ci: update ci

.github/workflows/docker-image-arm64.yml

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - '*'
+      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:

Midjourney.md

@@ -2,6 +2,21 @@
 
 **简介**:Midjourney Proxy API文档
 
+## 接口列表
+支持的接口如下：
++ [x] /mj/submit/imagine
++ [x] /mj/submit/change
++ [x] /mj/submit/blend
++ [x] /mj/submit/describe
++ [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
++ [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
++ [x] /task/list-by-condition
++ [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
++ [x] /mj/submit/modal
++ [x] /mj/submit/shorten
++ [x] /mj/task/{id}/image-seed
++ [x] /mj/insight-face/swap （InsightFace）
+
 ## 模型列表
 
 ### midjourney-proxy支持

README.md

@@ -16,19 +16,7 @@
 此分叉版本的主要变更如下：
 
 1. 全新的UI界面（部分界面还待更新）
-2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)，支持的接口如下：
-   + [x] /mj/submit/imagine
-   + [x] /mj/submit/change
-   + [x] /mj/submit/blend
-   + [x] /mj/submit/describe
-   + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
-   + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
-   + [x] /task/list-by-condition
-   + [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
-   + [x] /mj/submit/modal
-   + [x] /mj/submit/shorten
-   + [x] /mj/task/{id}/image-seed
-   + [x] /mj/insight-face/swap （InsightFace）
+2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
    + [x] 易支付
 4. 支持用key查询使用额度:
@@ -45,22 +33,21 @@
     2. 对[@Botfather](https://t.me/botfather)输入指令/setdomain
     3. 选择你的bot，然后输入http(s)://你的网站地址/login
     4. Telegram Bot 名称是bot username 去掉@后的字符串
-13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)，支持的接口如下：
-    + [x] /suno/submit/music
-    + [x] /suno/submit/lyrics
-    + [x] /suno/fetch
-    + [x] /suno/fetch/:id
+13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
+14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
 
 ## 模型支持
 此版本额外支持以下模型：
 1. 第三方模型 **gps** （gpt-4-gizmo-*）
 2. 智谱glm-4v，glm-4v识图
-3. Anthropic Claude 3 (claude-3-opus-20240229, claude-3-sonnet-20240229)
+3. Anthropic Claude 3
 4. [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)，添加渠道时，密钥可以随便填写，默认的请求地址是[http://localhost:11434](http://localhost:11434)，如果需要修改请在渠道中修改
 5. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[对接文档](Midjourney.md)
 6. [零一万物](https://platform.lingyiwanwu.com/)
 7. 自定义渠道，支持填入完整调用地址
 8. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
+9. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
+10. Dify
 
 您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
@@ -85,7 +72,8 @@
 
 ## 比原版One API多出的配置
 - `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒
-
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`， 可选值为 `true` 和 `false`
+- `FORCE_STREAM_OPTION`：覆盖客户端stream_options参数，请求上游返回流模式usage，目前仅支持 `OpenAI` 渠道类型
 ## 部署
 ### 部署要求
 - 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）

Rerank.md

@@ -0,0 +1,62 @@
+# Rerank API文档
+
+**简介**:Rerank API文档
+
+## 接入Dify
+模型供应商选择Jina，按要求填写模型信息即可接入Dify。
+
+## 请求方式
+
+Post: /v1/rerank
+
+Request:
+
+```json
+{
+  "model": "rerank-multilingual-v3.0",
+  "query": "What is the capital of the United States?",
+  "top_n": 3,
+  "documents": [
+    "Carson City is the capital city of the American state of Nevada.",
+    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+    "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
+    "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
+    "Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+  ]
+}
+```
+
+Response:
+
+```json
+{
+  "results": [
+    {
+      "document": {
+        "text": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district."
+      },
+      "index": 2,
+      "relevance_score": 0.9999702
+    },
+    {
+      "document": {
+        "text": "Carson City is the capital city of the American state of Nevada."
+      },
+      "index": 0,
+      "relevance_score": 0.67800725
+    },
+    {
+      "document": {
+        "text": "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages."
+      },
+      "index": 3,
+      "relevance_score": 0.02800752
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 158,
+    "completion_tokens": 0,
+    "total_tokens": 158
+  }
+}
+```

