feat: add warning in log when system prompt is reset

* fix:修复在渠道配置中设置模型重定向时，temperature为0被忽略的问题

* fix: set optional fields to pointer type

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>

.github/workflows/docker-image-amd64.yml

@@ -1,61 +0,0 @@
-name: Publish Docker image (amd64)
-
-on:
-  push:
-    tags:
-      - 'v*.*.*'
-  workflow_dispatch:
-    inputs:
-      name:
-        description: 'reason'
-        required: false
-jobs:
-  push_to_registries:
-    name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
-    permissions:
-      packages: write
-      contents: read
-    steps:
-      - name: Check out the repo
-        uses: actions/checkout@v3
-
-      - name: Check repository URL
-        run: |
-          REPO_URL=$(git config --get remote.origin.url)
-          if [[ $REPO_URL == *"pro" ]]; then
-            exit 1
-          fi        
-
-      - name: Save version info
-        run: |
-          git describe --tags > VERSION 
-
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v2
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: |
-            justsong/one-api
-            ghcr.io/${{ github.repository }}
-
-      - name: Build and push Docker images
-        uses: docker/build-push-action@v3
-        with:
-          context: .
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/docker-image-en.yml

@@ -1,4 +1,4 @@
-name: Publish Docker image (amd64, English)
+name: Publish Docker image (English)
 
 on:
   push:
@@ -34,6 +34,13 @@ jobs:
       - name: Translate
         run: |
           python ./i18n/translate.py --repository_path . --json_file_path ./i18n/en.json
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
       - name: Log in to Docker Hub
         uses: docker/login-action@v2
         with:
@@ -51,6 +58,7 @@ jobs:
         uses: docker/build-push-action@v3
         with:
           context: .
+          platforms: linux/amd64,linux/arm64
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}

.github/workflows/docker-image.yml

@@ -1,10 +1,9 @@
-name: Publish Docker image (arm64)
+name: Publish Docker image
 
 on:
   push:
     tags:
       - 'v*.*.*'
-      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:

Dockerfile

@@ -1,4 +1,4 @@
-FROM node:16 as builder
+FROM --platform=$BUILDPLATFORM node:16 AS builder
 
 WORKDIR /web
 COPY ./VERSION .

README.md

@@ -89,6 +89,8 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [DeepL](https://www.deepl.com/)
    + [x] [together.ai](https://www.together.ai/)
    + [x] [novita.ai](https://www.novita.ai/)
+   + [x] [硅基流动 SiliconCloud](https://siliconflow.cn/siliconcloud)
+   + [x] [xAI](https://x.ai/)
 2. 支持配置镜像以及众多[第三方代理服务](https://iamazing.cn/page/openai-api-third-party-services)。
 3. 支持通过**负载均衡**的方式访问多个渠道。
 4. 支持 **stream 模式**，可以通过流式传输实现打字机效果。
@@ -251,9 +253,9 @@ docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://ope
 #### QChatGPT - QQ机器人
 项目主页：https://github.com/RockChinQ/QChatGPT
 
-根据文档完成部署后，在`config.py`设置配置项`openai_config`的`reverse_proxy`为 One API 后端地址，设置`api_key`为 One API 生成的key，并在配置项`completion_api_params`的`model`参数设置为 One API 支持的模型名称。
+根据[文档](https://qchatgpt.rockchin.top)完成部署后，在 `data/provider.json`设置`requester.openai-chat-completions.base-url`为 One API 实例地址，并填写 API Key 到 `keys.openai` 组中，设置 `model` 为要使用的模型名称。
 
-可安装 [Switcher 插件](https://github.com/RockChinQ/Switcher)在运行时切换所使用的模型。
+运行期间可以通过`!model`命令查看、切换可用模型。
 
 ### 部署到第三方平台
 <details>
@@ -398,6 +400,7 @@ graph LR
 26. `METRIC_SUCCESS_RATE_THRESHOLD`：请求成功率阈值，默认为 `0.8`。
 27. `INITIAL_ROOT_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量值的 root 用户令牌。
 28. `INITIAL_ROOT_ACCESS_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量的 root 用户创建系统管理令牌。
+29. `ENFORCE_INCLUDE_USAGE`：是否强制在 stream 模型下返回 usage，默认不开启，可选值为 `true` 和 `false`。
 
 ### 命令行参数
 1. `--port <port_number>`: 指定服务器监听的端口号，默认为 `3000`。

common/config/config.go

@@ -35,6 +35,7 @@ var PasswordLoginEnabled = true
 var PasswordRegisterEnabled = true
 var EmailVerificationEnabled = false
 var GitHubOAuthEnabled = false
+var OidcEnabled = false
 var WeChatAuthEnabled = false
 var TurnstileCheckEnabled = false
 var RegisterEnabled = true
@@ -70,6 +71,13 @@ var GitHubClientSecret = ""
 var LarkClientId = ""
 var LarkClientSecret = ""
 
+var OidcClientId = ""
+var OidcClientSecret = ""
+var OidcWellKnown = ""
+var OidcAuthorizationEndpoint = ""
+var OidcTokenEndpoint = ""
+var OidcUserinfoEndpoint = ""
+
 var WeChatServerAddress = ""
 var WeChatServerToken = ""
 var WeChatAccountQRCodeImageURL = ""
@@ -147,9 +155,10 @@ var InitialRootAccessToken = os.Getenv("INITIAL_ROOT_ACCESS_TOKEN")
 
 var GeminiVersion = env.String("GEMINI_VERSION", "v1")
 
-
 var OnlyOneLogFile = env.Bool("ONLY_ONE_LOG_FILE", false)
 
 var RelayProxy = env.String("RELAY_PROXY", "")
 var UserContentRequestProxy = env.String("USER_CONTENT_REQUEST_PROXY", "")
 var UserContentRequestTimeout = env.Int("USER_CONTENT_REQUEST_TIMEOUT", 30)
+
+var EnforceIncludeUsage = env.Bool("ENFORCE_INCLUDE_USAGE", false)

common/ctxkey/key.go

@@ -20,4 +20,5 @@ const (
 	BaseURL           = "base_url"
 	AvailableModels   = "available_models"
 	KeyRequestBody    = "key_request_body"
+	SystemPrompt      = "system_prompt"
 )

common/gin.go

@@ -31,15 +31,15 @@ func UnmarshalBodyReusable(c *gin.Context, v any) error {
 	contentType := c.Request.Header.Get("Content-Type")
 	if strings.HasPrefix(contentType, "application/json") {
 		err = json.Unmarshal(requestBody, &v)
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 	} else {
-		// skip for now
-		// TODO: someday non json request have variant model, we will need to implementation this
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+		err = c.ShouldBind(&v)
 	}
 	if err != nil {
 		return err
 	}
 	// Reset request body
-	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 	return nil
 }
 

common/helper/helper.go

@@ -137,3 +137,23 @@ func String2Int(str string) int {
 	}
 	return num
 }
+
+func Float64PtrMax(p *float64, maxValue float64) *float64 {
+	if p == nil {
+		return nil
+	}
+	if *p > maxValue {
+		return &maxValue
+	}
+	return p
+}
+
+func Float64PtrMin(p *float64, minValue float64) *float64 {
+	if p == nil {
+		return nil
+	}
+	if *p < minValue {
+		return &minValue
+	}
+	return p
+}

controller/auth/oidc.go

@@ -0,0 +1,225 @@
+package auth
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/controller"
+	"github.com/songquanpeng/one-api/model"
+	"net/http"
+	"strconv"
+	"time"
+)
+
+type OidcResponse struct {
+	AccessToken  string `json:"access_token"`
+	IDToken      string `json:"id_token"`
+	RefreshToken string `json:"refresh_token"`
+	TokenType    string `json:"token_type"`
+	ExpiresIn    int    `json:"expires_in"`
+	Scope        string `json:"scope"`
+}
+
+type OidcUser struct {
+	OpenID            string `json:"sub"`
+	Email             string `json:"email"`
+	Name              string `json:"name"`
+	PreferredUsername string `json:"preferred_username"`
+	Picture           string `json:"picture"`
+}
+
+func getOidcUserInfoByCode(code string) (*OidcUser, error) {
+	if code == "" {
+		return nil, errors.New("无效的参数")
+	}
+	values := map[string]string{
+		"client_id":     config.OidcClientId,
+		"client_secret": config.OidcClientSecret,
+		"code":          code,
+		"grant_type":    "authorization_code",
+		"redirect_uri":  fmt.Sprintf("%s/oauth/oidc", config.ServerAddress),
+	}
+	jsonData, err := json.Marshal(values)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequest("POST", config.OidcTokenEndpoint, bytes.NewBuffer(jsonData))
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Accept", "application/json")
+	client := http.Client{
+		Timeout: 5 * time.Second,
+	}
+	res, err := client.Do(req)
+	if err != nil {
+		logger.SysLog(err.Error())
+		return nil, errors.New("无法连接至 OIDC 服务器，请稍后重试！")
+	}
+	defer res.Body.Close()
+	var oidcResponse OidcResponse
+	err = json.NewDecoder(res.Body).Decode(&oidcResponse)
+	if err != nil {
+		return nil, err
+	}
+	req, err = http.NewRequest("GET", config.OidcUserinfoEndpoint, nil)
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Authorization", "Bearer "+oidcResponse.AccessToken)
+	res2, err := client.Do(req)
+	if err != nil {
+		logger.SysLog(err.Error())
+		return nil, errors.New("无法连接至 OIDC 服务器，请稍后重试！")
+	}
+	var oidcUser OidcUser
+	err = json.NewDecoder(res2.Body).Decode(&oidcUser)
+	if err != nil {
+		return nil, err
+	}
+	return &oidcUser, nil
+}
+
+func OidcAuth(c *gin.Context) {
+	session := sessions.Default(c)
+	state := c.Query("state")
+	if state == "" || session.Get("oauth_state") == nil || state != session.Get("oauth_state").(string) {
+		c.JSON(http.StatusForbidden, gin.H{
+			"success": false,
+			"message": "state is empty or not same",
+		})
+		return
+	}
+	username := session.Get("username")
+	if username != nil {
+		OidcBind(c)
+		return
+	}
+	if !config.OidcEnabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未开启通过 OIDC 登录以及注册",
+		})
+		return
+	}
+	code := c.Query("code")
+	oidcUser, err := getOidcUserInfoByCode(code)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	user := model.User{
+		OidcId: oidcUser.OpenID,
+	}
+	if model.IsOidcIdAlreadyTaken(user.OidcId) {
+		err := user.FillUserByOidcId()
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
+	} else {
+		if config.RegisterEnabled {
+			user.Email = oidcUser.Email
+			if oidcUser.PreferredUsername != "" {
+				user.Username = oidcUser.PreferredUsername
+			} else {
+				user.Username = "oidc_" + strconv.Itoa(model.GetMaxUserId()+1)
+			}
+			if oidcUser.Name != "" {
+				user.DisplayName = oidcUser.Name
+			} else {
+				user.DisplayName = "OIDC User"
+			}
+			err := user.Insert(0)
+			if err != nil {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": err.Error(),
+				})
+				return
+			}
+		} else {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "管理员关闭了新用户注册",
+			})
+			return
+		}
+	}
+
+	if user.Status != model.UserStatusEnabled {
+		c.JSON(http.StatusOK, gin.H{
+			"message": "用户已被封禁",
+			"success": false,
+		})
+		return
+	}
+	controller.SetupLogin(&user, c)
+}
+
+func OidcBind(c *gin.Context) {
+	if !config.OidcEnabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未开启通过 OIDC 登录以及注册",
+		})
+		return
+	}
+	code := c.Query("code")
+	oidcUser, err := getOidcUserInfoByCode(code)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	user := model.User{
+		OidcId: oidcUser.OpenID,
+	}
+	if model.IsOidcIdAlreadyTaken(user.OidcId) {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "该 OIDC 账户已被绑定",
+		})
+		return
+	}
+	session := sessions.Default(c)
+	id := session.Get("id")
+	// id := c.GetInt("id")  // critical bug!
+	user.Id = id.(int)
+	err = user.FillUserById()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	user.OidcId = oidcUser.OpenID
+	err = user.Update(false)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "bind",
+	})
+	return
+}

controller/billing.go

@@ -17,9 +17,11 @@ func GetSubscription(c *gin.Context) {
 	if config.DisplayTokenStatEnabled {
 		tokenId := c.GetInt(ctxkey.TokenId)
 		token, err = model.GetTokenById(tokenId)
-		expiredTime = token.ExpiredTime
-		remainQuota = token.RemainQuota
-		usedQuota = token.UsedQuota
+		if err == nil {
+			expiredTime = token.ExpiredTime
+			remainQuota = token.RemainQuota
+			usedQuota = token.UsedQuota
+		}
 	} else {
 		userId := c.GetInt(ctxkey.Id)
 		remainQuota, err = model.GetUserQuota(userId)

controller/channel-billing.go

@@ -81,6 +81,26 @@ type APGC2DGPTUsageResponse struct {
 	TotalUsed      float64 `json:"total_used"`
 }
 
+type SiliconFlowUsageResponse struct {
+	Code    int    `json:"code"`
+	Message string `json:"message"`
+	Status  bool   `json:"status"`
+	Data    struct {
+		ID            string `json:"id"`
+		Name          string `json:"name"`
+		Image         string `json:"image"`
+		Email         string `json:"email"`
+		IsAdmin       bool   `json:"isAdmin"`
+		Balance       string `json:"balance"`
+		Status        string `json:"status"`
+		Introduction  string `json:"introduction"`
+		Role          string `json:"role"`
+		ChargeBalance string `json:"chargeBalance"`
+		TotalBalance  string `json:"totalBalance"`
+		Category      string `json:"category"`
+	} `json:"data"`
+}
+
 // GetAuthHeader get auth header
 func GetAuthHeader(token string) http.Header {
 	h := http.Header{}
@@ -203,6 +223,28 @@ func updateChannelAIGC2DBalance(channel *model.Channel) (float64, error) {
 	return response.TotalAvailable, nil
 }
 
+func updateChannelSiliconFlowBalance(channel *model.Channel) (float64, error) {
+	url := "https://api.siliconflow.cn/v1/user/info"
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
+	if err != nil {
+		return 0, err
+	}
+	response := SiliconFlowUsageResponse{}
+	err = json.Unmarshal(body, &response)
+	if err != nil {
+		return 0, err
+	}
+	if response.Code != 20000 {
+		return 0, fmt.Errorf("code: %d, message: %s", response.Code, response.Message)
+	}
+	balance, err := strconv.ParseFloat(response.Data.Balance, 64)
+	if err != nil {
+		return 0, err
+	}
+	channel.UpdateBalance(balance)
+	return balance, nil
+}
+
 func updateChannelBalance(channel *model.Channel) (float64, error) {
 	baseURL := channeltype.ChannelBaseURLs[channel.Type]
 	if channel.GetBaseURL() == "" {
@@ -227,6 +269,8 @@ func updateChannelBalance(channel *model.Channel) (float64, error) {
 		return updateChannelAPI2GPTBalance(channel)
 	case channeltype.AIGC2D:
 		return updateChannelAIGC2DBalance(channel)
+	case channeltype.SiliconFlow:
+		return updateChannelSiliconFlowBalance(channel)
 	default:
 		return 0, errors.New("尚未实现")
 	}

controller/channel-test.go

@@ -76,9 +76,9 @@ func testChannel(channel *model.Channel, request *relaymodel.GeneralOpenAIReques
 		if len(modelNames) > 0 {
 			modelName = modelNames[0]
 		}
-		if modelMap != nil && modelMap[modelName] != "" {
-			modelName = modelMap[modelName]
-		}
+	}
+	if modelMap != nil && modelMap[modelName] != "" {
+		modelName = modelMap[modelName]
 	}
 	meta.OriginModelName, meta.ActualModelName = request.Model, modelName
 	request.Model = modelName

controller/misc.go

@@ -18,24 +18,30 @@ func GetStatus(c *gin.Context) {
 		"success": true,
 		"message": "",
 		"data": gin.H{
-			"version":             common.Version,
-			"start_time":          common.StartTime,
-			"email_verification":  config.EmailVerificationEnabled,
-			"github_oauth":        config.GitHubOAuthEnabled,
-			"github_client_id":    config.GitHubClientId,
-			"lark_client_id":      config.LarkClientId,
-			"system_name":         config.SystemName,
-			"logo":                config.Logo,
-			"footer_html":         config.Footer,
-			"wechat_qrcode":       config.WeChatAccountQRCodeImageURL,
-			"wechat_login":        config.WeChatAuthEnabled,
-			"server_address":      config.ServerAddress,
-			"turnstile_check":     config.TurnstileCheckEnabled,
-			"turnstile_site_key":  config.TurnstileSiteKey,
-			"top_up_link":         config.TopUpLink,
-			"chat_link":           config.ChatLink,
-			"quota_per_unit":      config.QuotaPerUnit,
-			"display_in_currency": config.DisplayInCurrencyEnabled,
+			"version":                     common.Version,
+			"start_time":                  common.StartTime,
+			"email_verification":          config.EmailVerificationEnabled,
+			"github_oauth":                config.GitHubOAuthEnabled,
+			"github_client_id":            config.GitHubClientId,
+			"lark_client_id":              config.LarkClientId,
+			"system_name":                 config.SystemName,
+			"logo":                        config.Logo,
+			"footer_html":                 config.Footer,
+			"wechat_qrcode":               config.WeChatAccountQRCodeImageURL,
+			"wechat_login":                config.WeChatAuthEnabled,
+			"server_address":              config.ServerAddress,
+			"turnstile_check":             config.TurnstileCheckEnabled,
+			"turnstile_site_key":          config.TurnstileSiteKey,
+			"top_up_link":                 config.TopUpLink,
+			"chat_link":                   config.ChatLink,
+			"quota_per_unit":              config.QuotaPerUnit,
+			"display_in_currency":         config.DisplayInCurrencyEnabled,
+			"oidc":                        config.OidcEnabled,
+			"oidc_client_id":              config.OidcClientId,
+			"oidc_well_known":             config.OidcWellKnown,
+			"oidc_authorization_endpoint": config.OidcAuthorizationEndpoint,
+			"oidc_token_endpoint":         config.OidcTokenEndpoint,
+			"oidc_userinfo_endpoint":      config.OidcUserinfoEndpoint,
 		},
 	})
 	return

