fix: epay

修改readme错误

.gitignore

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

README.md

@@ -2,15 +2,21 @@
 # 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。
+> 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
 
-> 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。  
+> [!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 +24,9 @@
 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）
@@ -51,29 +57,15 @@
 
 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`， 可选值为 `true` 和 `false`
-- `FORCE_STREAM_OPTION`：覆盖客户端stream_options参数，请求上游返回流模式usage，目前仅支持 `OpenAI` 渠道类型
+- `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
+
 ## 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）
@@ -96,8 +88,25 @@ 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)

common/email-outlook-auth.go

@@ -0,0 +1,32 @@
+package common
+
+import (
+	"errors"
+	"net/smtp"
+)
+
+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
+}

common/email.go

@@ -62,6 +62,9 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err != nil {
 			return err
 		}
+	} else if strings.HasSuffix(SMTPAccount, "outlook.com") {
+		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
@@ -31,13 +32,15 @@ var defaultModelRatio = map[string]float64{
 	"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-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":               0.075,
+	"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":             0.25, // $0.0015 / 1K tokens
@@ -105,12 +108,13 @@ var defaultModelRatio = map[string]float64{
 	"gemini-1.0-pro-latest":          1,
 	"gemini-1.0-pro-vision-latest":   1,
 	"gemini-ultra":                   1,
-	"chatglm_turbo":                  0.3572, // ￥0.005 / 1k tokens
-	"chatglm_pro":                    0.7143, // ￥0.01 / 1k tokens
-	"chatglm_std":                    0.3572, // ￥0.005 / 1k tokens
-	"chatglm_lite":                   0.1429, // ￥0.002 / 1k tokens
-	"glm-4":                          7.143,  // ￥0.1 / 1k tokens
-	"glm-4v":                         7.143,  // ￥0.1 / 1k tokens
+	"chatglm_turbo":                  0.3572,     // ￥0.005 / 1k tokens
+	"chatglm_pro":                    0.7143,     // ￥0.01 / 1k tokens
+	"chatglm_std":                    0.3572,     // ￥0.005 / 1k tokens
+	"chatglm_lite":                   0.1429,     // ￥0.002 / 1k tokens
+	"glm-4":                          7.143,      // ￥0.1 / 1k tokens
+	"glm-4v":                         0.05 * RMB, // ￥0.05 / 1k tokens
+	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
 	"glm-3-turbo":                    0.3572,
 	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
 	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
@@ -158,6 +162,8 @@ var defaultModelRatio = map[string]float64{
 }
 
 var defaultModelPrice = map[string]float64{
+	"suno_music":        0.1,
+	"suno_lyrics":       0.01,
 	"dall-e-3":          0.04,
 	"gpt-4-gizmo-*":     0.1,
 	"mj_imagine":        0.1,
@@ -175,10 +181,17 @@ 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      = make(map[string]float64)
+	modelPriceMapMutex = sync.RWMutex{}
+)
+var (
+	modelRatioMap      map[string]float64 = nil
+	modelRatioMapMutex                    = sync.RWMutex{}
+)
 
 var CompletionRatio map[string]float64 = nil
 var defaultCompletionRatio = map[string]float64{
@@ -186,11 +199,18 @@ var defaultCompletionRatio = map[string]float64{
 	"gpt-4-all":     2,
 }
 
-func ModelPrice2JSONString() string {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
+func GetModelPriceMap() map[string]float64 {
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	if modelPriceMap == nil {
+		modelPriceMap = defaultModelPrice
 	}
-	jsonBytes, err := json.Marshal(modelPrice)
+	return modelPriceMap
+}
+
+func ModelPrice2JSONString() string {
+	GetModelPriceMap()
+	jsonBytes, err := json.Marshal(modelPriceMap)
 	if err != nil {
 		SysError("error marshalling model price: " + err.Error())
 	}
@@ -198,19 +218,19 @@ 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]
+	price, ok := modelPriceMap[name]
 	if !ok {
 		if printErr {
 			SysError("model price not found: " + name)
@@ -220,18 +240,18 @@ 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())
 	}
@@ -239,18 +259,18 @@ 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
@@ -302,7 +322,13 @@ 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") || strings.HasPrefix(name, "gpt-4o") {
+		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

common/str.go

@@ -0,0 +1,73 @@
+package common
+
+import (
+	"encoding/json"
+	"math/rand"
+	"strconv"
+	"unsafe"
+)
+
+func GetStringIfEmpty(str string, defaultValue string) string {
+	if str == "" {
+		return defaultValue
+	}
+	return str
+}
+
+func GetRandomString(length int) string {
+	//rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyChars[rand.Intn(len(keyChars))]
+	}
+	return string(key)
+}
+
+func MapToJsonStr(m map[string]interface{}) string {
+	bytes, err := json.Marshal(m)
+	if err != nil {
+		return ""
+	}
+	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)
+	if err != nil {
+		return nil
+	}
+	return m
+}
+
+func String2Int(str string) int {
+	num, err := strconv.Atoi(str)
+	if err != nil {
+		return 0
+	}
+	return num
+}
+
+func StringsContains(strs []string, str string) bool {
+	for _, s := range strs {
+		if s == str {
+			return true
+		}
+	}
+	return false
+}
+
+// StringToByteSlice []byte only read, panic on append
+func StringToByteSlice(s string) []byte {
+	tmp1 := (*[2]uintptr)(unsafe.Pointer(&s))
+	tmp2 := [3]uintptr{tmp1[0], tmp1[1], tmp1[1]}
+	return *(*[]byte)(unsafe.Pointer(&tmp2))
+}

common/utils.go

@@ -1,7 +1,6 @@
 package common
 
 import (
-	"encoding/json"
 	"fmt"
 	"github.com/google/uuid"
 	"html/template"
@@ -13,7 +12,6 @@ import (
 	"strconv"
 	"strings"
 	"time"
-	"unsafe"
 )
 
 func OpenBrowser(url string) {
@@ -159,15 +157,6 @@ func GenerateKey() string {
 	return string(key)
 }
 
-func GetRandomString(length int) string {
-	//rand.Seed(time.Now().UnixNano())
-	key := make([]byte, length)
-	for i := 0; i < length; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
-	}
-	return string(key)
-}
-
 func GetRandomInt(max int) int {
 	//rand.Seed(time.Now().UnixNano())
 	return rand.Intn(max)
@@ -194,56 +183,7 @@ func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }
 
-func String2Int(str string) int {
-	num, err := strconv.Atoi(str)
-	if err != nil {
-		return 0
-	}
-	return num
-}
-
-func StringsContains(strs []string, str string) bool {
-	for _, s := range strs {
-		if s == str {
-			return true
-		}
-	}
-	return false
-}
-
-// StringToByteSlice []byte only read, panic on append
-func StringToByteSlice(s string) []byte {
-	tmp1 := (*[2]uintptr)(unsafe.Pointer(&s))
-	tmp2 := [3]uintptr{tmp1[0], tmp1[1], tmp1[1]}
-	return *(*[]byte)(unsafe.Pointer(&tmp2))
-}
-
 func RandomSleep() {
 	// Sleep for 0-3000 ms
 	time.Sleep(time.Duration(rand.Intn(3000)) * time.Millisecond)
 }
-
-func MapToJsonStr(m map[string]interface{}) string {
-	bytes, err := json.Marshal(m)
-	if err != nil {
-		return ""
-	}
-	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)
-	if err != nil {
-		return nil
-	}
-	return m
-}

constant/env.go

@@ -1,7 +1,10 @@
 package constant
 
 import (
+	"fmt"
 	"one-api/common"
+	"os"
+	"strings"
 )
 
 var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
@@ -9,3 +12,35 @@ var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)
 
 // ForceStreamOption 覆盖请求参数，强制返回usage信息
 var ForceStreamOption = common.GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)
+
+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-flash-latest": "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))
+		}
+	}
+}

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

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"io"
 	"math"
 	"net/http"
@@ -85,7 +86,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 	meta.UpstreamModelName = testModel
 	common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
 
-	adaptor.Init(meta, *request)
+	adaptor.Init(meta)
 
 	convertedRequest, err := adaptor.ConvertRequest(c, meta, request)
 	if err != nil {
@@ -102,7 +103,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 		return err, nil
 	}
 	if resp != nil && resp.StatusCode != http.StatusOK {
-		err := relaycommon.RelayErrorHandler(resp)
+		err := service.RelayErrorHandler(resp)
 		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), err
 	}
 	usage, respErr := adaptor.DoResponse(c, resp, meta)
@@ -217,7 +218,7 @@ func testAllChannels(notify bool) error {
 	if disableThreshold == 0 {
 		disableThreshold = 10000000 // a impossible value
 	}
-	go func() {
+	gopool.Go(func() {
 		for _, channel := range channels {
 			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
@@ -239,7 +240,7 @@ func testAllChannels(notify bool) error {
 			}
 
 			// parse *int to bool
-			if channel.AutoBan != nil && *channel.AutoBan == 0 {
+			if !channel.GetAutoBan() {
 				ban = false
 			}
 
@@ -265,7 +266,7 @@ func testAllChannels(notify bool) error {
 				common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
 			}
 		}
-	}()
+	})
 	return nil
 }
 

controller/midjourney.go

@@ -146,28 +146,26 @@ func UpdateMidjourneyTaskBulk() {
 					buttonStr, _ := json.Marshal(responseItem.Buttons)
 					task.Buttons = string(buttonStr)
 				}
-
+				shouldReturnQuota := false
 				if (task.Progress != "100%" && responseItem.FailReason != "") || (task.Progress == "100%" && task.Status == "FAILURE") {
 					common.LogInfo(ctx, task.MjId+" 构建失败，"+task.FailReason)
 					task.Progress = "100%"
-					err = model.CacheUpdateUserQuota(task.UserId)
-					if err != nil {
-						common.LogError(ctx, "error update user quota cache: "+err.Error())
-					} else {
-						quota := task.Quota
-						if quota != 0 {
-							err = model.IncreaseUserQuota(task.UserId, quota)
-							if err != nil {
-								common.LogError(ctx, "fail to increase user quota: "+err.Error())
-							}
-							logContent := fmt.Sprintf("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(quota))
-							model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
-						}
+					if task.Quota != 0 {
+						shouldReturnQuota = true
 					}
 				}
 				err = task.Update()
 				if err != nil {
 					common.LogError(ctx, "UpdateMidjourneyTask task error: "+err.Error())
+				} else {
+					if shouldReturnQuota {
+						err = model.IncreaseUserQuota(task.UserId, task.Quota)
+						if err != nil {
+							common.LogError(ctx, "fail to increase user quota: "+err.Error())
+						}
+						logContent := fmt.Sprintf("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(task.Quota))
+						model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+					}
 				}
 			}
 		}

controller/model.go

@@ -131,7 +131,7 @@ func init() {
 		}
 		meta := &relaycommon.RelayInfo{ChannelType: i}
 		adaptor := relay.GetAdaptor(apiType)
-		adaptor.Init(meta, dto.GeneralOpenAIRequest{})
+		adaptor.Init(meta)
 		channelId2Models[i] = adaptor.GetModelList()
 	}
 }

controller/relay.go

@@ -2,6 +2,7 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -22,13 +23,13 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	var err *dto.OpenAIErrorWithStatusCode
 	switch relayMode {
 	case relayconstant.RelayModeImagesGenerations:
-		err = relay.RelayImageHelper(c, relayMode)
+		err = relay.ImageHelper(c, relayMode)
 	case relayconstant.RelayModeAudioSpeech:
 		fallthrough
 	case relayconstant.RelayModeAudioTranslation:
 		fallthrough
 	case relayconstant.RelayModeAudioTranscription:
-		err = relay.AudioHelper(c, relayMode)
+		err = relay.AudioHelper(c)
 	case relayconstant.RelayModeRerank:
 		err = relay.RerankHelper(c, relayMode)
 	default:
@@ -39,43 +40,35 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 
 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 {
@@ -89,7 +82,42 @@ func Relay(c *gin.Context) {
 	}
 }
 
-func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
+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 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
 	}
@@ -113,6 +141,10 @@ 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 {
@@ -128,11 +160,11 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 	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 +240,14 @@ 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 +257,7 @@ 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/topup.go

@@ -94,6 +94,7 @@ 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 +102,8 @@ 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 +121,7 @@ func RequestEpay(c *gin.Context) {
 		UserId:     id,
 		Amount:     amount,
 		Money:      payMoney,
-		TradeNo:    "A" + tradeNo,
+		TradeNo:    tradeNo,
 		CreateTime: time.Now().Unix(),
 		Status:     "pending",
 	}

controller/user.go

@@ -791,11 +791,11 @@ 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 {

dto/audio.go

@@ -1,13 +1,34 @@
 package dto
 
-type TextToSpeechRequest struct {
-	Model          string  `json:"model" binding:"required"`
-	Input          string  `json:"input" binding:"required"`
-	Voice          string  `json:"voice" binding:"required"`
-	Speed          float64 `json:"speed"`
-	ResponseFormat string  `json:"response_format"`
+type AudioRequest struct {
+	Model          string  `json:"model"`
+	Input          string  `json:"input"`
+	Voice          string  `json:"voice"`
+	Speed          float64 `json:"speed,omitempty"`
+	ResponseFormat string  `json:"response_format,omitempty"`
 }
 
 type AudioResponse struct {
 	Text string `json:"text"`
 }
+
+type WhisperVerboseJSONResponse struct {
+	Task     string    `json:"task,omitempty"`
+	Language string    `json:"language,omitempty"`
+	Duration float64   `json:"duration,omitempty"`
+	Text     string    `json:"text,omitempty"`
+	Segments []Segment `json:"segments,omitempty"`
+}
+
+type Segment struct {
+	Id               int     `json:"id"`
+	Seek             int     `json:"seek"`
+	Start            float64 `json:"start"`
+	End              float64 `json:"end"`
+	Text             string  `json:"text"`
+	Tokens           []int   `json:"tokens"`
+	Temperature      float64 `json:"temperature"`
+	AvgLogprob       float64 `json:"avg_logprob"`
+	CompressionRatio float64 `json:"compression_ratio"`
+	NoSpeechProb     float64 `json:"no_speech_prob"`
+}

dto/dalle.go

@@ -12,9 +12,11 @@ type ImageRequest struct {
 }
 
 type ImageResponse struct {
-	Created int `json:"created"`
-	Data    []struct {
-		Url     string `json:"url"`
-		B64Json string `json:"b64_json"`
-	}
+	Data    []ImageData `json:"data"`
+	Created int64       `json:"created"`
+}
+type ImageData struct {
+	Url           string `json:"url"`
+	B64Json       string `json:"b64_json"`
+	RevisedPrompt string `json:"revised_prompt"`
 }

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/text_request.go

@@ -26,11 +26,12 @@ type GeneralOpenAIRequest struct {
 	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
 	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
 	Seed             float64         `json:"seed,omitempty"`
-	Tools            any             `json:"tools,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"`
 }
 
 type OpenAITools struct {
@@ -103,6 +104,11 @@ func (m Message) StringContent() string {
 	return string(m.Content)
 }
 