Suno.md

@@ -2,6 +2,13 @@
 
 **简介**:Suno API文档
 
+## 接口列表
+支持的接口如下：
++ [x] /suno/submit/music
++ [x] /suno/submit/lyrics
++ [x] /suno/fetch
++ [x] /suno/fetch/:id
+
 ## 模型列表
 
 ### Suno API支持

common/constants.go

@@ -211,6 +211,7 @@ const (
 	ChannelTypeMiniMax        = 35
 	ChannelTypeSunoAPI        = 36
 	ChannelTypeDify           = 37
+	ChannelTypeJina           = 38
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
 
@@ -254,4 +255,6 @@ var ChannelBaseURLs = []string{
 	"https://api.cohere.ai",                     //34
 	"https://api.minimax.chat",                  //35
 	"",                                          //36
+	"",                                          //37
+	"https://api.jina.ai",                       //38
 }

common/env.go

@@ -24,3 +24,15 @@ func GetEnvOrDefaultString(env string, defaultValue string) string {
 	}
 	return os.Getenv(env)
 }
+
+func GetEnvOrDefaultBool(env string, defaultValue bool) bool {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	b, err := strconv.ParseBool(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %t", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return b
+}

constant/env.go

@@ -5,3 +5,7 @@ import (
 )
 
 var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
+var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)
+
+// ForceStreamOption 覆盖请求参数，强制返回usage信息
+var ForceStreamOption = common.GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)

constant/midjourney.go

@@ -4,6 +4,7 @@ var MjNotifyEnabled = false
 var MjAccountFilterEnabled = false
 var MjModeClearEnabled = false
 var MjForwardUrlEnabled = true
+var MjActionCheckSuccessEnabled = true
 
 const (
 	MjErrorUnknown = 5

controller/channel-test.go

@@ -67,8 +67,8 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		if channel.TestModel != nil && *channel.TestModel != "" {
 			testModel = *channel.TestModel
 		} else {
-			if len(adaptor.GetModelList()) > 0 {
-				testModel = adaptor.GetModelList()[0]
+			if len(channel.GetModels()) > 0 {
+				testModel = channel.GetModels()[0]
 			} else {
 				testModel = "gpt-3.5-turbo"
 			}

dto/text_request.go

@@ -11,6 +11,7 @@ type GeneralOpenAIRequest struct {
 	Messages         []Message       `json:"messages,omitempty"`
 	Prompt           any             `json:"prompt,omitempty"`
 	Stream           bool            `json:"stream,omitempty"`
+	StreamOptions    *StreamOptions  `json:"stream_options,omitempty"`
 	MaxTokens        uint            `json:"max_tokens,omitempty"`
 	Temperature      float64         `json:"temperature,omitempty"`
 	TopP             float64         `json:"top_p,omitempty"`
@@ -43,6 +44,10 @@ type OpenAIFunction struct {
 	Parameters  any    `json:"parameters,omitempty"`
 }
 
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
+}
+
 func (r GeneralOpenAIRequest) GetMaxTokens() int64 {
 	return int64(r.MaxTokens)
 }

dto/text_response.go

@@ -102,10 +102,12 @@ type ChatCompletionsStreamResponse struct {
 	Model             string                                `json:"model"`
 	SystemFingerprint *string                               `json:"system_fingerprint"`
 	Choices           []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage             *Usage                                `json:"usage"`
 }
 
 type ChatCompletionsStreamResponseSimple struct {
 	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage   *Usage                                `json:"usage"`
 }
 
 type CompletionsStreamResponse struct {

model/channel.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"gorm.io/gorm"
 	"one-api/common"
+	"strings"
 )
 
 type Channel struct {
@@ -33,6 +34,13 @@ type Channel struct {
 	OtherInfo         string  `json:"other_info"`
 }
 