controller/relay.go

@@ -34,6 +34,8 @@ func relayHelper(c *gin.Context, relayMode int) *model.ErrorWithStatusCode {
 		fallthrough
 	case relaymode.AudioTranscription:
 		err = controller.RelayAudioHelper(c, relayMode)
+	case relaymode.Proxy:
+		err = controller.RelayProxyHelper(c, relayMode)
 	default:
 		err = controller.RelayTextHelper(c)
 	}
@@ -85,12 +87,15 @@ func Relay(c *gin.Context) {
 		channelId := c.GetInt(ctxkey.ChannelId)
 		lastFailedChannelId = channelId
 		channelName := c.GetString(ctxkey.ChannelName)
+		// BUG: bizErr is in race condition
 		go processChannelRelayError(ctx, userId, channelId, channelName, bizErr)
 	}
 	if bizErr != nil {
 		if bizErr.StatusCode == http.StatusTooManyRequests {
 			bizErr.Error.Message = "当前分组上游负载已饱和，请稍后再试"
 		}
+
+		// BUG: bizErr is in race condition
 		bizErr.Error.Message = helper.MessageWithRequestId(bizErr.Error.Message, requestId)
 		c.JSON(bizErr.StatusCode, gin.H{
 			"error": bizErr.Error,

go.mod

@@ -4,6 +4,7 @@ module github.com/songquanpeng/one-api
 go 1.20
 
 require (
+	cloud.google.com/go/iam v1.1.10
 	github.com/aws/aws-sdk-go-v2 v1.27.0
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.15
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.8.3
@@ -19,12 +20,14 @@ require (
 	github.com/gorilla/websocket v1.5.1
 	github.com/jinzhu/copier v0.4.0
 	github.com/joho/godotenv v1.5.1
+	github.com/patrickmn/go-cache v2.1.0+incompatible
 	github.com/pkg/errors v0.9.1
 	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/smartystreets/goconvey v1.8.1
 	github.com/stretchr/testify v1.9.0
-	golang.org/x/crypto v0.23.0
+	golang.org/x/crypto v0.24.0
 	golang.org/x/image v0.18.0
+	google.golang.org/api v0.187.0
 	gorm.io/driver/mysql v1.5.6
 	gorm.io/driver/postgres v1.5.7
 	gorm.io/driver/sqlite v1.5.5
@@ -32,6 +35,9 @@ require (
 )
 
 require (
+	cloud.google.com/go/auth v0.6.1 // indirect
+	cloud.google.com/go/auth/oauth2adapt v0.2.2 // indirect
+	cloud.google.com/go/compute/metadata v0.3.0 // indirect
 	filippo.io/edwards25519 v1.1.0 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.7 // indirect
@@ -45,13 +51,21 @@ require (
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
+	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/go-logr/logr v1.4.1 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-sql-driver/mysql v1.8.1 // indirect
 	github.com/goccy/go-json v0.10.3 // indirect
+	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/google/s2a-go v0.1.7 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.3.2 // indirect
+	github.com/googleapis/gax-go/v2 v2.12.5 // indirect
 	github.com/gopherjs/gopherjs v1.17.2 // indirect
 	github.com/gorilla/context v1.1.2 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
@@ -76,11 +90,22 @@ require (
 	github.com/smarty/assertions v1.15.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
+	go.opencensus.io v0.24.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.49.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.49.0 // indirect
+	go.opentelemetry.io/otel v1.24.0 // indirect
+	go.opentelemetry.io/otel/metric v1.24.0 // indirect
+	go.opentelemetry.io/otel/trace v1.24.0 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/net v0.25.0 // indirect
+	golang.org/x/net v0.26.0 // indirect
+	golang.org/x/oauth2 v0.21.0 // indirect
 	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/sys v0.20.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
 	golang.org/x/text v0.16.0 // indirect
-	google.golang.org/protobuf v1.34.1 // indirect
+	golang.org/x/time v0.5.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240617180043-68d350f18fd4 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240624140628-dc46fd24d27d // indirect
+	google.golang.org/grpc v1.64.1 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -1,5 +1,15 @@
+cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+cloud.google.com/go/auth v0.6.1 h1:T0Zw1XM5c1GlpN2HYr2s+m3vr1p2wy+8VN+Z1FKxW38=
+cloud.google.com/go/auth v0.6.1/go.mod h1:eFHG7zDzbXHKmjJddFG/rBlcGp6t25SwRUiEQSlO4x4=
+cloud.google.com/go/auth/oauth2adapt v0.2.2 h1:+TTV8aXpjeChS9M+aTtN/TjdQnzJvmzKFt//oWu7HX4=
+cloud.google.com/go/auth/oauth2adapt v0.2.2/go.mod h1:wcYjgpZI9+Yu7LyYBg4pqSiaRkfEK3GQcpb7C/uyF1Q=
+cloud.google.com/go/compute/metadata v0.3.0 h1:Tz+eQXMEqDIKRsmY3cHTL6FVaynIjX2QxYC4trgAKZc=
+cloud.google.com/go/compute/metadata v0.3.0/go.mod h1:zFmK7XCadkQkj6TtorcaGlCW1hT1fIilQDwofLpJ20k=
+cloud.google.com/go/iam v1.1.10 h1:ZSAr64oEhQSClwBL670MsJAW5/RLiC6kfw3Bqmd5ZDI=
+cloud.google.com/go/iam v1.1.10/go.mod h1:iEgMq62sg8zx446GCaijmA2Miwg5o3UbO+nI47WHJps=
 filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
 filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/aws/aws-sdk-go-v2 v1.27.0 h1:7bZWKoXhzI+mMR/HjdMx8ZCC5+6fY0lS5tr0bbgiLlo=
 github.com/aws/aws-sdk-go-v2 v1.27.0/go.mod h1:ffIFB97e2yNsv4aTSGkqtHnppsIJzw7G7BReUZ3jCXM=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 h1:x6xsQXGSmW6frevwDA+vi/wqhp1ct18mVXYN08/93to=
@@ -18,12 +28,15 @@ github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc
 github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
 github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
+github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
 github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
 github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
 github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
+github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -32,6 +45,12 @@ github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/r
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
 github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
 github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
+github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
+github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
+github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
 github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
@@ -48,6 +67,11 @@ github.com/gin-contrib/static v1.1.2 h1:c3kT4bFkUJn2aoRU3s6XnMjJT8J6nNWJkR0Nglqm
 github.com/gin-contrib/static v1.1.2/go.mod h1:Fw90ozjHCmZBWbgrsqrDvO28YbhKEKzKp8GixhR4yLw=
 github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU=
 github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y=
+github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
+github.com/go-logr/logr v1.4.1 h1:pKouT5E8xu9zeFC39JXRDukb6JFQPXM5p5I91188VAQ=
+github.com/go-logr/logr v1.4.1/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
+github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
 github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
@@ -64,11 +88,40 @@ github.com/goccy/go-json v0.10.3 h1:KZ5WoDbxAIgm2HNbYckL0se1fHD6rz5j4ywS6ebzDqA=
 github.com/goccy/go-json v0.10.3/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
-github.com/google/go-cmp v0.5.6 h1:BKbKCqvP6I+rmFHt06ZmyQtvB8xAkWdhFyr0ZUNZcxQ=
+github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
+github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
+github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
+github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
+github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
+github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
+github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
+github.com/google/s2a-go v0.1.7 h1:60BLSyTrOV4/haCDW4zb1guZItoSq8foHCXrAnjBo/o=
+github.com/google/s2a-go v0.1.7/go.mod h1:50CgR4k1jNlWBu4UfS4AcfhVe1r6pdZPygJ3R8F0Qdw=
+github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/googleapis/enterprise-certificate-proxy v0.3.2 h1:Vie5ybvEvT75RniqhfFxPRy3Bf7vr3h0cechB90XaQs=
+github.com/googleapis/enterprise-certificate-proxy v0.3.2/go.mod h1:VLSiSSBs/ksPL8kq3OBOQ6WRI2QnaFynd1DCjZ62+V0=
+github.com/googleapis/gax-go/v2 v2.12.5 h1:8gw9KZK8TiVKB6q3zHY3SBzLnrGp6HQjyfYBYGmXdxA=
+github.com/googleapis/gax-go/v2 v2.12.5/go.mod h1:BUDKcWo+RaKq5SC9vVYL0wLADa3VcfswbOMMRmB9H3E=
 github.com/gopherjs/gopherjs v1.17.2 h1:fQnZVsXk8uxXIStYb0N4bGk7jeyTalG/wsZjQ25dO0g=
 github.com/gopherjs/gopherjs v1.17.2/go.mod h1:pRRIvn/QzFLrKfvEz3qUuEhtE/zLCWfreZ6J5gM2i+k=
 github.com/gorilla/context v1.1.2 h1:WRkNAv2uoa03QNIc1A6u4O7DAGMUVoopZhkiXWA2V1o=
@@ -120,6 +173,8 @@ github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjY
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
+github.com/patrickmn/go-cache v2.1.0+incompatible h1:HRMgzkcYKYpi3C8ajMPV8OFXaaRUnok+kx1WdO15EQc=
+github.com/patrickmn/go-cache v2.1.0+incompatible/go.mod h1:3Qf8kWWT7OJRJbdiICTKqZju1ZixQ/KpMGzzAfe6+WQ=
 github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
 github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
@@ -128,6 +183,7 @@ github.com/pkoukk/tiktoken-go v0.1.7 h1:qOBHXX4PHtvIvmOtyg1EeKlwFRiMKAcoMp4Q+bLQ
 github.com/pkoukk/tiktoken-go v0.1.7/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
 github.com/smarty/assertions v1.15.0 h1:cR//PqUBUiQRakZWqBiFFQ9wb8emQGDb0HeGdqGByCY=
 github.com/smarty/assertions v1.15.0/go.mod h1:yABtdzeQs6l1brC900WlRNwj6ZR55d7B+E8C6HtKdec=
@@ -149,26 +205,96 @@ github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
 github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0=
+go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo=
+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.49.0 h1:4Pp6oUg3+e/6M4C0A/3kJ2VYa++dsWVTtGgLVj5xtHg=
+go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.49.0/go.mod h1:Mjt1i1INqiaoZOMGR1RIUJN+i3ChKoFRqzrRQhlkbs0=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.49.0 h1:jq9TW8u3so/bN+JPT166wjOI6/vQPF6Xe7nMNIltagk=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.49.0/go.mod h1:p8pYQP+m5XfbZm9fxtSKAbM6oIllS7s2AfxrChvc7iw=
+go.opentelemetry.io/otel v1.24.0 h1:0LAOdjNmQeSTzGBzduGe/rU4tZhMwL5rWgtp9Ku5Jfo=
+go.opentelemetry.io/otel v1.24.0/go.mod h1:W7b9Ozg4nkF5tWI5zsXkaKKDjdVjpD4oAt9Qi/MArHo=
+go.opentelemetry.io/otel/metric v1.24.0 h1:6EhoGWWK28x1fbpA4tYTOWBkPefTDQnb8WSGXlc88kI=
+go.opentelemetry.io/otel/metric v1.24.0/go.mod h1:VYhLe1rFfxuTXLgj4CBiyz+9WYBA8pNGJgDcSFRKBco=
+go.opentelemetry.io/otel/trace v1.24.0 h1:CsKnnL4dUAr/0llH9FKuc698G04IrpWV0MQA/Y1YELI=
+go.opentelemetry.io/otel/trace v1.24.0/go.mod h1:HPc3Xr/cOApsBI154IU0OI0HJexz+aw5uPdbs3UCjNU=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
 golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
-golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
-golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.24.0 h1:mnl8DM0o513X8fdIkmyFE/5hTYxbwYOjDS/+rK6qpRI=
+golang.org/x/crypto v0.24.0/go.mod h1:Z1PMYSOR5nyMcyAVAIQSKCDwalqy85Aqn1x3Ws4L5DM=
+golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/image v0.18.0 h1:jGzIakQa/ZXI1I0Fxvaa9W7yP25TqT6cHIHn+6CqvSQ=
 golang.org/x/image v0.18.0/go.mod h1:4yyo5vMFQjVjUcVk4jEQcU9MGy/rulF5WvUILseCM2E=
-golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
-golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
+golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
+golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
+golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ=
+golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE=
+golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
+golang.org/x/oauth2 v0.21.0 h1:tsimM75w1tF/uws5rbeHzIWxEqElMehnc+iW793zsZs=
+golang.org/x/oauth2 v0.21.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
+golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/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 v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
-golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
 golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
-golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
-google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
-google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
+golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
+golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/api v0.187.0 h1:Mxs7VATVC2v7CY+7Xwm4ndkX71hpElcvx0D1Ji/p1eo=
+google.golang.org/api v0.187.0/go.mod h1:KIHlTc4x7N7gKKuVsdmfBXN13yEEWXWFURWY6SBp2gk=
+google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
+google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
+google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
+google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
+google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
+google.golang.org/genproto/googleapis/api v0.0.0-20240617180043-68d350f18fd4 h1:MuYw1wJzT+ZkybKfaOXKp5hJiZDn2iHaXRw0mRYdHSc=
+google.golang.org/genproto/googleapis/api v0.0.0-20240617180043-68d350f18fd4/go.mod h1:px9SlOOZBg1wM1zdnr8jEL4CNGUBZ+ZKYtNPApNQc4c=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240624140628-dc46fd24d27d h1:k3zyW3BYYR30e8v3x0bTDdE9vpYFjZHK+HcyqkrppWk=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240624140628-dc46fd24d27d/go.mod h1:Ue6ibwXGpU+dqIcODieyLOcgj7z8+IcskoNIgZxtrFY=
+google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
+google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
+google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
+google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.33.2/go.mod h1:JMHMWHQWaTccqQQlmk3MJZS+GWXOdAesneDmEnv2fbc=
+google.golang.org/grpc v1.64.1 h1:LKtvyfbX3UGVPFcGqJ9ItpVWW6oN/2XqTxfAnwRRXiA=
+google.golang.org/grpc v1.64.1/go.mod h1:hiQF4LFZelK2WKaP6W0L92zGHtiQdZxk8CrSdvyjeP0=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
@@ -185,5 +311,7 @@ gorm.io/driver/sqlite v1.5.5/go.mod h1:6NgQ7sQWAIFsPrJJl1lSNSu2TABh0ZZ/zm5fosATa
 gorm.io/gorm v1.25.7/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
 gorm.io/gorm v1.25.10 h1:dQpO+33KalOA+aFYGlK+EfxcI5MbO7EP2yYygwh9h+s=
 gorm.io/gorm v1.25.10/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
+honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

middleware/auth.go

@@ -140,6 +140,12 @@ func TokenAuth() func(c *gin.Context) {
 				return
 			}
 		}
+
+		// set channel id for proxy relay
+		if channelId := c.Param("channelid"); channelId != "" {
+			c.Set(ctxkey.SpecificChannelId, channelId)
+		}
+
 		c.Next()
 	}
 }

middleware/distributor.go

@@ -12,7 +12,7 @@ import (
 )
 
 type ModelRequest struct {
-	Model string `json:"model"`
+	Model string `json:"model" form:"model"`
 }
 
 func Distribute() func(c *gin.Context) {
@@ -61,6 +61,9 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	c.Set(ctxkey.Channel, channel.Type)
 	c.Set(ctxkey.ChannelId, channel.Id)
 	c.Set(ctxkey.ChannelName, channel.Name)
+	if channel.SystemPrompt != nil && *channel.SystemPrompt != "" {
+		c.Set(ctxkey.SystemPrompt, *channel.SystemPrompt)
+	}
 	c.Set(ctxkey.ModelMapping, channel.GetModelMapping())
 	c.Set(ctxkey.OriginalModel, modelName) // for retry
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))

middleware/rate-limit.go

@@ -3,11 +3,12 @@ package middleware
 import (
 	"context"
 	"fmt"
+	"net/http"
+	"time"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
-	"net/http"
-	"time"
 )
 
 var timeFormat = "2006-01-02T15:04:05.000Z"
@@ -70,6 +71,11 @@ func memoryRateLimiter(c *gin.Context, maxRequestNum int, duration int64, mark s
 }
 
 func rateLimitFactory(maxRequestNum int, duration int64, mark string) func(c *gin.Context) {
+	if maxRequestNum == 0 {
+		return func(c *gin.Context) {
+			c.Next()
+		}
+	}
 	if common.RedisEnabled {
 		return func(c *gin.Context) {
 			redisRateLimiter(c, maxRequestNum, duration, mark)

model/channel.go

@@ -3,6 +3,7 @@ package model
 import (
 	"encoding/json"
 	"fmt"
+
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/common/logger"
@@ -36,16 +37,19 @@ type Channel struct {
 	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
 	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
 	Config             string  `json:"config"`
+	SystemPrompt       *string `json:"system_prompt" gorm:"type:text"`
 }
 
 type ChannelConfig struct {
-	Region     string `json:"region,omitempty"`
-	SK         string `json:"sk,omitempty"`
-	AK         string `json:"ak,omitempty"`
-	UserID     string `json:"user_id,omitempty"`
-	APIVersion string `json:"api_version,omitempty"`
-	LibraryID  string `json:"library_id,omitempty"`
-	Plugin     string `json:"plugin,omitempty"`
+	Region            string `json:"region,omitempty"`
+	SK                string `json:"sk,omitempty"`
+	AK                string `json:"ak,omitempty"`
+	UserID            string `json:"user_id,omitempty"`
+	APIVersion        string `json:"api_version,omitempty"`
+	LibraryID         string `json:"library_id,omitempty"`
+	Plugin            string `json:"plugin,omitempty"`
+	VertexAIProjectID string `json:"vertex_ai_project_id,omitempty"`
+	VertexAIADC       string `json:"vertex_ai_adc,omitempty"`
 }
 
 func GetAllChannels(startIdx int, num int, scope string) ([]*Channel, error) {

model/log.go

@@ -3,6 +3,7 @@ package model
 import (
 	"context"
 	"fmt"
+
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -152,7 +153,11 @@ func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
 }
 
 func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (quota int64) {
-	tx := LOG_DB.Table("logs").Select("ifnull(sum(quota),0)")
+	ifnull := "ifnull"
+	if common.UsingPostgreSQL {
+		ifnull = "COALESCE"
+	}
+	tx := LOG_DB.Table("logs").Select(fmt.Sprintf("%s(sum(quota),0)", ifnull))
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -176,7 +181,11 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := LOG_DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
+	ifnull := "ifnull"
+	if common.UsingPostgreSQL {
+		ifnull = "COALESCE"
+	}
+	tx := LOG_DB.Table("logs").Select(fmt.Sprintf("%s(sum(prompt_tokens),0) + %s(sum(completion_tokens),0)", ifnull, ifnull))
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}