+func (m *Message) SetStringContent(content string) {
+	jsonContent, _ := json.Marshal(content)
+	m.Content = jsonContent
+}
+
 func (m Message) IsStringContent() bool {
 	var stringContent string
 	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
@@ -142,7 +148,7 @@ func (m Message) ParseContent() []MediaMessage {
 					if ok {
 						subObj["detail"] = detail.(string)
 					} else {
-						subObj["detail"] = "auto"
+						subObj["detail"] = "high"
 					}
 					contentList = append(contentList, MediaMessage{
 						Type: ContentTypeImageURL,
@@ -151,7 +157,16 @@ func (m Message) ParseContent() []MediaMessage {
 							Detail: subObj["detail"].(string),
 						},
 					})
+				} else if url, ok := contentMap["image_url"].(string); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeImageURL,
+						ImageUrl: MessageImageUrl{
+							Url:    url,
+							Detail: "high",
+						},
+					})
 				}
+
 			}
 		}
 		return contentList

dto/text_response.go

@@ -86,9 +86,11 @@ type ToolCall struct {
 }
 
 type FunctionCall struct {
-	Name string `json:"name,omitempty"`
+	Description string `json:"description,omitempty"`
+	Name        string `json:"name,omitempty"`
 	// call function with arguments in JSON format
-	Arguments string `json:"arguments,omitempty"`
+	Parameters any    `json:"parameters,omitempty"` // request
+	Arguments  string `json:"arguments,omitempty"`
 }
 
 type ChatCompletionsStreamResponse struct {

go.mod

@@ -38,6 +38,7 @@ 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/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect

go.sum

@@ -18,6 +18,8 @@ github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4 h1:JgHnonzbnA3pbqj76w
 github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4/go.mod h1:nZspkhg+9p8iApLFoyAqfyuMP0F38acy2Hm3r5r95Cg=
 github.com/aws/smithy-go v1.20.2 h1:tbp628ireGtzcHDDmLT/6ADHidqnwgF57XOXZe6tp4Q=
 github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC3qS14E=
+github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b h1:LTGVFpNmNHhj0vhOlfgWueFJ32eK9blaIlHR2ciXOT0=
+github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaUH4+NXIBF0aMdKKAnHTzqH+iMU4KUjAbL23Q=
 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=
@@ -198,6 +200,7 @@ 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/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/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -206,6 +209,7 @@ golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220110181412-a018aaa089fe/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

main.go

@@ -3,12 +3,14 @@ package main
 import (
 	"embed"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
 	"log"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/controller"
 	"one-api/middleware"
 	"one-api/model"
@@ -53,6 +55,8 @@ func main() {
 		common.FatalLog("failed to initialize Redis: " + err.Error())
 	}
 
+	// Initialize constants
+	constant.InitEnv()
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {
@@ -89,11 +93,11 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
-	if common.IsMasterNode {
-		common.SafeGoroutine(func() {
+	if common.IsMasterNode && constant.UpdateTask {
+		gopool.Go(func() {
 			controller.UpdateMidjourneyTaskBulk()
 		})
-		common.SafeGoroutine(func() {
+		gopool.Go(func() {
 			controller.UpdateTaskBulk()
 		})
 	}

middleware/auth.go

@@ -6,6 +6,7 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strconv"
 	"strings"
 )
 
@@ -15,6 +16,7 @@ func authHelper(c *gin.Context, minRole int) {
 	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")
@@ -33,6 +35,7 @@ func authHelper(c *gin.Context, minRole int) {
 			role = user.Role
 			id = user.Id
 			status = user.Status
+			useAccessToken = true
 		} else {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -42,6 +45,36 @@ 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,

middleware/distributor.go

@@ -1,6 +1,7 @@
 package middleware
 
 import (
+	"errors"
 	"fmt"
 	"net/http"
 	"one-api/common"
@@ -25,6 +26,10 @@ func Distribute() func(c *gin.Context) {
 		var channel *model.Channel
 		channelId, ok := c.Get("specific_channel_id")
 		modelRequest, shouldSelectChannel, err := getModelRequest(c)
+		if err != nil {
+			abortWithOpenAiMessage(c, http.StatusBadRequest, "Invalid request, "+err.Error())
+			return
+		}
 		userGroup, _ := model.CacheGetUserGroup(userId)
 		c.Set("group", userGroup)
 		if ok {
@@ -141,7 +146,7 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 	}
 	if err != nil {
 		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
-		return nil, false, err
+		return nil, false, errors.New("无效的请求, " + err.Error())
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
 		if modelRequest.Model == "" {
@@ -154,18 +159,22 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		}
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
-		if modelRequest.Model == "" {
-			modelRequest.Model = "dall-e"
-		}
+		modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "dall-e")
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
-		if modelRequest.Model == "" {
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
-				modelRequest.Model = "tts-1"
-			} else {
-				modelRequest.Model = "whisper-1"
-			}
+		relayMode := relayconstant.RelayModeAudioSpeech
+		if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "tts-1")
+		} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/translations") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, c.PostForm("model"))
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "whisper-1")
+			relayMode = relayconstant.RelayModeAudioTranslation
+		} else if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, c.PostForm("model"))
+			modelRequest.Model = common.GetStringIfEmpty(modelRequest.Model, "whisper-1")
+			relayMode = relayconstant.RelayModeAudioTranscription
 		}
+		c.Set("relay_mode", relayMode)
 	}
 	return &modelRequest, shouldSelectChannel, nil
 }
@@ -175,19 +184,13 @@ 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))

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/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
 }
@@ -100,8 +107,8 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	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+"%")
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " = ? AND " + modelsCol + " LIKE ?"
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, group, "%"+model+"%")
 	} else {
 		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
 		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")

model/log.go

@@ -3,9 +3,11 @@ package model
 import (
 	"context"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+	"time"
 )
 
 type Log struct {
@@ -87,7 +89,7 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		common.LogError(ctx, "failed to record log: "+err.Error())
 	}
 	if common.DataExportEnabled {
-		common.SafeGoroutine(func() {
+		gopool.Go(func() {
 			LogQuotaData(userId, username, modelName, quota, common.GetTimestamp(), promptTokens+completionTokens)
 		})
 	}
@@ -101,7 +103,7 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 		tx = 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)
@@ -130,7 +132,7 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		tx = 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)
@@ -171,12 +173,18 @@ 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 := DB.Table("logs").Select("sum(quota) quota")
+
+	// 为rpm和tpm创建单独的查询
+	rpmTpmQuery := 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)
@@ -186,11 +194,23 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	}
 	if modelName != "" {
 		tx = tx.Where("model_name = ?", modelName)
+		rpmTpmQuery = rpmTpmQuery.Where("model_name = ?", 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
 }
 

model/utils.go

@@ -2,6 +2,7 @@ package model
 
 import (
 	"errors"
+	"github.com/bytedance/gopkg/util/gopool"
 	"gorm.io/gorm"
 	"one-api/common"
 	"sync"
@@ -28,12 +29,12 @@ func init() {
 }
 
 func InitBatchUpdater() {
-	go func() {
+	gopool.Go(func() {
 		for {
 			time.Sleep(time.Duration(common.BatchUpdateInterval) * time.Second)
 			batchUpdate()
 		}
-	}()
+	})
 }
 
 func addNewRecord(type_ int, id int, value int) {

relay/channel/adapter.go

@@ -10,12 +10,13 @@ import (
 
 type Adaptor interface {
 	// Init IsStream bool
-	Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest)
-	InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest)
+	Init(info *relaycommon.RelayInfo)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
 	SetupRequestHeader(c *gin.Context, req *http.Request, 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)
 	GetModelList() []string

relay/channel/ali/adaptor.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
 )
@@ -15,17 +16,18 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
-}
-
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
-
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	fullRequestURL := fmt.Sprintf("%s/api/v1/services/aigc/text-generation/generation", info.BaseUrl)
-	if info.RelayMode == constant.RelayModeEmbeddings {
+	var fullRequestURL string
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
 		fullRequestURL = fmt.Sprintf("%s/api/v1/services/embeddings/text-embedding/text-embedding", info.BaseUrl)
+	case constant.RelayModeImagesGenerations:
+		fullRequestURL = fmt.Sprintf("%s/api/v1/services/aigc/text2image/image-synthesis", info.BaseUrl)
+	default:
+		fullRequestURL = fmt.Sprintf("%s/compatible-mode/v1/chat/completions", info.BaseUrl)
 	}
 	return fullRequestURL, nil
 }
@@ -51,13 +53,23 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
 		return baiduEmbeddingRequest, nil
 	default:
-		baiduRequest := requestOpenAI2Ali(*request)
-		return baiduRequest, nil
+		aliReq := requestOpenAI2Ali(*request)
+		return aliReq, nil
 	}
 }
 
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	aliRequest := oaiImage2Ali(request)
+	return aliRequest, nil
+}
+
 func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
-	return nil, nil
+	return nil, errors.New("not implemented")
+}
+
+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) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
@@ -65,14 +77,16 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = aliStreamHandler(c, resp)
-	} else {
-		switch info.RelayMode {
-		case constant.RelayModeEmbeddings:
-			err, usage = aliEmbeddingHandler(c, resp)
-		default:
-			err, usage = aliHandler(c, resp)
+	switch info.RelayMode {
+	case constant.RelayModeImagesGenerations:
+		err, usage = aliImageHandler(c, resp, info)
+	case constant.RelayModeEmbeddings:
+		err, usage = aliEmbeddingHandler(c, resp)
+	default:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 		}
 	}
 	return

relay/channel/ali/dto.go

@@ -60,13 +60,40 @@ type AliUsage struct {
 	TotalTokens  int `json:"total_tokens"`
 }
 
-type AliOutput struct {
-	Text         string `json:"text"`
-	FinishReason string `json:"finish_reason"`
+type TaskResult struct {
+	B64Image string `json:"b64_image,omitempty"`
+	Url      string `json:"url,omitempty"`
+	Code     string `json:"code,omitempty"`
+	Message  string `json:"message,omitempty"`
 }
 
-type AliChatResponse struct {
+type AliOutput struct {
+	TaskId       string       `json:"task_id,omitempty"`
+	TaskStatus   string       `json:"task_status,omitempty"`
+	Text         string       `json:"text"`
+	FinishReason string       `json:"finish_reason"`
+	Message      string       `json:"message,omitempty"`
+	Code         string       `json:"code,omitempty"`
+	Results      []TaskResult `json:"results,omitempty"`
+}
+
+type AliResponse struct {
 	Output AliOutput `json:"output"`
 	Usage  AliUsage  `json:"usage"`
 	AliError
 }
+
+type AliImageRequest struct {
+	Model string `json:"model"`
+	Input struct {
+		Prompt         string `json:"prompt"`
+		NegativePrompt string `json:"negative_prompt,omitempty"`
+	} `json:"input"`
+	Parameters struct {
+		Size  string `json:"size,omitempty"`
+		N     int    `json:"n,omitempty"`
+		Steps string `json:"steps,omitempty"`
+		Scale string `json:"scale,omitempty"`
+	} `json:"parameters,omitempty"`
+	ResponseFormat string `json:"response_format,omitempty"`
+}

relay/channel/ali/image.go

@@ -0,0 +1,177 @@
+package ali
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+func oaiImage2Ali(request dto.ImageRequest) *AliImageRequest {
+	var imageRequest AliImageRequest
+	imageRequest.Input.Prompt = request.Prompt
+	imageRequest.Model = request.Model
+	imageRequest.Parameters.Size = strings.Replace(request.Size, "x", "*", -1)
+	imageRequest.Parameters.N = request.N
+	imageRequest.ResponseFormat = request.ResponseFormat
+
+	return &imageRequest
+}
+
+func updateTask(info *relaycommon.RelayInfo, taskID string, key string) (*AliResponse, error, []byte) {
+	url := fmt.Sprintf("/api/v1/tasks/%s", taskID)
+
+	var aliResponse AliResponse
+
+	req, err := http.NewRequest("GET", url, nil)
+	if err != nil {
+		return &aliResponse, err, nil
+	}
+
+	req.Header.Set("Authorization", "Bearer "+key)
+
+	client := &http.Client{}
+	resp, err := client.Do(req)
+	if err != nil {
+		common.SysError("updateTask client.Do err: " + err.Error())
+		return &aliResponse, err, nil
+	}
+	defer resp.Body.Close()
+
+	responseBody, err := io.ReadAll(resp.Body)
+
+	var response AliResponse
+	err = json.Unmarshal(responseBody, &response)
+	if err != nil {
+		common.SysError("updateTask NewDecoder err: " + err.Error())
+		return &aliResponse, err, nil
+	}
+
+	return &response, nil, responseBody
+}
+
+func asyncTaskWait(info *relaycommon.RelayInfo, taskID string, key string) (*AliResponse, []byte, error) {
+	waitSeconds := 3
+	step := 0
+	maxStep := 20
+
+	var taskResponse AliResponse
+	var responseBody []byte
+
+	for {
+		step++
+		rsp, err, body := updateTask(info, taskID, key)
+		responseBody = body
+		if err != nil {
+			return &taskResponse, responseBody, err
+		}
+
+		if rsp.Output.TaskStatus == "" {
+			return &taskResponse, responseBody, nil
+		}
+
+		switch rsp.Output.TaskStatus {
+		case "FAILED":
+			fallthrough
+		case "CANCELED":
+			fallthrough
+		case "SUCCEEDED":
+			fallthrough
+		case "UNKNOWN":
+			return rsp, responseBody, nil
+		}
+		if step >= maxStep {
+			break
+		}
+		time.Sleep(time.Duration(waitSeconds) * time.Second)
+	}
+
+	return nil, nil, fmt.Errorf("aliAsyncTaskWait timeout")
+}
+
+func responseAli2OpenAIImage(c *gin.Context, response *AliResponse, info *relaycommon.RelayInfo, responseFormat string) *dto.ImageResponse {
+	imageResponse := dto.ImageResponse{
+		Created: info.StartTime.Unix(),
+	}
+
+	for _, data := range response.Output.Results {
+		var b64Json string
+		if responseFormat == "b64_json" {
+			_, b64, err := service.GetImageFromUrl(data.Url)
+			if err != nil {
+				common.LogError(c, "get_image_data_failed: "+err.Error())
+				continue
+			}
+			b64Json = b64
+		} else {
+			b64Json = data.B64Image
+		}
+
+		imageResponse.Data = append(imageResponse.Data, dto.ImageData{
+			Url:           data.Url,
+			B64Json:       b64Json,
+			RevisedPrompt: "",
+		})
+	}
+	return &imageResponse
+}
+
+func aliImageHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	apiKey := c.Request.Header.Get("Authorization")
+	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+	responseFormat := c.GetString("response_format")
+
+	var aliTaskResponse AliResponse
+	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
+	}
+	err = json.Unmarshal(responseBody, &aliTaskResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	if aliTaskResponse.Message != "" {
+		common.LogError(c, "ali_async_task_failed: "+aliTaskResponse.Message)
+		return service.OpenAIErrorWrapper(errors.New(aliTaskResponse.Message), "ali_async_task_failed", http.StatusInternalServerError), nil
+	}
+
+	aliResponse, _, err := asyncTaskWait(info, aliTaskResponse.Output.TaskId, apiKey)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "ali_async_task_wait_failed", http.StatusInternalServerError), nil
+	}
+
+	if aliResponse.Output.TaskStatus != "SUCCEEDED" {
+		return &dto.OpenAIErrorWithStatusCode{
+			Error: dto.OpenAIError{
+				Message: aliResponse.Output.Message,
+				Type:    "ali_error",
+				Param:   "",
+				Code:    aliResponse.Output.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+
+	fullTextResponse := responseAli2OpenAIImage(c, aliResponse, info, responseFormat)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	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, nil
+}

relay/channel/ali/text.go

@@ -16,34 +16,13 @@ import (
 
 const EnableSearchModelSuffix = "-internet"
 