+func (channel *Channel) GetModels() []string {
+	if channel.Models == "" {
+		return []string{}
+	}
+	return strings.Split(strings.Trim(channel.Models, ","), ",")
+}
+
 func (channel *Channel) GetOtherInfo() map[string]interface{} {
 	otherInfo := make(map[string]interface{})
 	if channel.OtherInfo != "" {

model/option.go

@@ -99,6 +99,7 @@ func InitOptionMap() {
 	common.OptionMap["MjAccountFilterEnabled"] = strconv.FormatBool(constant.MjAccountFilterEnabled)
 	common.OptionMap["MjModeClearEnabled"] = strconv.FormatBool(constant.MjModeClearEnabled)
 	common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(constant.MjForwardUrlEnabled)
+	common.OptionMap["MjActionCheckSuccessEnabled"] = strconv.FormatBool(constant.MjActionCheckSuccessEnabled)
 	common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(constant.CheckSensitiveEnabled)
 	common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnPromptEnabled)
 	//common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled)
@@ -210,6 +211,8 @@ func updateOptionMap(key string, value string) (err error) {
 			constant.MjModeClearEnabled = boolValue
 		case "MjForwardUrlEnabled":
 			constant.MjForwardUrlEnabled = boolValue
+		case "MjActionCheckSuccessEnabled":
+			constant.MjActionCheckSuccessEnabled = boolValue
 		case "CheckSensitiveEnabled":
 			constant.CheckSensitiveEnabled = boolValue
 		case "CheckSensitiveOnPromptEnabled":

model/user.go

@@ -295,10 +295,15 @@ func (user *User) ValidateAndFill() (err error) {
 	// that means if your field’s value is 0, '', false or other zero values,
 	// it won’t be used to build query conditions
 	password := user.Password
-	if user.Username == "" || password == "" {
+	if (user.Username == "" && user.Email == "") || password == "" {
 		return errors.New("用户名或密码为空")
 	}
-	DB.Where(User{Username: user.Username}).First(user)
+	// find buy username or email
+	if user.Username != "" {
+		DB.Where(User{Username: user.Username}).First(user)
+	} else if user.Email != "" {
+		DB.Where(User{Email: user.Email}).First(user)
+	}
 	okay := common.ValidatePasswordAndHash(password, user.Password)
 	if !okay || user.Status != common.UserStatusEnabled {
 		return errors.New("用户名或密码错误，或用户已被封禁")

relay/channel/aws/adaptor.go

@@ -68,7 +68,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = awsStreamHandler(c, info, a.RequestMode)
+		err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
 	} else {
 		err, usage = awsHandler(c, info, a.RequestMode)
 	}

relay/channel/aws/relay-aws.go

@@ -13,6 +13,7 @@ import (
 	relaymodel "one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
 	"time"
 
@@ -112,7 +113,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*
 	return nil, &usage
 }
 
-func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
+func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
 	awsCli, err := newAwsClient(c, info)
 	if err != nil {
 		return wrapErr(errors.Wrap(err, "newAwsClient")), nil
@@ -162,7 +163,6 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 	c.Stream(func(w io.Writer) bool {
 		event, ok := <-stream.Events()
 		if !ok {
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
 			return false
 		}
 
@@ -214,6 +214,17 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 			return false
 		}
 	})
-
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, createdTime, info.UpstreamModelName, usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
 	return nil, &usage
 }

relay/channel/baidu/dto.go

@@ -19,7 +19,7 @@ type BaiduChatRequest struct {
 	System          string         `json:"system,omitempty"`
 	DisableSearch   bool           `json:"disable_search,omitempty"`
 	EnableCitation  bool           `json:"enable_citation,omitempty"`
-	MaxOutputTokens int            `json:"max_output_tokens,omitempty"`
+	MaxOutputTokens *int           `json:"max_output_tokens,omitempty"`
 	UserId          string         `json:"user_id,omitempty"`
 }
 

relay/channel/baidu/relay-baidu.go

@@ -23,14 +23,17 @@ var baiduTokenStore sync.Map
 
 func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
 	baiduRequest := BaiduChatRequest{
-		Temperature:     request.Temperature,
-		TopP:            request.TopP,
-		PenaltyScore:    request.FrequencyPenalty,
-		Stream:          request.Stream,
-		DisableSearch:   false,
-		EnableCitation:  false,
-		MaxOutputTokens: int(request.MaxTokens),
-		UserId:          request.User,
+		Temperature:    request.Temperature,
+		TopP:           request.TopP,
+		PenaltyScore:   request.FrequencyPenalty,
+		Stream:         request.Stream,
+		DisableSearch:  false,
+		EnableCitation: false,
+		UserId:         request.User,
+	}
+	if request.MaxTokens != 0 {
+		maxTokens := int(request.MaxTokens)
+		baiduRequest.MaxOutputTokens = &maxTokens
 	}
 	for _, message := range request.Messages {
 		if message.Role == "system" {

relay/channel/claude/relay-claude.go

@@ -330,22 +330,15 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 			response.Created = createdTime
 			response.Model = info.UpstreamModelName
 