model/option.go

@@ -28,6 +28,7 @@ func InitOptionMap() {
 	config.OptionMap["PasswordRegisterEnabled"] = strconv.FormatBool(config.PasswordRegisterEnabled)
 	config.OptionMap["EmailVerificationEnabled"] = strconv.FormatBool(config.EmailVerificationEnabled)
 	config.OptionMap["GitHubOAuthEnabled"] = strconv.FormatBool(config.GitHubOAuthEnabled)
+	config.OptionMap["OidcEnabled"] = strconv.FormatBool(config.OidcEnabled)
 	config.OptionMap["WeChatAuthEnabled"] = strconv.FormatBool(config.WeChatAuthEnabled)
 	config.OptionMap["TurnstileCheckEnabled"] = strconv.FormatBool(config.TurnstileCheckEnabled)
 	config.OptionMap["RegisterEnabled"] = strconv.FormatBool(config.RegisterEnabled)
@@ -130,6 +131,8 @@ func updateOptionMap(key string, value string) (err error) {
 			config.EmailVerificationEnabled = boolValue
 		case "GitHubOAuthEnabled":
 			config.GitHubOAuthEnabled = boolValue
+		case "OidcEnabled":
+			config.OidcEnabled = boolValue
 		case "WeChatAuthEnabled":
 			config.WeChatAuthEnabled = boolValue
 		case "TurnstileCheckEnabled":
@@ -176,6 +179,18 @@ func updateOptionMap(key string, value string) (err error) {
 		config.LarkClientId = value
 	case "LarkClientSecret":
 		config.LarkClientSecret = value
+	case "OidcClientId":
+		config.OidcClientId = value
+	case "OidcClientSecret":
+		config.OidcClientSecret = value
+	case "OidcWellKnown":
+		config.OidcWellKnown = value
+	case "OidcAuthorizationEndpoint":
+		config.OidcAuthorizationEndpoint = value
+	case "OidcTokenEndpoint":
+		config.OidcTokenEndpoint = value
+	case "OidcUserinfoEndpoint":
+		config.OidcUserinfoEndpoint = value
 	case "Footer":
 		config.Footer = value
 	case "SystemName":

model/token.go

@@ -30,7 +30,7 @@ type Token struct {
 	RemainQuota    int64   `json:"remain_quota" gorm:"bigint;default:0"`
 	UnlimitedQuota bool    `json:"unlimited_quota" gorm:"default:false"`
 	UsedQuota      int64   `json:"used_quota" gorm:"bigint;default:0"` // used quota
-	Models         *string `json:"models" gorm:"default:''"`           // allowed models
+	Models         *string `json:"models" gorm:"type:text"`            // allowed models
 	Subnet         *string `json:"subnet" gorm:"default:''"`           // allowed subnet
 }
 
@@ -121,30 +121,40 @@ func GetTokenById(id int) (*Token, error) {
 	return &token, err
 }
 
-func (token *Token) Insert() error {
+func (t *Token) Insert() error {
 	var err error
-	err = DB.Create(token).Error
+	err = DB.Create(t).Error
 	return err
 }
 
 // Update Make sure your token's fields is completed, because this will update non-zero values
-func (token *Token) Update() error {
+func (t *Token) Update() error {
 	var err error
-	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota", "models", "subnet").Updates(token).Error
+	err = DB.Model(t).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota", "models", "subnet").Updates(t).Error
 	return err
 }
 
-func (token *Token) SelectUpdate() error {
+func (t *Token) SelectUpdate() error {
 	// This can update zero values
-	return DB.Model(token).Select("accessed_time", "status").Updates(token).Error
+	return DB.Model(t).Select("accessed_time", "status").Updates(t).Error
 }
 
-func (token *Token) Delete() error {
+func (t *Token) Delete() error {
 	var err error
-	err = DB.Delete(token).Error
+	err = DB.Delete(t).Error
 	return err
 }
 
+func (t *Token) GetModels() string {
+	if t == nil {
+		return ""
+	}
+	if t.Models == nil {
+		return ""
+	}
+	return *t.Models
+}
+
 func DeleteTokenById(id int, userId int) (err error) {
 	// Why we need userId here? In case user want to delete other's token.
 	if id == 0 || userId == 0 {
@@ -254,14 +264,14 @@ func PreConsumeTokenQuota(tokenId int, quota int64) (err error) {
 
 func PostConsumeTokenQuota(tokenId int, quota int64) (err error) {
 	token, err := GetTokenById(tokenId)
+	if err != nil {
+		return err
+	}
 	if quota > 0 {
 		err = DecreaseUserQuota(token.UserId, quota)
 	} else {
 		err = IncreaseUserQuota(token.UserId, -quota)
 	}
-	if err != nil {
-		return err
-	}
 	if !token.UnlimitedQuota {
 		if quota > 0 {
 			err = DecreaseTokenQuota(tokenId, quota)

model/user.go

@@ -39,6 +39,7 @@ type User struct {
 	GitHubId         string `json:"github_id" gorm:"column:github_id;index"`
 	WeChatId         string `json:"wechat_id" gorm:"column:wechat_id;index"`
 	LarkId           string `json:"lark_id" gorm:"column:lark_id;index"`
+	OidcId           string `json:"oidc_id" gorm:"column:oidc_id;index"`
 	VerificationCode string `json:"verification_code" gorm:"-:all"`                                    // this field is only for Email verification, don't save it to database!
 	AccessToken      string `json:"access_token" gorm:"type:char(32);column:access_token;uniqueIndex"` // this token is for system management
 	Quota            int64  `json:"quota" gorm:"bigint;default:0"`
@@ -245,6 +246,14 @@ func (user *User) FillUserByLarkId() error {
 	return nil
 }
 
+func (user *User) FillUserByOidcId() error {
+	if user.OidcId == "" {
+		return errors.New("oidc id 为空！")
+	}
+	DB.Where(User{OidcId: user.OidcId}).First(user)
+	return nil
+}
+
 func (user *User) FillUserByWeChatId() error {
 	if user.WeChatId == "" {
 		return errors.New("WeChat id 为空！")
@@ -277,6 +286,10 @@ func IsLarkIdAlreadyTaken(githubId string) bool {
 	return DB.Where("lark_id = ?", githubId).Find(&User{}).RowsAffected == 1
 }
 
+func IsOidcIdAlreadyTaken(oidcId string) bool {
+	return DB.Where("oidc_id = ?", oidcId).Find(&User{}).RowsAffected == 1
+}
+
 func IsUsernameAlreadyTaken(username string) bool {
 	return DB.Where("username = ?", username).Find(&User{}).RowsAffected == 1
 }

monitor/manage.go

@@ -1,10 +1,11 @@
 package monitor
 
 import (
-	"github.com/songquanpeng/one-api/common/config"
-	"github.com/songquanpeng/one-api/relay/model"
 	"net/http"
 	"strings"
+
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/relay/model"
 )
 
 func ShouldDisableChannel(err *model.Error, statusCode int) bool {
@@ -18,31 +19,23 @@ func ShouldDisableChannel(err *model.Error, statusCode int) bool {
 		return true
 	}
 	switch err.Type {
-	case "insufficient_quota":
-		return true
-	// https://docs.anthropic.com/claude/reference/errors
-	case "authentication_error":
-		return true
-	case "permission_error":
-		return true
-	case "forbidden":
+	case "insufficient_quota", "authentication_error", "permission_error", "forbidden":
 		return true
 	}
 	if err.Code == "invalid_api_key" || err.Code == "account_deactivated" {
 		return true
 	}
-	if strings.HasPrefix(err.Message, "Your credit balance is too low") { // anthropic
-		return true
-	} else if strings.HasPrefix(err.Message, "This organization has been disabled.") {
-		return true
-	}
-	//if strings.Contains(err.Message, "quota") {
-	//	return true
-	//}
-	if strings.Contains(err.Message, "credit") {
-		return true
-	}
-	if strings.Contains(err.Message, "balance") {
+
+	lowerMessage := strings.ToLower(err.Message)
+	if strings.Contains(lowerMessage, "your access was terminated") ||
+		strings.Contains(lowerMessage, "violation of our policies") ||
+		strings.Contains(lowerMessage, "your credit balance is too low") ||
+		strings.Contains(lowerMessage, "organization has been disabled") ||
+		strings.Contains(lowerMessage, "credit") ||
+		strings.Contains(lowerMessage, "balance") ||
+		strings.Contains(lowerMessage, "permission denied") ||
+  	strings.Contains(lowerMessage, "organization has been restricted") || // groq
+		strings.Contains(lowerMessage, "已欠费") {
 		return true
 	}
 	return false

relay/adaptor.go

@@ -15,7 +15,9 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/ollama"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/adaptor/palm"
+	"github.com/songquanpeng/one-api/relay/adaptor/proxy"
 	"github.com/songquanpeng/one-api/relay/adaptor/tencent"
+	"github.com/songquanpeng/one-api/relay/adaptor/vertexai"
 	"github.com/songquanpeng/one-api/relay/adaptor/xunfei"
 	"github.com/songquanpeng/one-api/relay/adaptor/zhipu"
 	"github.com/songquanpeng/one-api/relay/apitype"
@@ -55,6 +57,10 @@ func GetAdaptor(apiType int) adaptor.Adaptor {
 		return &cloudflare.Adaptor{}
 	case apitype.DeepL:
 		return &deepl.Adaptor{}
+	case apitype.VertexAI:
+		return &vertexai.Adaptor{}
+	case apitype.Proxy:
+		return &proxy.Adaptor{}
 	}
 	return nil
 }

relay/adaptor/ali/main.go

@@ -3,6 +3,7 @@ package ali
 import (
 	"bufio"
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/ctxkey"
 	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
@@ -35,9 +36,7 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		enableSearch = true
 		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
 	}
-	if request.TopP >= 1 {
-		request.TopP = 0.9999
-	}
+	request.TopP = helper.Float64PtrMax(request.TopP, 0.9999)
 	return &ChatRequest{
 		Model: aliModel,
 		Input: Input{
@@ -59,7 +58,7 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 
 func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *EmbeddingRequest {
 	return &EmbeddingRequest{
-		Model: "text-embedding-v1",
+		Model: request.Model,
 		Input: struct {
 			Texts []string `json:"texts"`
 		}{
@@ -102,8 +101,9 @@ func EmbeddingHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStat
 			StatusCode: resp.StatusCode,
 		}, nil
 	}
-
+	requestModel := c.GetString(ctxkey.RequestModel)
 	fullTextResponse := embeddingResponseAli2OpenAI(&aliResponse)
+	fullTextResponse.Model = requestModel
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
 		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil

relay/adaptor/ali/model.go

@@ -16,13 +16,13 @@ type Input struct {
 }
 
 type Parameters struct {
-	TopP              float64      `json:"top_p,omitempty"`
+	TopP              *float64     `json:"top_p,omitempty"`
 	TopK              int          `json:"top_k,omitempty"`
 	Seed              uint64       `json:"seed,omitempty"`
 	EnableSearch      bool         `json:"enable_search,omitempty"`
 	IncrementalOutput bool         `json:"incremental_output,omitempty"`
 	MaxTokens         int          `json:"max_tokens,omitempty"`
-	Temperature       float64      `json:"temperature,omitempty"`
+	Temperature       *float64     `json:"temperature,omitempty"`
 	ResultFormat      string       `json:"result_format,omitempty"`
 	Tools             []model.Tool `json:"tools,omitempty"`
 }

relay/adaptor/anthropic/adaptor.go

@@ -3,12 +3,14 @@ package anthropic
 import (
 	"errors"
 	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
 )
 
 type Adaptor struct {
@@ -31,6 +33,13 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *me
 	}
 	req.Header.Set("anthropic-version", anthropicVersion)
 	req.Header.Set("anthropic-beta", "messages-2023-12-15")
+
+	// https://x.com/alexalbert__/status/1812921642143900036
+	// claude-3-5-sonnet can support 8k context
+	if strings.HasPrefix(meta.ActualModelName, "claude-3-5-sonnet") {
+		req.Header.Set("anthropic-beta", "max-tokens-3-5-sonnet-2024-07-15")
+	}
+
 	return nil
 }
 

relay/adaptor/anthropic/constants.go

@@ -3,7 +3,11 @@ package anthropic
 var ModelList = []string{
 	"claude-instant-1.2", "claude-2.0", "claude-2.1",
 	"claude-3-haiku-20240307",
+	"claude-3-5-haiku-20241022",
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-5-sonnet-20240620",
+	"claude-3-5-sonnet-20241022",
+	"claude-3-5-sonnet-latest",
+	"claude-3-5-haiku-20241022",
 }

relay/adaptor/anthropic/model.go

@@ -48,8 +48,8 @@ type Request struct {
 	MaxTokens     int       `json:"max_tokens,omitempty"`
 	StopSequences []string  `json:"stop_sequences,omitempty"`
 	Stream        bool      `json:"stream,omitempty"`
-	Temperature   float64   `json:"temperature,omitempty"`
-	TopP          float64   `json:"top_p,omitempty"`
+	Temperature   *float64  `json:"temperature,omitempty"`
+	TopP          *float64  `json:"top_p,omitempty"`
 	TopK          int       `json:"top_k,omitempty"`
 	Tools         []Tool    `json:"tools,omitempty"`
 	ToolChoice    any       `json:"tool_choice,omitempty"`

relay/adaptor/aws/claude/main.go

@@ -29,10 +29,13 @@ var AwsModelIDMap = map[string]string{
 	"claude-instant-1.2":         "anthropic.claude-instant-v1",
 	"claude-2.0":                 "anthropic.claude-v2",
 	"claude-2.1":                 "anthropic.claude-v2:1",
-	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
-	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
-	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
+	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
+	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
+	"claude-3-5-sonnet-20241022": "anthropic.claude-3-5-sonnet-20241022-v2:0",
+	"claude-3-5-sonnet-latest":   "anthropic.claude-3-5-sonnet-20241022-v2:0",
+	"claude-3-5-haiku-20241022":  "anthropic.claude-3-5-haiku-20241022-v1:0",
 }
 
 func awsModelID(requestModel string) (string, error) {

relay/adaptor/aws/claude/model.go

@@ -11,8 +11,8 @@ type Request struct {
 	Messages         []anthropic.Message `json:"messages"`
 	System           string              `json:"system,omitempty"`
 	MaxTokens        int                 `json:"max_tokens,omitempty"`
-	Temperature      float64             `json:"temperature,omitempty"`
-	TopP             float64             `json:"top_p,omitempty"`
+	Temperature      *float64            `json:"temperature,omitempty"`
+	TopP             *float64            `json:"top_p,omitempty"`
 	TopK             int                 `json:"top_k,omitempty"`
 	StopSequences    []string            `json:"stop_sequences,omitempty"`
 	Tools            []anthropic.Tool    `json:"tools,omitempty"`

relay/adaptor/aws/llama3/model.go

@@ -4,10 +4,10 @@ package aws
 //
 // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
 type Request struct {
-	Prompt      string  `json:"prompt"`
-	MaxGenLen   int     `json:"max_gen_len,omitempty"`
-	Temperature float64 `json:"temperature,omitempty"`
-	TopP        float64 `json:"top_p,omitempty"`
+	Prompt      string   `json:"prompt"`
+	MaxGenLen   int      `json:"max_gen_len,omitempty"`
+	Temperature *float64 `json:"temperature,omitempty"`
+	TopP        *float64 `json:"top_p,omitempty"`
 }
 
 // Response is the response from AWS Llama3

relay/adaptor/baidu/main.go

@@ -35,9 +35,9 @@ type Message struct {
 
 type ChatRequest struct {
 	Messages        []Message `json:"messages"`
-	Temperature     float64   `json:"temperature,omitempty"`
-	TopP            float64   `json:"top_p,omitempty"`
-	PenaltyScore    float64   `json:"penalty_score,omitempty"`
+	Temperature     *float64  `json:"temperature,omitempty"`
+	TopP            *float64  `json:"top_p,omitempty"`
+	PenaltyScore    *float64  `json:"penalty_score,omitempty"`
 	Stream          bool      `json:"stream,omitempty"`
 	System          string    `json:"system,omitempty"`
 	DisableSearch   bool      `json:"disable_search,omitempty"`

relay/adaptor/cloudflare/adaptor.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"strings"
 
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/relay/adaptor"
@@ -28,14 +29,32 @@ func (a *Adaptor) Init(meta *meta.Meta) {
 	a.meta = meta
 }
 
+// WorkerAI cannot be used across accounts with AIGateWay
+// https://developers.cloudflare.com/ai-gateway/providers/workersai/#openai-compatible-endpoints
+// https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/workers-ai
+func (a *Adaptor) isAIGateWay(baseURL string) bool {
+	return strings.HasPrefix(baseURL, "https://gateway.ai.cloudflare.com") && strings.HasSuffix(baseURL, "/workers-ai")
+}
+
 func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
+	isAIGateWay := a.isAIGateWay(meta.BaseURL)
+	var urlPrefix string
+	if isAIGateWay {
+		urlPrefix = meta.BaseURL
+	} else {
+		urlPrefix = fmt.Sprintf("%s/client/v4/accounts/%s/ai", meta.BaseURL, meta.Config.UserID)
+	}
+
 	switch meta.Mode {
 	case relaymode.ChatCompletions:
-		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/chat/completions", meta.BaseURL, meta.Config.UserID), nil
+		return fmt.Sprintf("%s/v1/chat/completions", urlPrefix), nil
 	case relaymode.Embeddings:
-		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/embeddings", meta.BaseURL, meta.Config.UserID), nil
+		return fmt.Sprintf("%s/v1/embeddings", urlPrefix), nil
 	default:
-		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/run/%s", meta.BaseURL, meta.Config.UserID, meta.ActualModelName), nil
+		if isAIGateWay {
+			return fmt.Sprintf("%s/%s", urlPrefix, meta.ActualModelName), nil
+		}
+		return fmt.Sprintf("%s/run/%s", urlPrefix, meta.ActualModelName), nil
 	}
 }
 

relay/adaptor/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/adaptor/cloudflare/model.go