-func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliChatRequest {
-	messages := make([]AliMessage, 0, len(request.Messages))
-	//prompt := ""
-	for i := 0; i < len(request.Messages); i++ {
-		message := request.Messages[i]
-		messages = append(messages, AliMessage{
-			Content: message.StringContent(),
-			Role:    strings.ToLower(message.Role),
-		})
-	}
-	enableSearch := false
-	aliModel := request.Model
-	if strings.HasSuffix(aliModel, EnableSearchModelSuffix) {
-		enableSearch = true
-		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
-	}
-	return &AliChatRequest{
-		Model: request.Model,
-		Input: AliInput{
-			//Prompt:  prompt,
-			Messages: messages,
-		},
-		Parameters: AliParameters{
-			IncrementalOutput: request.Stream,
-			Seed:              uint64(request.Seed),
-			EnableSearch:      enableSearch,
-		},
+func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIRequest {
+	if request.TopP >= 1 {
+		request.TopP = 0.999
+	} else if request.TopP <= 0 {
+		request.TopP = 0.001
 	}
+	return &request
 }
 
 func embeddingRequestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliEmbeddingRequest {
@@ -110,7 +89,7 @@ func embeddingResponseAli2OpenAI(response *AliEmbeddingResponse) *dto.OpenAIEmbe
 	return &openAIEmbeddingResponse
 }
 
-func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
+func responseAli2OpenAI(response *AliResponse) *dto.OpenAITextResponse {
 	content, _ := json.Marshal(response.Output.Text)
 	choice := dto.OpenAITextResponseChoice{
 		Index: 0,
@@ -134,7 +113,7 @@ func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
 	return &fullTextResponse
 }
 
-func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *dto.ChatCompletionsStreamResponse {
+func streamResponseAli2OpenAI(aliResponse *AliResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
 	choice.Delta.SetContentString(aliResponse.Output.Text)
 	if aliResponse.Output.FinishReason != "null" {
@@ -154,18 +133,7 @@ func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *dto.ChatCompletions
 func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var usage dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
+	scanner.Split(bufio.ScanLines)
 	dataChan := make(chan string)
 	stopChan := make(chan bool)
 	go func() {
@@ -187,7 +155,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWith
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
-			var aliResponse AliChatResponse
+			var aliResponse AliResponse
 			err := json.Unmarshal([]byte(data), &aliResponse)
 			if err != nil {
 				common.SysError("error unmarshalling stream response: " + err.Error())
@@ -221,7 +189,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWith
 }
 
 func aliHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
-	var aliResponse AliChatResponse
+	var aliResponse AliResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil

relay/channel/api_request.go

@@ -7,14 +7,19 @@ import (
 	"io"
 	"net/http"
 	"one-api/relay/common"
+	"one-api/relay/constant"
 	"one-api/service"
 )
 
 func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Request) {
-	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
-	if info.IsStream && c.Request.Header.Get("Accept") == "" {
-		req.Header.Set("Accept", "text/event-stream")
+	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
+		// multipart/form-data
+	} else {
+		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		if info.IsStream && c.Request.Header.Get("Accept") == "" {
+			req.Header.Set("Accept", "text/event-stream")
+		}
 	}
 }
 
@@ -38,6 +43,29 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	return resp, nil
 }
 
+func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.GetRequestURL(info)
+	if err != nil {
+		return nil, fmt.Errorf("get request url failed: %w", err)
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	// set form data
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+
+	err = a.SetupRequestHeader(c, req, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := doRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, 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

@@ -20,12 +20,17 @@ type Adaptor struct {
 	RequestMode int
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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-3") {
 		a.RequestMode = RequestModeMessage
 	} else {

relay/channel/aws/relay-aws.go

@@ -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

@@ -16,12 +16,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {
 
 }
 

relay/channel/claude/adaptor.go

@@ -21,12 +21,17 @@ type Adaptor struct {
 	RequestMode int
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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-3") {
 		a.RequestMode = RequestModeMessage
 	} else {

relay/channel/claude/dto.go

@@ -5,11 +5,18 @@ type ClaudeMetadata struct {
 }
 
 type ClaudeMediaMessage struct {
-	Type       string               `json:"type"`
-	Text       string               `json:"text,omitempty"`
-	Source     *ClaudeMessageSource `json:"source,omitempty"`
-	Usage      *ClaudeUsage         `json:"usage,omitempty"`
-	StopReason *string              `json:"stop_reason,omitempty"`
+	Type        string               `json:"type"`
+	Text        string               `json:"text,omitempty"`
+	Source      *ClaudeMessageSource `json:"source,omitempty"`
+	Usage       *ClaudeUsage         `json:"usage,omitempty"`
+	StopReason  *string              `json:"stop_reason,omitempty"`
+	PartialJson string               `json:"partial_json,omitempty"`
+	// tool_calls
+	Id        string `json:"id,omitempty"`
+	Name      string `json:"name,omitempty"`
+	Input     any    `json:"input,omitempty"`
+	Content   string `json:"content,omitempty"`
+	ToolUseId string `json:"tool_use_id,omitempty"`
 }
 
 type ClaudeMessageSource struct {
@@ -23,6 +30,18 @@ type ClaudeMessage struct {
 	Content any    `json:"content"`
 }
 
+type Tool struct {
+	Name        string      `json:"name"`
+	Description string      `json:"description,omitempty"`
+	InputSchema InputSchema `json:"input_schema"`
+}
+
+type InputSchema struct {
+	Type       string `json:"type"`
+	Properties any    `json:"properties,omitempty"`
+	Required   any    `json:"required,omitempty"`
+}
+
 type ClaudeRequest struct {
 	Model             string          `json:"model"`
 	Prompt            string          `json:"prompt,omitempty"`
@@ -35,7 +54,9 @@ type ClaudeRequest struct {
 	TopP              float64         `json:"top_p,omitempty"`
 	TopK              int             `json:"top_k,omitempty"`
 	//ClaudeMetadata    `json:"metadata,omitempty"`
-	Stream bool `json:"stream,omitempty"`
+	Stream     bool   `json:"stream,omitempty"`
+	Tools      []Tool `json:"tools,omitempty"`
+	ToolChoice any    `json:"tool_choice,omitempty"`
 }
 
 type ClaudeError struct {
@@ -44,24 +65,20 @@ type ClaudeError struct {
 }
 
 type ClaudeResponse struct {
-	Id         string               `json:"id"`
-	Type       string               `json:"type"`
-	Content    []ClaudeMediaMessage `json:"content"`
-	Completion string               `json:"completion"`
-	StopReason string               `json:"stop_reason"`
-	Model      string               `json:"model"`
-	Error      ClaudeError          `json:"error"`
-	Usage      ClaudeUsage          `json:"usage"`
-	Index      int                  `json:"index"`   // stream only
-	Delta      *ClaudeMediaMessage  `json:"delta"`   // stream only
-	Message    *ClaudeResponse      `json:"message"` // stream only: message_start
+	Id           string               `json:"id"`
+	Type         string               `json:"type"`
+	Content      []ClaudeMediaMessage `json:"content"`
+	Completion   string               `json:"completion"`
+	StopReason   string               `json:"stop_reason"`
+	Model        string               `json:"model"`
+	Error        ClaudeError          `json:"error"`
+	Usage        ClaudeUsage          `json:"usage"`
+	Index        int                  `json:"index"` // stream only
+	ContentBlock *ClaudeMediaMessage  `json:"content_block"`
+	Delta        *ClaudeMediaMessage  `json:"delta"`   // stream only
+	Message      *ClaudeResponse      `json:"message"` // stream only: message_start
 }
 
-//type ClaudeResponseChoice struct {
-//	Index   int                `json:"index"`
-//	Type    string             `json:"type"`
-//}
-
 type ClaudeUsage struct {
 	InputTokens  int `json:"input_tokens"`
 	OutputTokens int `json:"output_tokens"`

relay/channel/claude/relay-claude.go

@@ -8,12 +8,10 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
-	"one-api/constant"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
-	"time"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -30,6 +28,7 @@ func stopReasonClaude2OpenAI(reason string) string {
 }
 
 func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
+
 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
 		Prompt:        "",
@@ -60,6 +59,22 @@ func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeR
 }
 
 func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
+	claudeTools := make([]Tool, 0, len(textRequest.Tools))
+
+	for _, tool := range textRequest.Tools {
+		if params, ok := tool.Function.Parameters.(map[string]any); ok {
+			claudeTools = append(claudeTools, Tool{
+				Name:        tool.Function.Name,
+				Description: tool.Function.Description,
+				InputSchema: InputSchema{
+					Type:       params["type"].(string),
+					Properties: params["properties"],
+					Required:   params["required"],
+				},
+			})
+		}
+	}
+
 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
 		MaxTokens:     textRequest.MaxTokens,
@@ -68,6 +83,7 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 		TopP:          textRequest.TopP,
 		TopK:          textRequest.TopK,
 		Stream:        textRequest.Stream,
+		Tools:         claudeTools,
 	}
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
@@ -184,6 +200,7 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 	response.Object = "chat.completion.chunk"
 	response.Model = claudeResponse.Model
 	response.Choices = make([]dto.ChatCompletionsStreamResponseChoice, 0)
+	tools := make([]dto.ToolCall, 0)
 	var choice dto.ChatCompletionsStreamResponseChoice
 	if reqMode == RequestModeCompletion {
 		choice.Delta.SetContentString(claudeResponse.Completion)
@@ -199,10 +216,33 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 			choice.Delta.SetContentString("")
 			choice.Delta.Role = "assistant"
 		} else if claudeResponse.Type == "content_block_start" {
-			return nil, nil
+			if claudeResponse.ContentBlock != nil {
+				//choice.Delta.SetContentString(claudeResponse.ContentBlock.Text)
+				if claudeResponse.ContentBlock.Type == "tool_use" {
+					tools = append(tools, dto.ToolCall{
+						ID:   claudeResponse.ContentBlock.Id,
+						Type: "function",
+						Function: dto.FunctionCall{
+							Name:      claudeResponse.ContentBlock.Name,
+							Arguments: "",
+						},
+					})
+				}
+			} else {
+				return nil, nil
+			}
 		} else if claudeResponse.Type == "content_block_delta" {
-			choice.Index = claudeResponse.Index
-			choice.Delta.SetContentString(claudeResponse.Delta.Text)
+			if claudeResponse.Delta != nil {
+				choice.Index = claudeResponse.Index
+				choice.Delta.SetContentString(claudeResponse.Delta.Text)
+				if claudeResponse.Delta.Type == "input_json_delta" {
+					tools = append(tools, dto.ToolCall{
+						Function: dto.FunctionCall{
+							Arguments: claudeResponse.Delta.PartialJson,
+						},
+					})
+				}
+			}
 		} else if claudeResponse.Type == "message_delta" {
 			finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
 			if finishReason != "null" {
@@ -218,6 +258,10 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 	if claudeUsage == nil {
 		claudeUsage = &ClaudeUsage{}
 	}
+	if len(tools) > 0 {
+		choice.Delta.Content = nil // compatible with other OpenAI derivative applications, like LobeOpenAICompatibleFactory ...
+		choice.Delta.ToolCalls = tools
+	}
 	response.Choices = append(response.Choices, choice)
 
 	return &response, claudeUsage
@@ -230,6 +274,11 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
 	}
+	var responseText string
+	if len(claudeResponse.Content) > 0 {
+		responseText = claudeResponse.Content[0].Text
+	}
+	tools := make([]dto.ToolCall, 0)
 	if reqMode == RequestModeCompletion {
 		content, _ := json.Marshal(strings.TrimPrefix(claudeResponse.Completion, " "))
 		choice := dto.OpenAITextResponseChoice{
@@ -244,20 +293,32 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 		choices = append(choices, choice)
 	} else {
 		fullTextResponse.Id = claudeResponse.Id
-		for i, message := range claudeResponse.Content {
-			content, _ := json.Marshal(message.Text)
-			choice := dto.OpenAITextResponseChoice{
-				Index: i,
-				Message: dto.Message{
-					Role:    "assistant",
-					Content: content,
-				},
-				FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
+		for _, message := range claudeResponse.Content {
+			if message.Type == "tool_use" {
+				args, _ := json.Marshal(message.Input)
+				tools = append(tools, dto.ToolCall{
+					ID:   message.Id,
+					Type: "function", // compatible with other OpenAI derivative applications
+					Function: dto.FunctionCall{
+						Name:      message.Name,
+						Arguments: string(args),
+					},
+				})
 			}
-			choices = append(choices, choice)
 		}
 	}
-
+	choice := dto.OpenAITextResponseChoice{
+		Index: 0,
+		Message: dto.Message{
+			Role: "assistant",
+		},
+		FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
+	}
+	choice.SetStringContent(responseText)
+	if len(tools) > 0 {
+		choice.Message.ToolCalls = tools
+	}
+	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
 	return &fullTextResponse
 }
@@ -269,89 +330,59 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	responseText := ""
 	createdTime := common.GetTimestamp()
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
+	scanner.Split(bufio.ScanLines)
+	service.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		info.SetFirstResponseTime()
+		if len(data) < 6 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
+		data = strings.TrimPrefix(data, "data:")
+		data = strings.TrimSpace(data)
+		var claudeResponse ClaudeResponse
+		err := json.Unmarshal([]byte(data), &claudeResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
 		}
-		if atEOF {
-			return len(data), data, nil
+
+		response, claudeUsage := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
+		if response == nil {
+			continue
 		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string, 5)
-	stopChan := make(chan bool, 2)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if !strings.HasPrefix(data, "data: ") {
+		if requestMode == RequestModeCompletion {
+			responseText += claudeResponse.Completion
+			responseId = response.Id
+		} else {
+			if claudeResponse.Type == "message_start" {
+				// message_start, 获取usage
+				responseId = claudeResponse.Message.Id
+				info.UpstreamModelName = claudeResponse.Message.Model
+				usage.PromptTokens = claudeUsage.InputTokens
+			} else if claudeResponse.Type == "content_block_delta" {
+				responseText += claudeResponse.Delta.Text
+			} else if claudeResponse.Type == "message_delta" {
+				usage.CompletionTokens = claudeUsage.OutputTokens
+				usage.TotalTokens = claudeUsage.InputTokens + claudeUsage.OutputTokens
+			} else if claudeResponse.Type == "content_block_start" {
+
+			} else {
 				continue
 			}
-			data = strings.TrimPrefix(data, "data: ")
-			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
-				// send data timeout, stop the stream
-				common.LogError(c, "send data timeout, stop the stream")
-				break
-			}
 		}
-		stopChan <- true
-	}()
-	isFirst := true
-	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			if isFirst {
-				isFirst = false
-				info.FirstResponseTime = time.Now()
-			}
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			var claudeResponse ClaudeResponse
-			err := json.Unmarshal([]byte(data), &claudeResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
+		//response.Id = responseId
+		response.Id = responseId
+		response.Created = createdTime
+		response.Model = info.UpstreamModelName
 