-			jsonStr, err := json.Marshal(response)
+			err = service.ObjectData(c, response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
+				common.SysError(err.Error())
 			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
 			return true
 		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
 			return false
 		}
 	})
-	err := resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-	}
 	if requestMode == RequestModeCompletion {
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
@@ -356,6 +349,18 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, usage.PromptTokens)
 		}
 	}
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(responseId, createdTime, info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	err := resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
 	return nil, usage
 }
 

relay/channel/cohere/relay-cohere.go

@@ -48,6 +48,9 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 }
 
 func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankRequest {
+	if rerankRequest.TopN == 0 {
+		rerankRequest.TopN = 1
+	}
 	cohereReq := CohereRerankRequest{
 		Query:           rerankRequest.Query,
 		Documents:       rerankRequest.Documents,
@@ -55,9 +58,6 @@ func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankR
 		TopN:            rerankRequest.TopN,
 		ReturnDocuments: true,
 	}
-	for _, doc := range rerankRequest.Documents {
-		cohereReq.Documents = append(cohereReq.Documents, doc)
-	}
 	return &cohereReq
 }
 

relay/channel/dify/relay-dify.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
@@ -48,9 +49,9 @@ func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dt
 		Model:   "dify",
 	}
 	var choice dto.ChatCompletionsStreamResponseChoice
-	if difyResponse.Event == "workflow_started" {
+	if constant.DifyDebug && difyResponse.Event == "workflow_started" {
 		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
-	} else if difyResponse.Event == "node_started" {
+	} else if constant.DifyDebug && difyResponse.Event == "node_started" {
 		choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
 	} else if difyResponse.Event == "message" {
 		choice.Delta.SetContentString(difyResponse.Answer)

relay/channel/jina/adaptor.go

@@ -0,0 +1,64 @@
+package jina
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+	}
+	return "", errors.New("invalid relay mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = jinaRerankHandler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/jina/constant.go

@@ -0,0 +1,8 @@
+package jina
+
+var ModelList = []string{
+	"jina-clip-v1",
+	"jina-reranker-v2-base-multilingual",
+}
+
+var ChannelName = "jina"

relay/channel/jina/relay-jina.go

@@ -0,0 +1,35 @@
+package jina
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var jinaResp dto.RerankResponse
+	err = json.Unmarshal(responseBody, &jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	jsonResponse, err := json.Marshal(jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &jinaResp.Usage
+}

relay/channel/ollama/adaptor.go

@@ -59,8 +59,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		}
 	} else {
 		if info.RelayMode == relayconstant.RelayModeEmbeddings {
 			err, usage = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)

relay/channel/openai/adaptor.go

@@ -89,9 +89,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		var responseText string
 		var toolCount int
-		err, responseText, toolCount = OpenaiStreamHandler(c, resp, info)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		usage.CompletionTokens += toolCount * 7
+		err, usage, responseText, toolCount = OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+			usage.CompletionTokens += toolCount * 7
+		}
 	} else {
 		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/openai/relay-openai.go

@@ -18,9 +18,10 @@ import (
 	"time"
 )
 