@@ -9,5 +9,5 @@ type Request struct {
 	Prompt      string          `json:"prompt,omitempty"`
 	Raw         bool            `json:"raw,omitempty"`
 	Stream      bool            `json:"stream,omitempty"`
-	Temperature float64         `json:"temperature,omitempty"`
+	Temperature *float64        `json:"temperature,omitempty"`
 }

relay/adaptor/cohere/main.go

@@ -43,7 +43,7 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
 		K:                textRequest.TopK,
 		Stream:           textRequest.Stream,
 		FrequencyPenalty: textRequest.FrequencyPenalty,
-		PresencePenalty:  textRequest.FrequencyPenalty,
+		PresencePenalty:  textRequest.PresencePenalty,
 		Seed:             int(textRequest.Seed),
 	}
 	if cohereRequest.Model == "" {

relay/adaptor/cohere/model.go

@@ -10,15 +10,15 @@ type Request struct {
 	PromptTruncation string        `json:"prompt_truncation,omitempty"` // 默认值为"AUTO"
 	Connectors       []Connector   `json:"connectors,omitempty"`
 	Documents        []Document    `json:"documents,omitempty"`
-	Temperature      float64       `json:"temperature,omitempty"` // 默认值为0.3
+	Temperature      *float64      `json:"temperature,omitempty"` // 默认值为0.3
 	MaxTokens        int           `json:"max_tokens,omitempty"`
 	MaxInputTokens   int           `json:"max_input_tokens,omitempty"`
 	K                int           `json:"k,omitempty"` // 默认值为0
-	P                float64       `json:"p,omitempty"` // 默认值为0.75
+	P                *float64      `json:"p,omitempty"` // 默认值为0.75
 	Seed             int           `json:"seed,omitempty"`
 	StopSequences    []string      `json:"stop_sequences,omitempty"`
-	FrequencyPenalty float64       `json:"frequency_penalty,omitempty"` // 默认值为0.0
-	PresencePenalty  float64       `json:"presence_penalty,omitempty"`  // 默认值为0.0
+	FrequencyPenalty *float64      `json:"frequency_penalty,omitempty"` // 默认值为0.0
+	PresencePenalty  *float64      `json:"presence_penalty,omitempty"`  // 默认值为0.0
 	Tools            []Tool        `json:"tools,omitempty"`
 	ToolResults      []ToolResult  `json:"tool_results,omitempty"`
 }

relay/adaptor/doubao/main.go

@@ -7,8 +7,12 @@ import (
 )
 
 func GetRequestURL(meta *meta.Meta) (string, error) {
-	if meta.Mode == relaymode.ChatCompletions {
+	switch meta.Mode {
+	case relaymode.ChatCompletions:
 		return fmt.Sprintf("%s/api/v3/chat/completions", meta.BaseURL), nil
+	case relaymode.Embeddings:
+		return fmt.Sprintf("%s/api/v3/embeddings", meta.BaseURL), nil
+	default:
 	}
 	return "", fmt.Errorf("unsupported relay mode %d for doubao", meta.Mode)
 }

relay/adaptor/gemini/constants.go

@@ -3,6 +3,5 @@ package gemini
 // https://ai.google.dev/models/gemini
 
 var ModelList = []string{
-	"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro",
-	"gemini-pro-vision", "gemini-1.0-pro-vision-001", "embedding-001", "text-embedding-004",
+	"gemini-pro", "gemini-1.0-pro", "gemini-1.5-flash", "gemini-1.5-pro", "text-embedding-004", "aqa",
 }

relay/adaptor/gemini/main.go

@@ -4,11 +4,12 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
 
+	"github.com/songquanpeng/one-api/common/render"
+
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -28,6 +29,11 @@ const (
 	VisionMaxImageNum = 16
 )
 
+var mimeTypeMap = map[string]string{
+	"json_object": "application/json",
+	"text":        "text/plain",
+}
+
 // Setting safety to the lowest possible values since Gemini is already powerless enough
 func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 	geminiRequest := ChatRequest{
@@ -56,6 +62,15 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 			MaxOutputTokens: textRequest.MaxTokens,
 		},
 	}
+	if textRequest.ResponseFormat != nil {
+		if mimeType, ok := mimeTypeMap[textRequest.ResponseFormat.Type]; ok {
+			geminiRequest.GenerationConfig.ResponseMimeType = mimeType
+		}
+		if textRequest.ResponseFormat.JsonSchema != nil {
+			geminiRequest.GenerationConfig.ResponseSchema = textRequest.ResponseFormat.JsonSchema.Schema
+			geminiRequest.GenerationConfig.ResponseMimeType = mimeTypeMap["json_object"]
+		}
+	}
 	if textRequest.Tools != nil {
 		functions := make([]model.Function, 0, len(textRequest.Tools))
 		for _, tool := range textRequest.Tools {

relay/adaptor/gemini/model.go

@@ -65,10 +65,12 @@ type ChatTools struct {
 }
 
 type ChatGenerationConfig struct {
-	Temperature     float64  `json:"temperature,omitempty"`
-	TopP            float64  `json:"topP,omitempty"`
-	TopK            float64  `json:"topK,omitempty"`
-	MaxOutputTokens int      `json:"maxOutputTokens,omitempty"`
-	CandidateCount  int      `json:"candidateCount,omitempty"`
-	StopSequences   []string `json:"stopSequences,omitempty"`
+	ResponseMimeType string   `json:"responseMimeType,omitempty"`
+	ResponseSchema   any      `json:"responseSchema,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
+	TopP             *float64 `json:"topP,omitempty"`
+	TopK             float64  `json:"topK,omitempty"`
+	MaxOutputTokens  int      `json:"maxOutputTokens,omitempty"`
+	CandidateCount   int      `json:"candidateCount,omitempty"`
+	StopSequences    []string `json:"stopSequences,omitempty"`
 }

relay/adaptor/groq/constants.go

@@ -4,9 +4,24 @@ package groq
 
 var ModelList = []string{
 	"gemma-7b-it",
-	"llama2-7b-2048",
-	"llama2-70b-4096",
-	"mixtral-8x7b-32768",
-	"llama3-8b-8192",
+	"gemma2-9b-it",
+	"llama-3.1-70b-versatile",
+	"llama-3.1-8b-instant",
+	"llama-3.2-11b-text-preview",
+	"llama-3.2-11b-vision-preview",
+	"llama-3.2-1b-preview",
+	"llama-3.2-3b-preview",
+	"llama-3.2-11b-vision-preview",
+	"llama-3.2-90b-text-preview",
+	"llama-3.2-90b-vision-preview",
+	"llama-guard-3-8b",
 	"llama3-70b-8192",
+	"llama3-8b-8192",
+	"llama3-groq-70b-8192-tool-use-preview",
+	"llama3-groq-8b-8192-tool-use-preview",
+	"llava-v1.5-7b-4096-preview",
+	"mixtral-8x7b-32768",
+	"distil-whisper-large-v3-en",
+	"whisper-large-v3",
+	"whisper-large-v3-turbo",
 }

relay/adaptor/ollama/adaptor.go

@@ -24,7 +24,7 @@ func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 	// https://github.com/ollama/ollama/blob/main/docs/api.md
 	fullRequestURL := fmt.Sprintf("%s/api/chat", meta.BaseURL)
 	if meta.Mode == relaymode.Embeddings {
-		fullRequestURL = fmt.Sprintf("%s/api/embeddings", meta.BaseURL)
+		fullRequestURL = fmt.Sprintf("%s/api/embed", meta.BaseURL)
 	}
 	return fullRequestURL, nil
 }

relay/adaptor/ollama/main.go

@@ -31,6 +31,8 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 			TopP:             request.TopP,
 			FrequencyPenalty: request.FrequencyPenalty,
 			PresencePenalty:  request.PresencePenalty,
+			NumPredict:  	  request.MaxTokens,
+			NumCtx:  	  request.NumCtx,
 		},
 		Stream: request.Stream,
 	}
@@ -118,8 +120,10 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 	common.SetEventStreamHeaders(c)
 
 	for scanner.Scan() {
-		data := strings.TrimPrefix(scanner.Text(), "}")
-		data = data + "}"
+		data := scanner.Text()
+		if strings.HasPrefix(data, "}") {
+		    data = strings.TrimPrefix(data, "}") + "}"
+		}
 
 		var ollamaResponse ChatResponse
 		err := json.Unmarshal([]byte(data), &ollamaResponse)
@@ -157,8 +161,15 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 
 func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *EmbeddingRequest {
 	return &EmbeddingRequest{
-		Model:  request.Model,
-		Prompt: strings.Join(request.ParseInput(), " "),
+		Model: request.Model,
+		Input: request.ParseInput(),
+		Options: &Options{
+			Seed:             int(request.Seed),
+			Temperature:      request.Temperature,
+			TopP:             request.TopP,
+			FrequencyPenalty: request.FrequencyPenalty,
+			PresencePenalty:  request.PresencePenalty,
+		},
 	}
 }
 
@@ -201,15 +212,17 @@ func embeddingResponseOllama2OpenAI(response *EmbeddingResponse) *openai.Embeddi
 	openAIEmbeddingResponse := openai.EmbeddingResponse{
 		Object: "list",
 		Data:   make([]openai.EmbeddingResponseItem, 0, 1),
-		Model:  "text-embedding-v1",
+		Model:  response.Model,
 		Usage:  model.Usage{TotalTokens: 0},
 	}
 
-	openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
-		Object:    `embedding`,
-		Index:     0,
-		Embedding: response.Embedding,
-	})
+	for i, embedding := range response.Embeddings {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
+			Object:    `embedding`,
+			Index:     i,
+			Embedding: embedding,
+		})
+	}
 	return &openAIEmbeddingResponse
 }
 

relay/adaptor/ollama/model.go

@@ -1,12 +1,14 @@
 package ollama
 
 type Options struct {
-	Seed             int     `json:"seed,omitempty"`
-	Temperature      float64 `json:"temperature,omitempty"`
-	TopK             int     `json:"top_k,omitempty"`
-	TopP             float64 `json:"top_p,omitempty"`
-	FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64 `json:"presence_penalty,omitempty"`
+	Seed             int      `json:"seed,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
+	TopK             int      `json:"top_k,omitempty"`
+	TopP             *float64 `json:"top_p,omitempty"`
+	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty"`
+	PresencePenalty  *float64 `json:"presence_penalty,omitempty"`
+	NumPredict       int      `json:"num_predict,omitempty"`
+	NumCtx           int      `json:"num_ctx,omitempty"`
 }
 
 type Message struct {
@@ -37,11 +39,15 @@ type ChatResponse struct {
 }
 
 type EmbeddingRequest struct {
-	Model  string `json:"model"`
-	Prompt string `json:"prompt"`
+	Model string   `json:"model"`
+	Input []string `json:"input"`
+	// Truncate  bool     `json:"truncate,omitempty"`
+	Options *Options `json:"options,omitempty"`
+	// KeepAlive string   `json:"keep_alive,omitempty"`
 }
 
 type EmbeddingResponse struct {
-	Error     string    `json:"error,omitempty"`
-	Embedding []float64 `json:"embedding,omitempty"`
+	Error      string      `json:"error,omitempty"`
+	Model      string      `json:"model"`
+	Embeddings [][]float64 `json:"embeddings"`
 }

relay/adaptor/openai/adaptor.go

@@ -75,6 +75,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
+	if request.Stream {
+		// always return usage in stream mode
+		if request.StreamOptions == nil {
+			request.StreamOptions = &model.StreamOptions{}
+		}
+		request.StreamOptions.IncludeUsage = true
+	}
 	return request, nil
 }
 

relay/adaptor/openai/compatible.go

@@ -11,8 +11,10 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/mistral"
 	"github.com/songquanpeng/one-api/relay/adaptor/moonshot"
 	"github.com/songquanpeng/one-api/relay/adaptor/novita"
+	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
 	"github.com/songquanpeng/one-api/relay/adaptor/stepfun"
 	"github.com/songquanpeng/one-api/relay/adaptor/togetherai"
+	"github.com/songquanpeng/one-api/relay/adaptor/xai"
 	"github.com/songquanpeng/one-api/relay/channeltype"
 )
 
@@ -30,6 +32,8 @@ var CompatibleChannels = []int{
 	channeltype.DeepSeek,
 	channeltype.TogetherAI,
 	channeltype.Novita,
+	channeltype.SiliconFlow,
+	channeltype.XAI,
 }
 
 func GetCompatibleChannelMeta(channelType int) (string, []string) {
@@ -60,6 +64,10 @@ func GetCompatibleChannelMeta(channelType int) (string, []string) {
 		return "doubao", doubao.ModelList
 	case channeltype.Novita:
 		return "novita", novita.ModelList
+	case channeltype.SiliconFlow:
+		return "siliconflow", siliconflow.ModelList
+	case channeltype.XAI:
+		return "xai", xai.ModelList
 	default:
 		return "openai", ModelList
 	}

relay/adaptor/openai/constants.go

@@ -8,6 +8,9 @@ var ModelList = []string{
 	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4o", "gpt-4o-2024-05-13",
+	"gpt-4o-2024-08-06",
+	"chatgpt-4o-latest",
+	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"gpt-4-vision-preview",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",

relay/adaptor/openai/main.go

@@ -55,8 +55,8 @@ func StreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*model.E
 				render.StringData(c, data) // if error happened, pass the data to client
 				continue                   // just ignore the error
 			}
-			if len(streamResponse.Choices) == 0 {
-				// but for empty choice, we should not pass it to client, this is for azure
+			if len(streamResponse.Choices) == 0 && streamResponse.Usage == nil {
+				// but for empty choice and no usage, we should not pass it to client, this is for azure
 				continue // just ignore empty choice
 			}
 			render.StringData(c, data)

relay/adaptor/openai/token.go

@@ -97,7 +97,11 @@ func CountTokenMessages(messages []model.Message, model string) int {
 				m := it.(map[string]any)
 				switch m["type"] {
 				case "text":
-					tokenNum += getTokenNum(tokenEncoder, m["text"].(string))
+					if textValue, ok := m["text"]; ok {
+						if textString, ok := textValue.(string); ok {
+							tokenNum += getTokenNum(tokenEncoder, textString)
+						}
+					}
 				case "image_url":
 					imageUrl, ok := m["image_url"].(map[string]any)
 					if ok {
@@ -106,7 +110,7 @@ func CountTokenMessages(messages []model.Message, model string) int {
 						if imageUrl["detail"] != nil {
 							detail = imageUrl["detail"].(string)
 						}
-						imageTokens, err := countImageTokens(url, detail)
+						imageTokens, err := countImageTokens(url, detail, model)
 						if err != nil {
 							logger.SysError("error counting image tokens: " + err.Error())
 						} else {
@@ -130,11 +134,15 @@ const (
 	lowDetailCost         = 85
 	highDetailCostPerTile = 170
 	additionalCost        = 85
+	// gpt-4o-mini cost higher than other model
+	gpt4oMiniLowDetailCost  = 2833
+	gpt4oMiniHighDetailCost = 5667
+	gpt4oMiniAdditionalCost = 2833
 )
 
 // https://platform.openai.com/docs/guides/vision/calculating-costs
 // https://github.com/openai/openai-cookbook/blob/05e3f9be4c7a2ae7ecf029a7c32065b024730ebe/examples/How_to_count_tokens_with_tiktoken.ipynb
-func countImageTokens(url string, detail string) (_ int, err error) {
+func countImageTokens(url string, detail string, model string) (_ int, err error) {
 	var fetchSize = true
 	var width, height int
 	// Reference: https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding
@@ -168,6 +176,9 @@ func countImageTokens(url string, detail string) (_ int, err error) {
 	}
 	switch detail {
 	case "low":
+		if strings.HasPrefix(model, "gpt-4o-mini") {
+			return gpt4oMiniLowDetailCost, nil
+		}
 		return lowDetailCost, nil
 	case "high":
 		if fetchSize {
@@ -187,6 +198,9 @@ func countImageTokens(url string, detail string) (_ int, err error) {
 			height = int(float64(height) * ratio)
 		}
 		numSquares := int(math.Ceil(float64(width)/512) * math.Ceil(float64(height)/512))
+		if strings.HasPrefix(model, "gpt-4o-mini") {
+			return numSquares*gpt4oMiniHighDetailCost + gpt4oMiniAdditionalCost, nil
+		}
 		result := numSquares*highDetailCostPerTile + additionalCost
 		return result, nil
 	default:

relay/adaptor/palm/model.go

@@ -19,11 +19,11 @@ type Prompt struct {
 }
 
 type ChatRequest struct {
-	Prompt         Prompt  `json:"prompt"`
-	Temperature    float64 `json:"temperature,omitempty"`
-	CandidateCount int     `json:"candidateCount,omitempty"`
-	TopP           float64 `json:"topP,omitempty"`
-	TopK           int     `json:"topK,omitempty"`
+	Prompt         Prompt   `json:"prompt"`
+	Temperature    *float64 `json:"temperature,omitempty"`
+	CandidateCount int      `json:"candidateCount,omitempty"`
+	TopP           *float64 `json:"topP,omitempty"`
+	TopK           int      `json:"topK,omitempty"`
 }
 
 type Error struct {

relay/adaptor/proxy/adaptor.go

@@ -0,0 +1,89 @@
+package proxy
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkg/errors"
+	"github.com/songquanpeng/one-api/relay/adaptor"
+	channelhelper "github.com/songquanpeng/one-api/relay/adaptor"
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/model"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
+)
+
+var _ adaptor.Adaptor = new(Adaptor)
+
+const channelName = "proxy"
+
+type Adaptor struct{}
+
+func (a *Adaptor) Init(meta *meta.Meta) {
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	return nil, errors.New("notimplement")
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Meta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	for k, v := range resp.Header {
+		for _, vv := range v {
+			c.Writer.Header().Set(k, vv)
+		}
+	}
+
+	c.Writer.WriteHeader(resp.StatusCode)
+	if _, gerr := io.Copy(c.Writer, resp.Body); gerr != nil {
+		return nil, &relaymodel.ErrorWithStatusCode{
+			StatusCode: http.StatusInternalServerError,
+			Error: relaymodel.Error{
+				Message: gerr.Error(),
+			},
+		}
+	}
+
+	return nil, nil
+}
+
+func (a *Adaptor) GetModelList() (models []string) {
+	return nil
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return channelName
+}
+
+// GetRequestURL remove static prefix, and return the real request url to the upstream service
+func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
+	prefix := fmt.Sprintf("/v1/oneapi/proxy/%d", meta.ChannelId)
+	return meta.BaseURL + strings.TrimPrefix(meta.RequestURLPath, prefix), nil
+
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *meta.Meta) error {
+	for k, v := range c.Request.Header {
+		req.Header.Set(k, v[0])
+	}
+
+	// remove unnecessary headers
+	req.Header.Del("Host")
+	req.Header.Del("Content-Length")
+	req.Header.Del("Accept-Encoding")
+	req.Header.Del("Connection")
+
+	// set authorization header
+	req.Header.Set("Authorization", meta.APIKey)
+
+	return nil
+}
+
+func (a *Adaptor) ConvertImageRequest(request *model.ImageRequest) (any, error) {
+	return nil, errors.Errorf("not implement")
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *meta.Meta, requestBody io.Reader) (*http.Response, error) {
+	return channelhelper.DoRequestHelper(a, c, meta, requestBody)
+}