-			response, claudeUsage := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
-			if response == nil {
-				return true
-			}
-			if requestMode == RequestModeCompletion {
-				responseText += claudeResponse.Completion
-				responseId = response.Id
-			} else {
-				if claudeResponse.Type == "message_start" {
-					// message_start, 获取usage
-					responseId = claudeResponse.Message.Id
-					info.UpstreamModelName = claudeResponse.Message.Model
-					usage.PromptTokens = claudeUsage.InputTokens
-				} else if claudeResponse.Type == "content_block_delta" {
-					responseText += claudeResponse.Delta.Text
-				} else if claudeResponse.Type == "message_delta" {
-					usage.CompletionTokens = claudeUsage.OutputTokens
-					usage.TotalTokens = claudeUsage.InputTokens + claudeUsage.OutputTokens
-				} else {
-					return true
-				}
-			}
-			//response.Id = responseId
-			response.Id = responseId
-			response.Created = createdTime
-			response.Model = info.UpstreamModelName
-
-			err = service.ObjectData(c, response)
-			if err != nil {
-				common.SysError(err.Error())
-			}
-			return true
-		case <-stopChan:
-			return false
+		err = service.ObjectData(c, response)
+		if err != nil {
+			common.LogError(c, "send_stream_response_failed: "+err.Error())
 		}
-	})
+	}
+
 	if requestMode == RequestModeCompletion {
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
@@ -370,10 +401,7 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 		}
 	}
 	service.Done(c)
-	err := resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
-	}
+	resp.Body.Close()
 	return nil, usage
 }
 

relay/channel/cloudflare/adaptor.go

@@ -1,6 +1,7 @@
 package cloudflare
 
 import (
+	"bytes"
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
@@ -15,10 +16,7 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
-}
-
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
@@ -58,11 +56,42 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	// 添加文件字段
+	file, _, err := c.Request.FormFile("file")
+	if err != nil {
+		return nil, errors.New("file is required")
+	}
+	defer file.Close()
+	// 打开临时文件用于保存上传的文件内容
+	requestBody := &bytes.Buffer{}
+
+	// 将上传的文件内容复制到临时文件
+	if _, err := io.Copy(requestBody, file); err != nil {
+		return nil, err
+	}
+	return requestBody, nil
+}
+
+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) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = cfStreamHandler(c, resp, info)
-	} else {
-		err, usage = cfHandler(c, resp, info)
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		fallthrough
+	case constant.RelayModeChatCompletions:
+		if info.IsStream {
+			err, usage = cfStreamHandler(c, resp, info)
+		} else {
+			err, usage = cfHandler(c, resp, info)
+		}
+	case constant.RelayModeAudioTranslation:
+		fallthrough
+	case constant.RelayModeAudioTranscription:
+		err, usage = cfSTTHandler(c, resp, info)
 	}
 	return
 }

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/dto.go

@@ -11,3 +11,11 @@ type CfRequest struct {
 	Stream      bool          `json:"stream,omitempty"`
 	Temperature float64       `json:"temperature,omitempty"`
 }
+
+type CfAudioResponse struct {
+	Result CfSTTResult `json:"result"`
+}
+
+type CfSTTResult struct {
+	Text string `json:"text"`
+}

relay/channel/cloudflare/relay_cloudflare.go

@@ -119,3 +119,38 @@ func cfHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo)
 	_, _ = c.Writer.Write(jsonResponse)
 	return nil, usage
 }
+
+func cfSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var cfResp CfAudioResponse
+	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
+	}
+	err = json.Unmarshal(responseBody, &cfResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	audioResp := &dto.AudioResponse{
+		Text: cfResp.Result.Text,
+	}
+
+	jsonResponse, err := json.Marshal(audioResp)
+	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)
+	_, _ = c.Writer.Write(jsonResponse)
+
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.CompletionTokens, _ = service.CountTokenText(cfResp.Result.Text, info.UpstreamModelName)
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+
+	return nil, usage
+}

relay/channel/cohere/adaptor.go

@@ -1,6 +1,7 @@
 package cohere
 
 import (
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -14,10 +15,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

relay/channel/dify/adaptor.go

@@ -14,12 +14,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

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)

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"
@@ -14,22 +15,23 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
 }
 
-// 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) Init(info *relaycommon.RelayInfo) {
+
 }
 
 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
@@ -40,7 +42,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 
 	action := "generateContent"
 	if info.IsStream {
-		action = "streamGenerateContent"
+		action = "streamGenerateContent?alt=sse"
 	}
 	return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
 }

relay/channel/gemini/dto.go

@@ -12,9 +12,15 @@ type GeminiInlineData struct {
 	Data     string `json:"data"`
 }
 
+type FunctionCall struct {
+	FunctionName string `json:"name"`
+	Arguments    any    `json:"args"`
+}
+
 type GeminiPart struct {
-	Text       string            `json:"text,omitempty"`
-	InlineData *GeminiInlineData `json:"inlineData,omitempty"`
+	Text         string            `json:"text,omitempty"`
+	InlineData   *GeminiInlineData `json:"inlineData,omitempty"`
+	FunctionCall *FunctionCall     `json:"functionCall,omitempty"`
 }
 
 type GeminiChatContent struct {

relay/channel/gemini/relay-gemini.go

@@ -4,18 +4,14 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"io"
-	"log"
 	"net/http"
 	"one-api/common"
-	"one-api/constant"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
-	"time"
-
-	"github.com/gin-gonic/gin"
 )
 
 // Setting safety to the lowest possible values since Gemini is already powerless enough
@@ -46,7 +42,17 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 			MaxOutputTokens: textRequest.MaxTokens,
 		},
 	}
-	if textRequest.Functions != nil {
+	if textRequest.Tools != nil {
+		functions := make([]dto.FunctionCall, 0, len(textRequest.Tools))
+		for _, tool := range textRequest.Tools {
+			functions = append(functions, tool.Function)
+		}
+		geminiRequest.Tools = []GeminiChatTools{
+			{
+				FunctionDeclarations: functions,
+			},
+		}
+	} else if textRequest.Functions != nil {
 		geminiRequest.Tools = []GeminiChatTools{
 			{
 				FunctionDeclarations: textRequest.Functions,
@@ -77,13 +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
@@ -126,6 +147,30 @@ func (g *GeminiChatResponse) GetResponseText() string {
 	return ""
 }
 
+func getToolCalls(candidate *GeminiChatCandidate) []dto.ToolCall {
+	var toolCalls []dto.ToolCall
+
+	item := candidate.Content.Parts[0]
+	if item.FunctionCall == nil {
+		return toolCalls
+	}
+	argsBytes, err := json.Marshal(item.FunctionCall.Arguments)
+	if err != nil {
+		//common.SysError("getToolCalls failed: " + err.Error())
+		return toolCalls
+	}
+	toolCall := dto.ToolCall{
+		ID:   fmt.Sprintf("call_%s", common.GetUUID()),
+		Type: "function",
+		Function: dto.FunctionCall{
+			Arguments: string(argsBytes),
+			Name:      item.FunctionCall.FunctionName,
+		},
+	}
+	toolCalls = append(toolCalls, toolCall)
+	return toolCalls
+}
+
 func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResponse {
 	fullTextResponse := dto.OpenAITextResponse{
 		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
@@ -144,8 +189,11 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResp
 			FinishReason: relaycommon.StopFinishReason,
 		}
 		if len(candidate.Content.Parts) > 0 {
-			content, _ = json.Marshal(candidate.Content.Parts[0].Text)
-			choice.Message.Content = content
+			if candidate.Content.Parts[0].FunctionCall != nil {
+				choice.Message.ToolCalls = getToolCalls(&candidate)
+			} else {
+				choice.Message.SetStringContent(candidate.Content.Parts[0].Text)
+			}
 		}
 		fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
 	}
@@ -154,8 +202,17 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResp
 
 func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
-	choice.Delta.SetContentString(geminiResponse.GetResponseText())
-	choice.FinishReason = &relaycommon.StopFinishReason
+	//choice.Delta.SetContentString(geminiResponse.GetResponseText())
+	if len(geminiResponse.Candidates) > 0 && len(geminiResponse.Candidates[0].Content.Parts) > 0 {
+		respFirst := geminiResponse.Candidates[0].Content.Parts[0]
+		if respFirst.FunctionCall != nil {
+			// function response
+			choice.Delta.ToolCalls = getToolCalls(&geminiResponse.Candidates[0])
+		} else {
+			// text response
+			choice.Delta.SetContentString(respFirst.Text)
+		}
+	}
 	var response dto.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = "gemini"
@@ -165,104 +222,60 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 
 func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseText := ""
-	responseJson := ""
 	id := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createAt := common.GetTimestamp()
 	var usage = &dto.Usage{}
-	dataChan := make(chan string, 5)
-	stopChan := make(chan bool, 2)
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			responseJson += data
-			data = strings.TrimSpace(data)
-			if !strings.HasPrefix(data, "\"text\": \"") {
-				continue
-			}
-			data = strings.TrimPrefix(data, "\"text\": \"")
-			data = strings.TrimSuffix(data, "\"")
-			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
-				// send data timeout, stop the stream
-				common.LogError(c, "send data timeout, stop the stream")
-				break
-			}
-		}
-		stopChan <- true
-	}()
-	isFirst := true
+	scanner.Split(bufio.ScanLines)
+
 	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			if isFirst {
-				isFirst = false
-				info.FirstResponseTime = time.Now()
-			}
-			// this is used to prevent annoying \ related format bug
-			data = fmt.Sprintf("{\"content\": \"%s\"}", data)
-			type dummyStruct struct {
-				Content string `json:"content"`
-			}
-			var dummy dummyStruct
-			err := json.Unmarshal([]byte(data), &dummy)
-			responseText += dummy.Content
-			var choice dto.ChatCompletionsStreamResponseChoice
-			choice.Delta.SetContentString(dummy.Content)
-			response := dto.ChatCompletionsStreamResponse{
-				Id:      id,
-				Object:  "chat.completion.chunk",
-				Created: createAt,
-				Model:   info.UpstreamModelName,
-				Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
-			}
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			return false
+	for scanner.Scan() {
+		data := scanner.Text()
+		info.SetFirstResponseTime()
+		data = strings.TrimSpace(data)
+		if !strings.HasPrefix(data, "data: ") {
+			continue
 		}
-	})
-	var geminiChatResponses []GeminiChatResponse
-	err := json.Unmarshal([]byte(responseJson), &geminiChatResponses)
-	if err != nil {
-		log.Printf("cannot get gemini usage: %s", err.Error())
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-	} else {
-		for _, response := range geminiChatResponses {
-			usage.PromptTokens = response.UsageMetadata.PromptTokenCount
-			usage.CompletionTokens = response.UsageMetadata.CandidatesTokenCount
+		data = strings.TrimPrefix(data, "data: ")
+		data = strings.TrimSuffix(data, "\"")
+		var geminiResponse GeminiChatResponse
+		err := json.Unmarshal([]byte(data), &geminiResponse)
+		if err != nil {
+			common.LogError(c, "error unmarshalling stream response: "+err.Error())
+			continue
+		}
+
+		response := streamResponseGeminiChat2OpenAI(&geminiResponse)
+		if response == nil {
+			continue
+		}
+		response.Id = id
+		response.Created = createAt
+		responseText += response.Choices[0].Delta.GetContentString()
+		if geminiResponse.UsageMetadata.TotalTokenCount != 0 {
+			usage.PromptTokens = geminiResponse.UsageMetadata.PromptTokenCount
+			usage.CompletionTokens = geminiResponse.UsageMetadata.CandidatesTokenCount
+		}
+		err = service.ObjectData(c, response)
+		if err != nil {
+			common.LogError(c, err.Error())
 		}
-		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	}
+
+	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())
 		}
 	}
 	service.Done(c)
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), usage
-	}
+	resp.Body.Close()
 	return nil, usage
 }
 

relay/channel/jina/adaptor.go

@@ -15,10 +15,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

relay/channel/ollama/adaptor.go

@@ -10,16 +10,22 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
-	"one-api/service"
 )
 
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {
@@ -58,11 +64,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		var responseText string
-		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
-		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		}
+		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
 		if info.RelayMode == relayconstant.RelayModeEmbeddings {
 			err, usage = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)

relay/channel/ollama/dto.go

@@ -3,14 +3,18 @@ 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   *dto.ResponseFormat `json:"response_format,omitempty"`
+	FrequencyPenalty float64             `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64             `json:"presence_penalty,omitempty"`
 }
 
 type OllamaEmbeddingRequest struct {
@@ -21,6 +25,3 @@ type OllamaEmbeddingRequest struct {
 type OllamaEmbeddingResponse struct {
 	Embedding []float64 `json:"embedding,omitempty"`
 }
-
-//type OllamaOptions struct {
-//}

relay/channel/ollama/relay-ollama.go

@@ -28,14 +28,18 @@ 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,
 	}
 }
 

relay/channel/openai/adaptor.go

@@ -1,10 +1,13 @@
 package openai
 
 import (
+	"bytes"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
+	"mime/multipart"
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
@@ -14,21 +17,16 @@ import (
 	"one-api/relay/channel/minimax"
 	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
 	"strings"
 )
 
 type Adaptor struct {
-	ChannelType int
+	ChannelType    int
+	ResponseFormat string
 }
 
-func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
-	return nil, nil
-}
-
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
-}
-
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 	a.ChannelType = info.ChannelType
 }
 
@@ -83,15 +81,74 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return request, nil
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	a.ResponseFormat = request.ResponseFormat
+	if info.RelayMode == constant.RelayModeAudioSpeech {
+		jsonData, err := json.Marshal(request)
+		if err != nil {
+			return nil, fmt.Errorf("error marshalling object: %w", err)
+		}
+		return bytes.NewReader(jsonData), nil
+	} else {
+		var requestBody bytes.Buffer
+		writer := multipart.NewWriter(&requestBody)
+
+		writer.WriteField("model", request.Model)
+
+		// 添加文件字段
+		file, header, err := c.Request.FormFile("file")
+		if err != nil {
+			return nil, errors.New("file is required")
+		}
+		defer file.Close()
+
+		part, err := writer.CreateFormFile("file", header.Filename)
+		if err != nil {
+			return nil, errors.New("create form file failed")
+		}
+		if _, err := io.Copy(part, file); err != nil {
+			return nil, errors.New("copy file failed")
+		}
+
+		// 关闭 multipart 编写器以设置分界线
+		writer.Close()
+		c.Request.Header.Set("Content-Type", writer.FormDataContentType())
+		return &requestBody, nil
+	}
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	return request, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
-	return channel.DoApiRequest(a, c, info, requestBody)
+	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
+		return channel.DoFormRequest(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) {
-	if info.IsStream {
-		err, usage, _, _ = OpenaiStreamHandler(c, resp, info)
-	} else {
-		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	switch info.RelayMode {
+	case constant.RelayModeAudioSpeech:
+		err, usage = OpenaiTTSHandler(c, resp, info)
+	case constant.RelayModeAudioTranslation:
+		fallthrough
+	case constant.RelayModeAudioTranscription:
+		err, usage = OpenaiSTTHandler(c, resp, info, a.ResponseFormat)
+	case constant.RelayModeImagesGenerations:
+		err, usage = OpenaiTTSHandler(c, resp, info)
+	default:
+		if info.IsStream {
+			err, usage = OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
 	}
 	return
 }

relay/channel/openai/constant.go

@@ -9,6 +9,7 @@ var ModelList = []string{
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
 	"gpt-4o", "gpt-4o-2024-05-13",
+	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"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

