-turbo":        12.0 / 1000 * RMB,
-	"yi-large-preview":      20.0 / 1000 * RMB,
-	"yi-large-rag-preview":  25.0 / 1000 * RMB,
-	"command":               0.5,
-	"command-nightly":       0.5,
-	"command-light":         0.5,
-	"command-light-nightly": 0.5,
-	"command-r":             0.25,
-	"command-r-plus	":       1.5,
-	"deepseek-chat":         0.07,
-	"deepseek-coder":        0.07,
+	"yi-34b-chat-0205":       0.18,
+	"yi-34b-chat-200k":       0.864,
+	"yi-vl-plus":             0.432,
+	"yi-large":               20.0 / 1000 * RMB,
+	"yi-medium":              2.5 / 1000 * RMB,
+	"yi-vision":              6.0 / 1000 * RMB,
+	"yi-medium-200k":         12.0 / 1000 * RMB,
+	"yi-spark":               1.0 / 1000 * RMB,
+	"yi-large-rag":           25.0 / 1000 * RMB,
+	"yi-large-turbo":         12.0 / 1000 * RMB,
+	"yi-large-preview":       20.0 / 1000 * RMB,
+	"yi-large-rag-preview":   25.0 / 1000 * RMB,
+	"command":                0.5,
+	"command-nightly":        0.5,
+	"command-light":          0.5,
+	"command-light-nightly":  0.5,
+	"command-r":              0.25,
+	"command-r-plus":         1.5,
+	"command-r-08-2024":      0.075,
+	"command-r-plus-08-2024": 1.25,
+	"deepseek-chat":          0.07,
+	"deepseek-coder":         0.07,
 	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
 	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
 	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
@@ -180,22 +203,37 @@ var defaultModelPrice = map[string]float64{
 	"mj_describe":       0.05,
 	"mj_upscale":        0.05,
 	"swap_face":         0.05,
+	"mj_upload":         0.05,
 }
 
-var modelPrice map[string]float64 = nil
-var modelRatio map[string]float64 = nil
+var (
+	modelPriceMap      map[string]float64 = nil
+	modelPriceMapMutex                    = sync.RWMutex{}
+)
+var (
+	modelRatioMap      map[string]float64 = nil
+	modelRatioMapMutex                    = sync.RWMutex{}
+)
 
 var CompletionRatio map[string]float64 = nil
 var defaultCompletionRatio = map[string]float64{
-	"gpt-4-gizmo-*": 2,
-	"gpt-4-all":     2,
+	"gpt-4-gizmo-*":  2,
+	"gpt-4o-gizmo-*": 3,
+	"gpt-4-all":      2,
+}
+
+func GetModelPriceMap() map[string]float64 {
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	if modelPriceMap == nil {
+		modelPriceMap = defaultModelPrice
+	}
+	return modelPriceMap
 }
 
 func ModelPrice2JSONString() string {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
-	}
-	jsonBytes, err := json.Marshal(modelPrice)
+	GetModelPriceMap()
+	jsonBytes, err := json.Marshal(modelPriceMap)
 	if err != nil {
 		SysError("error marshalling model price: " + err.Error())
 	}
@@ -203,19 +241,22 @@ func ModelPrice2JSONString() string {
 }
 
 func UpdateModelPriceByJSONString(jsonStr string) error {
-	modelPrice = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelPrice)
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	modelPriceMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelPriceMap)
 }
 
 // GetModelPrice 返回模型的价格，如果模型不存在则返回-1，false
 func GetModelPrice(name string, printErr bool) (float64, bool) {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
-	}
+	GetModelPriceMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
-	price, ok := modelPrice[name]
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
+	}
+	price, ok := modelPriceMap[name]
 	if !ok {
 		if printErr {
 			SysError("model price not found: " + name)
@@ -225,18 +266,18 @@ func GetModelPrice(name string, printErr bool) (float64, bool) {
 	return price, true
 }
 
-func GetModelPriceMap() map[string]float64 {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
+func GetModelRatioMap() map[string]float64 {
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	if modelRatioMap == nil {
+		modelRatioMap = defaultModelRatio
 	}
-	return modelPrice
+	return modelRatioMap
 }
 
 func ModelRatio2JSONString() string {
-	if modelRatio == nil {
-		modelRatio = defaultModelRatio
-	}
-	jsonBytes, err := json.Marshal(modelRatio)
+	GetModelRatioMap()
+	jsonBytes, err := json.Marshal(modelRatioMap)
 	if err != nil {
 		SysError("error marshalling model ratio: " + err.Error())
 	}
@@ -244,18 +285,18 @@ func ModelRatio2JSONString() string {
 }
 
 func UpdateModelRatioByJSONString(jsonStr string) error {
-	modelRatio = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelRatio)
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	modelRatioMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelRatioMap)
 }
 
 func GetModelRatio(name string) float64 {
-	if modelRatio == nil {
-		modelRatio = defaultModelRatio
-	}
+	GetModelRatioMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
-	ratio, ok := modelRatio[name]
+	ratio, ok := modelRatioMap[name]
 	if !ok {
 		SysError("model ratio not found: " + name)
 		return 30
@@ -295,6 +336,34 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
+	}
+	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
+		if strings.HasPrefix(name, "gpt-4o") {
+			if name == "gpt-4o-2024-05-13" {
+				return 3
+			}
+			return 4
+		}
+		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
+			return 3
+		}
+		return 2
+	}
+	if strings.HasPrefix(name, "o1-") {
+		return 4
+	}
+	if name == "chatgpt-4o-latest" {
+		return 3
+	}
+	if strings.Contains(name, "claude-instant-1") {
+		return 3
+	} else if strings.Contains(name, "claude-2") {
+		return 3
+	} else if strings.Contains(name, "claude-3") {
+		return 5
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
 		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
 			// https://openai.com/blog/new-embedding-models-and-api-updates
@@ -306,30 +375,11 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
-		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
-			return 3
-		}
-		if strings.HasPrefix(name, "gpt-4o") {
-			if strings.Contains(name, "mini") {
-				return 4
-			}
-			return 3
-		}
-		return 2
-	}
-	if strings.Contains(name, "claude-instant-1") {
-		return 3
-	} else if strings.Contains(name, "claude-2") {
-		return 3
-	} else if strings.Contains(name, "claude-3") {
-		return 5
-	}
 	if strings.HasPrefix(name, "mistral-") {
 		return 3
 	}
 	if strings.HasPrefix(name, "gemini-") {
-		return 3
+		return 4
 	}
 	if strings.HasPrefix(name, "command") {
 		switch name {
@@ -337,6 +387,10 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		case "command-r-plus":
 			return 5
+		case "command-r-08-2024":
+			return 4
+		case "command-r-plus-08-2024":
+			return 4
 		default:
 			return 2
 		}
@@ -367,6 +421,34 @@ func GetCompletionRatio(name string) float64 {
 	return 1
 }
 
+func GetAudioRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4o-realtime") {
+		return 20
+	}
+	return 20
+}
+
+func GetAudioCompletionRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4o-realtime") {
+		return 2
+	}
+	return 2
+}
+
+//func GetAudioPricePerMinute(name string) float64 {
+//	if strings.HasPrefix(name, "gpt-4o-realtime") {
+//		return 0.06
+//	}
+//	return 0.06
+//}
+//
+//func GetAudioCompletionPricePerMinute(name string) float64 {
+//	if strings.HasPrefix(name, "gpt-4o-realtime") {
+//		return 0.24
+//	}
+//	return 0.24
+//}
+
 func GetCompletionRatioMap() map[string]float64 {
 	if CompletionRatio == nil {
 		CompletionRatio = defaultCompletionRatio

common/str.go

@@ -31,14 +31,6 @@ func MapToJsonStr(m map[string]interface{}) string {
 	return string(bytes)
 }
 
-func MapToJsonStrFloat(m map[string]float64) string {
-	bytes, err := json.Marshal(m)
-	if err != nil {
-		return ""
-	}
-	return string(bytes)
-}
-
 func StrToMap(str string) map[string]interface{} {
 	m := make(map[string]interface{})
 	err := json.Unmarshal([]byte(str), &m)
@@ -48,6 +40,11 @@ func StrToMap(str string) map[string]interface{} {
 	return m
 }
 
+func IsJsonStr(str string) bool {
+	var js map[string]interface{}
+	return json.Unmarshal([]byte(str), &js) == nil
+}
+
 func String2Int(str string) int {
 	num, err := strconv.Atoi(str)
 	if err != nil {

common/user_groups.go

@@ -0,0 +1,46 @@
+package common
+
+import (
+	"encoding/json"
+)
+
+var UserUsableGroups = map[string]string{
+	"default": "默认分组",
+	"vip":     "vip分组",
+}
+
+func UserUsableGroups2JSONString() string {
+	jsonBytes, err := json.Marshal(UserUsableGroups)
+	if err != nil {
+		SysError("error marshalling user groups: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func UpdateUserUsableGroupsByJSONString(jsonStr string) error {
+	UserUsableGroups = make(map[string]string)
+	return json.Unmarshal([]byte(jsonStr), &UserUsableGroups)
+}
+
+func GetUserUsableGroups(userGroup string) map[string]string {
+	if userGroup == "" {
+		// 如果userGroup为空，返回UserUsableGroups
+		return UserUsableGroups
+	}
+	// 如果userGroup不在UserUsableGroups中，返回UserUsableGroups + userGroup
+	if _, ok := UserUsableGroups[userGroup]; !ok {
+		appendUserUsableGroups := make(map[string]string)
+		for k, v := range UserUsableGroups {
+			appendUserUsableGroups[k] = v
+		}
+		appendUserUsableGroups[userGroup] = "用户分组"
+		return appendUserUsableGroups
+	}
+	// 如果userGroup在UserUsableGroups中，返回UserUsableGroups
+	return UserUsableGroups
+}
+
+func GroupInUserUsableGroups(groupName string) bool {
+	_, ok := UserUsableGroups[groupName]
+	return ok
+}

common/utils.go

@@ -1,10 +1,13 @@
 package common
 
 import (
+	crand "crypto/rand"
+	"encoding/base64"
 	"fmt"
 	"github.com/google/uuid"
 	"html/template"
 	"log"
+	"math/big"
 	"math/rand"
 	"net"
 	"os/exec"
@@ -128,6 +131,11 @@ func IntMax(a int, b int) int {
 	}
 }
 
+func IsIP(s string) bool {
+	ip := net.ParseIP(s)
+	return ip != nil
+}
+
 func GetUUID() string {
 	code := uuid.New().String()
 	code = strings.Replace(code, "-", "", -1)
@@ -137,24 +145,35 @@ func GetUUID() string {
 const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
 
 func init() {
-	rand.Seed(time.Now().UnixNano())
+	rand.New(rand.NewSource(time.Now().UnixNano()))
 }
 
-func GenerateKey() string {
-	//rand.Seed(time.Now().UnixNano())
-	key := make([]byte, 48)
-	for i := 0; i < 16; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
-	}
-	uuid_ := GetUUID()
-	for i := 0; i < 32; i++ {
-		c := uuid_[i]
-		if i%2 == 0 && c >= 'a' && c <= 'z' {
-			c = c - 'a' + 'A'
+func GenerateRandomCharsKey(length int) (string, error) {
+	b := make([]byte, length)
+	maxI := big.NewInt(int64(len(keyChars)))
+
+	for i := range b {
+		n, err := crand.Int(crand.Reader, maxI)
+		if err != nil {
+			return "", err
 		}
-		key[i+16] = c
+		b[i] = keyChars[n.Int64()]
 	}
-	return string(key)
+
+	return string(b), nil
+}
+
+func GenerateRandomKey(length int) (string, error) {
+	bytes := make([]byte, length*3/4) // 对于48位的输出，这里应该是36
+	if _, err := crand.Read(bytes); err != nil {
+		return "", err
+	}
+	return base64.StdEncoding.EncodeToString(bytes), nil
+}
+
+func GenerateKey() (string, error) {
+	//rand.Seed(time.Now().UnixNano())
+	return GenerateRandomCharsKey(48)
 }
 
 func GetRandomInt(max int) int {

constant/chat.go

@@ -0,0 +1,35 @@
+package constant
+
+import (
+	"encoding/json"
+	"one-api/common"
+)
+
+var Chats = []map[string]string{
+	{
+		"ChatGPT Next Web 官方示例": "https://app.nextchat.dev/#/?settings={\"key\":\"{key}\",\"url\":\"{address}\"}",
+	},
+	{
+		"Lobe Chat 官方示例": "https://chat-preview.lobehub.com/?settings={\"keyVaults\":{\"openai\":{\"apiKey\":\"{key}\",\"baseURL\":\"{address}/v1\"}}}",
+	},
+	{
+		"AMA 问天": "ama://set-api-key?server={address}&key={key}",
+	},
+	{
+		"OpenCat": "opencat://team/join?domain={address}&token={key}",
+	},
+}
+
+func UpdateChatsByJsonString(jsonString string) error {
+	Chats = make([]map[string]string, 0)
+	return json.Unmarshal([]byte(jsonString), &Chats)
+}
+
+func Chats2JsonString() string {
+	jsonBytes, err := json.Marshal(Chats)
+	if err != nil {
+		common.SysError("error marshalling chats: " + err.Error())
+		return "[]"
+	}
+	return string(jsonBytes)
+}

constant/env.go

@@ -1,7 +1,10 @@
 package constant
 
 import (
+	"fmt"
 	"one-api/common"
+	"os"
+	"strings"
 )
 
 var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
@@ -15,3 +18,34 @@ var GetMediaToken = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN", true)
 var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STREAM", true)
 
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
+
+var GeminiModelMap = map[string]string{
+	"gemini-1.5-pro-latest":     "v1beta",
+	"gemini-1.5-pro-001":        "v1beta",
+	"gemini-1.5-pro":            "v1beta",
+	"gemini-1.5-pro-exp-0801":   "v1beta",
+	"gemini-1.5-pro-exp-0827":   "v1beta",
+	"gemini-1.5-flash-latest":   "v1beta",
+	"gemini-1.5-flash-exp-0827": "v1beta",
+	"gemini-1.5-flash-001":      "v1beta",
+	"gemini-1.5-flash":          "v1beta",
+	"gemini-ultra":              "v1beta",
+}
+
+func InitEnv() {
+	modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
+	if modelVersionMapStr == "" {
+		return
+	}
+	for _, pair := range strings.Split(modelVersionMapStr, ",") {
+		parts := strings.Split(pair, ":")
+		if len(parts) == 2 {
+			GeminiModelMap[parts[0]] = parts[1]
+		} else {
+			common.SysError(fmt.Sprintf("invalid model version map: %s", pair))
+		}
+	}
+}
+
+// 是否生成初始令牌，默认关闭。
+var GenerateDefaultToken = common.GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)

constant/midjourney.go

@@ -27,6 +27,7 @@ const (
 	MjActionLowVariation  = "LOW_VARIATION"
 	MjActionPan           = "PAN"
 	MjActionSwapFace      = "SWAP_FACE"
+	MjActionUpload        = "UPLOAD"
 )
 
 var MidjourneyModel2Action = map[string]string{
@@ -45,4 +46,5 @@ var MidjourneyModel2Action = map[string]string{
 	"mj_low_variation":  MjActionLowVariation,
 	"mj_pan":            MjActionPan,
 	"swap_face":         MjActionSwapFace,
+	"mj_upload":         MjActionUpload,
 }

controller/channel-test.go

@@ -20,6 +20,7 @@ import (
 	"one-api/relay/constant"
 	"one-api/service"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
 
@@ -81,8 +82,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
 	}
 
-	request := buildTestRequest()
-	request.Model = testModel
+	request := buildTestRequest(testModel)
 	meta.UpstreamModelName = testModel
 	common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
 
@@ -102,17 +102,22 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 	if err != nil {
 		return err, nil
 	}
-	if resp != nil && resp.StatusCode != http.StatusOK {
-		err := service.RelayErrorHandler(resp)
-		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), err
+	var httpResp *http.Response
+	if resp != nil {
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			err := service.RelayErrorHandler(httpResp)
+			return fmt.Errorf("status code %d: %s", httpResp.StatusCode, err.Error.Message), err
+		}
 	}
-	usage, respErr := adaptor.DoResponse(c, resp, meta)
+	usageA, respErr := adaptor.DoResponse(c, httpResp, meta)
 	if respErr != nil {
 		return fmt.Errorf("%s", respErr.Error.Message), respErr
 	}
-	if usage == nil {
+	if usageA == nil {
 		return errors.New("usage is nil"), nil
 	}
+	usage := usageA.(*dto.Usage)
 	result := w.Result()
 	respBody, err := io.ReadAll(result.Body)
 	if err != nil {
@@ -141,17 +146,22 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 	return nil, nil
 }
 
-func buildTestRequest() *dto.GeneralOpenAIRequest {
+func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 	testRequest := &dto.GeneralOpenAIRequest{
-		Model:     "", // this will be set later
-		MaxTokens: 1,
-		Stream:    false,
+		Model:  "", // this will be set later
+		Stream: false,
+	}
+	if strings.HasPrefix(model, "o1-") {
+		testRequest.MaxCompletionTokens = 1
+	} else {
+		testRequest.MaxTokens = 1
 	}
 	content, _ := json.Marshal("hi")
 	testMessage := dto.Message{
 		Role:    "user",
 		Content: content,
 	}
+	testRequest.Model = model
 	testRequest.Messages = append(testRequest.Messages, testMessage)
 	return testRequest
 }
@@ -226,26 +236,22 @@ func testAllChannels(notify bool) error {
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
 
-			ban := false
-			if 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))
-				ban = true
-			}
+			shouldBanChannel := false
 
 			// request error disables the channel
 			if openaiWithStatusErr != nil {
 				oaiErr := openaiWithStatusErr.Error
 				err = errors.New(fmt.Sprintf("type %s, httpCode %d, code %v, message %s", oaiErr.Type, openaiWithStatusErr.StatusCode, oaiErr.Code, oaiErr.Message))
-				ban = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
+				shouldBanChannel = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
 			}
 
-			// parse *int to bool
-			if channel.AutoBan != nil && *channel.AutoBan == 0 {
-				ban = false
+			if 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))
+				shouldBanChannel = true
 			}
 