relay/adaptor/siliconflow/constants.go

@@ -0,0 +1,36 @@
+package siliconflow
+
+// https://docs.siliconflow.cn/docs/getting-started
+
+var ModelList = []string{
+	"deepseek-ai/deepseek-llm-67b-chat",
+	"Qwen/Qwen1.5-14B-Chat",
+	"Qwen/Qwen1.5-7B-Chat",
+	"Qwen/Qwen1.5-110B-Chat",
+	"Qwen/Qwen1.5-32B-Chat",
+	"01-ai/Yi-1.5-6B-Chat",
+	"01-ai/Yi-1.5-9B-Chat-16K",
+	"01-ai/Yi-1.5-34B-Chat-16K",
+	"THUDM/chatglm3-6b",
+	"deepseek-ai/DeepSeek-V2-Chat",
+	"THUDM/glm-4-9b-chat",
+	"Qwen/Qwen2-72B-Instruct",
+	"Qwen/Qwen2-7B-Instruct",
+	"Qwen/Qwen2-57B-A14B-Instruct",
+	"deepseek-ai/DeepSeek-Coder-V2-Instruct",
+	"Qwen/Qwen2-1.5B-Instruct",
+	"internlm/internlm2_5-7b-chat",
+	"BAAI/bge-large-en-v1.5",
+	"BAAI/bge-large-zh-v1.5",
+	"Pro/Qwen/Qwen2-7B-Instruct",
+	"Pro/Qwen/Qwen2-1.5B-Instruct",
+	"Pro/Qwen/Qwen1.5-7B-Chat",
+	"Pro/THUDM/glm-4-9b-chat",
+	"Pro/THUDM/chatglm3-6b",
+	"Pro/01-ai/Yi-1.5-9B-Chat-16K",
+	"Pro/01-ai/Yi-1.5-6B-Chat",
+	"Pro/google/gemma-2-9b-it",
+	"Pro/internlm/internlm2_5-7b-chat",
+	"Pro/meta-llama/Meta-Llama-3-8B-Instruct",
+	"Pro/mistralai/Mistral-7B-Instruct-v0.2",
+}

relay/adaptor/stepfun/constants.go

@@ -1,7 +1,13 @@
 package stepfun
 
 var ModelList = []string{
+	"step-1-8k",
 	"step-1-32k",
+	"step-1-128k",
+	"step-1-256k",
+	"step-1-flash",
+	"step-2-16k",
+	"step-1v-8k",
 	"step-1v-32k",
-	"step-1-200k",
+	"step-1x-medium",
 }

relay/adaptor/tencent/constants.go

@@ -5,4 +5,5 @@ var ModelList = []string{
 	"hunyuan-standard",
 	"hunyuan-standard-256K",
 	"hunyuan-pro",
+	"hunyuan-vision",
 }

relay/adaptor/tencent/main.go

@@ -39,8 +39,8 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		Model:       &request.Model,
 		Stream:      &request.Stream,
 		Messages:    messages,
-		TopP:        &request.TopP,
-		Temperature: &request.Temperature,
+		TopP:        request.TopP,
+		Temperature: request.Temperature,
 	}
 }
 

relay/adaptor/vertexai/adaptor.go

@@ -0,0 +1,117 @@
+package vertexai
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/adaptor"
+	channelhelper "github.com/songquanpeng/one-api/relay/adaptor"
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/model"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
+)
+
+var _ adaptor.Adaptor = new(Adaptor)
+
+const channelName = "vertexai"
+
+type Adaptor struct{}
+
+func (a *Adaptor) Init(meta *meta.Meta) {
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+
+	adaptor := GetAdaptor(request.Model)
+	if adaptor == nil {
+		return nil, errors.New("adaptor not found")
+	}
+
+	return adaptor.ConvertRequest(c, relayMode, request)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Meta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	adaptor := GetAdaptor(meta.ActualModelName)
+	if adaptor == nil {
+		return nil, &relaymodel.ErrorWithStatusCode{
+			StatusCode: http.StatusInternalServerError,
+			Error: relaymodel.Error{
+				Message: "adaptor not found",
+			},
+		}
+	}
+	return adaptor.DoResponse(c, resp, meta)
+}
+
+func (a *Adaptor) GetModelList() (models []string) {
+	models = modelList
+	return
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return channelName
+}
+
+func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
+	suffix := ""
+	if strings.HasPrefix(meta.ActualModelName, "gemini") {
+		if meta.IsStream {
+			suffix = "streamGenerateContent?alt=sse"
+		} else {
+			suffix = "generateContent"
+		}
+	} else {
+		if meta.IsStream {
+			suffix = "streamRawPredict?alt=sse"
+		} else {
+			suffix = "rawPredict"
+		}
+	}
+
+	if meta.BaseURL != "" {
+		return fmt.Sprintf(
+			"%s/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
+			meta.BaseURL,
+			meta.Config.VertexAIProjectID,
+			meta.Config.Region,
+			meta.ActualModelName,
+			suffix,
+		), nil
+	}
+	return fmt.Sprintf(
+		"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
+		meta.Config.Region,
+		meta.Config.VertexAIProjectID,
+		meta.Config.Region,
+		meta.ActualModelName,
+		suffix,
+	), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *meta.Meta) error {
+	adaptor.SetupCommonRequestHeader(c, req, meta)
+	token, err := getToken(c, meta.ChannelId, meta.Config.VertexAIADC)
+	if err != nil {
+		return err
+	}
+	req.Header.Set("Authorization", "Bearer "+token)
+	return nil
+}
+
+func (a *Adaptor) ConvertImageRequest(request *model.ImageRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, meta *meta.Meta, requestBody io.Reader) (*http.Response, error) {
+	return channelhelper.DoRequestHelper(a, c, meta, requestBody)
+}

relay/adaptor/vertexai/claude/adapter.go

@@ -0,0 +1,60 @@
+package vertexai
+
+import (
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkg/errors"
+	"github.com/songquanpeng/one-api/common/ctxkey"
+	"github.com/songquanpeng/one-api/relay/adaptor/anthropic"
+
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/model"
+)
+
+var ModelList = []string{
+	"claude-3-haiku@20240307",
+	"claude-3-sonnet@20240229",
+	"claude-3-opus@20240229",
+	"claude-3-5-sonnet@20240620",
+	"claude-3-5-sonnet-v2@20241022",
+	"claude-3-5-haiku@20241022",
+}
+
+const anthropicVersion = "vertex-2023-10-16"
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+
+	claudeReq := anthropic.ConvertRequest(*request)
+	req := Request{
+		AnthropicVersion: anthropicVersion,
+		// Model:            claudeReq.Model,
+		Messages:    claudeReq.Messages,
+		System:      claudeReq.System,
+		MaxTokens:   claudeReq.MaxTokens,
+		Temperature: claudeReq.Temperature,
+		TopP:        claudeReq.TopP,
+		TopK:        claudeReq.TopK,
+		Stream:      claudeReq.Stream,
+		Tools:       claudeReq.Tools,
+	}
+
+	c.Set(ctxkey.RequestModel, request.Model)
+	c.Set(ctxkey.ConvertedRequest, req)
+	return req, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Meta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		err, usage = anthropic.StreamHandler(c, resp)
+	} else {
+		err, usage = anthropic.Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+	}
+	return
+}

relay/adaptor/vertexai/claude/model.go

@@ -0,0 +1,19 @@
+package vertexai
+
+import "github.com/songquanpeng/one-api/relay/adaptor/anthropic"
+
+type Request struct {
+	// AnthropicVersion must be "vertex-2023-10-16"
+	AnthropicVersion string `json:"anthropic_version"`
+	// Model            string              `json:"model"`
+	Messages      []anthropic.Message `json:"messages"`
+	System        string              `json:"system,omitempty"`
+	MaxTokens     int                 `json:"max_tokens,omitempty"`
+	StopSequences []string            `json:"stop_sequences,omitempty"`
+	Stream        bool                `json:"stream,omitempty"`
+	Temperature   *float64            `json:"temperature,omitempty"`
+	TopP          *float64            `json:"top_p,omitempty"`
+	TopK          int                 `json:"top_k,omitempty"`
+	Tools         []anthropic.Tool    `json:"tools,omitempty"`
+	ToolChoice    any                 `json:"tool_choice,omitempty"`
+}

relay/adaptor/vertexai/gemini/adapter.go

@@ -0,0 +1,49 @@
+package vertexai
+
+import (
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkg/errors"
+	"github.com/songquanpeng/one-api/common/ctxkey"
+	"github.com/songquanpeng/one-api/relay/adaptor/gemini"
+	"github.com/songquanpeng/one-api/relay/adaptor/openai"
+	"github.com/songquanpeng/one-api/relay/relaymode"
+
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/model"
+)
+
+var ModelList = []string{
+	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision", "gemini-1.5-pro-002", "gemini-1.5-flash-002", 
+}
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+
+	geminiRequest := gemini.ConvertRequest(*request)
+	c.Set(ctxkey.RequestModel, request.Model)
+	c.Set(ctxkey.ConvertedRequest, geminiRequest)
+	return geminiRequest, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Meta) (usage *model.Usage, err *model.ErrorWithStatusCode) {
+	if meta.IsStream {
+		var responseText string
+		err, responseText = gemini.StreamHandler(c, resp)
+		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
+	} else {
+		switch meta.Mode {
+		case relaymode.Embeddings:
+			err, usage = gemini.EmbeddingHandler(c, resp)
+		default:
+			err, usage = gemini.Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+		}
+	}
+	return
+}

relay/adaptor/vertexai/registry.go

@@ -0,0 +1,50 @@
+package vertexai
+
+import (
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+	claude "github.com/songquanpeng/one-api/relay/adaptor/vertexai/claude"
+	gemini "github.com/songquanpeng/one-api/relay/adaptor/vertexai/gemini"
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/model"
+)
+
+type VertexAIModelType int
+
+const (
+	VerterAIClaude VertexAIModelType = iota + 1
+	VerterAIGemini
+)
+
+var modelMapping = map[string]VertexAIModelType{}
+var modelList = []string{}
+
+func init() {
+	modelList = append(modelList, claude.ModelList...)
+	for _, model := range claude.ModelList {
+		modelMapping[model] = VerterAIClaude
+	}
+
+	modelList = append(modelList, gemini.ModelList...)
+	for _, model := range gemini.ModelList {
+		modelMapping[model] = VerterAIGemini
+	}
+}
+
+type innerAIAdapter interface {
+	ConvertRequest(c *gin.Context, relayMode int, request *model.GeneralOpenAIRequest) (any, error)
+	DoResponse(c *gin.Context, resp *http.Response, meta *meta.Meta) (usage *model.Usage, err *model.ErrorWithStatusCode)
+}
+
+func GetAdaptor(model string) innerAIAdapter {
+	adaptorType := modelMapping[model]
+	switch adaptorType {
+	case VerterAIClaude:
+		return &claude.Adaptor{}
+	case VerterAIGemini:
+		return &gemini.Adaptor{}
+	default:
+		return nil
+	}
+}

relay/adaptor/vertexai/token.go

@@ -0,0 +1,62 @@
+package vertexai
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"time"
+
+	credentials "cloud.google.com/go/iam/credentials/apiv1"
+	"cloud.google.com/go/iam/credentials/apiv1/credentialspb"
+	"github.com/patrickmn/go-cache"
+	"google.golang.org/api/option"
+)
+
+type ApplicationDefaultCredentials struct {
+	Type                    string `json:"type"`
+	ProjectID               string `json:"project_id"`
+	PrivateKeyID            string `json:"private_key_id"`
+	PrivateKey              string `json:"private_key"`
+	ClientEmail             string `json:"client_email"`
+	ClientID                string `json:"client_id"`
+	AuthURI                 string `json:"auth_uri"`
+	TokenURI                string `json:"token_uri"`
+	AuthProviderX509CertURL string `json:"auth_provider_x509_cert_url"`
+	ClientX509CertURL       string `json:"client_x509_cert_url"`
+	UniverseDomain          string `json:"universe_domain"`
+}
+
+var Cache = cache.New(50*time.Minute, 55*time.Minute)
+
+const defaultScope = "https://www.googleapis.com/auth/cloud-platform"
+
+func getToken(ctx context.Context, channelId int, adcJson string) (string, error) {
+	cacheKey := fmt.Sprintf("vertexai-token-%d", channelId)
+	if token, found := Cache.Get(cacheKey); found {
+		return token.(string), nil
+	}
+	adc := &ApplicationDefaultCredentials{}
+	if err := json.Unmarshal([]byte(adcJson), adc); err != nil {
+		return "", fmt.Errorf("Failed to decode credentials file: %w", err)
+	}
+
+	c, err := credentials.NewIamCredentialsClient(ctx, option.WithCredentialsJSON([]byte(adcJson)))
+	if err != nil {
+		return "", fmt.Errorf("Failed to create client: %w", err)
+	}
+	defer c.Close()
+
+	req := &credentialspb.GenerateAccessTokenRequest{
+		// See https://pkg.go.dev/cloud.google.com/go/iam/credentials/apiv1/credentialspb#GenerateAccessTokenRequest.
+		Name:  fmt.Sprintf("projects/-/serviceAccounts/%s", adc.ClientEmail),
+		Scope: []string{defaultScope},
+	}
+	resp, err := c.GenerateAccessToken(ctx, req)
+	if err != nil {
+		return "", fmt.Errorf("Failed to generate access token: %w", err)
+	}
+	_ = resp
+
+	Cache.Set(cacheKey, resp.AccessToken, cache.DefaultExpiration)
+	return resp.AccessToken, nil
+}

relay/adaptor/xai/constants.go

@@ -0,0 +1,5 @@
+package xai
+
+var ModelList = []string{
+	"grok-beta",
+}

relay/adaptor/xunfei/constants.go

@@ -5,6 +5,8 @@ var ModelList = []string{
 	"SparkDesk-v1.1",
 	"SparkDesk-v2.1",
 	"SparkDesk-v3.1",
+	"SparkDesk-v3.1-128K",
 	"SparkDesk-v3.5",
+	"SparkDesk-v3.5-32K",
 	"SparkDesk-v4.0",
 }

relay/adaptor/xunfei/main.go

@@ -272,9 +272,9 @@ func xunfeiMakeRequest(textRequest model.GeneralOpenAIRequest, domain, authUrl,
 }
 
 func parseAPIVersionByModelName(modelName string) string {
-	parts := strings.Split(modelName, "-")
-	if len(parts) == 2 {
-		return parts[1]
+	index := strings.IndexAny(modelName, "-")
+	if index != -1 {
+		return modelName[index+1:]
 	}
 	return ""
 }
@@ -283,13 +283,17 @@ func parseAPIVersionByModelName(modelName string) string {
 func apiVersion2domain(apiVersion string) string {
 	switch apiVersion {
 	case "v1.1":
-		return "general"
+		return "lite"
 	case "v2.1":
 		return "generalv2"
 	case "v3.1":
 		return "generalv3"
+	case "v3.1-128K":
+		return "pro-128k"
 	case "v3.5":
 		return "generalv3.5"
+	case "v3.5-32K":
+		return "max-32k"
 	case "v4.0":
 		return "4.0Ultra"
 	}
@@ -297,7 +301,17 @@ func apiVersion2domain(apiVersion string) string {
 }
 
 func getXunfeiAuthUrl(apiVersion string, apiKey string, apiSecret string) (string, string) {
+	var authUrl string
 	domain := apiVersion2domain(apiVersion)
-	authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
+	switch apiVersion {
+	case "v3.1-128K":
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/pro-128k"), apiKey, apiSecret)
+		break
+	case "v3.5-32K":
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/max-32k"), apiKey, apiSecret)
+		break
+	default:
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
+	}
 	return domain, authUrl
 }

relay/adaptor/xunfei/model.go

@@ -19,11 +19,11 @@ type ChatRequest struct {
 	} `json:"header"`
 	Parameter struct {
 		Chat struct {
-			Domain      string  `json:"domain,omitempty"`
-			Temperature float64 `json:"temperature,omitempty"`
-			TopK        int     `json:"top_k,omitempty"`
-			MaxTokens   int     `json:"max_tokens,omitempty"`
-			Auditing    bool    `json:"auditing,omitempty"`
+			Domain      string   `json:"domain,omitempty"`
+			Temperature *float64 `json:"temperature,omitempty"`
+			TopK        int      `json:"top_k,omitempty"`
+			MaxTokens   int      `json:"max_tokens,omitempty"`
+			Auditing    bool     `json:"auditing,omitempty"`
 		} `json:"chat"`
 	} `json:"parameter"`
 	Payload struct {

relay/adaptor/zhipu/adaptor.go

@@ -4,13 +4,13 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"
 	"io"
-	"math"
 	"net/http"
 	"strings"
 )
@@ -65,13 +65,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 		baiduEmbeddingRequest, err := ConvertEmbeddingRequest(*request)
 		return baiduEmbeddingRequest, err
 	default:
-		// TopP (0.0, 1.0)
-		request.TopP = math.Min(0.99, request.TopP)
-		request.TopP = math.Max(0.01, request.TopP)
+		// TopP [0.0, 1.0]
+		request.TopP = helper.Float64PtrMax(request.TopP, 1)
+		request.TopP = helper.Float64PtrMin(request.TopP, 0)
 