@@ -4,6 +4,8 @@ import (
 	"bufio"
 	"bytes"
 	"encoding/json"
+	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
@@ -14,31 +16,37 @@ import (
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
+	"sync"
 	"time"
 )
 
-func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage, string, int) {
-	hasStreamUsage := false
-	responseId := ""
+func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	containStreamUsage := false
+	var responseId string
 	var createAt int64 = 0
 	var systemFingerprint string
+	model := info.UpstreamModelName
 
 	var responseTextBuilder strings.Builder
 	var usage = &dto.Usage{}
+	var streamItems []string // store stream items
+
 	toolCount := 0
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(bufio.ScanLines)
-	var streamItems []string // store stream items
 
 	service.SetEventStreamHeaders(c)
 
 	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
 	defer ticker.Stop()
 
-	stopChan := make(chan bool, 2)
+	stopChan := make(chan bool)
 	defer close(stopChan)
-
-	go func() {
+	var (
+		lastStreamData string
+		mu             sync.Mutex
+	)
+	gopool.Go(func() {
 		for scanner.Scan() {
 			info.SetFirstResponseTime()
 			ticker.Reset(time.Duration(constant.StreamingTimeout) * time.Second)
@@ -49,14 +57,22 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
+			mu.Lock()
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
-				service.StringData(c, data)
+				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()
 		}
-		stopChan <- true
-	}()
+		common.SafeSendBool(stopChan, true)
+	})
 
 	select {
 	case <-ticker.C:
@@ -66,6 +82,26 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 		// 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 {
@@ -79,13 +115,9 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 				var streamResponse dto.ChatCompletionsStreamResponse
 				err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 				if err == nil {
-					responseId = streamResponse.Id
-					createAt = streamResponse.Created
-					systemFingerprint = streamResponse.GetSystemFingerprint()
-					if service.ValidUsage(streamResponse.Usage) {
-						usage = streamResponse.Usage
-						hasStreamUsage = true
-					}
+					//if service.ValidUsage(streamResponse.Usage) {
+					//	usage = streamResponse.Usage
+					//}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -102,13 +134,10 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 			}
 		} else {
 			for _, streamResponse := range streamResponses {
-				responseId = streamResponse.Id
-				createAt = streamResponse.Created
-				systemFingerprint = streamResponse.GetSystemFingerprint()
-				if service.ValidUsage(streamResponse.Usage) {
-					usage = streamResponse.Usage
-					hasStreamUsage = 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 {
@@ -147,24 +176,21 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 		}
 	}
 
-	if !hasStreamUsage {
+	if !containStreamUsage {
 		usage, _ = service.ResponseText2Usage(responseTextBuilder.String(), info.UpstreamModelName, info.PromptTokens)
 		usage.CompletionTokens += toolCount * 7
 	}
 
-	if info.ShouldIncludeUsage && !hasStreamUsage {
-		response := service.GenerateFinalUsageResponse(responseId, createAt, info.UpstreamModelName, *usage)
+	if info.ShouldIncludeUsage && !containStreamUsage {
+		response := service.GenerateFinalUsageResponse(responseId, createAt, model, *usage)
 		response.SetSystemFingerprint(systemFingerprint)
 		service.ObjectData(c, response)
 	}
 
 	service.Done(c)
 
-	err := resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil, "", toolCount
-	}
-	return nil, usage, responseTextBuilder.String(), toolCount
+	resp.Body.Close()
+	return nil, usage
 }
 
 func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
@@ -201,11 +227,7 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 	}
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-	}
-
+	resp.Body.Close()
 	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
@@ -220,3 +242,134 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	}
 	return nil, &simpleResponse.Usage
 }
+
+func OpenaiTTSHandler(c *gin.Context, resp *http.Response, 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
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	// Reset response body
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	// We shouldn't set the header before we parse the response body, because the parse part may fail.
+	// And then we will have to send an error response, but in this case, the header has already been set.
+	// So the httpClient will be confused by the response.
+	// For example, Postman will report error, and we cannot check the response at all.
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.TotalTokens = info.PromptTokens
+	return nil, usage
+}
+
+func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var audioResp dto.AudioResponse
+	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
+	}
+	err = json.Unmarshal(responseBody, &audioResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	// Reset response body
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	// We shouldn't set the header before we parse the response body, because the parse part may fail.
+	// And then we will have to send an error response, but in this case, the header has already been set.
+	// So the httpClient will be confused by the response.
+	// For example, Postman will report error, and we cannot check the response at all.
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
+	}
+	resp.Body.Close()
+
+	var text string
+	switch responseFormat {
+	case "json":
+		text, err = getTextFromJSON(responseBody)
+	case "text":
+		text, err = getTextFromText(responseBody)
+	case "srt":
+		text, err = getTextFromSRT(responseBody)
+	case "verbose_json":
+		text, err = getTextFromVerboseJSON(responseBody)
+	case "vtt":
+		text, err = getTextFromVTT(responseBody)
+	}
+
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.CompletionTokens, _ = service.CountTokenText(text, info.UpstreamModelName)
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	return nil, usage
+}
+
+func getTextFromVTT(body []byte) (string, error) {
+	return getTextFromSRT(body)
+}
+
+func getTextFromVerboseJSON(body []byte) (string, error) {
+	var whisperResponse dto.WhisperVerboseJSONResponse
+	if err := json.Unmarshal(body, &whisperResponse); err != nil {
+		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+	}
+	return whisperResponse.Text, nil
+}
+
+func getTextFromSRT(body []byte) (string, error) {
+	scanner := bufio.NewScanner(strings.NewReader(string(body)))
+	var builder strings.Builder
+	var textLine bool
+	for scanner.Scan() {
+		line := scanner.Text()
+		if textLine {
+			builder.WriteString(line)
+			textLine = false
+			continue
+		} else if strings.Contains(line, "-->") {
+			textLine = true
+			continue
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		return "", err
+	}
+	return builder.String(), nil
+}
+
+func getTextFromText(body []byte) (string, error) {
+	return strings.TrimSuffix(string(body), "\n"), nil
+}
+
+func getTextFromJSON(body []byte) (string, error) {
+	var whisperResponse dto.AudioResponse
+	if err := json.Unmarshal(body, &whisperResponse); err != nil {
+		return "", fmt.Errorf("unmarshal_response_body_failed err :%w", err)
+	}
+	return whisperResponse.Text, nil
+}

relay/channel/palm/adaptor.go

@@ -15,12 +15,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

relay/channel/perplexity/adaptor.go

@@ -10,18 +10,22 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
-	"one-api/service"
 )
 
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {
@@ -54,11 +58,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		var responseText string
-		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
-		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		}
+		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/tencent/adaptor.go

@@ -23,12 +23,17 @@ type Adaptor struct {
 	Timestamp int64
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {
 	a.Action = "ChatCompletions"
 	a.Version = "2023-09-01"
 	a.Timestamp = common.GetTimestamp()

relay/channel/xunfei/adaptor.go

@@ -16,12 +16,17 @@ type Adaptor struct {
 	request *dto.GeneralOpenAIRequest
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

relay/channel/zhipu/adaptor.go

@@ -14,12 +14,17 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {

relay/channel/zhipu/relay-zhipu.go

@@ -153,18 +153,7 @@ func streamMetaResponseZhipu2OpenAI(zhipuResponse *ZhipuStreamMetaResponse) (*dt
 func zhipuStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	var usage *dto.Usage
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n\n"); i >= 0 && strings.Index(string(data), ":") >= 0 {
-			return i + 2, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
+	scanner.Split(bufio.ScanLines)
 	dataChan := make(chan string)
 	metaChan := make(chan string)
 	stopChan := make(chan bool)

relay/channel/zhipu_4v/adaptor.go

@@ -10,18 +10,22 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
-	"one-api/service"
 )
 
 type Adaptor struct {
 }
 
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+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) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+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) {
@@ -55,13 +59,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		var responseText string
-		var toolCount int
-		err, usage, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info)
-		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-			usage.CompletionTokens += toolCount * 7
-		}
+		err, usage = openai.OaiStreamHandler(c, resp, info)
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

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", "glm-4v", "glm-3-turbo", "glm-4-alltools",
 }
 
 var ChannelName = "zhipu_4v"

relay/common/relay_info.go

@@ -33,7 +33,7 @@ type RelayInfo struct {
 }
 
 func GenRelayInfo(c *gin.Context) *RelayInfo {
-	channelType := c.GetInt("channel")
+	channelType := c.GetInt("channel_type")
 	channelId := c.GetInt("channel_id")
 
 	tokenId := c.GetInt("token_id")
@@ -112,7 +112,7 @@ type TaskRelayInfo struct {
 }
 
 func GenTaskRelayInfo(c *gin.Context) *TaskRelayInfo {
-	channelType := c.GetInt("channel")
+	channelType := c.GetInt("channel_type")
 	channelId := c.GetInt("channel_id")
 
 	tokenId := c.GetInt("token_id")

relay/common/relay_utils.go

@@ -1,50 +1,17 @@
 package common
 
 import (
-	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	_ "image/gif"
 	_ "image/jpeg"
 	_ "image/png"
-	"io"
-	"net/http"
 	"one-api/common"
-	"one-api/dto"
-	"strconv"
 	"strings"
 )
 
 var StopFinishReason = "stop"
 
-func RelayErrorHandler(resp *http.Response) (OpenAIErrorWithStatusCode *dto.OpenAIErrorWithStatusCode) {
-	OpenAIErrorWithStatusCode = &dto.OpenAIErrorWithStatusCode{
-		StatusCode: resp.StatusCode,
-		Error: dto.OpenAIError{
-			Message: fmt.Sprintf("bad response status code %d", resp.StatusCode),
-			Type:    "upstream_error",
-			Code:    "bad_response_status_code",
-			Param:   strconv.Itoa(resp.StatusCode),
-		},
-	}
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return
-	}
-	var textResponse dto.TextResponseWithError
-	err = json.Unmarshal(responseBody, &textResponse)
-	if err != nil {
-		OpenAIErrorWithStatusCode.Error.Message = fmt.Sprintf("error unmarshalling response body: %s", responseBody)
-		return
-	}
-	OpenAIErrorWithStatusCode.Error = textResponse.Error
-	return
-}
-
 func GetFullRequestURL(baseURL string, requestURL string, channelType int) string {
 	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
 

relay/constant/relay_mode.go

@@ -13,6 +13,7 @@ const (
 	RelayModeModerations
 	RelayModeImagesGenerations
 	RelayModeEdits
+
 	RelayModeMidjourneyImagine
 	RelayModeMidjourneyDescribe
 	RelayModeMidjourneyBlend
@@ -22,16 +23,20 @@ const (
 	RelayModeMidjourneyTaskFetch
 	RelayModeMidjourneyTaskImageSeed
 	RelayModeMidjourneyTaskFetchByCondition
-	RelayModeAudioSpeech
-	RelayModeAudioTranscription
-	RelayModeAudioTranslation
 	RelayModeMidjourneyAction
 	RelayModeMidjourneyModal
 	RelayModeMidjourneyShorten
 	RelayModeSwapFace
+	RelayModeMidjourneyUpload
+
+	RelayModeAudioSpeech        // tts
+	RelayModeAudioTranscription // whisper
+	RelayModeAudioTranslation   // whisper
+
 	RelayModeSunoFetch
 	RelayModeSunoFetchByID
 	RelayModeSunoSubmit
+
 	RelayModeRerank
 )
 
@@ -77,6 +82,9 @@ func Path2RelayModeMidjourney(path string) int {
 	} else if strings.HasSuffix(path, "/mj/insight-face/swap") {
 		// midjourney plus
 		relayMode = RelayModeSwapFace
+	} else if strings.HasSuffix(path, "/submit/upload-discord-images") {
+		// midjourney plus
+		relayMode = RelayModeMidjourneyUpload
 	} else if strings.HasSuffix(path, "/mj/submit/imagine") {
 		relayMode = RelayModeMidjourneyImagine
 	} else if strings.HasSuffix(path, "/mj/submit/blend") {

relay/relay-audio.go

@@ -1,13 +1,10 @@
 package relay
 
 import (
-	"bytes"
-	"context"
 	"encoding/json"
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/constant"
@@ -16,69 +13,71 @@ import (
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
-	"strings"
-	"time"
 )
 
-func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
-	tokenId := c.GetInt("token_id")
-	channelType := c.GetInt("channel")
-	channelId := c.GetInt("channel_id")
-	userId := c.GetInt("id")
-	group := c.GetString("group")
-	startTime := time.Now()
-
-	var audioRequest dto.TextToSpeechRequest
-	if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
-		err := common.UnmarshalBodyReusable(c, &audioRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
-		}
-	} else {
-		audioRequest = dto.TextToSpeechRequest{
-			Model: "whisper-1",
-		}
+func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.AudioRequest, error) {
+	audioRequest := &dto.AudioRequest{}
+	err := common.UnmarshalBodyReusable(c, audioRequest)
+	if err != nil {
+		return nil, err
 	}
-	//err := common.UnmarshalBodyReusable(c, &audioRequest)
-
-	// request validation
-	if audioRequest.Model == "" {
-		return service.OpenAIErrorWrapper(errors.New("model is required"), "required_field_missing", http.StatusBadRequest)
-	}
-
-	if strings.HasPrefix(audioRequest.Model, "tts-1") {
-		if audioRequest.Voice == "" {
-			return service.OpenAIErrorWrapper(errors.New("voice is required"), "required_field_missing", http.StatusBadRequest)
+	switch info.RelayMode {
+	case relayconstant.RelayModeAudioSpeech:
+		if audioRequest.Model == "" {
+			return nil, errors.New("model is required")
 		}
-	}
-	var err error
-	promptTokens := 0
-	preConsumedTokens := common.PreConsumedQuota
-	if strings.HasPrefix(audioRequest.Model, "tts-1") {
 		if constant.ShouldCheckPromptSensitive() {
-			err = service.CheckSensitiveInput(audioRequest.Input)
+			err := service.CheckSensitiveInput(audioRequest.Input)
 			if err != nil {
-				return service.OpenAIErrorWrapper(err, "sensitive_words_detected", http.StatusBadRequest)
+				return nil, err
 			}
 		}
+	default:
+		if audioRequest.Model == "" {
+			audioRequest.Model = c.PostForm("model")
+		}
+		if audioRequest.Model == "" {
+			return nil, errors.New("model is required")
+		}
+		if audioRequest.ResponseFormat == "" {
+			audioRequest.ResponseFormat = "json"
+		}
+	}
+	return audioRequest, nil
+}
+
+func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
+	relayInfo := relaycommon.GenRelayInfo(c)
+	audioRequest, err := getAndValidAudioRequest(c, relayInfo)
+
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidAudioRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapper(err, "invalid_audio_request", http.StatusBadRequest)
+	}
+
+	promptTokens := 0
+	preConsumedTokens := common.PreConsumedQuota
+	if relayInfo.RelayMode == relayconstant.RelayModeAudioSpeech {
 		promptTokens, err = service.CountAudioToken(audioRequest.Input, audioRequest.Model)
 		if err != nil {
 			return service.OpenAIErrorWrapper(err, "count_audio_token_failed", http.StatusInternalServerError)
 		}
 		preConsumedTokens = promptTokens
+		relayInfo.PromptTokens = promptTokens
 	}
+
 	modelRatio := common.GetModelRatio(audioRequest.Model)
-	groupRatio := common.GetGroupRatio(group)
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
 	ratio := modelRatio * groupRatio
 	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
-	userQuota, err := model.CacheGetUserQuota(userId)
+	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
 	if err != nil {
 		return service.OpenAIErrorWrapperLocal(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
 	if userQuota-preConsumedQuota < 0 {
 		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
-	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
+	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	if err != nil {
 		return service.OpenAIErrorWrapperLocal(err, "decrease_user_quota_failed", http.StatusInternalServerError)
 	}
@@ -88,28 +87,12 @@ func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 		preConsumedQuota = 0
 	}
 	if preConsumedQuota > 0 {
-		userQuota, err = model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
+		userQuota, err = model.PreConsumeTokenQuota(relayInfo.TokenId, preConsumedQuota)
 		if err != nil {
 			return service.OpenAIErrorWrapperLocal(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
 	}
 