 			// disable channel
-			if ban && isChannelEnabled {
+			if isChannelEnabled && shouldBanChannel && channel.GetAutoBan() {
 				service.DisableChannel(channel.Id, channel.Name, err.Error())
 			}
 

controller/channel.go

@@ -198,6 +198,28 @@ func AddChannel(c *gin.Context) {
 	}
 	channel.CreatedTime = common.GetTimestamp()
 	keys := strings.Split(channel.Key, "\n")
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+		keys = []string{channel.Key}
+	}
 	channels := make([]model.Channel, 0, len(keys))
 	for _, key := range keys {
 		if key == "" {
@@ -297,6 +319,27 @@ func UpdateChannel(c *gin.Context) {
 		})
 		return
 	}
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+	}
 	err = channel.Update()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{

controller/github.go

@@ -112,7 +112,9 @@ func GitHubOAuth(c *gin.Context) {
 	user := model.User{
 		GitHubId: githubUser.Login,
 	}
+	// IsGitHubIdAlreadyTaken is unscoped
 	if model.IsGitHubIdAlreadyTaken(user.GitHubId) {
+		// FillUserByGitHubId is scoped
 		err := user.FillUserByGitHubId()
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
@@ -121,6 +123,14 @@ func GitHubOAuth(c *gin.Context) {
 			})
 			return
 		}
+		// if user.Id == 0 , user has been deleted
+		if user.Id == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "用户已注销",
+			})
+			return
+		}
 	} else {
 		if common.RegisterEnabled {
 			user.Username = "github_" + strconv.Itoa(model.GetMaxUserId()+1)

controller/group.go

@@ -4,6 +4,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
+	"one-api/model"
 )
 
 func GetGroups(c *gin.Context) {
@@ -17,3 +18,22 @@ func GetGroups(c *gin.Context) {
 		"data":    groupNames,
 	})
 }
+
+func GetUserGroups(c *gin.Context) {
+	usableGroups := make(map[string]string)
+	userGroup := ""
+	userId := c.GetInt("id")
+	userGroup, _ = model.CacheGetUserGroup(userId)
+	for groupName, _ := range common.GroupRatio {
+		// UserUsableGroups contains the groups that the user can use
+		userUsableGroups := common.GetUserUsableGroups(userGroup)
+		if _, ok := userUsableGroups[groupName]; ok {
+			usableGroups[groupName] = userUsableGroups[groupName]
+		}
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    usableGroups,
+	})
+}

controller/log.go

@@ -1,18 +1,19 @@
 package controller
 
 import (
-	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+
+	"github.com/gin-gonic/gin"
 )
 
 func GetAllLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -24,7 +25,7 @@ func GetAllLogs(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
 	channel, _ := strconv.Atoi(c.Query("channel"))
-	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*pageSize, pageSize, channel)
+	logs, total, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, (p-1)*pageSize, pageSize, channel)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -35,16 +36,20 @@ func GetAllLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
-	return
 }
 
 func GetUserLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -58,7 +63,7 @@ func GetUserLogs(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*pageSize, pageSize)
+	logs, total, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, (p-1)*pageSize, pageSize)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -69,7 +74,12 @@ func GetUserLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
 	return
 }

controller/misc.go

@@ -63,6 +63,7 @@ func GetStatus(c *gin.Context) {
 			"default_collapse_sidebar": common.DefaultCollapseSidebar,
 			"enable_online_topup":      constant.PayAddress != "" && constant.EpayId != "" && constant.EpayKey != "",
 			"mj_notify_enabled":        constant.MjNotifyEnabled,
+			"chats":                    constant.Chats,
 		},
 	})
 	return

controller/model.go

@@ -137,31 +137,63 @@ func init() {
 }
 
 func ListModels(c *gin.Context) {
-	userId := c.GetInt("id")
-	user, err := model.GetUserById(userId, true)
-	if err != nil {
-		c.JSON(http.StatusOK, gin.H{
-			"success": false,
-			"message": err.Error(),
-		})
-		return
-	}
-	models := model.GetGroupModels(user.Group)
 	userOpenAiModels := make([]dto.OpenAIModels, 0)
 	permission := getPermission()
-	for _, s := range models {
-		if _, ok := openAIModelsMap[s]; ok {
-			userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+
+	modelLimitEnable := c.GetBool("token_model_limit_enabled")
+	if modelLimitEnable {
+		s, ok := c.Get("token_model_limit")
+		var tokenModelLimit map[string]bool
+		if ok {
+			tokenModelLimit = s.(map[string]bool)
 		} else {
-			userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
-				Id:         s,
-				Object:     "model",
-				Created:    1626777600,
-				OwnedBy:    "custom",
-				Permission: permission,
-				Root:       s,
-				Parent:     nil,
+			tokenModelLimit = map[string]bool{}
+		}
+		for allowModel, _ := range tokenModelLimit {
+			if _, ok := openAIModelsMap[allowModel]; ok {
+				userOpenAiModels = append(userOpenAiModels, openAIModelsMap[allowModel])
+			} else {
+				userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
+					Id:         allowModel,
+					Object:     "model",
+					Created:    1626777600,
+					OwnedBy:    "custom",
+					Permission: permission,
+					Root:       allowModel,
+					Parent:     nil,
+				})
+			}
+		}
+	} else {
+		userId := c.GetInt("id")
+		userGroup, err := model.GetUserGroup(userId)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "get user group failed",
 			})
+			return
+		}
+		group := userGroup
+		tokenGroup := c.GetString("token_group")
+		if tokenGroup != "" {
+			group = tokenGroup
+		}
+		models := model.GetGroupModels(group)
+		for _, s := range models {
+			if _, ok := openAIModelsMap[s]; ok {
+				userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+			} else {
+				userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
+					Id:         s,
+					Object:     "model",
+					Created:    1626777600,
+					OwnedBy:    "custom",
+					Permission: permission,
+					Root:       s,
+					Parent:     nil,
+				})
+			}
 		}
 	}
 	c.JSON(200, gin.H{

controller/pricing.go

@@ -7,18 +7,11 @@ import (
 )
 
 func GetPricing(c *gin.Context) {
-	userId := c.GetInt("id")
-	// if no login, get default group ratio
-	groupRatio := common.GetGroupRatio("default")
-	group, err := model.CacheGetUserGroup(userId)
-	if err == nil {
-		groupRatio = common.GetGroupRatio(group)
-	}
-	pricing := model.GetPricing(group)
+	pricing := model.GetPricing()
 	c.JSON(200, gin.H{
 		"success":     true,
 		"data":        pricing,
-		"group_ratio": groupRatio,
+		"group_ratio": common.GroupRatio,
 	})
 }
 

controller/relay.go

@@ -2,8 +2,10 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"log"
 	"net/http"
@@ -37,45 +39,98 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	return err
 }
 
+func wsHandler(c *gin.Context, ws *websocket.Conn, relayMode int) *dto.OpenAIErrorWithStatusCode {
+	var err *dto.OpenAIErrorWithStatusCode
+	switch relayMode {
+	default:
+		err = relay.TextHelper(c)
+	}
+	return err
+}
+
+func Playground(c *gin.Context) {
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	defer func() {
+		if openaiErr != nil {
+			c.JSON(openaiErr.StatusCode, gin.H{
+				"error": openaiErr.Error,
+			})
+		}
+	}()
+
+	useAccessToken := c.GetBool("use_access_token")
+	if useAccessToken {
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New("暂不支持使用 access token"), "access_token_not_supported", http.StatusBadRequest)
+		return
+	}
+
+	playgroundRequest := &dto.PlayGroundRequest{}
+	err := common.UnmarshalBodyReusable(c, playgroundRequest)
+	if err != nil {
+		openaiErr = service.OpenAIErrorWrapperLocal(err, "unmarshal_request_failed", http.StatusBadRequest)
+		return
+	}
+
+	if playgroundRequest.Model == "" {
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New("请选择模型"), "model_required", http.StatusBadRequest)
+		return
+	}
+	c.Set("original_model", playgroundRequest.Model)
+	group := playgroundRequest.Group
+	userGroup := c.GetString("group")
+
+	if group == "" {
+		group = userGroup
+	} else {
+		if !common.GroupInUserUsableGroups(group) && group != userGroup {
+			openaiErr = service.OpenAIErrorWrapperLocal(errors.New("无权访问该分组"), "group_not_allowed", http.StatusForbidden)
+			return
+		}
+		c.Set("group", group)
+	}
+	c.Set("token_name", "playground-"+group)
+	channel, err := model.CacheGetRandomSatisfiedChannel(group, playgroundRequest.Model, 0)
+	if err != nil {
+		message := fmt.Sprintf("当前分组 %s 下对于模型 %s 无可用渠道", group, playgroundRequest.Model)
+		openaiErr = service.OpenAIErrorWrapperLocal(errors.New(message), "get_playground_channel_failed", http.StatusInternalServerError)
+		return
+	}
+	middleware.SetupContextForSelectedChannel(c, channel, playgroundRequest.Model)
+	Relay(c)
+}
+
 func Relay(c *gin.Context) {
 	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
-	retryTimes := common.RetryTimes
 	requestId := c.GetString(common.RequestIdKey)
-	channelId := c.GetInt("channel_id")
-	channelType := c.GetInt("channel_type")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
-	openaiErr := relayHandler(c, relayMode)
-	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
-	if openaiErr != nil {
-		go processChannelError(c, channelId, channelType, openaiErr)
-	} else {
-		retryTimes = 0
-	}
-	for i := 0; shouldRetry(c, channelId, openaiErr, retryTimes) && i < retryTimes; i++ {
-		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
 		if err != nil {
-			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			common.LogError(c, err.Error())
+			openaiErr = service.OpenAIErrorWrapperLocal(err, "get_channel_failed", http.StatusInternalServerError)
 			break
 		}
-		channelId = channel.Id
-		useChannel := c.GetStringSlice("use_channel")
-		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
-		c.Set("use_channel", useChannel)
-		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
-		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
-		requestBody, err := common.GetRequestBody(c)
-		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
-		openaiErr = relayHandler(c, relayMode)
-		if openaiErr != nil {
-			go processChannelError(c, channelId, channel.Type, openaiErr)
+		openaiErr = relayRequest(c, relayMode, channel)
+
+		if openaiErr == nil {
+			return // 成功处理请求，直接返回
+		}
+
+		go processChannelError(c, channel.Id, channel.Type, channel.Name, channel.GetAutoBan(), openaiErr)
+
+		if !shouldRetry(c, openaiErr, common.RetryTimes-i) {
+			break
 		}
 	}
 	useChannel := c.GetStringSlice("use_channel")
 	if len(useChannel) > 1 {
 		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
-		common.LogInfo(c.Request.Context(), retryLogStr)
+		common.LogInfo(c, retryLogStr)
 	}
 
 	if openaiErr != nil {
@@ -89,10 +144,116 @@ func Relay(c *gin.Context) {
 	}
 }
 
-func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
+var upgrader = websocket.Upgrader{
+	Subprotocols: []string{"realtime"}, // WS 握手支持的协议，如果有使用 Sec-WebSocket-Protocol，则必须在此声明对应的 Protocol TODO add other protocol
+	CheckOrigin: func(r *http.Request) bool {
+		return true // 允许跨域
+	},
+}
+
+func WssRelay(c *gin.Context) {
+	// 将 HTTP 连接升级为 WebSocket 连接
+
+	ws, err := upgrader.Upgrade(c.Writer, c.Request, nil)
+	defer ws.Close()
+
+	if err != nil {
+		openaiErr := service.OpenAIErrorWrapper(err, "get_channel_failed", http.StatusInternalServerError)
+		service.WssError(c, ws, openaiErr.Error)
+		return
+	}
+
+	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
+	requestId := c.GetString(common.RequestIdKey)
+	group := c.GetString("group")
+	//wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01
+	originalModel := c.GetString("original_model")
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
+		if err != nil {
+			common.LogError(c, err.Error())
+			openaiErr = service.OpenAIErrorWrapperLocal(err, "get_channel_failed", http.StatusInternalServerError)
+			break
+		}
+
+		openaiErr = wssRequest(c, ws, relayMode, channel)
+
+		if openaiErr == nil {
+			return // 成功处理请求，直接返回
+		}
+
+		go processChannelError(c, channel.Id, channel.Type, channel.Name, channel.GetAutoBan(), openaiErr)
+
+		if !shouldRetry(c, openaiErr, common.RetryTimes-i) {
+			break
+		}
+	}
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c, retryLogStr)
+	}
+
+	if openaiErr != nil {
+		if openaiErr.StatusCode == http.StatusTooManyRequests {
+			openaiErr.Error.Message = "当前分组上游负载已饱和，请稍后再试"
+		}
+		openaiErr.Error.Message = common.MessageWithRequestId(openaiErr.Error.Message, requestId)
+		service.WssError(c, ws, openaiErr.Error)
+	}
+}
+
+func relayRequest(c *gin.Context, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
+	addUsedChannel(c, channel.Id)
+	requestBody, _ := common.GetRequestBody(c)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return relayHandler(c, relayMode)
+}
+
+func wssRequest(c *gin.Context, ws *websocket.Conn, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
+	addUsedChannel(c, channel.Id)
+	requestBody, _ := common.GetRequestBody(c)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return relay.WssHelper(c, ws)
+}
+
+func addUsedChannel(c *gin.Context, channelId int) {
+	useChannel := c.GetStringSlice("use_channel")
+	useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+	c.Set("use_channel", useChannel)
+}
+
+func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*model.Channel, error) {
+	if retryCount == 0 {
+		autoBan := c.GetBool("auto_ban")
+		autoBanInt := 1
+		if !autoBan {
+			autoBanInt = 0
+		}
+		return &model.Channel{
+			Id:      c.GetInt("channel_id"),
+			Type:    c.GetInt("channel_type"),
+			Name:    c.GetString("channel_name"),
+			AutoBan: &autoBanInt,
+		}, nil
+	}
+	channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, retryCount)
+	if err != nil {
+		return nil, errors.New(fmt.Sprintf("获取重试渠道失败: %s", err.Error()))
+	}
+	middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+	return channel, nil
+}
+
+func shouldRetry(c *gin.Context, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
 	if openaiErr == nil {
 		return false
 	}
+	if openaiErr.LocalError {
+		return false
+	}
 	if retryTimes <= 0 {
 		return false
 	}
@@ -113,26 +274,27 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 		return true
 	}
 	if openaiErr.StatusCode == http.StatusBadRequest {
+		channelType := c.GetInt("channel_type")
+		if channelType == common.ChannelTypeAnthropic {
+			return true
+		}
 		return false
 	}
 	if openaiErr.StatusCode == 408 {
 		// azure处理超时不重试
 		return false
 	}
-	if openaiErr.LocalError {
-		return false
-	}
 	if openaiErr.StatusCode/100 == 2 {
 		return false
 	}
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, channelType int, err *dto.OpenAIErrorWithStatusCode) {
-	autoBan := c.GetBool("auto_ban")
-	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
+func processChannelError(c *gin.Context, channelId int, channelType int, channelName string, autoBan bool, err *dto.OpenAIErrorWithStatusCode) {
+	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
+	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
+	common.LogError(c, fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
 	if service.ShouldDisableChannel(channelType, err) && autoBan {
-		channelName := c.GetString("channel_name")
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
 }
@@ -208,14 +370,14 @@ func RelayTask(c *gin.Context) {
 	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
 		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
 		if err != nil {
-			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			common.LogError(c, fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
 			break
 		}
 		channelId = channel.Id
 		useChannel := c.GetStringSlice("use_channel")
 		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
 		c.Set("use_channel", useChannel)
-		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
+		common.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
 		requestBody, err := common.GetRequestBody(c)
@@ -225,7 +387,7 @@ func RelayTask(c *gin.Context) {
 	useChannel := c.GetStringSlice("use_channel")
 	if len(useChannel) > 1 {
 		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
-		common.LogInfo(c.Request.Context(), retryLogStr)
+		common.LogInfo(c, retryLogStr)
 	}
 	if taskErr != nil {
 		if taskErr.StatusCode == http.StatusTooManyRequests {

controller/telegram.go

@@ -5,6 +5,7 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"io"
+	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"sort"
@@ -48,6 +49,13 @@ func TelegramBind(c *gin.Context) {
 		})
 		return
 	}
+	if user.Id == 0 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "用户已注销",
+		})
+		return
+	}
 	user.TelegramId = telegramId
 	if err := user.Update(false); err != nil {
 		c.JSON(200, gin.H{

controller/token.go

@@ -123,10 +123,19 @@ func AddToken(c *gin.Context) {
 		})
 		return
 	}
+	key, err := common.GenerateKey()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "生成令牌失败",
+		})
+		common.SysError("failed to generate token key: " + err.Error())
+		return
+	}
 	cleanToken := model.Token{
 		UserId:             c.GetInt("id"),
 		Name:               token.Name,
-		Key:                common.GenerateKey(),
+		Key:                key,
 		CreatedTime:        common.GetTimestamp(),
 		AccessedTime:       common.GetTimestamp(),
 		ExpiredTime:        token.ExpiredTime,
@@ -134,6 +143,8 @@ func AddToken(c *gin.Context) {
 		UnlimitedQuota:     token.UnlimitedQuota,
 		ModelLimitsEnabled: token.ModelLimitsEnabled,
 		ModelLimits:        token.ModelLimits,
+		AllowIps:           token.AllowIps,
+		Group:              token.Group,
 	}
 	err = cleanToken.Insert()
 	if err != nil {
@@ -221,6 +232,8 @@ func UpdateToken(c *gin.Context) {
 		cleanToken.UnlimitedQuota = token.UnlimitedQuota
 		cleanToken.ModelLimitsEnabled = token.ModelLimitsEnabled
 		cleanToken.ModelLimits = token.ModelLimits
+		cleanToken.AllowIps = token.AllowIps
+		cleanToken.Group = token.Group
 	}
 	err = cleanToken.Update()
 	if err != nil {

controller/topup.go

@@ -41,12 +41,12 @@ func GetEpayClient() *epay.Client {
 	return withUrl
 }
 
-func getPayMoney(amount float64, user model.User) float64 {
+func getPayMoney(amount float64, group string) float64 {
 	if !common.DisplayInCurrencyEnabled {
 		amount = amount / common.QuotaPerUnit
 	}
 	// 别问为什么用float64，问就是这么点钱没必要
-	topupGroupRatio := common.GetTopupGroupRatio(user.Group)
+	topupGroupRatio := common.GetTopupGroupRatio(group)
 	if topupGroupRatio == 0 {
 		topupGroupRatio = 1
 	}
@@ -75,8 +75,12 @@ func RequestEpay(c *gin.Context) {
 	}
 
 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	payMoney := getPayMoney(float64(req.Amount), *user)
+	group, err := model.CacheGetUserGroup(id)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
 	if payMoney < 0.01 {
 		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
 		return
@@ -94,6 +98,7 @@ func RequestEpay(c *gin.Context) {
 	returnUrl, _ := url.Parse(constant.ServerAddress + "/log")
 	notifyUrl, _ := url.Parse(callBackAddress + "/api/user/epay/notify")
 	tradeNo := fmt.Sprintf("%s%d", common.GetRandomString(6), time.Now().Unix())
+	tradeNo = fmt.Sprintf("USR%dNO%s", id, tradeNo)
 	client := GetEpayClient()
 	if client == nil {
 		c.JSON(200, gin.H{"message": "error", "data": "当前管理员未配置支付信息"})
@@ -101,8 +106,8 @@ func RequestEpay(c *gin.Context) {
 	}
 	uri, params, err := client.Purchase(&epay.PurchaseArgs{
 		Type:           payType,
-		ServiceTradeNo: "A" + tradeNo,
-		Name:           "B" + tradeNo,
+		ServiceTradeNo: tradeNo,
+		Name:           fmt.Sprintf("TUC%d", req.Amount),
 		Money:          strconv.FormatFloat(payMoney, 'f', 2, 64),
 		Device:         epay.PC,
 		NotifyUrl:      notifyUrl,
@@ -120,7 +125,7 @@ func RequestEpay(c *gin.Context) {
 		UserId:     id,
 		Amount:     amount,
 		Money:      payMoney,
-		TradeNo:    "A" + tradeNo,
+		TradeNo:    tradeNo,
 		CreateTime: time.Now().Unix(),
 		Status:     "pending",
 	}
@@ -232,8 +237,12 @@ func RequestAmount(c *gin.Context) {
 		return
 	}
 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	payMoney := getPayMoney(float64(req.Amount), *user)
+	group, err := model.CacheGetUserGroup(id)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
 	if payMoney <= 0.01 {
 		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
 		return

controller/user.go

@@ -7,10 +7,12 @@ import (
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+	"strings"
 	"sync"
 