-func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, string, int) {
+func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage, string, int) {
 	//checkSensitive := constant.ShouldCheckCompletionSensitive()
 	var responseTextBuilder strings.Builder
+	var usage dto.Usage
 	toolCount := 0
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
@@ -62,17 +63,26 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 				streamItems = append(streamItems, data)
 			}
 		}
+		// 计算token
 		streamResp := "[" + strings.Join(streamItems, ",") + "]"
 		switch info.RelayMode {
 		case relayconstant.RelayModeChatCompletions:
 			var streamResponses []dto.ChatCompletionsStreamResponseSimple
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
+				// 一次性解析失败，逐个解析
 				common.SysError("error unmarshalling stream response: " + err.Error())
 				for _, item := range streamItems {
 					var streamResponse dto.ChatCompletionsStreamResponseSimple
 					err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 					if err == nil {
+						if streamResponse.Usage != nil {
+							if streamResponse.Usage.TotalTokens != 0 {
+								usage.PromptTokens += streamResponse.Usage.PromptTokens
+								usage.CompletionTokens += streamResponse.Usage.CompletionTokens
+								usage.TotalTokens += streamResponse.Usage.TotalTokens
+							}
+						}
 						for _, choice := range streamResponse.Choices {
 							responseTextBuilder.WriteString(choice.Delta.GetContentString())
 							if choice.Delta.ToolCalls != nil {
@@ -89,6 +99,13 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 				}
 			} else {
 				for _, streamResponse := range streamResponses {
+					if streamResponse.Usage != nil {
+						if streamResponse.Usage.TotalTokens != 0 {
+							usage.PromptTokens += streamResponse.Usage.PromptTokens
+							usage.CompletionTokens += streamResponse.Usage.CompletionTokens
+							usage.TotalTokens += streamResponse.Usage.TotalTokens
+						}
+					}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -107,6 +124,7 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 			var streamResponses []dto.CompletionsStreamResponse
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
+				// 一次性解析失败，逐个解析
 				common.SysError("error unmarshalling stream response: " + err.Error())
 				for _, item := range streamItems {
 					var streamResponse dto.CompletionsStreamResponse
@@ -133,13 +151,19 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	}()
 	service.SetEventStreamHeaders(c)
 	isFirst := true
+	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
+	defer ticker.Stop()
 	c.Stream(func(w io.Writer) bool {
 		select {
+		case <-ticker.C:
+			common.LogError(c, "reading data from upstream timeout")
+			return false
 		case data := <-dataChan:
 			if isFirst {
 				isFirst = false
 				info.FirstResponseTime = time.Now()
 			}
+			ticker.Reset(time.Duration(constant.StreamingTimeout) * time.Second)
 			if strings.HasPrefix(data, "data: [DONE]") {
 				data = data[:12]
 			}
@@ -153,10 +177,10 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", toolCount
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil, "", toolCount
 	}
 	wg.Wait()
-	return nil, responseTextBuilder.String(), toolCount
+	return nil, &usage, responseTextBuilder.String(), toolCount
 }
 
 func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {

relay/channel/perplexity/adaptor.go

@@ -55,8 +55,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		}
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/zhipu_4v/adaptor.go

@@ -57,9 +57,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		var responseText string
 		var toolCount int
-		err, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		usage.CompletionTokens += toolCount * 7
+		err, usage, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+			usage.CompletionTokens += toolCount * 7
+		}
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/common/relay_info.go

@@ -9,24 +9,26 @@ import (
 )
 
 type RelayInfo struct {
-	ChannelType       int
-	ChannelId         int
-	TokenId           int
-	UserId            int
-	Group             string
-	TokenUnlimited    bool
-	StartTime         time.Time
-	FirstResponseTime time.Time
-	ApiType           int
-	IsStream          bool
-	RelayMode         int
-	UpstreamModelName string
-	RequestURLPath    string
-	ApiVersion        string
-	PromptTokens      int
-	ApiKey            string
-	Organization      string
-	BaseUrl           string
+	ChannelType          int
+	ChannelId            int
+	TokenId              int
+	UserId               int
+	Group                string
+	TokenUnlimited       bool
+	StartTime            time.Time
+	FirstResponseTime    time.Time
+	ApiType              int
+	IsStream             bool
+	RelayMode            int
+	UpstreamModelName    string
+	RequestURLPath       string
+	ApiVersion           string
+	PromptTokens         int
+	ApiKey               string
+	Organization         string
+	BaseUrl              string
+	SupportStreamOptions bool
+	ShouldIncludeUsage   bool
 }
 
 func GenRelayInfo(c *gin.Context) *RelayInfo {
@@ -65,6 +67,9 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	if info.ChannelType == common.ChannelTypeAzure {
 		info.ApiVersion = GetAPIVersion(c)
 	}
+	if info.ChannelType == common.ChannelTypeOpenAI || info.ChannelType == common.ChannelTypeAnthropic || info.ChannelType == common.ChannelTypeAws {
+		info.SupportStreamOptions = true
+	}
 	return info
 }
 

relay/constant/api_type.go

@@ -21,6 +21,7 @@ const (
 	APITypeAws
 	APITypeCohere
 	APITypeDify
+	APITypeJina
 