-		// Temperature (0.0, 1.0)
-		request.Temperature = math.Min(0.99, request.Temperature)
-		request.Temperature = math.Max(0.01, request.Temperature)
+		// Temperature [0.0, 1.0]
+		request.Temperature = helper.Float64PtrMax(request.Temperature, 1)
+		request.Temperature = helper.Float64PtrMin(request.Temperature, 0)
 		a.SetVersionByModeName(request.Model)
 		if a.APIVersion == "v4" {
 			return request, nil

relay/adaptor/zhipu/model.go

@@ -12,8 +12,8 @@ type Message struct {
 
 type Request struct {
 	Prompt      []Message `json:"prompt"`
-	Temperature float64   `json:"temperature,omitempty"`
-	TopP        float64   `json:"top_p,omitempty"`
+	Temperature *float64  `json:"temperature,omitempty"`
+	TopP        *float64  `json:"top_p,omitempty"`
 	RequestId   string    `json:"request_id,omitempty"`
 	Incremental bool      `json:"incremental,omitempty"`
 }

relay/apitype/define.go

@@ -17,6 +17,8 @@ const (
 	Cohere
 	Cloudflare
 	DeepL
+	VertexAI
+	Proxy
 
 	Dummy // this one is only for count, do not add any channel after this
 )

relay/billing/ratio/image.go

@@ -30,6 +30,14 @@ var ImageSizeRatios = map[string]map[string]float64{
 		"720x1280":  1,
 		"1280x720":  1,
 	},
+	"step-1x-medium": {
+		"256x256":   1,
+		"512x512":   1,
+		"768x768":   1,
+		"1024x1024": 1,
+		"1280x800":  1,
+		"800x1280":  1,
+	},
 }
 
 var ImageGenerationAmounts = map[string][2]int{
@@ -39,6 +47,7 @@ var ImageGenerationAmounts = map[string][2]int{
 	"ali-stable-diffusion-v1.5": {1, 4}, // Ali
 	"wanx-v1":                   {1, 4}, // Ali
 	"cogview-3":                 {1, 1},
+	"step-1x-medium":            {1, 1},
 }
 
 var ImagePromptLengthLimitations = map[string]int{
@@ -48,6 +57,7 @@ var ImagePromptLengthLimitations = map[string]int{
 	"ali-stable-diffusion-v1.5": 4000,
 	"wanx-v1":                   4000,
 	"cogview-3":                 833,
+	"step-1x-medium":            4000,
 }
 
 var ImageOriginModelName = map[string]string{

relay/billing/ratio/model.go

@@ -28,15 +28,19 @@ var ModelRatio = map[string]float64{
 	"gpt-4-32k":               30,
 	"gpt-4-32k-0314":          30,
 	"gpt-4-32k-0613":          30,
-	"gpt-4-1106-preview":      5,    // $0.01 / 1K tokens
-	"gpt-4-0125-preview":      5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-preview":     5,    // $0.01 / 1K tokens
-	"gpt-4-turbo":             5,    // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":  5,    // $0.01 / 1K tokens
-	"gpt-4o":                  2.5,  // $0.005 / 1K tokens
-	"gpt-4o-2024-05-13":       2.5,  // $0.005 / 1K tokens
-	"gpt-4-vision-preview":    5,    // $0.01 / 1K tokens
-	"gpt-3.5-turbo":           0.25, // $0.0005 / 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-turbo":             5,     // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":  5,     // $0.01 / 1K tokens
+	"gpt-4o":                  2.5,   // $0.005 / 1K tokens
+	"chatgpt-4o-latest":       2.5,   // $0.005 / 1K tokens
+	"gpt-4o-2024-05-13":       2.5,   // $0.005 / 1K tokens
+	"gpt-4o-2024-08-06":       1.25,  // $0.0025 / 1K tokens
+	"gpt-4o-mini":             0.075, // $0.00015 / 1K tokens
+	"gpt-4o-mini-2024-07-18":  0.075, // $0.00015 / 1K tokens
+	"gpt-4-vision-preview":    5,     // $0.01 / 1K tokens
+	"gpt-3.5-turbo":           0.25,  // $0.0005 / 1K tokens
 	"gpt-3.5-turbo-0301":      0.75,
 	"gpt-3.5-turbo-0613":      0.75,
 	"gpt-3.5-turbo-16k":       1.5, // $0.003 / 1K tokens
@@ -75,8 +79,10 @@ var ModelRatio = map[string]float64{
 	"claude-2.0":                 8.0 / 1000 * USD,
 	"claude-2.1":                 8.0 / 1000 * USD,
 	"claude-3-haiku-20240307":    0.25 / 1000 * USD,
+	"claude-3-5-haiku-20241022":  1.0 / 1000 * USD,
 	"claude-3-sonnet-20240229":   3.0 / 1000 * USD,
 	"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
+	"claude-3-5-sonnet-20241022": 3.0 / 1000 * USD,
 	"claude-3-opus-20240229":     15.0 / 1000 * USD,
 	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
 	"ERNIE-4.0-8K":       0.120 * RMB,
@@ -96,12 +102,11 @@ var ModelRatio = map[string]float64{
 	"bge-large-en":       0.002 * RMB,
 	"tao-8k":             0.002 * RMB,
 	// https://ai.google.dev/pricing
-	"PaLM-2":                    1,
-	"gemini-pro":                1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-pro-vision":         1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-1.0-pro-vision-001": 1,
-	"gemini-1.0-pro-001":        1,
-	"gemini-1.5-pro":            1,
+	"gemini-pro":       1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro":   1,
+	"gemini-1.5-flash": 1,
+	"gemini-1.5-pro":   1,
+	"aqa":              1,
 	// https://open.bigmodel.cn/pricing
 	"glm-4":         0.1 * RMB,
 	"glm-4v":        0.1 * RMB,
@@ -125,7 +130,9 @@ var ModelRatio = map[string]float64{
 	"SparkDesk-v1.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v2.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.1-128K":       1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5-32K":        1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v4.0":            1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
@@ -156,20 +163,35 @@ var ModelRatio = map[string]float64{
 	"mistral-large-latest":  8.0 / 1000 * USD,
 	"mistral-embed":         0.1 / 1000 * USD,
 	// https://wow.groq.com/#:~:text=inquiries%C2%A0here.-,Model,-Current%20Speed
-	"llama3-70b-8192":    0.59 / 1000 * USD,
-	"mixtral-8x7b-32768": 0.27 / 1000 * USD,
-	"llama3-8b-8192":     0.05 / 1000 * USD,
-	"gemma-7b-it":        0.1 / 1000 * USD,
-	"llama2-70b-4096":    0.64 / 1000 * USD,
-	"llama2-7b-2048":     0.1 / 1000 * USD,
+	"gemma-7b-it":                           0.07 / 1000000 * USD,
+	"gemma2-9b-it":                          0.20 / 1000000 * USD,
+	"llama-3.1-70b-versatile":               0.59 / 1000000 * USD,
+	"llama-3.1-8b-instant":                  0.05 / 1000000 * USD,
+	"llama-3.2-11b-text-preview":            0.05 / 1000000 * USD,
+	"llama-3.2-11b-vision-preview":          0.05 / 1000000 * USD,
+	"llama-3.2-1b-preview":                  0.05 / 1000000 * USD,
+	"llama-3.2-3b-preview":                  0.05 / 1000000 * USD,
+	"llama-3.2-90b-text-preview":            0.59 / 1000000 * USD,
+	"llama-guard-3-8b":                      0.05 / 1000000 * USD,
+	"llama3-70b-8192":                       0.59 / 1000000 * USD,
+	"llama3-8b-8192":                        0.05 / 1000000 * USD,
+	"llama3-groq-70b-8192-tool-use-preview": 0.89 / 1000000 * USD,
+	"llama3-groq-8b-8192-tool-use-preview":  0.19 / 1000000 * USD,
+	"mixtral-8x7b-32768":                    0.24 / 1000000 * USD,
+
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	"yi-34b-chat-0205": 2.5 / 1000 * RMB,
 	"yi-34b-chat-200k": 12.0 / 1000 * RMB,
 	"yi-vl-plus":       6.0 / 1000 * RMB,
-	// stepfun todo
-	"step-1v-32k": 0.024 * RMB,
-	"step-1-32k":  0.024 * RMB,
-	"step-1-200k": 0.15 * RMB,
+	// https://platform.stepfun.com/docs/pricing/details
+	"step-1-8k":    0.005 / 1000 * RMB,
+	"step-1-32k":   0.015 / 1000 * RMB,
+	"step-1-128k":  0.040 / 1000 * RMB,
+	"step-1-256k":  0.095 / 1000 * RMB,
+	"step-1-flash": 0.001 / 1000 * RMB,
+	"step-2-16k":   0.038 / 1000 * RMB,
+	"step-1v-8k":   0.005 / 1000 * RMB,
+	"step-1v-32k":  0.015 / 1000 * RMB,
 	// aws llama3 https://aws.amazon.com/cn/bedrock/pricing/
 	"llama3-8b-8192(33)":  0.0003 / 0.002,  // $0.0003 / 1K tokens
 	"llama3-70b-8192(33)": 0.00265 / 0.002, // $0.00265 / 1K tokens
@@ -187,6 +209,8 @@ var ModelRatio = map[string]float64{
 	"deepl-zh": 25.0 / 1000 * USD,
 	"deepl-en": 25.0 / 1000 * USD,
 	"deepl-ja": 25.0 / 1000 * USD,
+	// https://console.x.ai/
+	"grok-beta": 5.0 / 1000 * USD,
 }
 
 var CompletionRatio = map[string]float64{
@@ -195,8 +219,10 @@ var CompletionRatio = map[string]float64{
 	"llama3-70b-8192(33)": 0.0035 / 0.00265,
 }
 
-var DefaultModelRatio map[string]float64
-var DefaultCompletionRatio map[string]float64
+var (
+	DefaultModelRatio      map[string]float64
+	DefaultCompletionRatio map[string]float64
+)
 
 func init() {
 	DefaultModelRatio = make(map[string]float64)
@@ -308,6 +334,9 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") {
+		if strings.HasPrefix(name, "gpt-4o-mini") || name == "gpt-4o-2024-08-06" {
+			return 4
+		}
 		if strings.HasPrefix(name, "gpt-4-turbo") ||
 			strings.HasPrefix(name, "gpt-4o") ||
 			strings.HasSuffix(name, "preview") {
@@ -315,6 +344,9 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		}
 		return 2
 	}
+	if name == "chatgpt-4o-latest" {
+		return 3
+	}
 	if strings.HasPrefix(name, "claude-3") {
 		return 5
 	}
@@ -343,6 +375,8 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		return 3
 	case "command-r-plus":
 		return 5
+	case "grok-beta":
+		return 3
 	}
 	return 1
 }

relay/channeltype/define.go

@@ -43,5 +43,9 @@ const (
 	TogetherAI
 	Doubao
 	Novita
+	VertextAI
+	Proxy
+	SiliconFlow
+	XAI
 	Dummy
 )

relay/channeltype/helper.go

@@ -35,6 +35,10 @@ func ToAPIType(channelType int) int {
 		apiType = apitype.Cloudflare
 	case DeepL:
 		apiType = apitype.DeepL
+	case VertextAI:
+		apiType = apitype.VertexAI
+	case Proxy:
+		apiType = apitype.Proxy
 	}
 
 	return apiType

relay/channeltype/url.go

@@ -43,6 +43,10 @@ var ChannelBaseURLs = []string{
 	"https://api.together.xyz",                  // 39
 	"https://ark.cn-beijing.volces.com",         // 40
 	"https://api.novita.ai/v3/openai",           // 41
+	"",                                          // 42
+	"",                                          // 43
+	"https://api.siliconflow.cn",                // 44
+	"https://api.x.ai",                          // 45
 }
 
 func init() {

relay/constant/role/define.go

@@ -1,5 +1,6 @@
 package role
 
 const (
+	System    = "system"
 	Assistant = "assistant"
 )

relay/controller/helper.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/relay/constant/role"
 	"math"
 	"net/http"
 	"strings"
@@ -90,7 +91,7 @@ func preConsumeQuota(ctx context.Context, textRequest *relaymodel.GeneralOpenAIR
 	return preConsumedQuota, nil
 }
 
-func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.Meta, textRequest *relaymodel.GeneralOpenAIRequest, ratio float64, preConsumedQuota int64, modelRatio float64, groupRatio float64) {
+func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.Meta, textRequest *relaymodel.GeneralOpenAIRequest, ratio float64, preConsumedQuota int64, modelRatio float64, groupRatio float64, systemPromptReset bool) {
 	if usage == nil {
 		logger.Error(ctx, "usage is nil, which is unexpected")
 		return
@@ -118,7 +119,11 @@ func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *meta.M
 	if err != nil {
 		logger.Error(ctx, "error update user quota cache: "+err.Error())
 	}
-	logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio)
+	var extraLog string
+	if systemPromptReset {
+		extraLog = " （注意系统提示词已被重置）"
+	}
+	logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f%s", modelRatio, groupRatio, completionRatio, extraLog)
 	model.RecordConsumeLog(ctx, meta.UserId, meta.ChannelId, promptTokens, completionTokens, textRequest.Model, meta.TokenName, quota, logContent)
 	model.UpdateUserUsedQuotaAndRequestCount(meta.UserId, quota)
 	model.UpdateChannelUsedQuota(meta.ChannelId, quota)
@@ -154,3 +159,23 @@ func isErrorHappened(meta *meta.Meta, resp *http.Response) bool {
 	}
 	return false
 }
+
+func setSystemPrompt(ctx context.Context, request *relaymodel.GeneralOpenAIRequest, prompt string) (reset bool) {
+	if prompt == "" {
+		return false
+	}
+	if len(request.Messages) == 0 {
+		return false
+	}
+	if request.Messages[0].Role == role.System {
+		request.Messages[0].Content = prompt
+		logger.Infof(ctx, "rewrite system prompt")
+		return true
+	}
+	request.Messages = append([]relaymodel.Message{{
+		Role:    role.System,
+		Content: prompt,
+	}}, request.Messages...)
+	logger.Infof(ctx, "add system prompt")
+	return true
+}

relay/controller/proxy.go

@@ -0,0 +1,41 @@
+// Package controller is a package for handling the relay controller
+package controller
+
+import (
+	"fmt"
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay"
+	"github.com/songquanpeng/one-api/relay/adaptor/openai"
+	"github.com/songquanpeng/one-api/relay/meta"
+	relaymodel "github.com/songquanpeng/one-api/relay/model"
+)
+
+// RelayProxyHelper is a helper function to proxy the request to the upstream service
+func RelayProxyHelper(c *gin.Context, relayMode int) *relaymodel.ErrorWithStatusCode {
+	ctx := c.Request.Context()
+	meta := meta.GetByContext(c)
+
+	adaptor := relay.GetAdaptor(meta.APIType)
+	if adaptor == nil {
+		return openai.ErrorWrapper(fmt.Errorf("invalid api type: %d", meta.APIType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(meta)
+
+	resp, err := adaptor.DoRequest(c, meta, c.Request.Body)
+	if err != nil {
+		logger.Errorf(ctx, "DoRequest failed: %s", err.Error())
+		return openai.ErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+	}
+
+	// do response
+	_, respErr := adaptor.DoResponse(c, resp, meta)
+	if respErr != nil {
+		logger.Errorf(ctx, "respErr is not nil: %+v", respErr)
+		return respErr
+	}
+
+	return nil
+}

relay/controller/text.go

@@ -4,12 +4,14 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/config"
 	"io"
 	"net/http"
 
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/relay"
+	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/apitype"
 	"github.com/songquanpeng/one-api/relay/billing"
@@ -31,10 +33,11 @@ func RelayTextHelper(c *gin.Context) *model.ErrorWithStatusCode {
 	meta.IsStream = textRequest.Stream
 
 	// map model name
-	var isModelMapped bool
 	meta.OriginModelName = textRequest.Model
-	textRequest.Model, isModelMapped = getMappedModelName(textRequest.Model, meta.ModelMapping)
+	textRequest.Model, _ = getMappedModelName(textRequest.Model, meta.ModelMapping)
 	meta.ActualModelName = textRequest.Model
+	// set system prompt if not empty
+	systemPromptReset := setSystemPrompt(ctx, textRequest, meta.SystemPrompt)
 	// get model ratio & group ratio
 	modelRatio := billingratio.GetModelRatio(textRequest.Model, meta.ChannelType)
 	groupRatio := billingratio.GetGroupRatio(meta.Group)
@@ -55,30 +58,9 @@ func RelayTextHelper(c *gin.Context) *model.ErrorWithStatusCode {
 	adaptor.Init(meta)
 
 	// get request body
-	var requestBody io.Reader
-	if meta.APIType == apitype.OpenAI {
-		// no need to convert request for openai
-		shouldResetRequestBody := isModelMapped || meta.ChannelType == channeltype.Baichuan // frequency_penalty 0 is not acceptable for baichuan
-		if shouldResetRequestBody {
-			jsonStr, err := json.Marshal(textRequest)
-			if err != nil {
-				return openai.ErrorWrapper(err, "json_marshal_failed", http.StatusInternalServerError)
-			}
-			requestBody = bytes.NewBuffer(jsonStr)
-		} else {
-			requestBody = c.Request.Body
-		}
-	} else {
-		convertedRequest, err := adaptor.ConvertRequest(c, meta.Mode, textRequest)
-		if err != nil {
-			return openai.ErrorWrapper(err, "convert_request_failed", http.StatusInternalServerError)
-		}
-		jsonData, err := json.Marshal(convertedRequest)
-		if err != nil {
-			return openai.ErrorWrapper(err, "json_marshal_failed", http.StatusInternalServerError)
-		}
-		logger.Debugf(ctx, "converted request: \n%s", string(jsonData))
-		requestBody = bytes.NewBuffer(jsonData)
+	requestBody, err := getRequestBody(c, meta, textRequest, adaptor)
+	if err != nil {
+		return openai.ErrorWrapper(err, "convert_request_failed", http.StatusInternalServerError)
 	}
 