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
+	"one-api/constant"
 )
 
 type LoginRequest struct {
@@ -66,6 +68,7 @@ func setupLogin(user *model.User, c *gin.Context) {
 	session.Set("username", user.Username)
 	session.Set("role", user.Role)
 	session.Set("status", user.Status)
+	session.Set("group", user.Group)
 	err := session.Save()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
@@ -157,8 +160,9 @@ func Register(c *gin.Context) {
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
-			"message": err.Error(),
+			"message": "数据库错误，请稍后重试",
 		})
+		common.SysError(fmt.Sprintf("CheckUserExistOrDeleted error: %v", err))
 		return
 	}
 	if exist {
@@ -186,6 +190,48 @@ func Register(c *gin.Context) {
 		})
 		return
 	}
+
+	// 获取插入后的用户ID
+	var insertedUser model.User
+	if err := model.DB.Where("username = ?", cleanUser.Username).First(&insertedUser).Error; err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "用户注册失败或用户ID获取失败",
+		})
+		return
+	}
+	// 生成默认令牌
+	if constant.GenerateDefaultToken {
+		key, err := common.GenerateKey()
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "生成默认令牌失败",
+			})
+			common.SysError("failed to generate token key: " + err.Error())
+			return
+		}
+		// 生成默认令牌
+		token := model.Token{
+			UserId:             insertedUser.Id, // 使用插入后的用户ID
+			Name:               cleanUser.Username + "的初始令牌",
+			Key:                key,
+			CreatedTime:        common.GetTimestamp(),
+			AccessedTime:       common.GetTimestamp(),
+			ExpiredTime:        -1,     // 永不过期
+			RemainQuota:        500000, // 示例额度
+			UnlimitedQuota:     true,
+			ModelLimitsEnabled: false,
+		}
+		if err := token.Insert(); err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "创建默认令牌失败",
+			})
+			return
+		}
+	}
+
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
@@ -276,7 +322,18 @@ func GenerateAccessToken(c *gin.Context) {
 		})
 		return
 	}
-	user.AccessToken = common.GetUUID()
+	// get rand int 28-32
+	randI := common.GetRandomInt(4)
+	key, err := common.GenerateRandomKey(29 + randI)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "生成失败",
+		})
+		common.SysError("failed to generate key: " + err.Error())
+		return
+	}
+	user.SetAccessToken(key)
 
 	if model.DB.Where("access_token = ?", user.AccessToken).First(user).RowsAffected != 0 {
 		c.JSON(http.StatusOK, gin.H{
@@ -582,6 +639,7 @@ func DeleteSelf(c *gin.Context) {
 func CreateUser(c *gin.Context) {
 	var user model.User
 	err := json.NewDecoder(c.Request.Body).Decode(&user)
+	user.Username = strings.TrimSpace(user.Username)
 	if err != nil || user.Username == "" || user.Password == "" {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -629,8 +687,8 @@ func CreateUser(c *gin.Context) {
 }
 
 type ManageRequest struct {
-	Username string `json:"username"`
-	Action   string `json:"action"`
+	Id     int    `json:"id"`
+	Action string `json:"action"`
 }
 
 // ManageUser Only admin user can do this
@@ -646,7 +704,7 @@ func ManageUser(c *gin.Context) {
 		return
 	}
 	user := model.User{
-		Username: req.Username,
+		Id: req.Id,
 	}
 	// Fill attributes
 	model.DB.Unscoped().Where(&user).First(&user)
@@ -791,11 +849,11 @@ type topUpRequest struct {
 	Key string `json:"key"`
 }
 
-var lock = sync.Mutex{}
+var topUpLock = sync.Mutex{}
 
 func TopUp(c *gin.Context) {
-	lock.Lock()
-	defer lock.Unlock()
+	topUpLock.Lock()
+	defer topUpLock.Unlock()
 	req := topUpRequest{}
 	err := c.ShouldBindJSON(&req)
 	if err != nil {

controller/wechat.go

@@ -78,6 +78,13 @@ func WeChatAuth(c *gin.Context) {
 			})
 			return
 		}
+		if user.Id == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "用户已注销",
+			})
+			return
+		}
 	} else {
 		if common.RegisterEnabled {
 			user.Username = "wechat_" + strconv.Itoa(model.GetMaxUserId()+1)

dto/midjourney.go

@@ -33,6 +33,12 @@ type MidjourneyResponse struct {
 	Result      string      `json:"result"`
 }
 
+type MidjourneyUploadResponse struct {
+	Code        int      `json:"code"`
+	Description string   `json:"description"`
+	Result      []string `json:"result"`
+}
+
 type MidjourneyResponseWithStatusCode struct {
 	StatusCode int `json:"statusCode"`
 	Response   MidjourneyResponse

dto/openai_request.go

@@ -7,31 +7,35 @@ type ResponseFormat struct {
 }
 
 type GeneralOpenAIRequest struct {
-	Model            string          `json:"model,omitempty"`
-	Messages         []Message       `json:"messages,omitempty"`
-	Prompt           any             `json:"prompt,omitempty"`
-	Stream           bool            `json:"stream,omitempty"`
-	StreamOptions    *StreamOptions  `json:"stream_options,omitempty"`
-	MaxTokens        uint            `json:"max_tokens,omitempty"`
-	Temperature      float64         `json:"temperature,omitempty"`
-	TopP             float64         `json:"top_p,omitempty"`
-	TopK             int             `json:"top_k,omitempty"`
-	Stop             any             `json:"stop,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            []ToolCall      `json:"tools,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
-	User             string          `json:"user,omitempty"`
-	LogProbs         bool            `json:"logprobs,omitempty"`
-	TopLogProbs      int             `json:"top_logprobs,omitempty"`
-	Dimensions       int             `json:"dimensions,omitempty"`
+	Model               string         `json:"model,omitempty"`
+	Messages            []Message      `json:"messages,omitempty"`
+	Prompt              any            `json:"prompt,omitempty"`
+	Stream              bool           `json:"stream,omitempty"`
+	StreamOptions       *StreamOptions `json:"stream_options,omitempty"`
+	MaxTokens           uint           `json:"max_tokens,omitempty"`
+	MaxCompletionTokens uint           `json:"max_completion_tokens,omitempty"`
+	Temperature         float64        `json:"temperature,omitempty"`
+	TopP                float64        `json:"top_p,omitempty"`
+	TopK                int            `json:"top_k,omitempty"`
+	Stop                any            `json:"stop,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      any            `json:"response_format,omitempty"`
+	EncodingFormat      any            `json:"encoding_format,omitempty"`
+	Seed                float64        `json:"seed,omitempty"`
+	Tools               []ToolCall     `json:"tools,omitempty"`
+	ToolChoice          any            `json:"tool_choice,omitempty"`
+	User                string         `json:"user,omitempty"`
+	LogProbs            bool           `json:"logprobs,omitempty"`
+	TopLogProbs         int            `json:"top_logprobs,omitempty"`
+	Dimensions          int            `json:"dimensions,omitempty"`
+	Modalities          any            `json:"modalities,omitempty"`
+	Audio               any            `json:"audio,omitempty"`
 }
 
 type OpenAITools struct {
@@ -81,9 +85,10 @@ type Message struct {
 }
 
 type MediaMessage struct {
-	Type     string `json:"type"`
-	Text     string `json:"text"`
-	ImageUrl any    `json:"image_url,omitempty"`
+	Type       string `json:"type"`
+	Text       string `json:"text"`
+	ImageUrl   any    `json:"image_url,omitempty"`
+	InputAudio any    `json:"input_audio,omitempty"`
 }
 
 type MessageImageUrl struct {
@@ -91,9 +96,15 @@ type MessageImageUrl struct {
 	Detail string `json:"detail"`
 }
 
+type MessageInputAudio struct {
+	Data   string `json:"data"` //base64
+	Format string `json:"format"`
+}
+
 const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeText       = "text"
+	ContentTypeImageURL   = "image_url"
+	ContentTypeInputAudio = "input_audio"
 )
 
 func (m Message) StringContent() string {
@@ -166,11 +177,19 @@ func (m Message) ParseContent() []MediaMessage {
 						},
 					})
 				}
-
+			case ContentTypeInputAudio:
+				if subObj, ok := contentMap["input_audio"].(map[string]any); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeInputAudio,
+						InputAudio: MessageInputAudio{
+							Data:   subObj["data"].(string),
+							Format: subObj["format"].(string),
+						},
+					})
+				}
 			}
 		}
 		return contentList
 	}
-
 	return nil
 }

dto/openai_response.go

@@ -34,6 +34,7 @@ type OpenAITextResponseChoice struct {
 
 type OpenAITextResponse struct {
 	Id      string                     `json:"id"`
+	Model   string                     `json:"model"`
 	Object  string                     `json:"object"`
 	Created int64                      `json:"created"`
 	Choices []OpenAITextResponseChoice `json:"choices"`

dto/playground.go

@@ -0,0 +1,6 @@
+package dto
+
+type PlayGroundRequest struct {
+	Model string `json:"model,omitempty"`
+	Group string `json:"group,omitempty"`
+}

dto/realtime.go

@@ -0,0 +1,97 @@
+package dto
+
+const (
+	RealtimeEventTypeError              = "error"
+	RealtimeEventTypeSessionUpdate      = "session.update"
+	RealtimeEventTypeConversationCreate = "conversation.item.create"
+	RealtimeEventTypeResponseCreate     = "response.create"
+	RealtimeEventInputAudioBufferAppend = "input_audio_buffer.append"
+)
+
+const (
+	RealtimeEventTypeResponseDone                   = "response.done"
+	RealtimeEventTypeSessionUpdated                 = "session.updated"
+	RealtimeEventTypeSessionCreated                 = "session.created"
+	RealtimeEventResponseAudioDelta                 = "response.audio.delta"
+	RealtimeEventResponseAudioTranscriptionDelta    = "response.audio_transcript.delta"
+	RealtimeEventResponseFunctionCallArgumentsDelta = "response.function_call_arguments.delta"
+	RealtimeEventResponseFunctionCallArgumentsDone  = "response.function_call_arguments.done"
+	RealtimeEventConversationItemCreated            = "conversation.item.created"
+)
+
+type RealtimeEvent struct {
+	EventId string `json:"event_id"`
+	Type    string `json:"type"`
+	//PreviousItemId string `json:"previous_item_id"`
+	Session  *RealtimeSession  `json:"session,omitempty"`
+	Item     *RealtimeItem     `json:"item,omitempty"`
+	Error    *OpenAIError      `json:"error,omitempty"`
+	Response *RealtimeResponse `json:"response,omitempty"`
+	Delta    string            `json:"delta,omitempty"`
+	Audio    string            `json:"audio,omitempty"`
+}
+
+type RealtimeResponse struct {
+	Usage *RealtimeUsage `json:"usage"`
+}
+
+type RealtimeUsage struct {
+	TotalTokens        int                `json:"total_tokens"`
+	InputTokens        int                `json:"input_tokens"`
+	OutputTokens       int                `json:"output_tokens"`
+	InputTokenDetails  InputTokenDetails  `json:"input_token_details"`
+	OutputTokenDetails OutputTokenDetails `json:"output_token_details"`
+}
+
+type InputTokenDetails struct {
+	CachedTokens int `json:"cached_tokens"`
+	TextTokens   int `json:"text_tokens"`
+	AudioTokens  int `json:"audio_tokens"`
+}
+
+type OutputTokenDetails struct {
+	TextTokens  int `json:"text_tokens"`
+	AudioTokens int `json:"audio_tokens"`
+}
+
+type RealtimeSession struct {
+	Modalities              []string                `json:"modalities"`
+	Instructions            string                  `json:"instructions"`
+	Voice                   string                  `json:"voice"`
+	InputAudioFormat        string                  `json:"input_audio_format"`
+	OutputAudioFormat       string                  `json:"output_audio_format"`
+	InputAudioTranscription InputAudioTranscription `json:"input_audio_transcription"`
+	TurnDetection           interface{}             `json:"turn_detection"`
+	Tools                   []RealTimeTool          `json:"tools"`
+	ToolChoice              string                  `json:"tool_choice"`
+	Temperature             float64                 `json:"temperature"`
+	//MaxResponseOutputTokens int                     `json:"max_response_output_tokens"`
+}
+
+type InputAudioTranscription struct {
+	Model string `json:"model"`
+}
+
+type RealTimeTool struct {
+	Type        string `json:"type"`
+	Name        string `json:"name"`
+	Description string `json:"description"`
+	Parameters  any    `json:"parameters"`
+}
+
+type RealtimeItem struct {
+	Id        string            `json:"id"`
+	Type      string            `json:"type"`
+	Status    string            `json:"status"`
+	Role      string            `json:"role"`
+	Content   []RealtimeContent `json:"content"`
+	Name      *string           `json:"name,omitempty"`
+	ToolCalls any               `json:"tool_calls,omitempty"`
+	CallId    string            `json:"call_id,omitempty"`
+}
+type RealtimeContent struct {
+	Type       string `json:"type"`
+	Text       string `json:"text,omitempty"`
+	Audio      string `json:"audio,omitempty"` // Base64-encoded audio bytes.
+	Transcript string `json:"transcript,omitempty"`
+}

dto/rerank.go

@@ -1,14 +1,17 @@
 package dto
 
 type RerankRequest struct {
-	Documents []any  `json:"documents"`
-	Query     string `json:"query"`
-	Model     string `json:"model"`
-	TopN      int    `json:"top_n"`
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents,omitempty"`
+	MaxChunkPerDoc  int    `json:"max_chunk_per_doc,omitempty"`
+	OverLapTokens   int    `json:"overlap_tokens,omitempty"`
 }
 
 type RerankResponseDocument struct {
-	Document       any     `json:"document"`
+	Document       any     `json:"document,omitempty"`
 	Index          int     `json:"index"`
 	RelevanceScore float64 `json:"relevance_score"`
 }

go.mod

@@ -1,7 +1,9 @@
 module one-api
 
 // +heroku goVersion go1.18
-go 1.18
+go 1.21
+
+toolchain go1.22.4
 
 require (
 	github.com/Calcium-Ion/go-epay v0.0.2
@@ -9,6 +11,7 @@ require (
 	github.com/aws/aws-sdk-go-v2 v1.26.1
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
+	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
 	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -24,7 +27,7 @@ require (
 	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
-	golang.org/x/crypto v0.21.0
+	golang.org/x/crypto v0.26.0
 	golang.org/x/image v0.15.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
@@ -38,9 +41,8 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
-	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
-	github.com/cespare/xxhash/v2 v2.1.2 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
@@ -51,6 +53,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
 	github.com/gorilla/securecookie v1.1.1 // indirect
 	github.com/gorilla/sessions v1.2.1 // indirect
@@ -69,6 +72,7 @@ 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/stretchr/testify v1.9.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
@@ -76,10 +80,10 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.3.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/net v0.21.0 // indirect
-	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	google.golang.org/protobuf v1.30.0 // indirect
+	golang.org/x/net v0.28.0 // indirect
+	golang.org/x/sync v0.8.0 // indirect
+	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/text v0.17.0 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -23,8 +23,8 @@ github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaU
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
 github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
 github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
-github.com/cespare/xxhash/v2 v2.1.2 h1:YRXhKfTDauu4ajMg1TPgFO5jnlC2HCbmLXMcTG5cbYE=
-github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
@@ -37,6 +37,7 @@ github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cu
 github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
 github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
+github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
 github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
@@ -57,6 +58,7 @@ github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
 github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
+github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
 github.com/go-playground/locales v0.14.0/go.mod h1:sawfccIbzZTqEDETgFXqTho0QybSa7l++s0DH+LDiLs=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
@@ -81,7 +83,8 @@ github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzq
 github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -142,8 +145,11 @@ github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lN
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
+github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
+github.com/onsi/gomega v1.18.1/go.mod h1:0q+aL8jAiMXy9hbwj2mr5GziHiwhAIQpFmmtT5hitRs=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
@@ -172,7 +178,8 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
 github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
 github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
@@ -191,18 +198,18 @@ 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 v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
-golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
+golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
 golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
 golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
-golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
+golang.org/x/net v0.28.0 h1:a9JDOJc5GMUJ0+UDqmLT86WiEy7iWyIhz8gz8E4e5hE=
+golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 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=
@@ -214,26 +221,27 @@ golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
-golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
+golang.org/x/sys v0.24.0/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 v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
-google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
+gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=

main.go

@@ -42,6 +42,11 @@ func main() {
 	if err != nil {
 		common.FatalLog("failed to initialize database: " + err.Error())
 	}
+	// Initialize SQL Database
+	err = model.InitLogDB()
+	if err != nil {
+		common.FatalLog("failed to initialize database: " + err.Error())
+	}
 	defer func() {
 		err := model.CloseDB()
 		if err != nil {
@@ -55,6 +60,8 @@ func main() {
 		common.FatalLog("failed to initialize Redis: " + err.Error())
 	}
 
+	// Initialize constants
+	constant.InitEnv()
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {

middleware/auth.go

@@ -6,15 +6,28 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strconv"
 	"strings"
 )
 
+func validUserInfo(username string, role int) bool {
+	// check username is empty
+	if strings.TrimSpace(username) == "" {
+		return false
+	}
+	if !common.IsValidateRole(role) {
+		return false
+	}
+	return true
+}
+
 func authHelper(c *gin.Context, minRole int) {
 	session := sessions.Default(c)
 	username := session.Get("username")
 	role := session.Get("role")
 	id := session.Get("id")
 	status := session.Get("status")
+	useAccessToken := false
 	if username == nil {
 		// Check access token
 		accessToken := c.Request.Header.Get("Authorization")
@@ -28,11 +41,20 @@ func authHelper(c *gin.Context, minRole int) {
 		}
 		user := model.ValidateAccessToken(accessToken)
 		if user != nil && user.Username != "" {
+			if !validUserInfo(user.Username, user.Role) {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": "无权进行此操作，用户信息无效",
+				})
+				c.Abort()
+				return
+			}
 			// Token is valid
 			username = user.Username
 			role = user.Role
 			id = user.Id
 			status = user.Status
+			useAccessToken = true
 		} else {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -42,6 +64,36 @@ func authHelper(c *gin.Context, minRole int) {
 			return
 		}
 	}
+	if !useAccessToken {
+		// get header New-Api-User
+		apiUserIdStr := c.Request.Header.Get("New-Api-User")
+		if apiUserIdStr == "" {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，请刷新页面或清空缓存后重试",
+			})
+			c.Abort()
+			return
+		}
+		apiUserId, err := strconv.Atoi(apiUserIdStr)
+		if err != nil {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，登录信息无效，请重新登录",
+			})
+			c.Abort()
+			return
+
+		}
+		if id != apiUserId {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，与登录用户不匹配，请重新登录",
+			})
+			c.Abort()
+			return
+		}
+	}
 	if status.(int) == common.UserStatusDisabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -58,9 +110,19 @@ func authHelper(c *gin.Context, minRole int) {
 		c.Abort()
 		return
 	}
+	if !validUserInfo(username.(string), role.(int)) {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "无权进行此操作，用户信息无效",
+		})
+		c.Abort()
+		return
+	}
 	c.Set("username", username)
 	c.Set("role", role)
 	c.Set("id", id)
+	c.Set("group", session.Get("group"))
+	c.Set("use_access_token", useAccessToken)
 	c.Next()
 }
 