-	succeed := false
-	defer func() {
-		if succeed {
-			return
-		}
-		if preConsumedQuota > 0 {
-			// we need to roll back the pre-consumed quota
-			defer func() {
-				go func() {
-					// negative means add quota back for token & user
-					returnPreConsumedQuota(c, tokenId, userQuota, preConsumedQuota)
-				}()
-			}()
-		}
-	}()
-
 	// map model name
 	modelMapping := c.GetString("model_mapping")
 	if modelMapping != "" {
@@ -122,133 +105,44 @@ func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 			audioRequest.Model = modelMap[audioRequest.Model]
 		}
 	}
+	relayInfo.UpstreamModelName = audioRequest.Model
 
-	baseURL := common.ChannelBaseURLs[channelType]
-	requestURL := c.Request.URL.String()
-	if c.GetString("base_url") != "" {
-		baseURL = c.GetString("base_url")
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
 	}
+	adaptor.Init(relayInfo)
 
-	fullRequestURL := relaycommon.GetFullRequestURL(baseURL, requestURL, channelType)
-	if relayMode == relayconstant.RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
-		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
-		apiVersion := relaycommon.GetAPIVersion(c)
-		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/audio/transcriptions?api-version=%s", baseURL, audioRequest.Model, apiVersion)
-	}
-
-	requestBody := c.Request.Body
-
-	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	ioReader, err := adaptor.ConvertAudioRequest(c, relayInfo, *audioRequest)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "new_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
 	}
 
-	if relayMode == relayconstant.RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
-		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
-		apiKey := c.Request.Header.Get("Authorization")
-		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-		req.Header.Set("api-key", apiKey)
-		req.ContentLength = c.Request.ContentLength
-	} else {
-		req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
-	}
-
-	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
-
-	resp, err := service.GetHttpClient().Do(req)
+	resp, err := adaptor.DoRequest(c, relayInfo, ioReader)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}
 
-	err = req.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-	}
-	err = c.Request.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-	}
-
-	if resp.StatusCode != http.StatusOK {
-		return relaycommon.RelayErrorHandler(resp)
-	}
-	succeed = true
-
-	var audioResponse dto.AudioResponse
-
-	defer func(ctx context.Context) {
-		go func() {
-			useTimeSeconds := time.Now().Unix() - startTime.Unix()
-			quota := 0
-			if strings.HasPrefix(audioRequest.Model, "tts-1") {
-				quota = promptTokens
-			} else {
-				quota, err = service.CountAudioToken(audioResponse.Text, audioRequest.Model)
-			}
-			quota = int(float64(quota) * ratio)
-			if ratio != 0 && quota <= 0 {
-				quota = 1
-			}
-			quotaDelta := quota - preConsumedQuota
-			err := model.PostConsumeTokenQuota(tokenId, userQuota, quotaDelta, preConsumedQuota, true)
-			if err != nil {
-				common.SysError("error consuming token remain quota: " + err.Error())
-			}
-			err = model.CacheUpdateUserQuota(userId)
-			if err != nil {
-				common.SysError("error update user quota cache: " + err.Error())
-			}
-			if quota != 0 {
-				tokenName := c.GetString("token_name")
-				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				other := make(map[string]interface{})
-				other["model_ratio"] = modelRatio
-				other["group_ratio"] = groupRatio
-				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, 0, audioRequest.Model, tokenName, quota, logContent, tokenId, userQuota, int(useTimeSeconds), false, other)
-				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				channelId := c.GetInt("channel_id")
-				model.UpdateChannelUsedQuota(channelId, quota)
-			}
-		}()
-	}(c.Request.Context())
-
-	responseBody, err := io.ReadAll(resp.Body)
-
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-	}
-	if strings.HasPrefix(audioRequest.Model, "tts-1") {
-
-	} else {
-		err = json.Unmarshal(responseBody, &audioResponse)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
-		}
-		contains, words := service.SensitiveWordContains(audioResponse.Text)
-		if contains {
-			return service.OpenAIErrorWrapper(errors.New("response contains sensitive words: "+strings.Join(words, ", ")), "response_contains_sensitive_words", http.StatusBadRequest)
+	statusCodeMappingStr := c.GetString("status_code_mapping")
+	if resp != nil {
+		if resp.StatusCode != http.StatusOK {
+			returnPreConsumedQuota(c, relayInfo.TokenId, userQuota, preConsumedQuota)
+			openaiErr := service.RelayErrorHandler(resp)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
 		}
 	}
 
-	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	if openaiErr != nil {
+		returnPreConsumedQuota(c, relayInfo.TokenId, userQuota, preConsumedQuota)
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
 
-	for k, v := range resp.Header {
-		c.Writer.Header().Set(k, v[0])
-	}
-	c.Writer.WriteHeader(resp.StatusCode)
+	postConsumeQuota(c, relayInfo, audioRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, 0, false, "")
 
-	_, err = io.Copy(c.Writer, resp.Body)
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-	}
 	return nil
 }

relay/relay-image.go

@@ -2,7 +2,6 @@ package relay
 
 import (
 	"bytes"
-	"context"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -14,72 +13,71 @@ import (
 	"one-api/dto"
 	"one-api/model"
 	relaycommon "one-api/relay/common"
-	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
-	"time"
 )
 
-func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
-	tokenId := c.GetInt("token_id")
-	channelType := c.GetInt("channel")
-	channelId := c.GetInt("channel_id")
-	userId := c.GetInt("id")
-	group := c.GetString("group")
-	startTime := time.Now()
-
-	var imageRequest dto.ImageRequest
-	err := common.UnmarshalBodyReusable(c, &imageRequest)
+func getAndValidImageRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.ImageRequest, error) {
+	imageRequest := &dto.ImageRequest{}
+	err := common.UnmarshalBodyReusable(c, imageRequest)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
+		return nil, err
 	}
-
-	if imageRequest.Model == "" {
-		imageRequest.Model = "dall-e-3"
+	if imageRequest.Prompt == "" {
+		return nil, errors.New("prompt is required")
 	}
-	if imageRequest.Size == "" {
-		imageRequest.Size = "1024x1024"
+	if strings.Contains(imageRequest.Size, "×") {
+		return nil, errors.New("size an unexpected error occurred in the parameter, please use 'x' instead of the multiplication sign '×'")
 	}
 	if imageRequest.N == 0 {
 		imageRequest.N = 1
 	}
-	// Prompt validation
-	if imageRequest.Prompt == "" {
-		return service.OpenAIErrorWrapper(errors.New("prompt is required"), "required_field_missing", http.StatusBadRequest)
+	if imageRequest.Size == "" {
+		imageRequest.Size = "1024x1024"
 	}
-
-	if constant.ShouldCheckPromptSensitive() {
-		err = service.CheckSensitiveInput(imageRequest.Prompt)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "sensitive_words_detected", http.StatusBadRequest)
-		}
+	if imageRequest.Model == "" {
+		imageRequest.Model = "dall-e-2"
 	}
-
-	if strings.Contains(imageRequest.Size, "×") {
-		return service.OpenAIErrorWrapper(errors.New("size an unexpected error occurred in the parameter, please use 'x' instead of the multiplication sign '×'"), "invalid_field_value", http.StatusBadRequest)
+	if imageRequest.Quality == "" {
+		imageRequest.Quality = "standard"
 	}
 	// Not "256x256", "512x512", or "1024x1024"
 	if imageRequest.Model == "dall-e-2" || imageRequest.Model == "dall-e" {
 		if imageRequest.Size != "" && imageRequest.Size != "256x256" && imageRequest.Size != "512x512" && imageRequest.Size != "1024x1024" {
-			return service.OpenAIErrorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
+			return nil, errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024")
 		}
 	} else if imageRequest.Model == "dall-e-3" {
 		if imageRequest.Size != "" && imageRequest.Size != "1024x1024" && imageRequest.Size != "1024x1792" && imageRequest.Size != "1792x1024" {
-			return service.OpenAIErrorWrapper(errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024"), "invalid_field_value", http.StatusBadRequest)
+			return nil, errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024")
 		}
-		if imageRequest.N != 1 {
-			return service.OpenAIErrorWrapper(errors.New("n must be 1"), "invalid_field_value", http.StatusBadRequest)
+		//if imageRequest.N != 1 {
+		//	return nil, errors.New("n must be 1")
+		//}
+	}
+	// N should between 1 and 10
+	//if imageRequest.N != 0 && (imageRequest.N < 1 || imageRequest.N > 10) {
+	//	return service.OpenAIErrorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
+	//}
+	if constant.ShouldCheckPromptSensitive() {
+		err := service.CheckSensitiveInput(imageRequest.Prompt)
+		if err != nil {
+			return nil, err
 		}
 	}
+	return imageRequest, nil
+}
 
-	// N should between 1 and 10
-	if imageRequest.N != 0 && (imageRequest.N < 1 || imageRequest.N > 10) {
-		return service.OpenAIErrorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
+func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
+	relayInfo := relaycommon.GenRelayInfo(c)
+
+	imageRequest, err := getAndValidImageRequest(c, relayInfo)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidImageRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapper(err, "invalid_image_request", http.StatusBadRequest)
 	}
 
 	// map model name
 	modelMapping := c.GetString("model_mapping")
-	isModelMapped := false
 	if modelMapping != "" {
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
@@ -88,31 +86,9 @@ func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusC
 		}
 		if modelMap[imageRequest.Model] != "" {
 			imageRequest.Model = modelMap[imageRequest.Model]
-			isModelMapped = true
 		}
 	}
-	baseURL := common.ChannelBaseURLs[channelType]
-	requestURL := c.Request.URL.String()
-	if c.GetString("base_url") != "" {
-		baseURL = c.GetString("base_url")
-	}
-	fullRequestURL := relaycommon.GetFullRequestURL(baseURL, requestURL, channelType)
-	if channelType == common.ChannelTypeAzure && relayMode == relayconstant.RelayModeImagesGenerations {
-		// https://learn.microsoft.com/en-us/azure/ai-services/openai/dall-e-quickstart?tabs=dalle3%2Ccommand-line&pivots=rest-api
-		apiVersion := relaycommon.GetAPIVersion(c)
-		// https://{resource_name}.openai.azure.com/openai/deployments/dall-e-3/images/generations?api-version=2023-06-01-preview
-		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/images/generations?api-version=%s", baseURL, imageRequest.Model, apiVersion)
-	}
-	var requestBody io.Reader
-	if isModelMapped || channelType == common.ChannelTypeAzure { // make Azure channel request body
-		jsonStr, err := json.Marshal(imageRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonStr)
-	} else {
-		requestBody = c.Request.Body
-	}
+	relayInfo.UpstreamModelName = imageRequest.Model
 
 	modelPrice, success := common.GetModelPrice(imageRequest.Model, true)
 	if !success {
@@ -121,8 +97,9 @@ func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusC
 		// per 1 modelRatio = $0.04 / 16
 		modelPrice = 0.0025 * modelRatio
 	}
-	groupRatio := common.GetGroupRatio(group)
-	userQuota, err := model.CacheGetUserQuota(userId)
+
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
 
 	sizeRatio := 1.0
 	// Size
@@ -144,104 +121,67 @@ func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusC
 		}
 	}
 
-	quota := int(modelPrice*groupRatio*common.QuotaPerUnit*sizeRatio*qualityRatio) * imageRequest.N
+	imageRatio := modelPrice * sizeRatio * qualityRatio * float64(imageRequest.N)
+	quota := int(imageRatio * groupRatio * common.QuotaPerUnit)
 
 	if userQuota-quota < 0 {
 		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 
-	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo)
+
+	var requestBody io.Reader
+
+	convertedRequest, err := adaptor.ConvertImageRequest(c, relayInfo, *imageRequest)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "new_request_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
 	}
 
-	token := c.Request.Header.Get("Authorization")
-	if channelType == common.ChannelTypeAzure { // Azure authentication
-		token = strings.TrimPrefix(token, "Bearer ")
-		req.Header.Set("api-key", token)
-	} else {
-		req.Header.Set("Authorization", token)
+	jsonData, err := json.Marshal(convertedRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
-	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+	requestBody = bytes.NewBuffer(jsonData)
 
-	resp, err := service.GetHttpClient().Do(req)
+	statusCodeMappingStr := c.GetString("status_code_mapping")
+	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
 	}
 
-	err = req.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-	}
-	err = c.Request.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
-	}
-
-	if resp.StatusCode != http.StatusOK {
-		return relaycommon.RelayErrorHandler(resp)
-	}
-
-	var textResponse dto.ImageResponse
-	defer func(ctx context.Context) {
-		useTimeSeconds := time.Now().Unix() - startTime.Unix()
+	if resp != nil {
+		relayInfo.IsStream = relayInfo.IsStream || strings.HasPrefix(resp.Header.Get("Content-Type"), "text/event-stream")
 		if resp.StatusCode != http.StatusOK {
-			return
+			openaiErr := service.RelayErrorHandler(resp)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
 		}
-		err := model.PostConsumeTokenQuota(tokenId, userQuota, quota, 0, true)
-		if err != nil {
-			common.SysError("error consuming token remain quota: " + err.Error())
-		}
-		err = model.CacheUpdateUserQuota(userId)
-		if err != nil {
-			common.SysError("error update user quota cache: " + err.Error())
-		}
-		if quota != 0 {
-			tokenName := c.GetString("token_name")
-			quality := "normal"
-			if imageRequest.Quality == "hd" {
-				quality = "hd"
-			}
-			logContent := fmt.Sprintf("模型价格 %.2f，分组倍率 %.2f, 大小 %s, 品质 %s", modelPrice, groupRatio, imageRequest.Size, quality)
-			other := make(map[string]interface{})
-			other["model_price"] = modelPrice
-			other["group_ratio"] = groupRatio
-			model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageRequest.Model, tokenName, quota, logContent, tokenId, userQuota, int(useTimeSeconds), false, other)
-			model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-			channelId := c.GetInt("channel_id")
-			model.UpdateChannelUsedQuota(channelId, quota)
-		}
-	}(c.Request.Context())
-
-	responseBody, err := io.ReadAll(resp.Body)
-
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-	}
-	err = json.Unmarshal(responseBody, &textResponse)
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
 	}
 