 	// do request
@@ -100,6 +82,29 @@ func RelayTextHelper(c *gin.Context) *model.ErrorWithStatusCode {
 		return respErr
 	}
 	// post-consume quota
-	go postConsumeQuota(ctx, usage, meta, textRequest, ratio, preConsumedQuota, modelRatio, groupRatio)
+	go postConsumeQuota(ctx, usage, meta, textRequest, ratio, preConsumedQuota, modelRatio, groupRatio, systemPromptReset)
 	return nil
 }
+
+func getRequestBody(c *gin.Context, meta *meta.Meta, textRequest *model.GeneralOpenAIRequest, adaptor adaptor.Adaptor) (io.Reader, error) {
+	if !config.EnforceIncludeUsage && meta.APIType == apitype.OpenAI && meta.OriginModelName == meta.ActualModelName && meta.ChannelType != channeltype.Baichuan {
+		// no need to convert request for openai
+		return c.Request.Body, nil
+	}
+
+	// get request body
+	var requestBody io.Reader
+	convertedRequest, err := adaptor.ConvertRequest(c, meta.Mode, textRequest)
+	if err != nil {
+		logger.Debugf(c.Request.Context(), "converted request failed: %s\n", err.Error())
+		return nil, err
+	}
+	jsonData, err := json.Marshal(convertedRequest)
+	if err != nil {
+		logger.Debugf(c.Request.Context(), "converted request json_marshal_failed: %s\n", err.Error())
+		return nil, err
+	}
+	logger.Debugf(c.Request.Context(), "converted request: \n%s", string(jsonData))
+	requestBody = bytes.NewBuffer(jsonData)
+	return requestBody, nil
+}

relay/meta/relay_meta.go

@@ -10,23 +10,27 @@ import (
 )
 
 type Meta struct {
-	Mode            int
-	ChannelType     int
-	ChannelId       int
-	TokenId         int
-	TokenName       string
-	UserId          int
-	Group           string
-	ModelMapping    map[string]string
-	BaseURL         string
-	APIKey          string
-	APIType         int
-	Config          model.ChannelConfig
-	IsStream        bool
+	Mode         int
+	ChannelType  int
+	ChannelId    int
+	TokenId      int
+	TokenName    string
+	UserId       int
+	Group        string
+	ModelMapping map[string]string
+	// BaseURL is the proxy url set in the channel config
+	BaseURL  string
+	APIKey   string
+	APIType  int
+	Config   model.ChannelConfig
+	IsStream bool
+	// OriginModelName is the model name from the raw user request
 	OriginModelName string
+	// ActualModelName is the model name after mapping
 	ActualModelName string
 	RequestURLPath  string
 	PromptTokens    int // only for DoResponse
+	SystemPrompt    string
 }
 
 func GetByContext(c *gin.Context) *Meta {
@@ -43,6 +47,7 @@ func GetByContext(c *gin.Context) *Meta {
 		BaseURL:         c.GetString(ctxkey.BaseURL),
 		APIKey:          strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
 		RequestURLPath:  c.Request.URL.String(),
+		SystemPrompt:    c.GetString(ctxkey.SystemPrompt),
 	}
 	cfg, ok := c.Get(ctxkey.Config)
 	if ok {

relay/model/constant.go

@@ -1,6 +1,7 @@
 package model
 
 const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeText       = "text"
+	ContentTypeImageURL   = "image_url"
+	ContentTypeInputAudio = "input_audio"
 )

relay/model/general.go

@@ -1,33 +1,70 @@
 package model
 
 type ResponseFormat struct {
-	Type string `json:"type,omitempty"`
+	Type       string      `json:"type,omitempty"`
+	JsonSchema *JSONSchema `json:"json_schema,omitempty"`
+}
+
+type JSONSchema struct {
+	Description string                 `json:"description,omitempty"`
+	Name        string                 `json:"name"`
+	Schema      map[string]interface{} `json:"schema,omitempty"`
+	Strict      *bool                  `json:"strict,omitempty"`
+}
+
+type Audio struct {
+	Voice  string `json:"voice,omitempty"`
+	Format string `json:"format,omitempty"`
+}
+
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
 }
 
 type GeneralOpenAIRequest struct {
-	Messages         []Message       `json:"messages,omitempty"`
-	Model            string          `json:"model,omitempty"`
-	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
-	MaxTokens        int             `json:"max_tokens,omitempty"`
-	N                int             `json:"n,omitempty"`
-	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
-	Seed             float64         `json:"seed,omitempty"`
-	Stream           bool            `json:"stream,omitempty"`
-	Temperature      float64         `json:"temperature,omitempty"`
-	TopP             float64         `json:"top_p,omitempty"`
-	TopK             int             `json:"top_k,omitempty"`
-	Tools            []Tool          `json:"tools,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
-	FunctionCall     any             `json:"function_call,omitempty"`
-	Functions        any             `json:"functions,omitempty"`
-	User             string          `json:"user,omitempty"`
-	Prompt           any             `json:"prompt,omitempty"`
-	Input            any             `json:"input,omitempty"`
-	EncodingFormat   string          `json:"encoding_format,omitempty"`
-	Dimensions       int             `json:"dimensions,omitempty"`
-	Instruction      string          `json:"instruction,omitempty"`
-	Size             string          `json:"size,omitempty"`
+	// https://platform.openai.com/docs/api-reference/chat/create
+	Messages            []Message       `json:"messages,omitempty"`
+	Model               string          `json:"model,omitempty"`
+	Store               *bool           `json:"store,omitempty"`
+	Metadata            any             `json:"metadata,omitempty"`
+	FrequencyPenalty    *float64        `json:"frequency_penalty,omitempty"`
+	LogitBias           any             `json:"logit_bias,omitempty"`
+	Logprobs            *bool           `json:"logprobs,omitempty"`
+	TopLogprobs         *int            `json:"top_logprobs,omitempty"`
+	MaxTokens           int             `json:"max_tokens,omitempty"`
+	MaxCompletionTokens *int            `json:"max_completion_tokens,omitempty"`
+	N                   int             `json:"n,omitempty"`
+	Modalities          []string        `json:"modalities,omitempty"`
+	Prediction          any             `json:"prediction,omitempty"`
+	Audio               *Audio          `json:"audio,omitempty"`
+	PresencePenalty     *float64        `json:"presence_penalty,omitempty"`
+	ResponseFormat      *ResponseFormat `json:"response_format,omitempty"`
+	Seed                float64         `json:"seed,omitempty"`
+	ServiceTier         *string         `json:"service_tier,omitempty"`
+	Stop                any             `json:"stop,omitempty"`
+	Stream              bool            `json:"stream,omitempty"`
+	StreamOptions       *StreamOptions  `json:"stream_options,omitempty"`
+	Temperature         *float64        `json:"temperature,omitempty"`
+	TopP                *float64        `json:"top_p,omitempty"`
+	TopK                int             `json:"top_k,omitempty"`
+	Tools               []Tool          `json:"tools,omitempty"`
+	ToolChoice          any             `json:"tool_choice,omitempty"`
+	ParallelTooCalls    *bool           `json:"parallel_tool_calls,omitempty"`
+	User                string          `json:"user,omitempty"`
+	FunctionCall        any             `json:"function_call,omitempty"`
+	Functions           any             `json:"functions,omitempty"`
+	// https://platform.openai.com/docs/api-reference/embeddings/create
+	Input          any    `json:"input,omitempty"`
+	EncodingFormat string `json:"encoding_format,omitempty"`
+	Dimensions     int    `json:"dimensions,omitempty"`
+	// https://platform.openai.com/docs/api-reference/images/create
+	Prompt  any     `json:"prompt,omitempty"`
+	Quality *string `json:"quality,omitempty"`
+	Size    string  `json:"size,omitempty"`
+	Style   *string `json:"style,omitempty"`
+	// Others
+	Instruction string `json:"instruction,omitempty"`
+	NumCtx      int    `json:"num_ctx,omitempty"`
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {

relay/relaymode/define.go

@@ -11,4 +11,6 @@ const (
 	AudioSpeech
 	AudioTranscription
 	AudioTranslation
+	// Proxy is a special relay mode for proxying requests to custom upstream
+	Proxy
 )

relay/relaymode/helper.go

@@ -24,6 +24,8 @@ func GetByPath(path string) int {
 		relayMode = AudioTranscription
 	} else if strings.HasPrefix(path, "/v1/audio/translations") {
 		relayMode = AudioTranslation
+	} else if strings.HasPrefix(path, "/v1/oneapi/proxy") {
+		relayMode = Proxy
 	}
 	return relayMode
 }

router/api.go

@@ -23,6 +23,7 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/reset_password", middleware.CriticalRateLimit(), middleware.TurnstileCheck(), controller.SendPasswordResetEmail)
 		apiRouter.POST("/user/reset", middleware.CriticalRateLimit(), controller.ResetPassword)
 		apiRouter.GET("/oauth/github", middleware.CriticalRateLimit(), auth.GitHubOAuth)
+		apiRouter.GET("/oauth/oidc", middleware.CriticalRateLimit(), auth.OidcAuth)
 		apiRouter.GET("/oauth/lark", middleware.CriticalRateLimit(), auth.LarkOAuth)
 		apiRouter.GET("/oauth/state", middleware.CriticalRateLimit(), auth.GenerateOAuthCode)
 		apiRouter.GET("/oauth/wechat", middleware.CriticalRateLimit(), auth.WeChatAuth)

router/relay.go

@@ -19,6 +19,7 @@ func SetRelayRouter(router *gin.Engine) {
 	relayV1Router := router.Group("/v1")
 	relayV1Router.Use(middleware.RelayPanicRecover(), middleware.TokenAuth(), middleware.Distribute())
 	{
+		relayV1Router.Any("/oneapi/proxy/:channelid/*target", controller.Relay)
 		relayV1Router.POST("/completions", controller.Relay)
 		relayV1Router.POST("/chat/completions", controller.Relay)
 		relayV1Router.POST("/edits", controller.Relay)

web/air/src/components/TokensTable.js

@@ -11,12 +11,14 @@ import EditToken from '../pages/Token/EditToken';
 const COPY_OPTIONS = [
   { key: 'next', text: 'ChatGPT Next Web', value: 'next' },
   { key: 'ama', text: 'ChatGPT Web & Midjourney', value: 'ama' },
-  { key: 'opencat', text: 'OpenCat', value: 'opencat' }
+  { key: 'opencat', text: 'OpenCat', value: 'opencat' },
+  { key: 'lobechat', text: 'LobeChat', value: 'lobechat' },
 ];
 
 const OPEN_LINK_OPTIONS = [
   { key: 'ama', text: 'ChatGPT Web & Midjourney', value: 'ama' },
-  { key: 'opencat', text: 'OpenCat', value: 'opencat' }
+  { key: 'opencat', text: 'OpenCat', value: 'opencat' },
+  { key: 'lobechat', text: 'LobeChat', value: 'lobechat' }
 ];
 
 function renderTimestamp(timestamp) {
@@ -60,7 +62,12 @@ const TokensTable = () => {
         onOpenLink('next-mj');
       }
     },
-    { node: 'item', key: 'opencat', name: 'OpenCat', value: 'opencat' }
+    { node: 'item', key: 'opencat', name: 'OpenCat', value: 'opencat' },
+    {
+      node: 'item', key: 'lobechat', name: 'LobeChat', onClick: () => {
+        onOpenLink('lobechat');
+      }
+    }
   ];
 
   const columns = [
@@ -177,6 +184,11 @@ const TokensTable = () => {
                   node: 'item', key: 'opencat', name: 'OpenCat', onClick: () => {
                     onOpenLink('opencat', record.key);
                   }
+                },
+                {
+                  node: 'item', key: 'lobechat', name: 'LobeChat', onClick: () => {
+                    onOpenLink('lobechat');
+                  }
                 }
               ]
             }
@@ -382,6 +394,9 @@ const TokensTable = () => {
       case 'next-mj':
         url = mjLink + `/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
         break;
+      case 'lobechat':
+        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
+        break;
       default:
         if (!chatLink) {
           showError('管理员未设置聊天链接');

web/air/src/constants/channel.constants.js

@@ -1,10 +1,13 @@
 export const CHANNEL_OPTIONS = [
   { key: 1, text: 'OpenAI', value: 1, color: 'green' },
   { key: 14, text: 'Anthropic Claude', value: 14, color: 'black' },
+  { key: 33, text: 'AWS', value: 33, color: 'black' },
   { key: 3, text: 'Azure OpenAI', value: 3, color: 'olive' },
   { key: 11, text: 'Google PaLM2', value: 11, color: 'orange' },
   { key: 24, text: 'Google Gemini', value: 24, color: 'orange' },
   { key: 28, text: 'Mistral AI', value: 28, color: 'orange' },
+  { key: 41, text: 'Novita', value: 41, color: 'purple' },
+  { key: 40, text: '字节跳动豆包', value: 40, color: 'blue' },
   { key: 15, text: '百度文心千帆', value: 15, color: 'blue' },
   { key: 17, text: '阿里通义千问', value: 17, color: 'orange' },
   { key: 18, text: '讯飞星火认知', value: 18, color: 'blue' },
@@ -17,6 +20,17 @@ export const CHANNEL_OPTIONS = [
   { key: 29, text: 'Groq', value: 29, color: 'orange' },
   { key: 30, text: 'Ollama', value: 30, color: 'black' },
   { key: 31, text: '零一万物', value: 31, color: 'green' },
+  { key: 32, text: '阶跃星辰', value: 32, color: 'blue' },
+  { key: 34, text: 'Coze', value: 34, color: 'blue' },
+  { key: 35, text: 'Cohere', value: 35, color: 'blue' },
+  { key: 36, text: 'DeepSeek', value: 36, color: 'black' },
+  { key: 37, text: 'Cloudflare', value: 37, color: 'orange' },
+  { key: 38, text: 'DeepL', value: 38, color: 'black' },
+  { key: 39, text: 'together.ai', value: 39, color: 'blue' },
+  { key: 42, text: 'VertexAI', value: 42, color: 'blue' },
+  { key: 43, text: 'Proxy', value: 43, color: 'blue' },
+  { key: 44, text: 'SiliconFlow', value: 44, color: 'blue' },
+  { key: 45, text: 'xAI', value: 45, color: 'blue' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
   { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
   { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },
@@ -34,4 +48,4 @@ export const CHANNEL_OPTIONS = [
 
 for (let i = 0; i < CHANNEL_OPTIONS.length; i++) {
   CHANNEL_OPTIONS[i].label = CHANNEL_OPTIONS[i].text;
-}
+}