@@ -93,8 +155,27 @@ func RootAuth() func(c *gin.Context) {
 	}
 }
 
+func WssAuth(c *gin.Context) {
+
+}
+
 func TokenAuth() func(c *gin.Context) {
 	return func(c *gin.Context) {
+		// 先检测是否为ws
+		if c.Request.Header.Get("Sec-WebSocket-Protocol") != "" {
+			// Sec-WebSocket-Protocol: realtime, openai-insecure-api-key.sk-xxx, openai-beta.realtime-v1
+			// read sk from Sec-WebSocket-Protocol
+			key := c.Request.Header.Get("Sec-WebSocket-Protocol")
+			parts := strings.Split(key, ",")
+			for _, part := range parts {
+				part = strings.TrimSpace(part)
+				if strings.HasPrefix(part, "openai-insecure-api-key") {
+					key = strings.TrimPrefix(part, "openai-insecure-api-key.")
+					break
+				}
+			}
+			c.Request.Header.Set("Authorization", "Bearer "+key)
+		}
 		key := c.Request.Header.Get("Authorization")
 		parts := make([]string, 0)
 		key = strings.TrimPrefix(key, "Bearer ")
@@ -110,6 +191,12 @@ func TokenAuth() func(c *gin.Context) {
 			key = parts[0]
 		}
 		token, err := model.ValidateUserToken(key)
+		if token != nil {
+			id := c.GetInt("id")
+			if id == 0 {
+				c.Set("id", token.UserId)
+			}
+		}
 		if err != nil {
 			abortWithOpenAiMessage(c, http.StatusUnauthorized, err.Error())
 			return
@@ -136,6 +223,8 @@ func TokenAuth() func(c *gin.Context) {
 		} else {
 			c.Set("token_model_limit_enabled", false)
 		}
+		c.Set("allow_ips", token.GetIpLimitsMap())
+		c.Set("token_group", token.Group)
 		if len(parts) > 1 {
 			if model.IsAdmin(token.UserId) {
 				c.Set("specific_channel_id", parts[1])

middleware/distributor.go

@@ -22,6 +22,14 @@ type ModelRequest struct {
 
 func Distribute() func(c *gin.Context) {
 	return func(c *gin.Context) {
+		allowIpsMap := c.GetStringMap("allow_ips")
+		if len(allowIpsMap) != 0 {
+			clientIp := c.ClientIP()
+			if _, ok := allowIpsMap[clientIp]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, "您的 IP 不在令牌允许访问的列表中")
+				return
+			}
+		}
 		userId := c.GetInt("id")
 		var channel *model.Channel
 		channelId, ok := c.Get("specific_channel_id")
@@ -31,6 +39,20 @@ func Distribute() func(c *gin.Context) {
 			return
 		}
 		userGroup, _ := model.CacheGetUserGroup(userId)
+		tokenGroup := c.GetString("token_group")
+		if tokenGroup != "" {
+			// check common.UserUsableGroups[userGroup]
+			if _, ok := common.GetUserUsableGroups(userGroup)[tokenGroup]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, fmt.Sprintf("令牌分组 %s 已被禁用", tokenGroup))
+				return
+			}
+			// check group in common.GroupRatio
+			if _, ok := common.GroupRatio[tokenGroup]; !ok {
+				abortWithOpenAiMessage(c, http.StatusForbidden, fmt.Sprintf("分组 %s 已被弃用", tokenGroup))
+				return
+			}
+			userGroup = tokenGroup
+		}
 		c.Set("group", userGroup)
 		if ok {
 			id, err := strconv.Atoi(channelId.(string))
@@ -148,6 +170,10 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
 		return nil, false, errors.New("无效的请求, " + err.Error())
 	}
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/realtime") {
+		//wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01
+		modelRequest.Model = c.Query("model")
+	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
 		if modelRequest.Model == "" {
 			modelRequest.Model = "text-moderation-stable"
@@ -184,19 +210,13 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	if channel == nil {
 		return
 	}
-	c.Set("channel", channel.Type)
 	c.Set("channel_id", channel.Id)
 	c.Set("channel_name", channel.Name)
 	c.Set("channel_type", channel.Type)
-	ban := true
-	// parse *int to bool
-	if channel.AutoBan != nil && *channel.AutoBan == 0 {
-		ban = false
-	}
 	if nil != channel.OpenAIOrganization && "" != *channel.OpenAIOrganization {
 		c.Set("channel_organization", *channel.OpenAIOrganization)
 	}
-	c.Set("auto_ban", ban)
+	c.Set("auto_ban", channel.GetAutoBan())
 	c.Set("model_mapping", channel.GetModelMapping())
 	c.Set("status_code_mapping", channel.GetStatusCodeMapping())
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
@@ -205,6 +225,8 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	switch channel.Type {
 	case common.ChannelTypeAzure:
 		c.Set("api_version", channel.Other)
+	case common.ChannelTypeVertexAi:
+		c.Set("region", channel.Other)
 	case common.ChannelTypeXunfei:
 		c.Set("api_version", channel.Other)
 	case common.ChannelTypeGemini:

middleware/utils.go

@@ -1,11 +1,13 @@
 package middleware
 
 import (
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"one-api/common"
 )
 
 func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
+	userId := c.GetInt("id")
 	c.JSON(statusCode, gin.H{
 		"error": gin.H{
 			"message": common.MessageWithRequestId(message, c.GetString(common.RequestIdKey)),
@@ -13,7 +15,7 @@ func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
 		},
 	})
 	c.Abort()
-	common.LogError(c.Request.Context(), message)
+	common.LogError(c.Request.Context(), fmt.Sprintf("user %d | %s", userId, message))
 }
 
 func abortWithMidjourneyMessage(c *gin.Context, statusCode int, code int, description string) {

model/ability.go

@@ -36,6 +36,12 @@ func GetEnabledModels() []string {
 	return models
 }
 
+func GetAllEnableAbilities() []Ability {
+	var abilities []Ability
+	DB.Find(&abilities, "enabled = ?", true)
+	return abilities
+}
+
 func getPriority(group string, model string, retry int) (int, error) {
 	groupCol := "`group`"
 	trueVal := "1"

model/cache.go

@@ -270,6 +270,9 @@ func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Cha
 	if strings.HasPrefix(model, "gpt-4-gizmo") {
 		model = "gpt-4-gizmo-*"
 	}
+	if strings.HasPrefix(model, "gpt-4o-gizmo") {
+		model = "gpt-4o-gizmo-*"
+	}
 
 	// if memory cache is disabled, get channel directly from database
 	if !common.MemoryCacheEnabled {

model/channel.go

@@ -61,6 +61,13 @@ func (channel *Channel) SetOtherInfo(otherInfo map[string]interface{}) {
 	channel.OtherInfo = string(otherInfoBytes)
 }
 
+func (channel *Channel) GetAutoBan() bool {
+	if channel.AutoBan == nil {
+		return false
+	}
+	return *channel.AutoBan == 1
+}
+
 func (channel *Channel) Save() error {
 	return DB.Save(channel).Error
 }
@@ -99,16 +106,23 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	// 构造WHERE子句
 	var whereClause string
 	var args []interface{}
-	if group != "" {
-		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " LIKE ? AND " + modelsCol + " LIKE ?"
-		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+group+"%", "%"+model+"%")
+	if group != "" && group != "null" {
+		var groupCondition string
+		if common.UsingMySQL {
+			groupCondition = `CONCAT(',', ` + groupCol + `, ',') LIKE ?`
+		} else {
+			// sqlite, PostgreSQL
+			groupCondition = `(',' || ` + groupCol + ` || ',') LIKE ?`
+		}
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + ` LIKE ? AND ` + groupCondition
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%", "%,"+group+",%")
 	} else {
 		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
 		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")
 	}
 
 	// 执行查询
-	err := baseQuery.Where(whereClause, args...).Find(&channels).Error
+	err := baseQuery.Where(whereClause, args...).Order("priority desc").Find(&channels).Error
 	if err != nil {
 		return nil, err
 	}

model/log.go

@@ -3,10 +3,12 @@ package model
 import (
 	"context"
 	"fmt"
-	"github.com/bytedance/gopkg/util/gopool"
-	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+	"time"
+
+	"github.com/bytedance/gopkg/util/gopool"
+	"gorm.io/gorm"
 )
 
 type Log struct {
@@ -37,7 +39,7 @@ const (
 )
 
 func GetLogByKey(key string) (logs []*Log, err error) {
-	err = DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
+	err = LOG_DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
 	return logs, err
 }
 
@@ -53,7 +55,7 @@ func RecordLog(userId int, logType int, content string) {
 		Type:      logType,
 		Content:   content,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.SysError("failed to record log: " + err.Error())
 	}
@@ -83,7 +85,7 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		IsStream:         isStream,
 		Other:            otherStr,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.LogError(ctx, "failed to record log: "+err.Error())
 	}
@@ -94,15 +96,15 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 	}
 }
 
-func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel 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, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB
+		tx = LOG_DB
 	} else {
-		tx = DB.Where("type = ?", logType)
+		tx = LOG_DB.Where("type = ?", logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if username != "" {
 		tx = tx.Where("username = ?", username)
@@ -119,19 +121,26 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
 	}
+	err = tx.Model(&Log{}).Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
-	return logs, err
+	if err != nil {
+		return nil, 0, err
+	}
+	return logs, total, err
 }
 
-func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int) (logs []*Log, err error) {
+func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB.Where("user_id = ?", userId)
+		tx = LOG_DB.Where("user_id = ?", userId)
 	} else {
-		tx = DB.Where("user_id = ? and type = ?", userId, logType)
+		tx = LOG_DB.Where("user_id = ? and type = ?", userId, logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
@@ -142,6 +151,10 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 	if endTimestamp != 0 {
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
+	err = tx.Model(&Log{}).Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
 	for i := range logs {
 		var otherMap map[string]interface{}
@@ -152,16 +165,16 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		}
 		logs[i].Other = common.MapToJsonStr(otherMap)
 	}
-	return logs, err
+	return logs, total, err
 }
 
 func SearchAllLogs(keyword string) (logs []*Log, err error) {
-	err = DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
+	err = LOG_DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
 	return logs, err
 }
 
 func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
-	err = DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
+	err = LOG_DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
 	return logs, err
 }
 
@@ -172,12 +185,18 @@ type Stat struct {
 }
 
 func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (stat Stat) {
-	tx := DB.Table("logs").Select("sum(quota) quota, count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+	tx := LOG_DB.Table("logs").Select("sum(quota) quota")
+
+	// 为rpm和tpm创建单独的查询
+	rpmTpmQuery := LOG_DB.Table("logs").Select("count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+
 	if username != "" {
 		tx = tx.Where("username = ?", username)
+		rpmTpmQuery = rpmTpmQuery.Where("username = ?", username)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
+		rpmTpmQuery = rpmTpmQuery.Where("token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
 		tx = tx.Where("created_at >= ?", startTimestamp)
@@ -186,17 +205,29 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
+		rpmTpmQuery = rpmTpmQuery.Where("model_name like ?", modelName)
 	}
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
+		rpmTpmQuery = rpmTpmQuery.Where("channel_id = ?", channel)
 	}
-	tx.Where("type = ?", LogTypeConsume).Scan(&stat)
+
+	tx = tx.Where("type = ?", LogTypeConsume)
+	rpmTpmQuery = rpmTpmQuery.Where("type = ?", LogTypeConsume)
+
+	// 只统计最近60秒的rpm和tpm
+	rpmTpmQuery = rpmTpmQuery.Where("created_at >= ?", time.Now().Add(-60*time.Second).Unix())
+
+	// 执行查询
+	tx.Scan(&stat)
+	rpmTpmQuery.Scan(&stat)
+
 	return stat
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
+	tx := LOG_DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -217,6 +248,6 @@ func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelNa
 }
 
 func DeleteOldLog(targetTimestamp int64) (int64, error) {
-	result := DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
+	result := LOG_DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
 	return result.RowsAffected, result.Error
 }

model/main.go

@@ -15,6 +15,8 @@ import (
 
 var DB *gorm.DB
 
+var LOG_DB *gorm.DB
+
 func createRootAccountIfNeed() error {
 	var user User
 	//if user.Status != common.UserStatusEnabled {
@@ -30,7 +32,7 @@ func createRootAccountIfNeed() error {
 			Role:        common.RoleRootUser,
 			Status:      common.UserStatusEnabled,
 			DisplayName: "Root User",
-			AccessToken: common.GetUUID(),
+			AccessToken: nil,
 			Quota:       100000000,
 		}
 		DB.Create(&rootUser)
@@ -38,9 +40,9 @@ func createRootAccountIfNeed() error {
 	return nil
 }
 
-func chooseDB() (*gorm.DB, error) {
-	if os.Getenv("SQL_DSN") != "" {
-		dsn := os.Getenv("SQL_DSN")
+func chooseDB(envName string) (*gorm.DB, error) {
+	dsn := os.Getenv(envName)
+	if dsn != "" {
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
 			common.SysLog("using PostgreSQL as database")
@@ -52,6 +54,13 @@ func chooseDB() (*gorm.DB, error) {
 				PrepareStmt: true, // precompile SQL
 			})
 		}
+		if strings.HasPrefix(dsn, "local") {
+			common.SysLog("SQL_DSN not set, using SQLite as database")
+			common.UsingSQLite = true
+			return gorm.Open(sqlite.Open(common.SQLitePath), &gorm.Config{
+				PrepareStmt: true, // precompile SQL
+			})
+		}
 		// Use MySQL
 		common.SysLog("using MySQL as database")
 		// check parseTime
@@ -76,7 +85,7 @@ func chooseDB() (*gorm.DB, error) {
 }
 
 func InitDB() (err error) {
-	db, err := chooseDB()
+	db, err := chooseDB("SQL_DSN")
 	if err == nil {
 		if common.DebugEnabled {
 			db = db.Debug()
@@ -100,52 +109,7 @@ func InitDB() (err error) {
 		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
 		//}
 		common.SysLog("database migration started")
-		err = db.AutoMigrate(&Channel{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Token{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&User{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Option{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Redemption{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Ability{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Log{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Midjourney{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&TopUp{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&QuotaData{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Task{})
-		if err != nil {
-			return err
-		}
-		common.SysLog("database migrated")
-		err = createRootAccountIfNeed()
+		err = migrateDB()
 		return err
 	} else {
 		common.FatalLog(err)
@@ -153,8 +117,103 @@ func InitDB() (err error) {
 	return err
 }
 
-func CloseDB() error {
-	sqlDB, err := DB.DB()
+func InitLogDB() (err error) {
+	if os.Getenv("LOG_SQL_DSN") == "" {
+		LOG_DB = DB
+		return
+	}
+	db, err := chooseDB("LOG_SQL_DSN")
+	if err == nil {
+		if common.DebugEnabled {
+			db = db.Debug()
+		}
+		LOG_DB = db
+		sqlDB, err := LOG_DB.DB()
+		if err != nil {
+			return err
+		}
+		sqlDB.SetMaxIdleConns(common.GetEnvOrDefault("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(common.GetEnvOrDefault("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetEnvOrDefault("SQL_MAX_LIFETIME", 60)))
+
+		if !common.IsMasterNode {
+			return nil
+		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
+		common.SysLog("database migration started")
+		err = migrateLOGDB()
+		return err
+	} else {
+		common.FatalLog(err)
+	}
+	return err
+}
+
+func migrateDB() error {
+	err := DB.AutoMigrate(&Channel{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Token{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&User{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Option{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Redemption{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Ability{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Log{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Midjourney{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&TopUp{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&QuotaData{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Task{})
+	if err != nil {
+		return err
+	}
+	common.SysLog("database migrated")
+	err = createRootAccountIfNeed()
+	return err
+}
+
+func migrateLOGDB() error {
+	var err error
+	if err = LOG_DB.AutoMigrate(&Log{}); err != nil {
+		return err
+	}
+	return nil
+}
+
+func closeDB(db *gorm.DB) error {
+	sqlDB, err := db.DB()
 	if err != nil {
 		return err
 	}
@@ -162,6 +221,16 @@ func CloseDB() error {
 	return err
 }
 
+func CloseDB() error {
+	if LOG_DB != DB {
+		err := closeDB(LOG_DB)
+		if err != nil {
+			return err
+		}
+	}
+	return closeDB(DB)
+}
+
 var (
 	lastPingTime time.Time
 	pingMutex    sync.Mutex

model/option.go

@@ -69,6 +69,7 @@ func InitOptionMap() {
 	common.OptionMap["Price"] = strconv.FormatFloat(constant.Price, 'f', -1, 64)
 	common.OptionMap["MinTopUp"] = strconv.Itoa(constant.MinTopUp)
 	common.OptionMap["TopupGroupRatio"] = common.TopupGroupRatio2JSONString()
+	common.OptionMap["Chats"] = constant.Chats2JsonString()
 	common.OptionMap["GitHubClientId"] = ""
 	common.OptionMap["GitHubClientSecret"] = ""
 	common.OptionMap["TelegramBotToken"] = ""
@@ -86,6 +87,7 @@ func InitOptionMap() {
 	common.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
 	common.OptionMap["ModelPrice"] = common.ModelPrice2JSONString()
 	common.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
+	common.OptionMap["UserUsableGroups"] = common.UserUsableGroups2JSONString()
 	common.OptionMap["CompletionRatio"] = common.CompletionRatio2JSONString()
 	common.OptionMap["TopUpLink"] = common.TopUpLink
 	common.OptionMap["ChatLink"] = common.ChatLink
@@ -247,6 +249,8 @@ func updateOptionMap(key string, value string) (err error) {
 		constant.WorkerValidKey = value
 	case "PayAddress":
 		constant.PayAddress = value
+	case "Chats":
+		err = constant.UpdateChatsByJsonString(value)
 	case "CustomCallbackAddress":
 		constant.CustomCallbackAddress = value
 	case "EpayId":
@@ -303,6 +307,8 @@ func updateOptionMap(key string, value string) (err error) {
 		err = common.UpdateModelRatioByJSONString(value)
 	case "GroupRatio":
 		err = common.UpdateGroupRatioByJSONString(value)
+	case "UserUsableGroups":
+		err = common.UpdateUserUsableGroupsByJSONString(value)
 	case "CompletionRatio":
 		err = common.UpdateCompletionRatioByJSONString(value)
 	case "ModelPrice":

model/pricing.go

@@ -7,14 +7,13 @@ import (
 )
 
 type Pricing struct {
-	Available       bool     `json:"available"`
 	ModelName       string   `json:"model_name"`
 	QuotaType       int      `json:"quota_type"`
 	ModelRatio      float64  `json:"model_ratio"`
 	ModelPrice      float64  `json:"model_price"`
 	OwnerBy         string   `json:"owner_by"`
 	CompletionRatio float64  `json:"completion_ratio"`
-	EnableGroup     []string `json:"enable_group,omitempty"`
+	EnableGroup     []string `json:"enable_groups,omitempty"`
 }
 
 var (
@@ -23,40 +22,47 @@ var (
 	updatePricingLock  sync.Mutex
 )
 