-	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
+	_, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	if openaiErr != nil {
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
 
-	for k, v := range resp.Header {
-		c.Writer.Header().Set(k, v[0])
+	usage := &dto.Usage{
+		PromptTokens: imageRequest.N,
+		TotalTokens:  imageRequest.N,
 	}
-	c.Writer.WriteHeader(resp.StatusCode)
 
-	_, err = io.Copy(c.Writer, resp.Body)
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
-	}
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+	quality := "standard"
+	if imageRequest.Quality == "hd" {
+		quality = "hd"
 	}
+
+	logContent := fmt.Sprintf("大小 %s, 品质 %s", imageRequest.Size, quality)
+	postConsumeQuota(c, relayInfo, imageRequest.Model, usage, 0, 0, userQuota, 0, groupRatio, imageRatio, true, logContent)
+
 	return nil
 }

relay/relay-mj.go

@@ -382,6 +382,8 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		midjRequest.Action = constant.MjActionShorten
 	} else if relayMode == relayconstant.RelayModeMidjourneyBlend { //绘画任务，此类任务可重复
 		midjRequest.Action = constant.MjActionBlend
+	} else if relayMode == relayconstant.RelayModeMidjourneyUpload { //绘画任务，此类任务可重复
+		midjRequest.Action = constant.MjActionUpload
 	} else if midjRequest.TaskId != "" { //放大、变换任务，此类任务，如果重复且已有结果，远端api会直接返回最终结果
 		mjId := ""
 		if relayMode == relayconstant.RelayModeMidjourneyChange {
@@ -547,7 +549,7 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		if err != nil {
 			common.SysError("get_channel_null: " + err.Error())
 		}
-		if channel.AutoBan != nil && *channel.AutoBan == 1 && common.AutomaticDisableChannelEnabled {
+		if channel.GetAutoBan() && common.AutomaticDisableChannelEnabled {
 			model.UpdateChannelStatusById(midjourneyTask.ChannelId, 2, "No available account instance")
 		}
 	}
@@ -580,7 +582,10 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 			responseBody = []byte(newBody)
 		}
 	}
-
+	if midjResponse.Code == 1 && midjRequest.Action == "UPLOAD" {
+		midjourneyTask.Progress = "100%"
+		midjourneyTask.Status = "SUCCESS"
+	}
 	err = midjourneyTask.Insert()
 	if err != nil {
 		return &dto.MidjourneyResponse{
@@ -594,7 +599,6 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		newBody := strings.Replace(string(responseBody), `"code":22`, `"code":1`, -1)
 		responseBody = []byte(newBody)
 	}
-
 	//resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	bodyReader := io.NopCloser(bytes.NewBuffer(responseBody))
 

relay/relay-text.go

@@ -91,7 +91,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		}
 	}
 	relayInfo.UpstreamModelName = textRequest.Model
-	modelPrice, success := common.GetModelPrice(textRequest.Model, false)
+	modelPrice, getModelPriceSuccess := common.GetModelPrice(textRequest.Model, false)
 	groupRatio := common.GetGroupRatio(relayInfo.Group)
 
 	var preConsumedQuota int
@@ -112,7 +112,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return service.OpenAIErrorWrapper(err, "count_token_messages_failed", http.StatusInternalServerError)
 	}
 
-	if !success {
+	if !getModelPriceSuccess {
 		preConsumedTokens := common.PreConsumedQuota
 		if textRequest.MaxTokens != 0 {
 			preConsumedTokens = promptTokens + int(textRequest.MaxTokens)
@@ -130,6 +130,12 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return openaiErr
 	}
 
+	includeUsage := false
+	// 判断用户是否需要返回使用情况
+	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
+		includeUsage = true
+	}
+
 	// 如果不支持StreamOptions，将StreamOptions设置为nil
 	if !relayInfo.SupportStreamOptions || !textRequest.Stream {
 		textRequest.StreamOptions = nil
@@ -142,15 +148,15 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		}
 	}
 
-	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
-		relayInfo.ShouldIncludeUsage = textRequest.StreamOptions.IncludeUsage
+	if includeUsage {
+		relayInfo.ShouldIncludeUsage = true
 	}
 
 	adaptor := GetAdaptor(relayInfo.ApiType)
 	if adaptor == nil {
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
 	}
-	adaptor.Init(relayInfo, *textRequest)
+	adaptor.Init(relayInfo)
 	var requestBody io.Reader
 
 	convertedRequest, err := adaptor.ConvertRequest(c, relayInfo, textRequest)
@@ -187,7 +193,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, textRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success)
+	postConsumeQuota(c, relayInfo, textRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	return nil
 }
 
@@ -247,13 +253,13 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 			if tokenQuota > 100*preConsumedQuota {
 				// 令牌额度充足，信任令牌
 				preConsumedQuota = 0
-				common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
+				common.LogInfo(c, fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
 			}
 		} else {
 			// in this case, we do not pre-consume quota
 			// because the user has enough quota
 			preConsumedQuota = 0
-			common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
+			common.LogInfo(c, fmt.Sprintf("user %d with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
 		}
 	}
 	if preConsumedQuota > 0 {
@@ -279,8 +285,15 @@ func returnPreConsumedQuota(c *gin.Context, tokenId int, userQuota int, preConsu
 
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
 	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
-	modelPrice float64, usePrice bool) {
-
+	modelPrice float64, usePrice bool, extraContent string) {
+	if usage == nil {
+		usage = &dto.Usage{
+			PromptTokens:     relayInfo.PromptTokens,
+			CompletionTokens: 0,
+			TotalTokens:      relayInfo.PromptTokens,
+		}
+		extraContent += "  ，（可能是请求出错）"
+	}
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	promptTokens := usage.PromptTokens
 	completionTokens := usage.CompletionTokens
@@ -300,7 +313,7 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 	}
 	totalTokens := promptTokens + completionTokens
 	var logContent string
-	if modelPrice == -1 {
+	if !usePrice {
 		logContent = fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio)
 	} else {
 		logContent = fmt.Sprintf("模型价格 %.2f，分组倍率 %.2f", modelPrice, groupRatio)
@@ -338,6 +351,9 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 		logModel = "gpt-4-gizmo-*"
 		logContent += fmt.Sprintf("，模型 %s", modelName)
 	}
+	if extraContent != "" {
+		logContent += ", " + extraContent
+	}
 	other := service.GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, modelPrice)
 	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel,
 		tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)

relay/relay_rerank.go

@@ -66,7 +66,7 @@ func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	if adaptor == nil {
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
 	}
-	adaptor.InitRerank(relayInfo, *rerankRequest)
+	adaptor.Init(relayInfo)
 
 	convertedRequest, err := adaptor.ConvertRerankRequest(c, relayInfo.RelayMode, *rerankRequest)
 	if err != nil {
@@ -99,6 +99,6 @@ func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success)
+	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
 	return nil
 }

router/relay-router.go

@@ -79,5 +79,6 @@ func registerMjRouterGroup(relayMjRouter *gin.RouterGroup) {
 		relayMjRouter.GET("/task/:id/image-seed", controller.RelayMidjourney)
 		relayMjRouter.POST("/task/list-by-condition", controller.RelayMidjourney)
 		relayMjRouter.POST("/insight-face/swap", controller.RelayMidjourney)
+		relayMjRouter.POST("/submit/upload-discord-images", controller.RelayMidjourney)
 	}
 }

service/error.go

@@ -56,10 +56,9 @@ func RelayErrorHandler(resp *http.Response) (errWithStatusCode *dto.OpenAIErrorW
 	errWithStatusCode = &dto.OpenAIErrorWithStatusCode{
 		StatusCode: resp.StatusCode,
 		Error: dto.OpenAIError{
-			Message: "",
-			Type:    "upstream_error",
-			Code:    "bad_response_status_code",
-			Param:   strconv.Itoa(resp.StatusCode),
+			Type:  "upstream_error",
+			Code:  "bad_response_status_code",
+			Param: strconv.Itoa(resp.StatusCode),
 		},
 	}
 	responseBody, err := io.ReadAll(resp.Body)

service/midjourney.go

@@ -49,6 +49,8 @@ func GetMjRequestModel(relayMode int, midjRequest *dto.MidjourneyRequest) (strin
 			action = constant.MjActionModal
 		case relayconstant.RelayModeSwapFace:
 			action = constant.MjActionSwapFace
+		case relayconstant.RelayModeMidjourneyUpload:
+			action = constant.MjActionUpload
 		case relayconstant.RelayModeMidjourneySimpleChange:
 			params := ConvertSimpleChangeParams(midjRequest.Content)
 			if params == nil {
@@ -220,7 +222,7 @@ func DoMidjourneyHttpRequest(c *gin.Context, timeout time.Duration, fullRequestU
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "close_request_body_failed", statusCode), nullBytes, err
 	}
 	var midjResponse dto.MidjourneyResponse
-
+	var midjourneyUploadsResponse dto.MidjourneyUploadResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "read_response_body_failed", statusCode), nullBytes, err
@@ -230,13 +232,16 @@ func DoMidjourneyHttpRequest(c *gin.Context, timeout time.Duration, fullRequestU
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "close_response_body_failed", statusCode), responseBody, err
 	}
 	respStr := string(responseBody)
-	log.Printf("responseBody: %s", respStr)
+	log.Printf("respStr: %s", respStr)
 	if respStr == "" {
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "empty_response_body", statusCode), responseBody, nil
 	} else {
 		err = json.Unmarshal(responseBody, &midjResponse)
 		if err != nil {
-			return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "unmarshal_response_body_failed", statusCode), responseBody, err
+			err2 := json.Unmarshal(responseBody, &midjourneyUploadsResponse)
+			if err2 != nil {
+				return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "unmarshal_response_body_failed", statusCode), responseBody, err
+			}
 		}
 	}
 	//log.Printf("midjResponse: %v", midjResponse)

service/relay.go

@@ -2,10 +2,12 @@ package service
 
 import (
 	"encoding/json"
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"net/http"
 	"one-api/common"
-	"strings"
+	"one-api/dto"
 )
 
 func SetEventStreamHeaders(c *gin.Context) {
@@ -16,11 +18,16 @@ func SetEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("X-Accel-Buffering", "no")
 }
 
-func StringData(c *gin.Context, str string) {
-	str = strings.TrimPrefix(str, "data: ")
-	str = strings.TrimSuffix(str, "\r")
+func StringData(c *gin.Context, str string) error {
+	//str = strings.TrimPrefix(str, "data: ")
+	//str = strings.TrimSuffix(str, "\r")
 	c.Render(-1, common.CustomEvent{Data: "data: " + str})
-	c.Writer.Flush()
+	if flusher, ok := c.Writer.(http.Flusher); ok {
+		flusher.Flush()
+	} else {
+		return errors.New("streaming error: flusher not found")
+	}
+	return nil
 }
 
 func ObjectData(c *gin.Context, object interface{}) error {
@@ -28,15 +35,41 @@ func ObjectData(c *gin.Context, object interface{}) error {
 	if err != nil {
 		return fmt.Errorf("error marshalling object: %w", err)
 	}
-	StringData(c, string(jsonData))
-	return nil
+	return StringData(c, string(jsonData))
 }
 
 func Done(c *gin.Context) {
-	StringData(c, "[DONE]")
+	_ = StringData(c, "[DONE]")
 }
 
 func GetResponseID(c *gin.Context) string {
 	logID := c.GetString("X-Oneapi-Request-Id")
 	return fmt.Sprintf("chatcmpl-%s", logID)
 }
+
+func GenerateStopResponse(id string, createAt int64, model string, finishReason string) *dto.ChatCompletionsStreamResponse {
+	return &dto.ChatCompletionsStreamResponse{
+		Id:                id,
+		Object:            "chat.completion.chunk",
+		Created:           createAt,
+		Model:             model,
+		SystemFingerprint: nil,
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{
+				FinishReason: &finishReason,
+			},
+		},
+	}
+}
+
+func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
+	return &dto.ChatCompletionsStreamResponse{
+		Id:                id,
+		Object:            "chat.completion.chunk",
+		Created:           createAt,
+		Model:             model,
+		SystemFingerprint: nil,
+		Choices:           make([]dto.ChatCompletionsStreamResponseChoice, 0),
+		Usage:             &usage,
+	}
+}

service/token_counter.go

@@ -9,6 +9,7 @@ import (
 	"log"
 	"math"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	"strings"
 	"unicode/utf8"
@@ -81,17 +82,31 @@ func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
 }
 
 func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (int, error) {
-	// TODO: 非流模式下不计算图片token数量
+	baseTokens := 85
 	if model == "glm-4v" {
 		return 1047, nil
 	}
 	if imageUrl.Detail == "low" {
-		return 85, nil
+		return baseTokens, nil
+	}
+	// TODO: 非流模式下不计算图片token数量
+	if !constant.GetMediaTokenNotStream && !stream {
+		return 1000, nil
+	}
+	// 是否统计图片token
+	if !constant.GetMediaToken {
+		return 1000, nil
 	}
 	// 同步One API的图片计费逻辑
 	if imageUrl.Detail == "auto" || imageUrl.Detail == "" {
 		imageUrl.Detail = "high"
 	}
+
+	tileTokens := 170
+	if strings.HasPrefix(model, "gpt-4o-mini") {
+		tileTokens = 5667
+		baseTokens = 2833
+	}
 	var config image.Config
 	var err error
 	var format string
@@ -138,7 +153,7 @@ func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (in
 	// 计算图片的token数量(边的长度除以512，向上取整)
 	tiles := (shortSide + 511) / 512 * ((otherSide + 511) / 512)
 	log.Printf("tiles: %d", tiles)
-	return tiles*170 + 85, nil
+	return tiles*tileTokens + baseTokens, nil
 }
 
 func CountTokenChatRequest(request dto.GeneralOpenAIRequest, model string) (int, error) {

service/usage_helpr.go

@@ -25,18 +25,6 @@ func ResponseText2Usage(responseText string, modeName string, promptTokens int)
 	return usage, err
 }
 