 	APITypeDummy // this one is only for count, do not add any channel after this
 )
@@ -60,6 +61,8 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeCohere
 	case common.ChannelTypeDify:
 		apiType = APITypeDify
+	case common.ChannelTypeJina:
+		apiType = APITypeJina
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false

relay/relay-mj.go

@@ -415,9 +415,12 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		originTask := model.GetByMJId(userId, mjId)
 		if originTask == nil {
 			return service.MidjourneyErrorWrapper(constant.MjRequestError, "task_not_found")
-		} else if originTask.Status != "SUCCESS" && relayMode != relayconstant.RelayModeMidjourneyModal {
-			return service.MidjourneyErrorWrapper(constant.MjRequestError, "task_status_not_success")
 		} else { //原任务的Status=SUCCESS，则可以做放大UPSCALE、变换VARIATION等动作，此时必须使用原来的请求地址才能正确处理
+			if constant.MjActionCheckSuccessEnabled {
+				if originTask.Status != "SUCCESS" && relayMode != relayconstant.RelayModeMidjourneyModal {
+					return service.MidjourneyErrorWrapper(constant.MjRequestError, "task_status_not_success")
+				}
+			}
 			channel, err := model.GetChannelById(originTask.ChannelId, true)
 			if err != nil {
 				return service.MidjourneyErrorWrapper(constant.MjRequestError, "get_channel_info_failed")

relay/relay-text.go

@@ -77,7 +77,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 
 	// map model name
 	modelMapping := c.GetString("model_mapping")
-	isModelMapped := false
+	//isModelMapped := false
 	if modelMapping != "" && modelMapping != "{}" {
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
@@ -87,7 +87,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		if modelMap[textRequest.Model] != "" {
 			textRequest.Model = modelMap[textRequest.Model]
 			// set upstream model name
-			isModelMapped = true
+			//isModelMapped = true
 		}
 	}
 	relayInfo.UpstreamModelName = textRequest.Model
@@ -130,33 +130,38 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return openaiErr
 	}
 
+	// 如果不支持StreamOptions，将StreamOptions设置为nil
+	if !relayInfo.SupportStreamOptions || !textRequest.Stream {
+		textRequest.StreamOptions = nil
+	} else {
+		// 如果支持StreamOptions，且请求中没有设置StreamOptions，根据配置文件设置StreamOptions
+		if constant.ForceStreamOption {
+			textRequest.StreamOptions = &dto.StreamOptions{
+				IncludeUsage: true,
+			}
+		}
+	}
+
+	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
+		relayInfo.ShouldIncludeUsage = textRequest.StreamOptions.IncludeUsage
+	}
+
 	adaptor := GetAdaptor(relayInfo.ApiType)
 	if adaptor == nil {
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
 	}
 	adaptor.Init(relayInfo, *textRequest)
 	var requestBody io.Reader
-	if relayInfo.ApiType == relayconstant.APITypeOpenAI {
-		if isModelMapped {
-			jsonStr, err := json.Marshal(textRequest)
-			if err != nil {
-				return service.OpenAIErrorWrapperLocal(err, "marshal_text_request_failed", http.StatusInternalServerError)
-			}
-			requestBody = bytes.NewBuffer(jsonStr)
-		} else {
-			requestBody = c.Request.Body
-		}
-	} else {
-		convertedRequest, err := adaptor.ConvertRequest(c, relayInfo.RelayMode, textRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
-		}
-		jsonData, err := json.Marshal(convertedRequest)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
-		}
-		requestBody = bytes.NewBuffer(jsonData)
+
+	convertedRequest, err := adaptor.ConvertRequest(c, relayInfo.RelayMode, textRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
 	}
+	jsonData, err := json.Marshal(convertedRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
+	}
+	requestBody = bytes.NewBuffer(jsonData)
 