-func GetPricing(group string) []Pricing {
+func GetPricing() []Pricing {
 	updatePricingLock.Lock()
 	defer updatePricingLock.Unlock()
 
 	if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
 		updatePricing()
 	}
-	if group != "" {
-		userPricingMap := make([]Pricing, 0)
-		models := GetGroupModels(group)
-		for _, pricing := range pricingMap {
-			if !common.StringsContains(models, pricing.ModelName) {
-				pricing.Available = false
-			}
-			userPricingMap = append(userPricingMap, pricing)
-		}
-		return userPricingMap
-	}
+	//if group != "" {
+	//	userPricingMap := make([]Pricing, 0)
+	//	models := GetGroupModels(group)
+	//	for _, pricing := range pricingMap {
+	//		if !common.StringsContains(models, pricing.ModelName) {
+	//			pricing.Available = false
+	//		}
+	//		userPricingMap = append(userPricingMap, pricing)
+	//	}
+	//	return userPricingMap
+	//}
 	return pricingMap
 }
 
 func updatePricing() {
 	//modelRatios := common.GetModelRatios()
-	enabledModels := GetEnabledModels()
-	allModels := make(map[string]int)
-	for i, model := range enabledModels {
-		allModels[model] = i
+	enableAbilities := GetAllEnableAbilities()
+	modelGroupsMap := make(map[string][]string)
+	for _, ability := range enableAbilities {
+		groups := modelGroupsMap[ability.Model]
+		if groups == nil {
+			groups = make([]string, 0)
+		}
+		if !common.StringsContains(groups, ability.Group) {
+			groups = append(groups, ability.Group)
+		}
+		modelGroupsMap[ability.Model] = groups
 	}
 
 	pricingMap = make([]Pricing, 0)
-	for model, _ := range allModels {
+	for model, groups := range modelGroupsMap {
 		pricing := Pricing{
-			Available: true,
-			ModelName: model,
+			ModelName:   model,
+			EnableGroup: groups,
 		}
 		modelPrice, findPrice := common.GetModelPrice(model, false)
 		if findPrice {

model/token.go

@@ -6,6 +6,7 @@ import (
 	"gorm.io/gorm"
 	"one-api/common"
 	"one-api/constant"
+	relaycommon "one-api/relay/common"
 	"strconv"
 	"strings"
 )
@@ -23,10 +24,34 @@ type Token struct {
 	UnlimitedQuota     bool           `json:"unlimited_quota" gorm:"default:false"`
 	ModelLimitsEnabled bool           `json:"model_limits_enabled" gorm:"default:false"`
 	ModelLimits        string         `json:"model_limits" gorm:"type:varchar(1024);default:''"`
+	AllowIps           *string        `json:"allow_ips" gorm:"default:''"`
 	UsedQuota          int            `json:"used_quota" gorm:"default:0"` // used quota
+	Group              string         `json:"group" gorm:"default:''"`
 	DeletedAt          gorm.DeletedAt `gorm:"index"`
 }
 
+func (token *Token) GetIpLimitsMap() map[string]any {
+	// delete empty spaces
+	//split with \n
+	ipLimitsMap := make(map[string]any)
+	if token.AllowIps == nil {
+		return ipLimitsMap
+	}
+	cleanIps := strings.ReplaceAll(*token.AllowIps, " ", "")
+	if cleanIps == "" {
+		return ipLimitsMap
+	}
+	ips := strings.Split(cleanIps, "\n")
+	for _, ip := range ips {
+		ip = strings.TrimSpace(ip)
+		ip = strings.ReplaceAll(ip, ",", "")
+		if common.IsIP(ip) {
+			ipLimitsMap[ip] = true
+		}
+	}
+	return ipLimitsMap
+}
+
 func GetAllUserTokens(userId int, startIdx int, num int) ([]*Token, error) {
 	var tokens []*Token
 	var err error
@@ -51,12 +76,12 @@ func ValidateUserToken(key string) (token *Token, err error) {
 		if token.Status == common.TokenStatusExhausted {
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
+			return token, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
 		} else if token.Status == common.TokenStatusExpired {
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if token.Status != common.TokenStatusEnabled {
-			return nil, errors.New("该令牌状态不可用")
+			return token, errors.New("该令牌状态不可用")
 		}
 		if token.ExpiredTime != -1 && token.ExpiredTime < common.GetTimestamp() {
 			if !common.RedisEnabled {
@@ -66,7 +91,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 					common.SysError("failed to update token status" + err.Error())
 				}
 			}
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if !token.UnlimitedQuota && token.RemainQuota <= 0 {
 			if !common.RedisEnabled {
@@ -79,7 +104,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 			}
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
+			return token, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
 		}
 		return token, nil
 	}
@@ -130,7 +155,8 @@ func (token *Token) Insert() error {
 // Update Make sure your token's fields is completed, because this will update non-zero values
 func (token *Token) Update() error {
 	var err error
-	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota", "model_limits_enabled", "model_limits").Updates(token).Error
+	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota",
+		"model_limits_enabled", "model_limits", "allow_ips", "group").Updates(token).Error
 	return err
 }
 
@@ -232,51 +258,56 @@ func decreaseTokenQuota(id int, quota int) (err error) {
 	return err
 }
 
-func PreConsumeTokenQuota(tokenId int, quota int) (userQuota int, err error) {
+func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) (userQuota int, err error) {
 	if quota < 0 {
 		return 0, errors.New("quota 不能为负数！")
 	}
-	token, err := GetTokenById(tokenId)
-	if err != nil {
-		return 0, err
+	if !relayInfo.IsPlayground {
+		token, err := GetTokenById(relayInfo.TokenId)
+		if err != nil {
+			return 0, err
+		}
+		if !token.UnlimitedQuota && token.RemainQuota < quota {
+			return 0, errors.New("令牌额度不足")
+		}
 	}
-	if !token.UnlimitedQuota && token.RemainQuota < quota {
-		return 0, errors.New("令牌额度不足")
-	}
-	userQuota, err = GetUserQuota(token.UserId)
+	userQuota, err = GetUserQuota(relayInfo.UserId)
 	if err != nil {
 		return 0, err
 	}
 	if userQuota < quota {
 		return 0, errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
-	err = DecreaseTokenQuota(tokenId, quota)
-	if err != nil {
-		return 0, err
+	if !relayInfo.IsPlayground {
+		err = DecreaseTokenQuota(relayInfo.TokenId, quota)
+		if err != nil {
+			return 0, err
+		}
 	}
-	err = DecreaseUserQuota(token.UserId, quota)
+	err = DecreaseUserQuota(relayInfo.UserId, quota)
 	return userQuota - quota, err
 }
 
-func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuota int, sendEmail bool) (err error) {
-	token, err := GetTokenById(tokenId)
+func PostConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, userQuota int, quota int, preConsumedQuota int, sendEmail bool) (err error) {
 
 	if quota > 0 {
-		err = DecreaseUserQuota(token.UserId, quota)
+		err = DecreaseUserQuota(relayInfo.UserId, quota)
 	} else {
-		err = IncreaseUserQuota(token.UserId, -quota)
+		err = IncreaseUserQuota(relayInfo.UserId, -quota)
 	}
 	if err != nil {
 		return err
 	}
 
-	if quota > 0 {
-		err = DecreaseTokenQuota(tokenId, quota)
-	} else {
-		err = IncreaseTokenQuota(tokenId, -quota)
-	}
-	if err != nil {
-		return err
+	if !relayInfo.IsPlayground {
+		if quota > 0 {
+			err = DecreaseTokenQuota(relayInfo.TokenId, quota)
+		} else {
+			err = IncreaseTokenQuota(relayInfo.TokenId, -quota)
+		}
+		if err != nil {
+			return err
+		}
 	}
 
 	if sendEmail {
@@ -285,7 +316,7 @@ func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuo
 			noMoreQuota := userQuota-(quota+preConsumedQuota) <= 0
 			if quotaTooLow || noMoreQuota {
 				go func() {
-					email, err := GetUserEmail(token.UserId)
+					email, err := GetUserEmail(relayInfo.UserId)
 					if err != nil {
 						common.SysError("failed to fetch user email: " + err.Error())
 					}

model/user.go

@@ -25,7 +25,7 @@ type User struct {
 	WeChatId         string         `json:"wechat_id" gorm:"column:wechat_id;index"`
 	TelegramId       string         `json:"telegram_id" gorm:"column:telegram_id;index"`
 	VerificationCode string         `json:"verification_code" gorm:"-:all"`                                    // this field is only for Email verification, don't save it to database!
-	AccessToken      string         `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
+	AccessToken      *string        `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
 	Quota            int            `json:"quota" gorm:"type:int;default:0"`
 	UsedQuota        int            `json:"used_quota" gorm:"type:int;default:0;column:used_quota"` // used quota
 	RequestCount     int            `json:"request_count" gorm:"type:int;default:0;"`               // request number
@@ -38,6 +38,17 @@ type User struct {
 	DeletedAt        gorm.DeletedAt `gorm:"index"`
 }
 
+func (user *User) GetAccessToken() string {
+	if user.AccessToken == nil {
+		return ""
+	}
+	return *user.AccessToken
+}
+
+func (user *User) SetAccessToken(token string) {
+	user.AccessToken = &token
+}
+
 // CheckUserExistOrDeleted check if user exist or deleted, if not exist, return false, nil, if deleted or exist, return true, nil
 func CheckUserExistOrDeleted(username string, email string) (bool, error) {
 	var user User
@@ -201,7 +212,7 @@ func (user *User) Insert(inviterId int) error {
 		}
 	}
 	user.Quota = common.QuotaForNewUser
-	user.AccessToken = common.GetUUID()
+	//user.SetAccessToken(common.GetUUID())
 	user.AffCode = common.GetRandomString(4)
 	result := DB.Create(user)
 	if result.Error != nil {
@@ -295,11 +306,12 @@ func (user *User) ValidateAndFill() (err error) {
 	// that means if your field’s value is 0, '', false or other zero values,
 	// it won’t be used to build query conditions
 	password := user.Password
-	if user.Username == "" || password == "" {
+	username := strings.TrimSpace(user.Username)
+	if username == "" || password == "" {
 		return errors.New("用户名或密码为空")
 	}
 	// find buy username or email
-	DB.Where("username = ? OR email = ?", user.Username, user.Username).First(user)
+	DB.Where("username = ? OR email = ?", username, username).First(user)
 	okay := common.ValidatePasswordAndHash(password, user.Password)
 	if !okay || user.Status != common.UserStatusEnabled {
 		return errors.New("用户名或密码错误，或用户已被封禁")
@@ -339,14 +351,6 @@ func (user *User) FillUserByWeChatId() error {
 	return nil
 }
 
-func (user *User) FillUserByUsername() error {
-	if user.Username == "" {
-		return errors.New("username 为空！")
-	}
-	DB.Where(User{Username: user.Username}).First(user)
-	return nil
-}
-
 func (user *User) FillUserByTelegramId() error {
 	if user.TelegramId == "" {
 		return errors.New("Telegram id 为空！")
@@ -359,23 +363,19 @@ func (user *User) FillUserByTelegramId() error {
 }
 
 func IsEmailAlreadyTaken(email string) bool {
-	return DB.Where("email = ?", email).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("email = ?", email).Find(&User{}).RowsAffected == 1
 }
 
 func IsWeChatIdAlreadyTaken(wechatId string) bool {
-	return DB.Where("wechat_id = ?", wechatId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("wechat_id = ?", wechatId).Find(&User{}).RowsAffected == 1
 }
 
 func IsGitHubIdAlreadyTaken(githubId string) bool {
-	return DB.Where("github_id = ?", githubId).Find(&User{}).RowsAffected == 1
-}
-
-func IsUsernameAlreadyTaken(username string) bool {
-	return DB.Where("username = ?", username).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("github_id = ?", githubId).Find(&User{}).RowsAffected == 1
 }
 
 func IsTelegramIdAlreadyTaken(telegramId string) bool {
-	return DB.Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
+	return DB.Unscoped().Where("telegram_id = ?", telegramId).Find(&User{}).RowsAffected == 1
 }
 
 func ResetUserPasswordByEmail(email string, password string) error {

relay/channel/adapter.go

@@ -12,13 +12,13 @@ type Adaptor interface {
 	// Init IsStream bool
 	Init(info *relaycommon.RelayInfo)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
-	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
+	SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
 	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
 	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
 	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
-	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
-	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode)
+	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string
 	GetChannelName() string
 }

relay/channel/ali/adaptor.go

@@ -32,14 +32,14 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fullRequestURL, nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	if info.IsStream {
-		req.Header.Set("X-DashScope-SSE", "enable")
+		req.Set("X-DashScope-SSE", "enable")
 	}
 	if c.GetString("plugin") != "" {
-		req.Header.Set("X-DashScope-Plugin", c.GetString("plugin"))
+		req.Set("X-DashScope-Plugin", c.GetString("plugin"))
 	}
 	return nil
 }
@@ -72,11 +72,11 @@ func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInf
 	return nil, errors.New("not implemented")
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeImagesGenerations:
 		err, usage = aliImageHandler(c, resp, info)

relay/channel/api_request.go

@@ -4,6 +4,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"net/http"
 	"one-api/relay/common"
@@ -11,14 +12,16 @@ import (
 	"one-api/service"
 )
 
-func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Request) {
+func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Header) {
 	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
 		// multipart/form-data
+	} else if info.RelayMode == constant.RelayModeRealtime {
+		// websocket
 	} else {
-		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		req.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+		req.Set("Accept", c.Request.Header.Get("Accept"))
 		if info.IsStream && c.Request.Header.Get("Accept") == "" {
-			req.Header.Set("Accept", "text/event-stream")
+			req.Set("Accept", "text/event-stream")
 		}
 	}
 }
@@ -32,7 +35,7 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	if err != nil {
 		return nil, fmt.Errorf("new request failed: %w", err)
 	}
-	err = a.SetupRequestHeader(c, req, info)
+	err = a.SetupRequestHeader(c, &req.Header, info)
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
@@ -55,7 +58,7 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	// set form data
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 
-	err = a.SetupRequestHeader(c, req, info)
+	err = a.SetupRequestHeader(c, &req.Header, info)
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
@@ -66,6 +69,27 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	return resp, nil
 }
 
+func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*websocket.Conn, error) {
+	fullRequestURL, err := a.GetRequestURL(info)
+	if err != nil {
+		return nil, fmt.Errorf("get request url failed: %w", err)
+	}
+	targetHeader := http.Header{}
+	err = a.SetupRequestHeader(c, &targetHeader, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	targetHeader.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	targetConn, _, err := websocket.DefaultDialer.Dial(fullRequestURL, targetHeader)
+	if err != nil {
+		return nil, fmt.Errorf("dial failed to %s: %w", fullRequestURL, err)
+	}
+	// send request body
+	//all, err := io.ReadAll(requestBody)
+	//err = service.WssString(c, targetConn, string(all))
+	return targetConn, nil
+}
+
 func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {

relay/channel/aws/adaptor.go

@@ -8,7 +8,6 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
-	"strings"
 )
 
 const (
@@ -31,18 +30,14 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
-	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
-		a.RequestMode = RequestModeMessage
-	} else {
-		a.RequestMode = RequestModeCompletion
-	}
+	a.RequestMode = RequestModeMessage
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return "", nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	return nil
 }
 
@@ -53,11 +48,8 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 
 	var claudeReq *claude.ClaudeRequest
 	var err error
-	if a.RequestMode == RequestModeCompletion {
-		claudeReq = claude.RequestOpenAI2ClaudeComplete(*request)
-	} else {
-		claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)
-	}
+	claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)
+
 	c.Set("request_model", request.Model)
 	c.Set("converted_request", claudeReq)
 	return claudeReq, err
@@ -67,11 +59,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return nil, nil
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
 	} else {

relay/channel/aws/constants.go

@@ -1,13 +1,14 @@
 package aws
 
 var awsModelIDMap = map[string]string{
-	"claude-instant-1.2":       "anthropic.claude-instant-v1",
-	"claude-2.0":               "anthropic.claude-v2",
-	"claude-2.1":               "anthropic.claude-v2:1",
-	"claude-3-sonnet-20240229": "anthropic.claude-3-sonnet-20240229-v1:0",
-	"claude-3-opus-20240229":   "anthropic.claude-3-opus-20240229-v1:0",
-	"claude-3-haiku-20240307":  "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-instant-1.2":         "anthropic.claude-instant-v1",
+	"claude-2.0":                 "anthropic.claude-v2",
+	"claude-2.1":                 "anthropic.claude-v2:1",
+	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
+	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
+	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
+	"claude-3-5-sonnet-20241022": "anthropic.claude-3-5-sonnet-20241022-v2:0",
 }
 
 var ChannelName = "aws"

relay/channel/aws/dto.go

@@ -1,6 +1,8 @@
 package aws
 
-import "one-api/relay/channel/claude"
+import (
+	"one-api/relay/channel/claude"
+)
 
 type AwsClaudeRequest struct {
 	// AnthropicVersion should be "bedrock-2023-05-31"
@@ -12,4 +14,6 @@ type AwsClaudeRequest struct {
 	TopP             float64                `json:"top_p,omitempty"`
 	TopK             int                    `json:"top_k,omitempty"`
 	StopSequences    []string               `json:"stop_sequences,omitempty"`
+	Tools            []claude.Tool          `json:"tools,omitempty"`
+	ToolChoice       any                    `json:"tool_choice,omitempty"`
 }

relay/channel/aws/relay-aws.go

@@ -53,7 +53,7 @@ func awsModelID(requestModel string) (string, error) {
 		return awsModelID, nil
 	}
 
-	return "", errors.Errorf("model %s not found", requestModel)
+	return requestModel, nil
 }
 
 func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
@@ -222,9 +222,11 @@ func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 		}
 	}
 	service.Done(c)
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	if resp != nil {
+		err = resp.Body.Close()
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		}
 	}
 	return nil, &usage
 }

relay/channel/baidu/adaptor.go

@@ -98,9 +98,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fullRequestURL, nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }
 