-func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
-	return &dto.ChatCompletionsStreamResponse{
-		Id:                id,
-		Object:            "chat.completion.chunk",
-		Created:           createAt,
-		Model:             model,
-		SystemFingerprint: nil,
-		Choices:           make([]dto.ChatCompletionsStreamResponseChoice, 0),
-		Usage:             &usage,
-	}
-}
-
 func ValidUsage(usage *dto.Usage) bool {
 	return usage != nil && (usage.PromptTokens != 0 || usage.CompletionTokens != 0)
 }

web/src/components/LoginForm.js

@@ -1,7 +1,7 @@
 import React, { useContext, useEffect, useState } from 'react';
 import { Link, useNavigate, useSearchParams } from 'react-router-dom';
 import { UserContext } from '../context/User';
-import { API, getLogo, showError, showInfo, showSuccess } from '../helpers';
+import { API, getLogo, showError, showInfo, showSuccess, updateAPI } from '../helpers';
 import { onGitHubOAuthClicked } from './utils';
 import Turnstile from 'react-turnstile';
 import {
@@ -101,6 +101,7 @@ const LoginForm = () => {
       if (success) {
         userDispatch({ type: 'login', payload: data });
         setUserData(data);
+        updateAPI()
         showSuccess('登录成功！');
         if (username === 'root' && password === '123456') {
           Modal.error({

web/src/components/LogsTable.js

@@ -1,11 +1,11 @@
 import React, { useEffect, useState } from 'react';
 import {
   API,
-  copy,
+  copy, getTodayStartTimestamp,
   isAdmin,
   showError,
   showSuccess,
-  timestamp2string,
+  timestamp2string
 } from '../helpers';
 
 import {
@@ -367,7 +367,7 @@ const LogsTable = () => {
       dataIndex: 'content',
       render: (text, record, index) => {
         let other = getLogOther(record.other);
-        if (other == null) {
+        if (other == null || record.type !== 2) {
           return (
             <Paragraph
               ellipsis={{
@@ -419,12 +419,12 @@ const LogsTable = () => {
   const [logType, setLogType] = useState(0);
   const isAdminUser = isAdmin();
   let now = new Date();
-  // 初始化start_timestamp为前一天
+  // 初始化start_timestamp为今天0点
   const [inputs, setInputs] = useState({
     username: '',
     token_name: '',
     model_name: '',
-    start_timestamp: timestamp2string(now.getTime() / 1000 - 86400),
+    start_timestamp: timestamp2string(getTodayStartTimestamp()),
     end_timestamp: timestamp2string(now.getTime() / 1000 + 3600),
     channel: '',
   });
@@ -449,8 +449,10 @@ const LogsTable = () => {
   const getLogSelfStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
+    let url = `/api/log/self/stat?type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+    url = encodeURI(url);
     let res = await API.get(
-      `/api/log/self/stat?type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`,
+      url,
     );
     const { success, message, data } = res.data;
     if (success) {
@@ -463,8 +465,10 @@ const LogsTable = () => {
   const getLogStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
+    let url = `/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
+    url = encodeURI(url);
     let res = await API.get(
-      `/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`,
+      url,
     );
     const { success, message, data } = res.data;
     if (success) {
@@ -475,6 +479,9 @@ const LogsTable = () => {
   };
 
   const handleEyeClick = async () => {
+    if (loadingStat) {
+      return;
+    }
     setLoadingStat(true);
     if (isAdminUser) {
       await getLogStat();
@@ -531,6 +538,7 @@ const LogsTable = () => {
     } else {
       url = `/api/log/self/?p=${startIdx}&page_size=${pageSize}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
+    url = encodeURI(url);
     const res = await API.get(url);
     const { success, message, data } = res.data;
     if (success) {
@@ -574,6 +582,7 @@ const LogsTable = () => {
   const refresh = async () => {
     // setLoading(true);
     setActivePage(1);
+    handleEyeClick();
     await loadLogs(0, pageSize, logType);
   };
 
@@ -596,6 +605,7 @@ const LogsTable = () => {
       .catch((reason) => {
         showError(reason);
       });
+    handleEyeClick();
   }, []);
 
   const searchLogs = async () => {
@@ -622,19 +632,17 @@ const LogsTable = () => {
       <Layout>
         <Header>
           <Spin spinning={loadingStat}>
-            <h3>
-              使用明细（总消耗额度：
-              <span
-                onClick={handleEyeClick}
-                style={{
-                  cursor: 'pointer',
-                  color: 'gray',
-                }}
-              >
-                {showStat ? renderQuota(stat.quota) : '点击查看'}
-              </span>
-              ）
-            </h3>
+            <Space>
+              <Tag color='green' size='large' style={{ padding: 15 }}>
+                总消耗额度: {renderQuota(stat.quota)}
+              </Tag>
+              <Tag color='blue' size='large' style={{ padding: 15 }}>
+                RPM: {stat.rpm}
+              </Tag>
+              <Tag color='purple' size='large' style={{ padding: 15 }}>
+                TPM: {stat.tpm}
+              </Tag>
+            </Space>
           </Spin>
         </Header>
         <Form layout='horizontal' style={{ marginTop: 10 }}>
@@ -700,17 +708,19 @@ const LogsTable = () => {
                 />
               </>
             )}
+            <Button
+              label='查询'
+              type='primary'
+              htmlType='submit'
+              className='btn-margin-right'
+              onClick={refresh}
+              loading={loading}
+              style={{ marginTop: 24 }}
+            >
+              查询
+            </Button>
             <Form.Section>
-              <Button
-                label='查询'
-                type='primary'
-                htmlType='submit'
-                className='btn-margin-right'
-                onClick={refresh}
-                loading={loading}
-              >
-                查询
-              </Button>
+
             </Form.Section>
           </>
         </Form>

web/src/components/MjLogsTable.js

@@ -90,6 +90,12 @@ function renderType(type) {
           图混合
         </Tag>
       );
+    case 'UPLOAD':
+      return (
+          <Tag color='blue' size='large'>
+            上传文件
+          </Tag>
+      );
     case 'SHORTEN':
       return (
         <Tag color='pink' size='large'>
@@ -239,7 +245,7 @@ const renderTimestamp = (timestampInSeconds) => {
 // 修改renderDuration函数以包含颜色逻辑
 function renderDuration(submit_time, finishTime) {
   // 确保startTime和finishTime都是有效的时间戳
-  if (!submit_time || !finishTime) return 'N/A'; 
+  if (!submit_time || !finishTime) return 'N/A';
 
   // 将时间戳转换为Date对象
   const start = new Date(submit_time);

web/src/components/RegisterForm.js

@@ -1,16 +1,10 @@
 import React, { useEffect, useState } from 'react';
-import {
-  Button,
-  Form,
-  Grid,
-  Header,
-  Image,
-  Message,
-  Segment,
-} from 'semantic-ui-react';
 import { Link, useNavigate } from 'react-router-dom';
 import { API, getLogo, showError, showInfo, showSuccess } from '../helpers';
 import Turnstile from 'react-turnstile';
+import { Button, Card, Form, Layout } from '@douyinfe/semi-ui';
+import Title from '@douyinfe/semi-ui/lib/es/typography/title';
+import Text from '@douyinfe/semi-ui/lib/es/typography/text';
 
 const RegisterForm = () => {
   const [inputs, setInputs] = useState({
@@ -18,7 +12,7 @@ const RegisterForm = () => {
     password: '',
     password2: '',
     email: '',
-    verification_code: '',
+    verification_code: ''
   });
   const { username, password, password2 } = inputs;
   const [showEmailVerification, setShowEmailVerification] = useState(false);
@@ -46,9 +40,7 @@ const RegisterForm = () => {
 
   let navigate = useNavigate();
 
-  function handleChange(e) {
-    const { name, value } = e.target;
-    console.log(name, value);
+  function handleChange(name, value) {
     setInputs((inputs) => ({ ...inputs, [name]: value }));
   }
 
@@ -73,7 +65,7 @@ const RegisterForm = () => {
       inputs.aff_code = affCode;
       const res = await API.post(
         `/api/user/register?turnstile=${turnstileToken}`,
-        inputs,
+        inputs
       );
       const { success, message } = res.data;
       if (success) {
@@ -94,7 +86,7 @@ const RegisterForm = () => {
     }
     setLoading(true);
     const res = await API.get(
-      `/api/verification?email=${inputs.email}&turnstile=${turnstileToken}`,
+      `/api/verification?email=${inputs.email}&turnstile=${turnstileToken}`
     );
     const { success, message } = res.data;
     if (success) {
@@ -106,96 +98,113 @@ const RegisterForm = () => {
   };
 
   return (
-    <Grid textAlign='center' style={{ marginTop: '48px' }}>
-      <Grid.Column style={{ maxWidth: 450 }}>
-        <Header as='h2' color='' textAlign='center'>
-          <Image src={logo} /> 新用户注册
-        </Header>
-        <Form size='large'>
-          <Segment>
-            <Form.Input
-              fluid
-              icon='user'
-              iconPosition='left'
-              placeholder='输入用户名，最长 12 位'
-              onChange={handleChange}
-              name='username'
-            />
-            <Form.Input
-              fluid
-              icon='lock'
-              iconPosition='left'
-              placeholder='输入密码，最短 8 位，最长 20 位'
-              onChange={handleChange}
-              name='password'
-              type='password'
-            />
-            <Form.Input
-              fluid
-              icon='lock'
-              iconPosition='left'
-              placeholder='输入密码，最短 8 位，最长 20 位'
-              onChange={handleChange}
-              name='password2'
-              type='password'
-            />
-            {showEmailVerification ? (
-              <>
-                <Form.Input
-                  fluid
-                  icon='mail'
-                  iconPosition='left'
-                  placeholder='输入邮箱地址'
-                  onChange={handleChange}
-                  name='email'
-                  type='email'
-                  action={
-                    <Button onClick={sendVerificationCode} disabled={loading}>
-                      获取验证码
-                    </Button>
-                  }
+    <div>
+      <Layout>
+        <Layout.Header></Layout.Header>
+        <Layout.Content>
+          <div
+            style={{
+              justifyContent: 'center',
+              display: 'flex',
+              marginTop: 120
+            }}
+          >
+            <div style={{ width: 500 }}>
+              <Card>
+                <Title heading={2} style={{ textAlign: 'center' }}>
+                  新用户注册
+                </Title>
+                <Form size="large">
+                  <Form.Input
+                    field={'username'}
+                    label={'用户名'}
+                    placeholder="用户名"
+                    name="username"
+                    onChange={(value) => handleChange('username', value)}
+                  />
+                  <Form.Input
+                    field={'password'}
+                    label={'密码'}
+                    placeholder="密码，最短 8 位，最长 20 位"
+                    name="password"
+                    type="password"
+                    onChange={(value) => handleChange('password', value)}
+                  />
+                  <Form.Input
+                    field={'password2'}
+                    label={'确认密码'}
+                    placeholder="确认密码"
+                    name="password2"
+                    type="password"
+                    onChange={(value) => handleChange('password2', value)}
+                  />
+                  {showEmailVerification ? (
+                    <>
+                      <Form.Input
+                        field={'email'}
+                        label={'邮箱'}
+                        placeholder="输入邮箱地址"
+                        onChange={(value) => handleChange('email', value)}
+                        name="email"
+                        type="email"
+                        suffix={
+                          <Button onClick={sendVerificationCode} disabled={loading}>
+                            获取验证码
+                          </Button>
+                        }
+                      />
+                      <Form.Input
+                        field={'verification_code'}
+                        label={'验证码'}
+                        placeholder="输入验证码"
+                        onChange={(value) => handleChange('verification_code', value)}
+                        name="verification_code"
+                      />
+                    </>
+                  ) : (
+                    <></>
+                  )}
+                  <Button
+                    theme='solid'
+                    style={{ width: '100%' }}
+                    type={'primary'}
+                    size='large'
+                    htmlType={'submit'}
+                    onClick={handleSubmit}
+                  >
+                    注册
+                  </Button>
+                </Form>
+                <div
+                  style={{
+                    display: 'flex',
+                    justifyContent: 'space-between',
+                    marginTop: 20
+                  }}
+                >
+                  <Text>
+                    已有账户？
+                    <Link to="/login">
+                      点击登录
+                    </Link>
+                  </Text>
+                </div>
+              </Card>
+              {turnstileEnabled ? (
+                <Turnstile
+                  sitekey={turnstileSiteKey}
+                  onVerify={(token) => {
+                    setTurnstileToken(token);
+                  }}
                 />
-                <Form.Input
-                  fluid
-                  icon='lock'
-                  iconPosition='left'
-                  placeholder='输入验证码'
-                  onChange={handleChange}
-                  name='verification_code'
-                />
-              </>
-            ) : (
-              <></>
-            )}
-            {turnstileEnabled ? (
-              <Turnstile
-                sitekey={turnstileSiteKey}
-                onVerify={(token) => {
-                  setTurnstileToken(token);
-                }}
-              />
-            ) : (
-              <></>
-            )}
-            <Button
-              color='green'
-              fluid
-              size='large'
-              onClick={handleSubmit}
-              loading={loading}
-            >
-              注册
-            </Button>
-          </Segment>
-        </Form>
-        <Message>
-          已有账户？
-          <Link to='/login' className='btn btn-link'>
-            点击登录
-          </Link>
-        </Message>
-      </Grid.Column>
-    </Grid>
+              ) : (
+                <></>
+              )}
+            </div>
+          </div>
+        </Layout.Content>
+      </Layout>
+    </div>
   );
 };
 

web/src/helpers/api.js

@@ -1,12 +1,26 @@
-import { showError } from './utils';
+import { getUserIdFromLocalStorage, showError } from './utils';
 import axios from 'axios';
 
-export const API = axios.create({
+export let API = axios.create({
   baseURL: import.meta.env.VITE_REACT_APP_SERVER_URL
     ? import.meta.env.VITE_REACT_APP_SERVER_URL
     : '',
+  headers: {
+    'New-API-User': getUserIdFromLocalStorage()
+  }
 });
 
+export function updateAPI() {
+  API = axios.create({
+    baseURL: import.meta.env.VITE_REACT_APP_SERVER_URL
+      ? import.meta.env.VITE_REACT_APP_SERVER_URL
+      : '',
+    headers: {
+      'New-API-User': getUserIdFromLocalStorage()
+    }
+  });
+}
+
 API.interceptors.response.use(
   (response) => response,
   (error) => {

web/src/helpers/utils.js

@@ -33,6 +33,13 @@ export function getLogo() {
   return logo;
 }
 
+export function getUserIdFromLocalStorage() {
+  let user = localStorage.getItem('user');
+  if (!user) return -1;
+  user = JSON.parse(user);
+  return user.id;
+}
+
 export function getFooterHTML() {
   return localStorage.getItem('footer_html');
 }
@@ -133,6 +140,12 @@ export function removeTrailingSlash(url) {
   }
 }
 
+export function getTodayStartTimestamp() {
+  var now = new Date();
+  now.setHours(0, 0, 0, 0);
+  return Math.floor(now.getTime() / 1000);
+}
+
 export function timestamp2string(timestamp) {
   let date = new Date(timestamp * 1000);
   let year = date.getFullYear().toString();

web/src/pages/Token/index.js

@@ -1,11 +1,14 @@
 import React from 'react';
 import TokensTable from '../../components/TokensTable';
-import { Layout } from '@douyinfe/semi-ui';
+import { Banner, Layout } from '@douyinfe/semi-ui';
 const Token = () => (
   <>
     <Layout>
       <Layout.Header>
-        <h3>我的令牌</h3>
+        <Banner
+          type='warning'
+          description='令牌无法精确控制使用额度，请勿直接将令牌分发给用户。'
+        />
       </Layout.Header>
       <Layout.Content>
         <TokensTable />