 	statusCodeMappingStr := c.GetString("status_code_mapping")
 	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)

relay/relay_adaptor.go

@@ -10,6 +10,7 @@ import (
 	"one-api/relay/channel/cohere"
 	"one-api/relay/channel/dify"
 	"one-api/relay/channel/gemini"
+	"one-api/relay/channel/jina"
 	"one-api/relay/channel/ollama"
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
@@ -56,6 +57,8 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &cohere.Adaptor{}
 	case constant.APITypeDify:
 		return &dify.Adaptor{}
+	case constant.APITypeJina:
+		return &jina.Adaptor{}
 	}
 	return nil
 }

service/usage_helpr.go

@@ -24,3 +24,15 @@ func ResponseText2Usage(responseText string, modeName string, promptTokens int)
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	return usage, err
 }
+
+func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
+	return &dto.ChatCompletionsStreamResponse{
+		Id:                id,
+		Object:            "chat.completion.chunk",
+		Created:           createAt,
+		Model:             model,
+		SystemFingerprint: nil,
+		Choices:           nil,
+		Usage:             &usage,
+	}
+}

web/src/components/ChannelsTable.js

@@ -550,7 +550,7 @@ const ChannelsTable = () => {
     );
     const { success, message, data } = res.data;
     if (success) {
-      setChannels(data);
+      setChannelFormat(data);
       setActivePage(1);
     } else {
       showError(message);

web/src/components/OperationSetting.js

@@ -42,6 +42,7 @@ const OperationSetting = () => {
     MjAccountFilterEnabled: false,
     MjModeClearEnabled: false,
     MjForwardUrlEnabled: false,
+    MjActionCheckSuccessEnabled: false,
     DrawingEnabled: false,
     DataExportEnabled: false,
     DataExportDefaultTime: 'hour',

web/src/constants/channel.constants.js

@@ -104,7 +104,8 @@ export const CHANNEL_OPTIONS = [
   { key: 23, text: '腾讯混元', value: 23, color: 'teal', label: '腾讯混元' },
   { key: 31, text: '零一万物', value: 31, color: 'green', label: '零一万物' },
   { key: 35, text: 'MiniMax', value: 35, color: 'green', label: 'MiniMax' },
-  { key: 37, text: 'Dify', value: 37, color: 'green', label: 'Dify' },
+  { key: 37, text: 'Dify', value: 37, color: 'teal', label: 'Dify' },
+  { key: 38, text: 'Jina', value: 38, color: 'blue', label: 'Jina' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink', label: '自定义渠道' },
   {
     key: 22,

web/src/helpers/render.js

@@ -153,8 +153,8 @@ export function renderModelPrice(
     let inputRatioPrice = modelRatio * 2.0;
     let completionRatioPrice = modelRatio * 2.0 * completionRatio;
     let price =
-      (inputTokens / 1000000) * inputRatioPrice +
-      (completionTokens / 1000000) * completionRatioPrice;
+      (inputTokens / 1000000) * inputRatioPrice * groupRatio +
+      (completionTokens / 1000000) * completionRatioPrice * groupRatio;
     return (
       <>
         <article>

web/src/pages/Setting/Operation/SettingsDrawing.js

@@ -16,6 +16,7 @@ export default function SettingsDrawing(props) {
     MjAccountFilterEnabled: false,
     MjForwardUrlEnabled: false,
     MjModeClearEnabled: false,
+    MjActionCheckSuccessEnabled: false,
   });
   const refForm = useRef();
   const [inputsRow, setInputsRow] = useState(inputs);
@@ -156,6 +157,25 @@ export default function SettingsDrawing(props) {
                   }
                 />
               </Col>
+              <Col span={8}>
+                <Form.Switch
+                  field={'MjActionCheckSuccessEnabled'}
+                  label={
+                    <>
+                      检测必须等待绘图成功才能进行放大等操作
+                    </>
+                  }
+                  size='large'
+                  checkedText='｜'
+                  uncheckedText='〇'
+                  onChange={(value) =>
+                    setInputs({
+                      ...inputs,
+                      MjActionCheckSuccessEnabled: value,
+                    })
+                  }
+                />
+              </Col>
             </Row>
             <Row>
               <Button size='large' onClick={onSubmit}>