@@ -122,11 +122,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = baiduStreamHandler(c, resp)
 	} else {

relay/channel/claude/adaptor.go

@@ -47,14 +47,14 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-api-key", info.ApiKey)
+	req.Set("x-api-key", info.ApiKey)
 	anthropicVersion := c.Request.Header.Get("anthropic-version")
 	if anthropicVersion == "" {
 		anthropicVersion = "2023-06-01"
 	}
-	req.Header.Set("anthropic-version", anthropicVersion)
+	req.Set("anthropic-version", anthropicVersion)
 	return nil
 }
 
@@ -73,15 +73,15 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = claudeStreamHandler(c, resp, info, a.RequestMode)
+		err, usage = ClaudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
-		err, usage = claudeHandler(a.RequestMode, c, resp, info.PromptTokens, info.UpstreamModelName)
+		err, usage = ClaudeHandler(c, resp, a.RequestMode, info)
 	}
 	return
 }

relay/channel/claude/constants.go

@@ -8,7 +8,9 @@ var ModelList = []string{
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-haiku-20240307",
+	"claude-3-5-haiku-20241022",
 	"claude-3-5-sonnet-20240620",
+	"claude-3-5-sonnet-20241022",
 }
 
 var ChannelName = "claude"

relay/channel/claude/dto.go

@@ -31,9 +31,9 @@ type ClaudeMessage struct {
 }
 
 type Tool struct {
-	Name        string      `json:"name"`
-	Description string      `json:"description,omitempty"`
-	InputSchema InputSchema `json:"input_schema"`
+	Name        string                 `json:"name"`
+	Description string                 `json:"description,omitempty"`
+	InputSchema map[string]interface{} `json:"input_schema"`
 }
 
 type InputSchema struct {

relay/channel/claude/relay-claude.go

@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -63,15 +64,21 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 
 	for _, tool := range textRequest.Tools {
 		if params, ok := tool.Function.Parameters.(map[string]any); ok {
-			claudeTools = append(claudeTools, Tool{
+			claudeTool := Tool{
 				Name:        tool.Function.Name,
 				Description: tool.Function.Description,
-				InputSchema: InputSchema{
-					Type:       params["type"].(string),
-					Properties: params["properties"],
-					Required:   params["required"],
-				},
-			})
+			}
+			claudeTool.InputSchema = make(map[string]interface{})
+			claudeTool.InputSchema["type"] = params["type"].(string)
+			claudeTool.InputSchema["properties"] = params["properties"]
+			claudeTool.InputSchema["required"] = params["required"]
+			for s, a := range params {
+				if s == "type" || s == "properties" || s == "required" {
+					continue
+				}
+				claudeTool.InputSchema[s] = a
+			}
+			claudeTools = append(claudeTools, claudeTool)
 		}
 	}
 
@@ -102,13 +109,10 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 		}
 	}
 	formatMessages := make([]dto.Message, 0)
-	var lastMessage *dto.Message
+	lastMessage := dto.Message{
+		Role: "tool",
+	}
 	for i, message := range textRequest.Messages {
-		//if message.Role == "system" {
-		//	if i != 0 {
-		//		message.Role = "user"
-		//	}
-		//}
 		if message.Role == "" {
 			textRequest.Messages[i].Role = "user"
 		}
@@ -116,7 +120,13 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			Role:    message.Role,
 			Content: message.Content,
 		}
-		if lastMessage != nil && lastMessage.Role == message.Role {
+		if message.Role == "tool" {
+			fmtMessage.ToolCallId = message.ToolCallId
+		}
+		if message.Role == "assistant" && message.ToolCalls != nil {
+			fmtMessage.ToolCalls = message.ToolCalls
+		}
+		if lastMessage.Role == message.Role && lastMessage.Role != "tool" {
 			if lastMessage.IsStringContent() && message.IsStringContent() {
 				content, _ := json.Marshal(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
 				fmtMessage.Content = content
@@ -129,10 +139,11 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			fmtMessage.Content = content
 		}
 		formatMessages = append(formatMessages, fmtMessage)
-		lastMessage = &textRequest.Messages[i]
+		lastMessage = fmtMessage
 	}
 
 	claudeMessages := make([]ClaudeMessage, 0)
+	isFirstMessage := true
 	for _, message := range formatMessages {
 		if message.Role == "system" {
 			if message.IsStringContent() {
@@ -148,10 +159,54 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 				claudeRequest.System = content
 			}
 		} else {
+			if isFirstMessage {
+				isFirstMessage = false
+				if message.Role != "user" {
+					// fix: first message is assistant, add user message
+					claudeMessage := ClaudeMessage{
+						Role: "user",
+						Content: []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: "...",
+							},
+						},
+					}
+					claudeMessages = append(claudeMessages, claudeMessage)
+				}
+			}
 			claudeMessage := ClaudeMessage{
 				Role: message.Role,
 			}
-			if message.IsStringContent() {
+			if message.Role == "tool" {
+				if len(claudeMessages) > 0 && claudeMessages[len(claudeMessages)-1].Role == "user" {
+					lastMessage := claudeMessages[len(claudeMessages)-1]
+					if content, ok := lastMessage.Content.(string); ok {
+						lastMessage.Content = []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: content,
+							},
+						}
+					}
+					lastMessage.Content = append(lastMessage.Content.([]ClaudeMediaMessage), ClaudeMediaMessage{
+						Type:      "tool_result",
+						ToolUseId: message.ToolCallId,
+						Content:   message.StringContent(),
+					})
+					claudeMessages[len(claudeMessages)-1] = lastMessage
+					continue
+				} else {
+					claudeMessage.Role = "user"
+					claudeMessage.Content = []ClaudeMediaMessage{
+						{
+							Type:      "tool_result",
+							ToolUseId: message.ToolCallId,
+							Content:   message.StringContent(),
+						},
+					}
+				}
+			} else if message.IsStringContent() && message.ToolCalls == nil {
 				claudeMessage.Content = message.StringContent()
 			} else {
 				claudeMediaMessages := make([]ClaudeMediaMessage, 0)
@@ -184,6 +239,28 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 					}
 					claudeMediaMessages = append(claudeMediaMessages, claudeMediaMessage)
 				}
+				if message.ToolCalls != nil {
+					for _, tc := range message.ToolCalls.([]interface{}) {
+						toolCallJSON, _ := json.Marshal(tc)
+						var toolCall dto.ToolCall
+						err := json.Unmarshal(toolCallJSON, &toolCall)
+						if err != nil {
+							common.SysError("tool call is not a dto.ToolCall: " + fmt.Sprintf("%v", tc))
+							continue
+						}
+						inputObj := make(map[string]any)
+						if err := json.Unmarshal([]byte(toolCall.Function.Arguments), &inputObj); err != nil {
+							common.SysError("tool call function arguments is not a map[string]any: " + fmt.Sprintf("%v", toolCall.Function.Arguments))
+							continue
+						}
+						claudeMediaMessages = append(claudeMediaMessages, ClaudeMediaMessage{
+							Type:  "tool_use",
+							Id:    toolCall.ID,
+							Name:  toolCall.Function.Name,
+							Input: inputObj,
+						})
+					}
+				}
 				claudeMessage.Content = claudeMediaMessages
 			}
 			claudeMessages = append(claudeMessages, claudeMessage)
@@ -318,12 +395,13 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	if len(tools) > 0 {
 		choice.Message.ToolCalls = tools
 	}
+	fullTextResponse.Model = claudeResponse.Model
 	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
 	return &fullTextResponse
 }
 
-func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	var usage *dto.Usage
 	usage = &dto.Usage{}
@@ -405,7 +483,7 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	return nil, usage
 }
 
-func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func ClaudeHandler(c *gin.Context, resp *http.Response, requestMode int, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -431,15 +509,15 @@ func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptT
 		}, nil
 	}
 	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err := service.CountTokenText(claudeResponse.Completion, model)
+	completionTokens, err := service.CountTextToken(claudeResponse.Completion, info.OriginModelName)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}
 	usage := dto.Usage{}
 	if requestMode == RequestModeCompletion {
-		usage.PromptTokens = promptTokens
+		usage.PromptTokens = info.PromptTokens
 		usage.CompletionTokens = completionTokens
-		usage.TotalTokens = promptTokens + completionTokens
+		usage.TotalTokens = info.PromptTokens + completionTokens
 	} else {
 		usage.PromptTokens = claudeResponse.Usage.InputTokens
 		usage.CompletionTokens = claudeResponse.Usage.OutputTokens

relay/channel/cloudflare/adaptor.go

@@ -30,9 +30,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }
 
@@ -48,7 +48,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	}
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
@@ -78,7 +78,7 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 	return nil, errors.New("not implemented")
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		fallthrough

relay/channel/cloudflare/constant.go

@@ -1,6 +1,7 @@
 package cloudflare
 
 var ModelList = []string{
+	"@cf/meta/llama-3.1-8b-instruct",
 	"@cf/meta/llama-2-7b-chat-fp16",
 	"@cf/meta/llama-2-7b-chat-int8",
 	"@cf/mistral/mistral-7b-instruct-v0.1",

relay/channel/cloudflare/relay_cloudflare.go

@@ -149,7 +149,7 @@ func cfSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayIn
 
 	usage := &dto.Usage{}
 	usage.PromptTokens = info.PromptTokens
-	usage.CompletionTokens, _ = service.CountTokenText(cfResp.Result.Text, info.UpstreamModelName)
+	usage.CompletionTokens, _ = service.CountTextToken(cfResp.Result.Text, info.UpstreamModelName)
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 
 	return nil, usage

relay/channel/cohere/adaptor.go

@@ -36,9 +36,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }
 
@@ -46,7 +46,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return requestOpenAI2Cohere(*request), nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
@@ -54,7 +54,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return requestConvertRerank2Cohere(request), nil
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = cohereRerankHandler(c, resp, info)
 	} else {

relay/channel/cohere/constant.go

@@ -1,7 +1,10 @@
 package cohere
 
 var ModelList = []string{
-	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"command-r", "command-r-plus",
+	"command-r-08-2024", "command-r-plus-08-2024",
+	"c4ai-aya-23-35b", "c4ai-aya-23-8b",
+	"command-light", "command-light-nightly", "command", "command-nightly",
 	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
 }
 

relay/channel/cohere/dto.go

@@ -8,6 +8,7 @@ type CohereRequest struct {
 	Message     string        `json:"message"`
 	Stream      bool          `json:"stream"`
 	MaxTokens   int           `json:"max_tokens"`
+	SafetyMode  string        `json:"safety_mode,omitempty"`
 }
 
 type ChatHistory struct {

relay/channel/cohere/relay-cohere.go

@@ -23,6 +23,9 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 		Stream:      textRequest.Stream,
 		MaxTokens:   textRequest.GetMaxTokens(),
 	}
+	if common.CohereSafetySetting != "NONE" {
+		cohereReq.SafetyMode = common.CohereSafetySetting
+	}
 	if cohereReq.MaxTokens == 0 {
 		cohereReq.MaxTokens = 4000
 	}
@@ -44,6 +47,7 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 			})
 		}
 	}
+
 	return &cohereReq
 }
 

relay/channel/dify/adaptor.go

@@ -31,9 +31,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/v1/chat-messages", info.BaseUrl), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }
 
@@ -48,11 +48,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = difyStreamHandler(c, resp, info)
 	} else {

relay/channel/dify/relay-dify.go

@@ -53,7 +53,7 @@ func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dt
 		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
 	} else if constant.DifyDebug && difyResponse.Event == "node_started" {
 		choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
-	} else if difyResponse.Event == "message" {
+	} else if difyResponse.Event == "message" || difyResponse.Event == "agent_message" {
 		choice.Delta.SetContentString(difyResponse.Answer)
 	}
 	response.Choices = append(response.Choices, choice)
@@ -108,7 +108,7 @@ func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Re
 	}
 	if usage.TotalTokens == 0 {
 		usage.PromptTokens = info.PromptTokens
-		usage.CompletionTokens, _ = service.CountTokenText("gpt-3.5-turbo", responseText)
+		usage.CompletionTokens, _ = service.CountTextToken("gpt-3.5-turbo", responseText)
 		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	}
 	return nil, usage

relay/channel/gemini/adaptor.go

@@ -6,6 +6,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
+	"one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
@@ -25,18 +26,12 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
-}
 
-// 定义一个映射，存储模型名称和对应的版本
-var modelVersionMap = map[string]string{
-	"gemini-1.5-pro-latest":   "v1beta",
-	"gemini-1.5-flash-latest": "v1beta",
-	"gemini-ultra":            "v1beta",
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	// 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1"
-	version, beta := modelVersionMap[info.UpstreamModelName]
+	version, beta := constant.GeminiModelMap[info.UpstreamModelName]
 	if !beta {
 		if info.ApiVersion != "" {
 			version = info.ApiVersion
@@ -52,9 +47,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-goog-api-key", info.ApiKey)
+	req.Set("x-goog-api-key", info.ApiKey)
 	return nil
 }
 
@@ -69,15 +64,15 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = geminiChatStreamHandler(c, resp, info)
+		err, usage = GeminiChatStreamHandler(c, resp, info)
 	} else {
-		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		err, usage = GeminiChatHandler(c, resp)
 	}
 	return
 }

relay/channel/gemini/constant.go

@@ -6,7 +6,7 @@ const (
 
 var ModelList = []string{
 	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
-	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001",
+	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001", "gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
 }
 
 var ChannelName = "google gemini"

relay/channel/gemini/relay-gemini.go

@@ -83,13 +83,28 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				if imageNum > GeminiVisionMaxImageNum {
 					continue
 				}
-				mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
-				parts = append(parts, GeminiPart{
-					InlineData: &GeminiInlineData{
-						MimeType: mimeType,
-						Data:     data,
-					},
-				})
+				// 判断是否是url
+				if strings.HasPrefix(part.ImageUrl.(dto.MessageImageUrl).Url, "http") {
+					// 是url，获取图片的类型和base64编码的数据
+					mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
+					parts = append(parts, GeminiPart{
+						InlineData: &GeminiInlineData{
+							MimeType: mimeType,
+							Data:     data,
+						},
+					})
+				} else {
+					_, format, base64String, err := service.DecodeBase64ImageData(part.ImageUrl.(dto.MessageImageUrl).Url)
+					if err != nil {
+						continue
+					}
+					parts = append(parts, GeminiPart{
+						InlineData: &GeminiInlineData{
+							MimeType: "image/" + format,
+							Data:     base64String,
+						},
+					})
+				}
 			}
 		}
 		content.Parts = parts
@@ -198,7 +213,6 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 			choice.Delta.SetContentString(respFirst.Text)
 		}
 	}
-	choice.FinishReason = &relaycommon.StopFinishReason
 	var response dto.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = "gemini"
@@ -206,7 +220,7 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 	return &response
 }
 
-func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseText := ""
 	id := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createAt := common.GetTimestamp()
@@ -247,10 +261,14 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 			common.LogError(c, err.Error())
 		}
 	}
+
+	response := service.GenerateStopResponse(id, createAt, info.UpstreamModelName, relaycommon.StopFinishReason)
+	service.ObjectData(c, response)
+
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 
 	if info.ShouldIncludeUsage {
-		response := service.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
+		response = service.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
 		err := service.ObjectData(c, response)
 		if err != nil {
 			common.SysError("send final response failed: " + err.Error())
@@ -261,7 +279,7 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 	return nil, usage
 }
 
-func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func GeminiChatHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil

relay/channel/jina/adaptor.go

@@ -32,14 +32,14 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if info.RelayMode == constant.RelayModeRerank {
 		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
 	} else if info.RelayMode == constant.RelayModeEmbeddings {
-		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+		return fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
 	}
 	return "", errors.New("invalid relay mode")
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
 	return nil
 }
 
@@ -47,7 +47,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return request, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
@@ -55,9 +55,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = jinaRerankHandler(c, resp)
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		err, usage = jinaEmbeddingHandler(c, resp)
 	}
 	return
 }

relay/channel/jina/relay-jina.go

@@ -33,3 +33,28 @@ func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWit
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &jinaResp.Usage
 }
+
+func jinaEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var jinaResp dto.OpenAIEmbeddingResponse
+	err = json.Unmarshal(responseBody, &jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	jsonResponse, err := json.Marshal(jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(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, &jinaResp.Usage
+}

relay/channel/mistral/adaptor.go

@@ -0,0 +1,72 @@
+package mistral
+
+import (
+	"errors"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	mistralReq := requestOpenAI2Mistral(*request)
+	//common.LogJson(c, "body", mistralReq)
+	return mistralReq, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = openai.OaiStreamHandler(c, resp, info)
+	} else {
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/mistral/constants.go