web/air/src/pages/Channel/EditChannel.js

@@ -43,6 +43,7 @@ const EditChannel = (props) => {
         base_url: '',
         other: '',
         model_mapping: '',
+        system_prompt: '',
         models: [],
         auto_ban: 1,
         groups: ['default']
@@ -63,7 +64,7 @@ const EditChannel = (props) => {
             let localModels = [];
             switch (value) {
                 case 14:
-                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-sonnet-20240620"];
+                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-haiku-20241022", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022"];
                     break;
                 case 11:
                     localModels = ['PaLM-2'];
@@ -78,7 +79,7 @@ const EditChannel = (props) => {
                     localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
                     break;
                 case 18:
-                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.5', 'SparkDesk-v4.0'];
+                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v3.5-32K', 'SparkDesk-v4.0'];
                     break;
                 case 19:
                     localModels = ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1'];
@@ -304,163 +305,163 @@ const EditChannel = (props) => {
                 width={isMobile() ? '100%' : 600}
             >
                 <Spin spinning={loading}>
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>类型：</Typography.Text>
                     </div>
                     <Select
-                        name='type'
-                        required
-                        optionList={CHANNEL_OPTIONS}
-                        value={inputs.type}
-                        onChange={value => handleInputChange('type', value)}
-                        style={{width: '50%'}}
+                      name='type'
+                      required
+                      optionList={CHANNEL_OPTIONS}
+                      value={inputs.type}
+                      onChange={value => handleInputChange('type', value)}
+                      style={{ width: '50%' }}
                     />
                     {
-                        inputs.type === 3 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Banner type={"warning"} description={
-                                        <>
-                                            注意，<strong>模型部署名称必须和模型名称保持一致</strong>，因为 One API 会把请求体中的
-                                            model
-                                            参数替换为你的部署名称（模型名称中的点会被剔除），<a target='_blank'
-                                                                                              href='https://github.com/songquanpeng/one-api/issues/133?notification_referrer_id=NT_kwDOAmJSYrM2NjIwMzI3NDgyOjM5OTk4MDUw#issuecomment-1571602271'>图片演示</a>。
-                                        </>
-                                    }>
-                                    </Banner>
-                                </div>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>AZURE_OPENAI_ENDPOINT：</Typography.Text>
-                                </div>
-                                <Input
-                                    label='AZURE_OPENAI_ENDPOINT'
-                                    name='azure_base_url'
-                                    placeholder={'请输入 AZURE_OPENAI_ENDPOINT，例如：https://docs-test-001.openai.azure.com'}
-                                    onChange={value => {
-                                        handleInputChange('base_url', value)
-                                    }}
-                                    value={inputs.base_url}
-                                    autoComplete='new-password'
-                                />
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>默认 API 版本：</Typography.Text>
-                                </div>
-                                <Input
-                                    label='默认 API 版本'
-                                    name='azure_other'
-                                    placeholder={'请输入默认 API 版本，例如：2024-03-01-preview，该配置可以被实际的请求查询参数所覆盖'}
-                                    onChange={value => {
-                                        handleInputChange('other', value)
-                                    }}
-                                    value={inputs.other}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
+                      inputs.type === 3 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Banner type={"warning"} description={
+                                    <>
+                                        注意，<strong>模型部署名称必须和模型名称保持一致</strong>，因为 One API 会把请求体中的
+                                        model
+                                        参数替换为你的部署名称（模型名称中的点会被剔除），<a target='_blank'
+                                                                                          href='https://github.com/songquanpeng/one-api/issues/133?notification_referrer_id=NT_kwDOAmJSYrM2NjIwMzI3NDgyOjM5OTk4MDUw#issuecomment-1571602271'>图片演示</a>。
+                                    </>
+                                }>
+                                </Banner>
+                            </div>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>AZURE_OPENAI_ENDPOINT：</Typography.Text>
+                            </div>
+                            <Input
+                              label='AZURE_OPENAI_ENDPOINT'
+                              name='azure_base_url'
+                              placeholder={'请输入 AZURE_OPENAI_ENDPOINT，例如：https://docs-test-001.openai.azure.com'}
+                              onChange={value => {
+                                  handleInputChange('base_url', value)
+                              }}
+                              value={inputs.base_url}
+                              autoComplete='new-password'
+                            />
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>默认 API 版本：</Typography.Text>
+                            </div>
+                            <Input
+                              label='默认 API 版本'
+                              name='azure_other'
+                              placeholder={'请输入默认 API 版本，例如：2024-03-01-preview，该配置可以被实际的请求查询参数所覆盖'}
+                              onChange={value => {
+                                  handleInputChange('other', value)
+                              }}
+                              value={inputs.other}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
                     {
-                        inputs.type === 8 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>Base URL：</Typography.Text>
-                                </div>
-                                <Input
-                                    name='base_url'
-                                    placeholder={'请输入自定义渠道的 Base URL'}
-                                    onChange={value => {
-                                        handleInputChange('base_url', value)
-                                    }}
-                                    value={inputs.base_url}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
+                      inputs.type === 8 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>Base URL：</Typography.Text>
+                            </div>
+                            <Input
+                              name='base_url'
+                              placeholder={'请输入自定义渠道的 Base URL'}
+                              onChange={value => {
+                                  handleInputChange('base_url', value)
+                              }}
+                              value={inputs.base_url}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>名称：</Typography.Text>
                     </div>
                     <Input
-                        required
-                        name='name'
-                        placeholder={'请为渠道命名'}
-                        onChange={value => {
-                            handleInputChange('name', value)
-                        }}
-                        value={inputs.name}
-                        autoComplete='new-password'
+                      required
+                      name='name'
+                      placeholder={'请为渠道命名'}
+                      onChange={value => {
+                          handleInputChange('name', value)
+                      }}
+                      value={inputs.name}
+                      autoComplete='new-password'
                     />
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>分组：</Typography.Text>
                     </div>
                     <Select
-                        placeholder={'请选择可以使用该渠道的分组'}
-                        name='groups'
-                        required
-                        multiple
-                        selection
-                        allowAdditions
-                        additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
-                        onChange={value => {
-                            handleInputChange('groups', value)
-                        }}
-                        value={inputs.groups}
-                        autoComplete='new-password'
-                        optionList={groupOptions}
+                      placeholder={'请选择可以使用该渠道的分组'}
+                      name='groups'
+                      required
+                      multiple
+                      selection
+                      allowAdditions
+                      additionLabel={'请在系统设置页面编辑分组倍率以添加新的分组：'}
+                      onChange={value => {
+                          handleInputChange('groups', value)
+                      }}
+                      value={inputs.groups}
+                      autoComplete='new-password'
+                      optionList={groupOptions}
                     />
                     {
-                        inputs.type === 18 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>模型版本：</Typography.Text>
-                                </div>
-                                <Input
-                                    name='other'
-                                    placeholder={'请输入星火大模型版本，注意是接口地址中的版本号，例如：v2.1'}
-                                    onChange={value => {
-                                        handleInputChange('other', value)
-                                    }}
-                                    value={inputs.other}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
+                      inputs.type === 18 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>模型版本：</Typography.Text>
+                            </div>
+                            <Input
+                              name='other'
+                              placeholder={'请输入星火大模型版本，注意是接口地址中的版本号，例如：v2.1'}
+                              onChange={value => {
+                                  handleInputChange('other', value)
+                              }}
+                              value={inputs.other}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
                     {
-                        inputs.type === 21 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>知识库 ID：</Typography.Text>
-                                </div>
-                                <Input
-                                    label='知识库 ID'
-                                    name='other'
-                                    placeholder={'请输入知识库 ID，例如：123456'}
-                                    onChange={value => {
-                                        handleInputChange('other', value)
-                                    }}
-                                    value={inputs.other}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
+                      inputs.type === 21 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>知识库 ID：</Typography.Text>
+                            </div>
+                            <Input
+                              label='知识库 ID'
+                              name='other'
+                              placeholder={'请输入知识库 ID，例如：123456'}
+                              onChange={value => {
+                                  handleInputChange('other', value)
+                              }}
+                              value={inputs.other}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>模型：</Typography.Text>
                     </div>
                     <Select
-                        placeholder={'请选择该渠道所支持的模型'}
-                        name='models'
-                        required
-                        multiple
-                        selection
-                        onChange={value => {
-                            handleInputChange('models', value)
-                        }}
-                        value={inputs.models}
-                        autoComplete='new-password'
-                        optionList={modelOptions}
+                      placeholder={'请选择该渠道所支持的模型'}
+                      name='models'
+                      required
+                      multiple
+                      selection
+                      onChange={value => {
+                          handleInputChange('models', value)
+                      }}
+                      value={inputs.models}
+                      autoComplete='new-password'
+                      optionList={modelOptions}
                     />
-                    <div style={{lineHeight: '40px', marginBottom: '12px'}}>
+                    <div style={{ lineHeight: '40px', marginBottom: '12px' }}>
                         <Space>
                             <Button type='primary' onClick={() => {
                                 handleInputChange('models', basicModels);
@@ -473,28 +474,41 @@ const EditChannel = (props) => {
                             }}>清除所有模型</Button>
                         </Space>
                         <Input
-                            addonAfter={
-                                <Button type='primary' onClick={addCustomModel}>填入</Button>
-                            }
-                            placeholder='输入自定义模型名称'
-                            value={customModel}
-                            onChange={(value) => {
-                                setCustomModel(value.trim());
-                            }}
+                          addonAfter={
+                              <Button type='primary' onClick={addCustomModel}>填入</Button>
+                          }
+                          placeholder='输入自定义模型名称'
+                          value={customModel}
+                          onChange={(value) => {
+                              setCustomModel(value.trim());
+                          }}
                         />
                     </div>
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>模型重定向：</Typography.Text>
                     </div>
                     <TextArea
-                        placeholder={`此项可选，用于修改请求体中的模型名称，为一个 JSON 字符串，键为请求中模型名称，值为要替换的模型名称，例如：\n${JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)}`}
-                        name='model_mapping'
-                        onChange={value => {
-                            handleInputChange('model_mapping', value)
-                        }}
-                        autosize
-                        value={inputs.model_mapping}
-                        autoComplete='new-password'
+                      placeholder={`此项可选，用于修改请求体中的模型名称，为一个 JSON 字符串，键为请求中模型名称，值为要替换的模型名称，例如：\n${JSON.stringify(MODEL_MAPPING_EXAMPLE, null, 2)}`}
+                      name='model_mapping'
+                      onChange={value => {
+                          handleInputChange('model_mapping', value)
+                      }}
+                      autosize
+                      value={inputs.model_mapping}
+                      autoComplete='new-password'
+                    />
+                    <div style={{ marginTop: 10 }}>
+                        <Typography.Text strong>系统提示词：</Typography.Text>
+                    </div>
+                    <TextArea
+                      placeholder={`此项可选，用于强制设置给定的系统提示词，请配合自定义模型 & 模型重定向使用，首先创建一个唯一的自定义模型名称并在上面填入，之后将该自定义模型重定向映射到该渠道一个原生支持的模型`}
+                      name='system_prompt'
+                      onChange={value => {
+                          handleInputChange('system_prompt', value)
+                      }}
+                      autosize
+                      value={inputs.system_prompt}
+                      autoComplete='new-password'
                     />
                     <Typography.Text style={{
                         color: 'rgba(var(--semi-blue-5), 1)',
@@ -507,116 +521,116 @@ const EditChannel = (props) => {
                     }>
                         填入模板
                     </Typography.Text>
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>密钥：</Typography.Text>
                     </div>
                     {
                         batch ?
-                            <TextArea
-                                label='密钥'
-                                name='key'
-                                required
-                                placeholder={'请输入密钥，一行一个'}
-                                onChange={value => {
-                                    handleInputChange('key', value)
-                                }}
-                                value={inputs.key}
-                                style={{minHeight: 150, fontFamily: 'JetBrains Mono, Consolas'}}
-                                autoComplete='new-password'
-                            />
-                            :
-                            <Input
-                                label='密钥'
-                                name='key'
-                                required
-                                placeholder={type2secretPrompt(inputs.type)}
-                                onChange={value => {
-                                    handleInputChange('key', value)
-                                }}
-                                value={inputs.key}
-                                autoComplete='new-password'
-                            />
+                          <TextArea
+                            label='密钥'
+                            name='key'
+                            required
+                            placeholder={'请输入密钥，一行一个'}
+                            onChange={value => {
+                                handleInputChange('key', value)
+                            }}
+                            value={inputs.key}
+                            style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
+                            autoComplete='new-password'
+                          />
+                          :
+                          <Input
+                            label='密钥'
+                            name='key'
+                            required
+                            placeholder={type2secretPrompt(inputs.type)}
+                            onChange={value => {
+                                handleInputChange('key', value)
+                            }}
+                            value={inputs.key}
+                            autoComplete='new-password'
+                          />
                     }
-                    <div style={{marginTop: 10}}>
+                    <div style={{ marginTop: 10 }}>
                         <Typography.Text strong>组织：</Typography.Text>
                     </div>
                     <Input
-                        label='组织，可选，不填则为默认组织'
-                        name='openai_organization'
-                        placeholder='请输入组织org-xxx'
-                        onChange={value => {
-                            handleInputChange('openai_organization', value)
-                        }}
-                        value={inputs.openai_organization}
+                      label='组织，可选，不填则为默认组织'
+                      name='openai_organization'
+                      placeholder='请输入组织org-xxx'
+                      onChange={value => {
+                          handleInputChange('openai_organization', value)
+                      }}
+                      value={inputs.openai_organization}
                     />
-                    <div style={{marginTop: 10, display: 'flex'}}>
+                    <div style={{ marginTop: 10, display: 'flex' }}>
                         <Space>
                             <Checkbox
-                                name='auto_ban'
-                                checked={autoBan}
-                                onChange={
-                                    () => {
-                                        setAutoBan(!autoBan);
-                                    }
-                                }
-                                // onChange={handleInputChange}
+                              name='auto_ban'
+                              checked={autoBan}
+                              onChange={
+                                  () => {
+                                      setAutoBan(!autoBan);
+                                  }
+                              }
+                              // onChange={handleInputChange}
                             />
                             <Typography.Text
-                                strong>是否自动禁用（仅当自动禁用开启时有效），关闭后不会自动禁用该渠道：</Typography.Text>
+                              strong>是否自动禁用（仅当自动禁用开启时有效），关闭后不会自动禁用该渠道：</Typography.Text>
                         </Space>
                     </div>
 
                     {
-                        !isEdit && (
-                            <div style={{marginTop: 10, display: 'flex'}}>
-                                <Space>
-                                    <Checkbox
-                                        checked={batch}
-                                        label='批量创建'
-                                        name='batch'
-                                        onChange={() => setBatch(!batch)}
-                                    />
-                                    <Typography.Text strong>批量创建</Typography.Text>
-                                </Space>
+                      !isEdit && (
+                        <div style={{ marginTop: 10, display: 'flex' }}>
+                            <Space>
+                                <Checkbox
+                                  checked={batch}
+                                  label='批量创建'
+                                  name='batch'
+                                  onChange={() => setBatch(!batch)}
+                                />
+                                <Typography.Text strong>批量创建</Typography.Text>
+                            </Space>
+                        </div>
+                      )
+                    }
+                    {
+                      inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>代理：</Typography.Text>
                             </div>
-                        )
+                            <Input
+                              label='代理'
+                              name='base_url'
+                              placeholder={'此项可选，用于通过代理站来进行 API 调用'}
+                              onChange={value => {
+                                  handleInputChange('base_url', value)
+                              }}
+                              value={inputs.base_url}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
                     {
-                        inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>代理：</Typography.Text>
-                                </div>
-                                <Input
-                                    label='代理'
-                                    name='base_url'
-                                    placeholder={'此项可选，用于通过代理站来进行 API 调用'}
-                                    onChange={value => {
-                                        handleInputChange('base_url', value)
-                                    }}
-                                    value={inputs.base_url}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
-                    }
-                    {
-                        inputs.type === 22 && (
-                            <>
-                                <div style={{marginTop: 10}}>
-                                    <Typography.Text strong>私有部署地址：</Typography.Text>
-                                </div>
-                                <Input
-                                    name='base_url'
-                                    placeholder={'请输入私有部署地址，格式为：https://fastgpt.run/api/openapi'}
-                                    onChange={value => {
-                                        handleInputChange('base_url', value)
-                                    }}
-                                    value={inputs.base_url}
-                                    autoComplete='new-password'
-                                />
-                            </>
-                        )
+                      inputs.type === 22 && (
+                        <>
+                            <div style={{ marginTop: 10 }}>
+                                <Typography.Text strong>私有部署地址：</Typography.Text>
+                            </div>
+                            <Input
+                              name='base_url'
+                              placeholder={'请输入私有部署地址，格式为：https://fastgpt.run/api/openapi'}
+                              onChange={value => {
+                                  handleInputChange('base_url', value)
+                              }}
+                              value={inputs.base_url}
+                              autoComplete='new-password'
+                            />
+                        </>
+                      )
                     }
 
                 </Spin>

web/berry/src/assets/images/icons/oidc.svg

@@ -0,0 +1,7 @@
+<svg t="1723135116886" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg"
+     p-id="10969" width="200" height="200">
+    <path d="M512 960C265 960 64 759 64 512S265 64 512 64s448 201 448 448-201 448-448 448z m0-882.6c-239.7 0-434.6 195-434.6 434.6s195 434.6 434.6 434.6 434.6-195 434.6-434.6S751.7 77.4 512 77.4z"
+          p-id="10970" fill="#2c2c2c" stroke="#2c2c2c" stroke-width="60"></path>
+    <path d="M197.7 512c0-78.3 31.6-98.8 87.2-98.8 56.2 0 87.2 20.5 87.2 98.8s-31 98.8-87.2 98.8c-55.7 0-87.2-20.5-87.2-98.8z m130.4 0c0-46.8-7.8-64.5-43.2-64.5-35.2 0-42.9 17.7-42.9 64.5 0 47.1 7.8 63.7 42.9 63.7 35.4 0 43.2-16.6 43.2-63.7zM409.7 415.9h42.1V608h-42.1V415.9zM653.9 512c0 74.2-37.1 96.1-93.6 96.1h-65.9V415.9h65.9c56.5 0 93.6 16.1 93.6 96.1z m-43.5 0c0-49.3-17.7-60.6-52.3-60.6h-21.6v120.7h21.6c35.4 0 52.3-13.3 52.3-60.1zM686.5 512c0-74.2 36.3-98.8 92.7-98.8 18.3 0 33.2 2.2 44.8 6.4v36.3c-11.9-4.2-26-6.6-42.1-6.6-34.6 0-49.8 15.5-49.8 62.6 0 50.1 15.2 62.6 49.3 62.6 15.8 0 30.2-2.2 44.8-7.5v36c-11.3 4.7-28.5 8-46.8 8-56.1-0.2-92.9-18.7-92.9-99z"
+          p-id="10971" fill="#2c2c2c" stroke="#2c2c2c" stroke-width="20"></path>
+</svg>

web/berry/src/config.js

@@ -22,7 +22,12 @@ const config = {
     turnstile_site_key: '',
     version: '',
     wechat_login: false,
-    wechat_qrcode: ''
+    wechat_qrcode: '',
+    oidc: false,
+    oidc_client_id: '',
+    oidc_authorization_endpoint: '',
+    oidc_token_endpoint: '',
+    oidc_userinfo_endpoint: '',
   }
 };
 

web/berry/src/constants/ChannelConstants.js

@@ -161,6 +161,30 @@ export const CHANNEL_OPTIONS = {
     value: 39,
     color: 'primary'
   },
+  42: {
+    key: 42,
+    text: 'VertexAI',
+    value: 42,
+    color: 'primary'
+  },
+  43: {
+    key: 43,
+    text: 'Proxy',
+    value: 43,
+    color: 'primary'
+  },
+  44: {
+    key: 44,
+    text: 'SiliconFlow',
+    value: 44,
+    color: 'primary'
+  },
+  45: {
+    key: 45,
+    text: 'xAI',
+    value: 45,
+    color: 'primary'
+  },
   41: {
     key: 41,
     text: 'Novita',

web/berry/src/hooks/useLogin.js

@@ -70,6 +70,28 @@ const useLogin = () => {
     }
   };
 
+  const oidcLogin = async (code, state) => {
+    try {
+      const res = await API.get(`/api/oauth/oidc?code=${code}&state=${state}`);
+      const { success, message, data } = res.data;
+      if (success) {
+        if (message === 'bind') {
+          showSuccess('绑定成功！');
+          navigate('/panel');
+        } else {
+          dispatch({ type: LOGIN, payload: data });
+          localStorage.setItem('user', JSON.stringify(data));
+          showSuccess('登录成功！');
+          navigate('/panel');
+        }
+      }
+      return { success, message };
+    } catch (err) {
+      // 请求失败，设置错误信息
+      return { success: false, message: '' };
+    }
+  }
+
   const wechatLogin = async (code) => {
     try {
       const res = await API.get(`/api/oauth/wechat?code=${code}`);
@@ -94,7 +116,7 @@ const useLogin = () => {
     navigate('/');
   };
 
-  return { login, logout, githubLogin, wechatLogin, larkLogin };
+  return { login, logout, githubLogin, wechatLogin, larkLogin,oidcLogin };
 };
 
 export default useLogin;

web/berry/src/routes/OtherRoutes.js

@@ -9,6 +9,7 @@ const AuthLogin = Loadable(lazy(() => import('views/Authentication/Auth/Login'))
 const AuthRegister = Loadable(lazy(() => import('views/Authentication/Auth/Register')));
 const GitHubOAuth = Loadable(lazy(() => import('views/Authentication/Auth/GitHubOAuth')));
 const LarkOAuth = Loadable(lazy(() => import('views/Authentication/Auth/LarkOAuth')));
+const OidcOAuth = Loadable(lazy(() => import('views/Authentication/Auth/OidcOAuth')));
 const ForgetPassword = Loadable(lazy(() => import('views/Authentication/Auth/ForgetPassword')));
 const ResetPassword = Loadable(lazy(() => import('views/Authentication/Auth/ResetPassword')));
 const Home = Loadable(lazy(() => import('views/Home')));
@@ -53,6 +54,10 @@ const OtherRoutes = {
       path: '/oauth/lark',
       element: <LarkOAuth />
     },
+    {
+      path: 'oauth/oidc',
+      element: <OidcOAuth />
+    },
     {
       path: '/404',
       element: <NotFoundView />

web/berry/src/utils/common.js

@@ -98,6 +98,21 @@ export async function onLarkOAuthClicked(lark_client_id) {
   window.open(`https://open.feishu.cn/open-apis/authen/v1/index?redirect_uri=${redirect_uri}&app_id=${lark_client_id}&state=${state}`);
 }
 
+export async function onOidcClicked(auth_url, client_id, openInNewTab = false) {
+  const state = await getOAuthState();
+  if (!state) return;
+  const redirect_uri = `${window.location.origin}/oauth/oidc`;
+  const response_type = "code";
+  const scope = "openid profile email";
+  const url = `${auth_url}?client_id=${client_id}&redirect_uri=${redirect_uri}&response_type=${response_type}&scope=${scope}&state=${state}`;
+  if (openInNewTab) {
+    window.open(url);
+  } else
+  {
+    window.location.href = url;
+  }
+}
+
 export function isAdmin() {
   let user = localStorage.getItem('user');
   if (!user) return false;