@@ -0,0 +1,12 @@
+package mistral
+
+var ModelList = []string{
+	"open-mistral-7b",
+	"open-mixtral-8x7b",
+	"mistral-small-latest",
+	"mistral-medium-latest",
+	"mistral-large-latest",
+	"mistral-embed",
+}
+
+var ChannelName = "mistral"

relay/channel/mistral/text.go

@@ -0,0 +1,40 @@
+package mistral
+
+import (
+	"encoding/json"
+	"one-api/dto"
+)
+
+func requestOpenAI2Mistral(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIRequest {
+	messages := make([]dto.Message, 0, len(request.Messages))
+	for _, message := range request.Messages {
+		if !message.IsStringContent() {
+			mediaMessages := message.ParseContent()
+			for j, mediaMessage := range mediaMessages {
+				if mediaMessage.Type == dto.ContentTypeImageURL {
+					imageUrl := mediaMessage.ImageUrl.(dto.MessageImageUrl)
+					mediaMessage.ImageUrl = imageUrl.Url
+					mediaMessages[j] = mediaMessage
+				}
+			}
+			messageRaw, _ := json.Marshal(mediaMessages)
+			message.Content = messageRaw
+		}
+		messages = append(messages, dto.Message{
+			Role:       message.Role,
+			Content:    message.Content,
+			ToolCalls:  message.ToolCalls,
+			ToolCallId: message.ToolCallId,
+		})
+	}
+	return &dto.GeneralOpenAIRequest{
+		Model:       request.Model,
+		Stream:      request.Stream,
+		Messages:    messages,
+		Temperature: request.Temperature,
+		TopP:        request.TopP,
+		MaxTokens:   request.MaxTokens,
+		Tools:       request.Tools,
+		ToolChoice:  request.ToolChoice,
+	}
+}

relay/channel/ollama/adaptor.go

@@ -31,13 +31,13 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	switch info.RelayMode {
 	case relayconstant.RelayModeEmbeddings:
-		return info.BaseUrl + "/api/embeddings", nil
+		return info.BaseUrl + "/api/embed", nil
 	default:
 		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 	}
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	return nil
 }
@@ -58,11 +58,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {

relay/channel/ollama/dto.go

@@ -3,24 +3,39 @@ package ollama
 import "one-api/dto"
 
 type OllamaRequest struct {
-	Model       string        `json:"model,omitempty"`
-	Messages    []dto.Message `json:"messages,omitempty"`
-	Stream      bool          `json:"stream,omitempty"`
-	Temperature float64       `json:"temperature,omitempty"`
-	Seed        float64       `json:"seed,omitempty"`
-	Topp        float64       `json:"top_p,omitempty"`
-	TopK        int           `json:"top_k,omitempty"`
-	Stop        any           `json:"stop,omitempty"`
+	Model            string         `json:"model,omitempty"`
+	Messages         []dto.Message  `json:"messages,omitempty"`
+	Stream           bool           `json:"stream,omitempty"`
+	Temperature      float64        `json:"temperature,omitempty"`
+	Seed             float64        `json:"seed,omitempty"`
+	Topp             float64        `json:"top_p,omitempty"`
+	TopK             int            `json:"top_k,omitempty"`
+	Stop             any            `json:"stop,omitempty"`
+	Tools            []dto.ToolCall `json:"tools,omitempty"`
+	ResponseFormat   any            `json:"response_format,omitempty"`
+	FrequencyPenalty float64        `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64        `json:"presence_penalty,omitempty"`
+}
+
+type Options struct {
+	Seed             int     `json:"seed,omitempty"`
+	Temperature      float64 `json:"temperature,omitempty"`
+	TopK             int     `json:"top_k,omitempty"`
+	TopP             float64 `json:"top_p,omitempty"`
+	FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64 `json:"presence_penalty,omitempty"`
+	NumPredict       int     `json:"num_predict,omitempty"`
+	NumCtx           int     `json:"num_ctx,omitempty"`
 }
 
 type OllamaEmbeddingRequest struct {
-	Model  string `json:"model,omitempty"`
-	Prompt any    `json:"prompt,omitempty"`
+	Model   string   `json:"model,omitempty"`
+	Input   []string `json:"input"`
+	Options *Options `json:"options,omitempty"`
 }
 
 type OllamaEmbeddingResponse struct {
-	Embedding []float64 `json:"embedding,omitempty"`
+	Error     string    `json:"error,omitempty"`
+	Model     string    `json:"model"`
+	Embedding [][]float64 `json:"embeddings,omitempty"`
 }
-
-//type OllamaOptions struct {
-//}

relay/channel/ollama/relay-ollama.go

@@ -9,7 +9,6 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/service"
-	"strings"
 )
 
 func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
@@ -28,21 +27,32 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 		Stop, _ = request.Stop.([]string)
 	}
 	return &OllamaRequest{
-		Model:       request.Model,
-		Messages:    messages,
-		Stream:      request.Stream,
-		Temperature: request.Temperature,
-		Seed:        request.Seed,
-		Topp:        request.TopP,
-		TopK:        request.TopK,
-		Stop:        Stop,
+		Model:            request.Model,
+		Messages:         messages,
+		Stream:           request.Stream,
+		Temperature:      request.Temperature,
+		Seed:             request.Seed,
+		Topp:             request.TopP,
+		TopK:             request.TopK,
+		Stop:             Stop,
+		Tools:            request.Tools,
+		ResponseFormat:   request.ResponseFormat,
+		FrequencyPenalty: request.FrequencyPenalty,
+		PresencePenalty:  request.PresencePenalty,
 	}
 }
 
 func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
 	return &OllamaEmbeddingRequest{
-		Model:  request.Model,
-		Prompt: strings.Join(request.ParseInput(), " "),
+		Model: request.Model,
+		Input: request.ParseInput(),
+		Options: &Options{
+			Seed:             int(request.Seed),
+			Temperature:      request.Temperature,
+			TopP:             request.TopP,
+			FrequencyPenalty: request.FrequencyPenalty,
+			PresencePenalty:  request.PresencePenalty,
+		},
 	}
 }
 
@@ -60,9 +70,13 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
+	if ollamaEmbeddingResponse.Error != "" {
+		return service.OpenAIErrorWrapper(err, "ollama_error", resp.StatusCode), nil
+	}
+	flattenedEmbeddings := flattenEmbeddings(ollamaEmbeddingResponse.Embedding)
 	data := make([]dto.OpenAIEmbeddingResponseItem, 0, 1)
 	data = append(data, dto.OpenAIEmbeddingResponseItem{
-		Embedding: ollamaEmbeddingResponse.Embedding,
+		Embedding: flattenedEmbeddings,
 		Object:    "embedding",
 	})
 	usage := &dto.Usage{
@@ -107,3 +121,11 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 	}
 	return nil, usage
 }
+
+func flattenEmbeddings(embeddings [][]float64) []float64 {
+flattened := []float64{}
+for _, row := range embeddings {
+	flattened = append(flattened, row...)
+}
+return flattened
+}

relay/channel/openai/adaptor.go

@@ -31,6 +31,13 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRealtime {
+		// trim https
+		baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
+		baseUrl = strings.TrimPrefix(baseUrl, "http://")
+		baseUrl = "wss://" + baseUrl
+		info.BaseUrl = baseUrl
+	}
 	switch info.ChannelType {
 	case common.ChannelTypeAzure:
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
@@ -40,8 +47,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		model_ := info.UpstreamModelName
 		model_ = strings.Replace(model_, ".", "", -1)
 		// https://github.com/songquanpeng/one-api/issues/67
-
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
+		if info.RelayMode == constant.RelayModeRealtime {
+			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion)
+		}
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
 	case common.ChannelTypeMiniMax:
 		return minimax.GetRequestURL(info)
@@ -54,16 +63,34 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
-	channel.SetupApiRequestHeader(info, c, req)
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, header *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, header)
 	if info.ChannelType == common.ChannelTypeAzure {
-		req.Header.Set("api-key", info.ApiKey)
+		header.Set("api-key", info.ApiKey)
 		return nil
 	}
 	if info.ChannelType == common.ChannelTypeOpenAI && "" != info.Organization {
-		req.Header.Set("OpenAI-Organization", info.Organization)
+		header.Set("OpenAI-Organization", info.Organization)
+	}
+	if info.RelayMode == constant.RelayModeRealtime {
+		swp := c.Request.Header.Get("Sec-WebSocket-Protocol")
+		if swp != "" {
+			items := []string{
+				"realtime",
+				"openai-insecure-api-key." + info.ApiKey,
+				"openai-beta.realtime-v1",
+			}
+			header.Set("Sec-WebSocket-Protocol", strings.Join(items, ","))
+			//req.Header.Set("Sec-WebSocket-Key", c.Request.Header.Get("Sec-WebSocket-Key"))
+			//req.Header.Set("Sec-Websocket-Extensions", c.Request.Header.Get("Sec-Websocket-Extensions"))
+			//req.Header.Set("Sec-Websocket-Version", c.Request.Header.Get("Sec-Websocket-Version"))
+		} else {
+			header.Set("openai-beta", "realtime=v1")
+			header.Set("Authorization", "Bearer "+info.ApiKey)
+		}
+	} else {
+		header.Set("Authorization", "Bearer "+info.ApiKey)
 	}
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
 	//if info.ChannelType == common.ChannelTypeOpenRouter {
 	//	req.Header.Set("HTTP-Referer", "https://github.com/songquanpeng/one-api")
 	//	req.Header.Set("X-Title", "One API")
@@ -78,6 +105,12 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	if info.ChannelType != common.ChannelTypeOpenAI {
 		request.StreamOptions = nil
 	}
+	if strings.HasPrefix(request.Model, "o1-") {
+		if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 {
+			request.MaxCompletionTokens = request.MaxTokens
+			request.MaxTokens = 0
+		}
+	}
 	return request, nil
 }
 
@@ -125,16 +158,20 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 	return request, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
 		return channel.DoFormRequest(a, c, info, requestBody)
+	} else if info.RelayMode == constant.RelayModeRealtime {
+		return channel.DoWssRequest(a, c, info, requestBody)
 	} else {
 		return channel.DoApiRequest(a, c, info, requestBody)
 	}
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
+	case constant.RelayModeRealtime:
+		err, usage = OpenaiRealtimeHandler(c, info)
 	case constant.RelayModeAudioSpeech:
 		err, usage = OpenaiTTSHandler(c, resp, info)
 	case constant.RelayModeAudioTranslation:

relay/channel/openai/constant.go

@@ -8,8 +8,13 @@ var ModelList = []string{
 	"gpt-4-32k", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
-	"gpt-4o", "gpt-4o-2024-05-13",
+	"chatgpt-4o-latest",
+	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
+	"o1-preview", "o1-preview-2024-09-12",
+	"o1-mini", "o1-mini-2024-09-12",
+	"gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01",
+	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",

relay/channel/openai/relay-openai.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -16,12 +17,13 @@ import (
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
+	"sync"
 	"time"
 )
 
 func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	containStreamUsage := false
-	responseId := ""
+	var responseId string
 	var createAt int64 = 0
 	var systemFingerprint string
 	model := info.UpstreamModelName
@@ -41,7 +43,10 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 
 	stopChan := make(chan bool)
 	defer close(stopChan)
-
+	var (
+		lastStreamData string
+		mu             sync.Mutex
+	)
 	gopool.Go(func() {
 		for scanner.Scan() {
 			info.SetFirstResponseTime()
@@ -53,14 +58,19 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
+			mu.Lock()
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
-				err := service.StringData(c, data)
-				if err != nil {
-					common.LogError(c, "streaming error: "+err.Error())
+				if lastStreamData != "" {
+					err := service.StringData(c, lastStreamData)
+					if err != nil {
+						common.LogError(c, "streaming error: "+err.Error())
+					}
 				}
+				lastStreamData = data
 				streamItems = append(streamItems, data)
 			}
+			mu.Unlock()
 		}
 		common.SafeSendBool(stopChan, true)
 	})
@@ -73,6 +83,26 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 		// 正常结束
 	}
 
+	shouldSendLastResp := true
+	var lastStreamResponse dto.ChatCompletionsStreamResponse
+	err := json.Unmarshal(common.StringToByteSlice(lastStreamData), &lastStreamResponse)
+	if err == nil {
+		responseId = lastStreamResponse.Id
+		createAt = lastStreamResponse.Created
+		systemFingerprint = lastStreamResponse.GetSystemFingerprint()
+		model = lastStreamResponse.Model
+		if service.ValidUsage(lastStreamResponse.Usage) {
+			containStreamUsage = true
+			usage = lastStreamResponse.Usage
+			if !info.ShouldIncludeUsage {
+				shouldSendLastResp = false
+			}
+		}
+	}
+	if shouldSendLastResp {
+		service.StringData(c, lastStreamData)
+	}
+
 	// 计算token
 	streamResp := "[" + strings.Join(streamItems, ",") + "]"
 	switch info.RelayMode {
@@ -86,14 +116,9 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 				var streamResponse dto.ChatCompletionsStreamResponse
 				err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 				if err == nil {
-					responseId = streamResponse.Id
-					createAt = streamResponse.Created
-					systemFingerprint = streamResponse.GetSystemFingerprint()
-					model = streamResponse.Model
-					if service.ValidUsage(streamResponse.Usage) {
-						usage = streamResponse.Usage
-						containStreamUsage = true
-					}
+					//if service.ValidUsage(streamResponse.Usage) {
+					//	usage = streamResponse.Usage
+					//}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -110,14 +135,10 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			}
 		} else {
 			for _, streamResponse := range streamResponses {
-				responseId = streamResponse.Id
-				createAt = streamResponse.Created
-				systemFingerprint = streamResponse.GetSystemFingerprint()
-				model = streamResponse.Model
-				if service.ValidUsage(streamResponse.Usage) {
-					usage = streamResponse.Usage
-					containStreamUsage = true
-				}
+				//if service.ValidUsage(streamResponse.Usage) {
+				//	usage = streamResponse.Usage
+				//	containStreamUsage = true
+				//}
 				for _, choice := range streamResponse.Choices {
 					responseTextBuilder.WriteString(choice.Delta.GetContentString())
 					if choice.Delta.ToolCalls != nil {
@@ -211,7 +232,7 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
-			ctkm, _ := service.CountTokenText(string(choice.Message.Content), model)
+			ctkm, _ := service.CountTextToken(string(choice.Message.Content), model)
 			completionTokens += ctkm
 		}
 		simpleResponse.Usage = dto.Usage{
@@ -304,7 +325,7 @@ func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 
 	usage := &dto.Usage{}
 	usage.PromptTokens = info.PromptTokens
-	usage.CompletionTokens, _ = service.CountTokenText(text, info.UpstreamModelName)
+	usage.CompletionTokens, _ = service.CountTextToken(text, info.UpstreamModelName)
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	return nil, usage
 }
@@ -353,3 +374,210 @@ func getTextFromJSON(body []byte) (string, error) {
 	}
 	return whisperResponse.Text, nil
 }
+
+func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.RealtimeUsage) {
+	info.IsStream = true
+	clientConn := info.ClientWs
+	targetConn := info.TargetWs
+
+	clientClosed := make(chan struct{})
+	targetClosed := make(chan struct{})
+	sendChan := make(chan []byte, 100)
+	receiveChan := make(chan []byte, 100)
+	errChan := make(chan error, 2)
+
+	usage := &dto.RealtimeUsage{}
+	localUsage := &dto.RealtimeUsage{}
+	sumUsage := &dto.RealtimeUsage{}
+
+	gopool.Go(func() {
+		for {
+			select {
+			case <-c.Done():
+				return
+			default:
+				_, message, err := clientConn.ReadMessage()
+				if err != nil {
+					if !websocket.IsCloseError(err, websocket.CloseNormalClosure, websocket.CloseGoingAway) {
+						errChan <- fmt.Errorf("error reading from client: %v", err)
+					}
+					close(clientClosed)
+					return
+				}
+
+				realtimeEvent := &dto.RealtimeEvent{}
+				err = json.Unmarshal(message, realtimeEvent)
+				if err != nil {
+					errChan <- fmt.Errorf("error unmarshalling message: %v", err)
+					return
+				}
+
+				if realtimeEvent.Type == dto.RealtimeEventTypeSessionUpdate {
+					if realtimeEvent.Session != nil {
+						if realtimeEvent.Session.Tools != nil {
+							info.RealtimeTools = realtimeEvent.Session.Tools
+						}
+					}
+				}
+
+				textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+				if err != nil {
+					errChan <- fmt.Errorf("error counting text token: %v", err)
+					return
+				}
+				common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+				localUsage.TotalTokens += textToken + audioToken
+				localUsage.InputTokens += textToken + audioToken
+				localUsage.InputTokenDetails.TextTokens += textToken
+				localUsage.InputTokenDetails.AudioTokens += audioToken
+
+				err = service.WssString(c, targetConn, string(message))
+				if err != nil {
+					errChan <- fmt.Errorf("error writing to target: %v", err)
+					return
+				}
+
+				select {
+				case sendChan <- message:
+				default:
+				}
+			}
+		}
+	})
+
+	gopool.Go(func() {
+		for {
+			select {
+			case <-c.Done():
+				return
+			default:
+				_, message, err := targetConn.ReadMessage()
+				if err != nil {
+					if !websocket.IsCloseError(err, websocket.CloseNormalClosure, websocket.CloseGoingAway) {
+						errChan <- fmt.Errorf("error reading from target: %v", err)
+					}
+					close(targetClosed)
+					return
+				}
+				info.SetFirstResponseTime()
+				realtimeEvent := &dto.RealtimeEvent{}
+				err = json.Unmarshal(message, realtimeEvent)
+				if err != nil {
+					errChan <- fmt.Errorf("error unmarshalling message: %v", err)
+					return
+				}
+
+				if realtimeEvent.Type == dto.RealtimeEventTypeResponseDone {
+					realtimeUsage := realtimeEvent.Response.Usage
+					if realtimeUsage != nil {
+						usage.TotalTokens += realtimeUsage.TotalTokens
+						usage.InputTokens += realtimeUsage.InputTokens
+						usage.OutputTokens += realtimeUsage.OutputTokens
+						usage.InputTokenDetails.AudioTokens += realtimeUsage.InputTokenDetails.AudioTokens
+						usage.InputTokenDetails.CachedTokens += realtimeUsage.InputTokenDetails.CachedTokens
+						usage.InputTokenDetails.TextTokens += realtimeUsage.InputTokenDetails.TextTokens
+						usage.OutputTokenDetails.AudioTokens += realtimeUsage.OutputTokenDetails.AudioTokens
+						usage.OutputTokenDetails.TextTokens += realtimeUsage.OutputTokenDetails.TextTokens
+						err := preConsumeUsage(c, info, usage, sumUsage)
+						if err != nil {
+							errChan <- fmt.Errorf("error consume usage: %v", err)
+							return
+						}
+						// 本次计费完成，清除
+						usage = &dto.RealtimeUsage{}
+
+						localUsage = &dto.RealtimeUsage{}
+					} else {
+						textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+						if err != nil {
+							errChan <- fmt.Errorf("error counting text token: %v", err)
+							return
+						}
+						common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+						localUsage.TotalTokens += textToken + audioToken
+						info.IsFirstRequest = false
+						localUsage.InputTokens += textToken + audioToken
+						localUsage.InputTokenDetails.TextTokens += textToken
+						localUsage.InputTokenDetails.AudioTokens += audioToken
+						err = preConsumeUsage(c, info, localUsage, sumUsage)
+						if err != nil {
+							errChan <- fmt.Errorf("error consume usage: %v", err)
+							return
+						}
+						// 本次计费完成，清除
+						localUsage = &dto.RealtimeUsage{}
+						// print now usage
+					}
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming sumUsage: %v", sumUsage))
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming localUsage: %v", localUsage))
+					//common.LogInfo(c, fmt.Sprintf("realtime streaming localUsage: %v", localUsage))
+
+				} else if realtimeEvent.Type == dto.RealtimeEventTypeSessionUpdated || realtimeEvent.Type == dto.RealtimeEventTypeSessionCreated {
+					realtimeSession := realtimeEvent.Session
+					if realtimeSession != nil {
+						// update audio format
+						info.InputAudioFormat = common.GetStringIfEmpty(realtimeSession.InputAudioFormat, info.InputAudioFormat)
+						info.OutputAudioFormat = common.GetStringIfEmpty(realtimeSession.OutputAudioFormat, info.OutputAudioFormat)
+					}
+				} else {
+					textToken, audioToken, err := service.CountTokenRealtime(info, *realtimeEvent, info.UpstreamModelName)
+					if err != nil {
+						errChan <- fmt.Errorf("error counting text token: %v", err)
+						return
+					}
+					common.LogInfo(c, fmt.Sprintf("type: %s, textToken: %d, audioToken: %d", realtimeEvent.Type, textToken, audioToken))
+					localUsage.TotalTokens += textToken + audioToken
+					localUsage.OutputTokens += textToken + audioToken
+					localUsage.OutputTokenDetails.TextTokens += textToken
+					localUsage.OutputTokenDetails.AudioTokens += audioToken
+				}
+
+				err = service.WssString(c, clientConn, string(message))
+				if err != nil {
+					errChan <- fmt.Errorf("error writing to client: %v", err)
+					return
+				}
+
+				select {
+				case receiveChan <- message:
+				default:
+				}
+			}
+		}
+	})
+
+	select {
+	case <-clientClosed:
+	case <-targetClosed:
+	case err := <-errChan:
+		//return service.OpenAIErrorWrapper(err, "realtime_error", http.StatusInternalServerError), nil
+		common.LogError(c, "realtime error: "+err.Error())
+	case <-c.Done():
+	}
+
+	if usage.TotalTokens != 0 {
+		_ = preConsumeUsage(c, info, usage, sumUsage)
+	}
+
+	if localUsage.TotalTokens != 0 {
+		_ = preConsumeUsage(c, info, localUsage, sumUsage)
+	}
+
+	// check usage total tokens, if 0, use local usage
+
+	return nil, sumUsage
+}
+
+func preConsumeUsage(ctx *gin.Context, info *relaycommon.RelayInfo, usage *dto.RealtimeUsage, totalUsage *dto.RealtimeUsage) error {
+	totalUsage.TotalTokens += usage.TotalTokens
+	totalUsage.InputTokens += usage.InputTokens
+	totalUsage.OutputTokens += usage.OutputTokens
+	totalUsage.InputTokenDetails.CachedTokens += usage.InputTokenDetails.CachedTokens
+	totalUsage.InputTokenDetails.TextTokens += usage.InputTokenDetails.TextTokens
+	totalUsage.InputTokenDetails.AudioTokens += usage.InputTokenDetails.AudioTokens
+	totalUsage.OutputTokenDetails.TextTokens += usage.OutputTokenDetails.TextTokens
+	totalUsage.OutputTokenDetails.AudioTokens += usage.OutputTokenDetails.AudioTokens
+	// clear usage
+	err := service.PreWssConsumeQuota(ctx, info, usage)
+	return err
+}

relay/channel/palm/adaptor.go

@@ -32,9 +32,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/v1beta2/models/chat-bison-001:generateMessage", info.BaseUrl), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("x-goog-api-key", info.ApiKey)
+	req.Set("x-goog-api-key", info.ApiKey)
 	return nil
 }
 
@@ -49,11 +49,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
 		err, responseText = palmStreamHandler(c, resp)

relay/channel/palm/relay-palm.go

@@ -156,7 +156,7 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	completionTokens, _ := service.CountTokenText(palmResponse.Candidates[0].Content, model)
+	completionTokens, _ := service.CountTextToken(palmResponse.Candidates[0].Content, model)
 	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,

relay/channel/perplexity/adaptor.go

@@ -32,9 +32,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/chat/completions", info.BaseUrl), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }
 
@@ -52,11 +52,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {

relay/channel/siliconflow/adaptor.go

@@ -0,0 +1,83 @@
+package siliconflow
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		return fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeChatCompletions {
+		return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
+	}
+	return "", errors.New("invalid relay mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	switch info.RelayMode {
+	case constant.RelayModeRerank:
+		err, usage = siliconflowRerankHandler(c, resp)
+	case constant.RelayModeChatCompletions:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
+	case constant.RelayModeEmbeddings:
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/siliconflow/constant.go

@@ -0,0 +1,51 @@
+package siliconflow
+
+var ModelList = []string{
+	"THUDM/glm-4-9b-chat",
+	//"stabilityai/stable-diffusion-xl-base-1.0",
+	//"TencentARC/PhotoMaker",
+	"InstantX/InstantID",
+	//"stabilityai/stable-diffusion-2-1",
+	//"stabilityai/sd-turbo",
+	//"stabilityai/sdxl-turbo",
+	"ByteDance/SDXL-Lightning",
+	"deepseek-ai/deepseek-llm-67b-chat",
+	"Qwen/Qwen1.5-14B-Chat",
+	"Qwen/Qwen1.5-7B-Chat",
+	"Qwen/Qwen1.5-110B-Chat",
+	"Qwen/Qwen1.5-32B-Chat",
+	"01-ai/Yi-1.5-6B-Chat",
+	"01-ai/Yi-1.5-9B-Chat-16K",
+	"01-ai/Yi-1.5-34B-Chat-16K",
+	"THUDM/chatglm3-6b",
+	"deepseek-ai/DeepSeek-V2-Chat",
+	"Qwen/Qwen2-72B-Instruct",
+	"Qwen/Qwen2-7B-Instruct",
+	"Qwen/Qwen2-57B-A14B-Instruct",
+	//"stabilityai/stable-diffusion-3-medium",
+	"deepseek-ai/DeepSeek-Coder-V2-Instruct",
+	"Qwen/Qwen2-1.5B-Instruct",
+	"internlm/internlm2_5-7b-chat",
+	"BAAI/bge-large-en-v1.5",
+	"BAAI/bge-large-zh-v1.5",
+	"Pro/Qwen/Qwen2-7B-Instruct",
+	"Pro/Qwen/Qwen2-1.5B-Instruct",
+	"Pro/Qwen/Qwen1.5-7B-Chat",
+	"Pro/THUDM/glm-4-9b-chat",
+	"Pro/THUDM/chatglm3-6b",
+	"Pro/01-ai/Yi-1.5-9B-Chat-16K",
+	"Pro/01-ai/Yi-1.5-6B-Chat",
+	"Pro/google/gemma-2-9b-it",
+	"Pro/internlm/internlm2_5-7b-chat",
+	"Pro/meta-llama/Meta-Llama-3-8B-Instruct",
+	"Pro/mistralai/Mistral-7B-Instruct-v0.2",
+	"black-forest-labs/FLUX.1-schnell",
+	"iic/SenseVoiceSmall",
+	"netease-youdao/bce-embedding-base_v1",
+	"BAAI/bge-m3",
+	"internlm/internlm2_5-20b-chat",
+	"Qwen/Qwen2-Math-72B-Instruct",
+	"netease-youdao/bce-reranker-base_v1",
+	"BAAI/bge-reranker-v2-m3",
+}
+var ChannelName = "siliconflow"

relay/channel/siliconflow/dto.go

@@ -0,0 +1,17 @@
+package siliconflow
+
+import "one-api/dto"
+
+type SFTokens struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+}
+
+type SFMeta struct {
+	Tokens SFTokens `json:"tokens"`
+}
+
+type SFRerankResponse struct {
+	Results []dto.RerankResponseDocument `json:"results"`
+	Meta    SFMeta                       `json:"meta"`
+}

relay/channel/siliconflow/relay-siliconflow.go

@@ -0,0 +1,44 @@
+package siliconflow
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func siliconflowRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var siliconflowResp SFRerankResponse
+	err = json.Unmarshal(responseBody, &siliconflowResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := &dto.Usage{
+		PromptTokens:     siliconflowResp.Meta.Tokens.InputTokens,
+		CompletionTokens: siliconflowResp.Meta.Tokens.OutputTokens,
+		TotalTokens:      siliconflowResp.Meta.Tokens.InputTokens + siliconflowResp.Meta.Tokens.OutputTokens,
+	}
+	rerankResp := &dto.RerankResponse{
+		Results: siliconflowResp.Results,
+		Usage:   *usage,
+	}
+
+	jsonResponse, err := json.Marshal(rerankResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(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
+}

relay/channel/tencent/adaptor.go

@@ -43,12 +43,12 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/", info.BaseUrl), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
-	req.Header.Set("Authorization", a.Sign)
-	req.Header.Set("X-TC-Action", a.Action)
-	req.Header.Set("X-TC-Version", a.Version)
-	req.Header.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
+	req.Set("Authorization", a.Sign)
+	req.Set("X-TC-Action", a.Action)
+	req.Set("X-TC-Version", a.Version)
+	req.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
 	return nil
 }
 
@@ -73,11 +73,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
 		err, responseText = tencentStreamHandler(c, resp)

relay/channel/vertex/adaptor.go

@@ -0,0 +1,184 @@
+package vertex
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/jinzhu/copier"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/claude"
+	"one-api/relay/channel/gemini"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"strings"
+)
+
+const (
+	RequestModeClaude = 1
+	RequestModeGemini = 2
+	RequestModeLlama  = 3
+)
+
+var claudeModelMap = map[string]string{
+	"claude-3-sonnet-20240229":   "claude-3-sonnet@20240229",
+	"claude-3-opus-20240229":     "claude-3-opus@20240229",
+	"claude-3-haiku-20240307":    "claude-3-haiku@20240307",
+	"claude-3-5-sonnet-20240620": "claude-3-5-sonnet@20240620",
+}
+
+const anthropicVersion = "vertex-2023-10-16"
+
+type Adaptor struct {
+	RequestMode        int
+	AccountCredentials Credentials
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+	if strings.HasPrefix(info.UpstreamModelName, "claude") {
+		a.RequestMode = RequestModeClaude
+	} else if strings.HasPrefix(info.UpstreamModelName, "gemini") {
+		a.RequestMode = RequestModeGemini
+	} else if strings.Contains(info.UpstreamModelName, "llama") {
+		a.RequestMode = RequestModeLlama
+	}
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	adc := &Credentials{}
+	if err := json.Unmarshal([]byte(info.ApiKey), adc); err != nil {
+		return "", fmt.Errorf("failed to decode credentials file: %w", err)
+	}
+	region := GetModelRegion(info.ApiVersion, info.OriginModelName)
+	a.AccountCredentials = *adc
+	suffix := ""
+	if a.RequestMode == RequestModeGemini {
+		if info.IsStream {
+			suffix = "streamGenerateContent?alt=sse"
+		} else {
+			suffix = "generateContent"
+		}
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
+			region,
+			adc.ProjectID,
+			region,
+			info.UpstreamModelName,
+			suffix,
+		), nil
+	} else if a.RequestMode == RequestModeClaude {
+		if info.IsStream {
+			suffix = "streamRawPredict?alt=sse"
+		} else {
+			suffix = "rawPredict"
+		}
+		if v, ok := claudeModelMap[info.UpstreamModelName]; ok {
+			info.UpstreamModelName = v
+		}
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/anthropic/models/%s:%s",
+			region,
+			adc.ProjectID,
+			region,
+			info.UpstreamModelName,
+			suffix,
+		), nil
+	} else if a.RequestMode == RequestModeLlama {
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1beta1/projects/%s/locations/%s/endpoints/openapi/chat/completions",
+			region,
+			adc.ProjectID,
+			region,
+		), nil
+	}
+	return "", errors.New("unsupported request mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	accessToken, err := getAccessToken(a, info)
+	if err != nil {
+		return err
+	}
+	req.Set("Authorization", "Bearer "+accessToken)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	if a.RequestMode == RequestModeClaude {
+		claudeReq, err := claude.RequestOpenAI2ClaudeMessage(*request)
+		if err != nil {
+			return nil, err
+		}
+		vertexClaudeReq := &VertexAIClaudeRequest{
+			AnthropicVersion: anthropicVersion,
+		}
+		if err = copier.Copy(vertexClaudeReq, claudeReq); err != nil {
+			return nil, errors.New("failed to copy claude request")
+		}
+		c.Set("request_model", request.Model)
+		return vertexClaudeReq, nil
+	} else if a.RequestMode == RequestModeGemini {
+		geminiRequest := gemini.CovertGemini2OpenAI(*request)
+		c.Set("request_model", request.Model)
+		return geminiRequest, nil
+	} else if a.RequestMode == RequestModeLlama {
+		return request, nil
+	}
+	return nil, errors.New("unsupported request mode")
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		switch a.RequestMode {
+		case RequestModeClaude:
+			err, usage = claude.ClaudeStreamHandler(c, resp, info, claude.RequestModeMessage)
+		case RequestModeGemini:
+			err, usage = gemini.GeminiChatStreamHandler(c, resp, info)
+		case RequestModeLlama:
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		}
+	} else {
+		switch a.RequestMode {
+		case RequestModeClaude:
+			err, usage = claude.ClaudeHandler(c, resp, claude.RequestModeMessage, info)
+		case RequestModeGemini:
+			err, usage = gemini.GeminiChatHandler(c, resp)
+		case RequestModeLlama:
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.OriginModelName)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/vertex/constants.go

@@ -0,0 +1,15 @@
+package vertex
+
+var ModelList = []string{
+	"claude-3-sonnet-20240229",
+	"claude-3-opus-20240229",
+	"claude-3-haiku-20240307",
+	"claude-3-5-sonnet-20240620",
+
+	//"gemini-1.5-pro-latest", "gemini-1.5-flash-latest",
+	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision",
+
+	"meta/llama3-405b-instruct-maas",
+}
+
+var ChannelName = "vertex-ai"

relay/channel/vertex/dto.go

@@ -0,0 +1,17 @@
+package vertex
+
+import "one-api/relay/channel/claude"
+
+type VertexAIClaudeRequest struct {
+	AnthropicVersion string                 `json:"anthropic_version"`
+	Messages         []claude.ClaudeMessage `json:"messages"`
+	System           string                 `json:"system,omitempty"`
+	MaxTokens        int                    `json:"max_tokens,omitempty"`
+	StopSequences    []string               `json:"stop_sequences,omitempty"`
+	Stream           bool                   `json:"stream,omitempty"`
+	Temperature      float64                `json:"temperature,omitempty"`
+	TopP             float64                `json:"top_p,omitempty"`
+	TopK             int                    `json:"top_k,omitempty"`
+	Tools            []claude.Tool          `json:"tools,omitempty"`
+	ToolChoice       any                    `json:"tool_choice,omitempty"`
+}

relay/channel/vertex/relay-vertex.go

@@ -0,0 +1,16 @@
+package vertex
+
+import "one-api/common"
+
+func GetModelRegion(other string, localModelName string) string {
+	// if other is json string
+	if common.IsJsonStr(other) {
+		m := common.StrToMap(other)
+		if m[localModelName] != nil {
+			return m[localModelName].(string)
+		} else {
+			return m["default"].(string)
+		}
+	}
+	return other
+}

relay/channel/vertex/service_account.go

@@ -0,0 +1,122 @@
+package vertex
+
+import (
+	"crypto/rsa"
+	"crypto/x509"
+	"encoding/json"
+	"encoding/pem"
+	"errors"
+	"github.com/bytedance/gopkg/cache/asynccache"
+	"github.com/golang-jwt/jwt"
+	"net/http"
+	"net/url"
+	relaycommon "one-api/relay/common"
+	"strings"
+
+	"fmt"
+	"time"
+)
+
+type Credentials struct {
+	ProjectID    string `json:"project_id"`
+	PrivateKeyID string `json:"private_key_id"`
+	PrivateKey   string `json:"private_key"`
+	ClientEmail  string `json:"client_email"`
+	ClientID     string `json:"client_id"`
+}
+
+var Cache = asynccache.NewAsyncCache(asynccache.Options{
+	RefreshDuration: time.Minute * 35,
+	EnableExpire:    true,
+	ExpireDuration:  time.Minute * 30,
+	Fetcher: func(key string) (interface{}, error) {
+		return nil, errors.New("not found")
+	},
+})
+
+func getAccessToken(a *Adaptor, info *relaycommon.RelayInfo) (string, error) {
+	cacheKey := fmt.Sprintf("access-token-%d", info.ChannelId)
+	val, err := Cache.Get(cacheKey)
+	if err == nil {
+		return val.(string), nil
+	}
+
+	signedJWT, err := createSignedJWT(a.AccountCredentials.ClientEmail, a.AccountCredentials.PrivateKey)
+	if err != nil {
+		return "", fmt.Errorf("failed to create signed JWT: %w", err)
+	}
+	newToken, err := exchangeJwtForAccessToken(signedJWT)
+	if err != nil {
+		return "", fmt.Errorf("failed to exchange JWT for access token: %w", err)
+	}
+	if err := Cache.SetDefault(cacheKey, newToken); err {
+		return newToken, nil
+	}
+	return newToken, nil
+}
+
+func createSignedJWT(email, privateKeyPEM string) (string, error) {
+
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "-----BEGIN PRIVATE KEY-----", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "-----END PRIVATE KEY-----", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\r", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\n", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\\n", "")
+
+	block, _ := pem.Decode([]byte("-----BEGIN PRIVATE KEY-----\n" + privateKeyPEM + "\n-----END PRIVATE KEY-----"))
+	if block == nil {
+		return "", fmt.Errorf("failed to parse PEM block containing the private key")
+	}
+
+	privateKey, err := x509.ParsePKCS8PrivateKey(block.Bytes)
+	if err != nil {
+		return "", err
+	}
+
+	rsaPrivateKey, ok := privateKey.(*rsa.PrivateKey)
+	if !ok {
+		return "", fmt.Errorf("not an RSA private key")
+	}
+
+	now := time.Now()
+	claims := jwt.MapClaims{
+		"iss":   email,
+		"scope": "https://www.googleapis.com/auth/cloud-platform",
+		"aud":   "https://www.googleapis.com/oauth2/v4/token",
+		"exp":   now.Add(time.Minute * 35).Unix(),
+		"iat":   now.Unix(),
+	}
+
+	token := jwt.NewWithClaims(jwt.SigningMethodRS256, claims)
+	signedToken, err := token.SignedString(rsaPrivateKey)
+	if err != nil {
+		return "", err
+	}
+
+	return signedToken, nil
+}
+
+func exchangeJwtForAccessToken(signedJWT string) (string, error) {
+
+	authURL := "https://www.googleapis.com/oauth2/v4/token"
+	data := url.Values{}
+	data.Set("grant_type", "urn:ietf:params:oauth:grant-type:jwt-bearer")
+	data.Set("assertion", signedJWT)
+
+	resp, err := http.PostForm(authURL, data)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+
+	var result map[string]interface{}
+	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+		return "", err
+	}
+
+	if accessToken, ok := result["access_token"].(string); ok {
+		return accessToken, nil
+	}
+
+	return "", fmt.Errorf("failed to get access token: %v", result)
+}

relay/channel/xunfei/adaptor.go

@@ -33,7 +33,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return "", nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	return nil
 }
@@ -50,14 +50,14 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	// xunfei's request is not http request, so we don't need to do anything here
 	dummyResp := &http.Response{}
 	dummyResp.StatusCode = http.StatusOK
 	return dummyResp, nil
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	splits := strings.Split(info.ApiKey, "|")
 	if len(splits) != 3 {
 		return nil, service.OpenAIErrorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)

relay/channel/zhipu/adaptor.go

@@ -35,10 +35,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/api/paas/v3/model-api/%s/%s", info.BaseUrl, info.UpstreamModelName, method), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	token := getZhipuToken(info.ApiKey)
-	req.Header.Set("Authorization", token)
+	req.Set("Authorization", token)
 	return nil
 }
 
@@ -56,11 +56,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = zhipuStreamHandler(c, resp)
 	} else {

relay/channel/zhipu_4v/adaptor.go

@@ -32,10 +32,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return fmt.Sprintf("%s/api/paas/v4/chat/completions", info.BaseUrl), nil
 }
 
-func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	token := getZhipuToken(info.ApiKey)
-	req.Header.Set("Authorization", token)
+	req.Set("Authorization", token)
 	return nil
 }
 
@@ -53,11 +53,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
-func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
-func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {

relay/channel/zhipu_4v/constants.go

@@ -1,7 +1,7 @@
 package zhipu_4v
 
 var ModelList = []string{
-	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools",
+	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools", "glm-4-plus", "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-long", "glm-4-flash", "glm-4v-plus",
 }
 
 var ChannelName = "zhipu_4v"