chore: adjust ui

README.en.md

@@ -57,15 +57,13 @@ _✨ Access all LLM through the standard OpenAI API format, easy to deploy & use
 > **Note**: The latest image pulled from Docker may be an `alpha` release. Specify the version manually if you require stability.
 
 ## Features
-1. Supports multiple API access channels:
-    + [x] Official OpenAI channel (support proxy configuration)
-    + [x] **Azure OpenAI API**
-    + [x] [API Distribute](https://api.gptjk.top/register?aff=QGxj)
-    + [x] [OpenAI-SB](https://openai-sb.com)
-    + [x] [API2D](https://api2d.com/r/197971)
-    + [x] [OhMyGPT](https://aigptx.top?aff=uFpUl2Kf)
-    + [x] [AI Proxy](https://aiproxy.io/?i=OneAPI) (invitation code: `OneAPI`)
-    + [x] Custom channel: Various third-party proxy services not included in the list
+1. Support for multiple large models:
+   + [x] [OpenAI ChatGPT Series Models](https://platform.openai.com/docs/guides/gpt/chat-completions-api) (Supports [Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference))
+   + [x] [Anthropic Claude Series Models](https://anthropic.com)
+   + [x] [Google PaLM2 Series Models](https://developers.generativeai.google)
+   + [x] [Baidu Wenxin Yiyuan Series Models](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
+   + [x] [Alibaba Tongyi Qianwen Series Models](https://help.aliyun.com/document_detail/2400395.html)
+   + [x] [Zhipu ChatGLM Series Models](https://bigmodel.cn)
 2. Supports access to multiple channels through **load balancing**.
 3. Supports **stream mode** that enables typewriter-like effect through stream transmission.
 4. Supports **multi-machine deployment**. [See here](#multi-machine-deployment) for more details.

README.md

@@ -63,9 +63,9 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [Anthropic Claude 系列模型](https://anthropic.com)
    + [x] [Google PaLM2 系列模型](https://developers.generativeai.google)
    + [x] [百度文心一言系列模型](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
+   + [x] [阿里通义千问系列模型](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [智谱 ChatGLM 系列模型](https://bigmodel.cn)
 2. 支持配置镜像以及众多第三方代理服务：
-   + [x] [API Distribute](https://api.gptjk.top/register?aff=QGxj)
    + [x] [OpenAI-SB](https://openai-sb.com)
    + [x] [API2D](https://api2d.com/r/197971)
    + [x] [OhMyGPT](https://aigptx.top?aff=uFpUl2Kf)

common/constants.go

@@ -156,24 +156,26 @@ const (
 	ChannelTypeAnthropic = 14
 	ChannelTypeBaidu     = 15
 	ChannelTypeZhipu     = 16
+	ChannelTypeAli       = 17
 )
 
 var ChannelBaseURLs = []string{
-	"",                              // 0
-	"https://api.openai.com",        // 1
-	"https://oa.api2d.net",          // 2
-	"",                              // 3
-	"https://api.closeai-proxy.xyz", // 4
-	"https://api.openai-sb.com",     // 5
-	"https://api.openaimax.com",     // 6
-	"https://api.ohmygpt.com",       // 7
-	"",                              // 8
-	"https://api.caipacity.com",     // 9
-	"https://api.aiproxy.io",        // 10
-	"",                              // 11
-	"https://api.api2gpt.com",       // 12
-	"https://api.aigc2d.com",        // 13
-	"https://api.anthropic.com",     // 14
-	"https://aip.baidubce.com",      // 15
-	"https://open.bigmodel.cn",      // 16
+	"",                               // 0
+	"https://api.openai.com",         // 1
+	"https://oa.api2d.net",           // 2
+	"",                               // 3
+	"https://api.closeai-proxy.xyz",  // 4
+	"https://api.openai-sb.com",      // 5
+	"https://api.openaimax.com",      // 6
+	"https://api.ohmygpt.com",        // 7
+	"",                               // 8
+	"https://api.caipacity.com",      // 9
+	"https://api.aiproxy.io",         // 10
+	"",                               // 11
+	"https://api.api2gpt.com",        // 12
+	"https://api.aigc2d.com",         // 13
+	"https://api.anthropic.com",      // 14
+	"https://aip.baidubce.com",       // 15
+	"https://open.bigmodel.cn",       // 16
+	"https://dashscope.aliyuncs.com", // 17
 }

common/model-ratio.go

@@ -42,10 +42,13 @@ var ModelRatio = map[string]float64{
 	"claude-2":                30,
 	"ERNIE-Bot":               0.8572, // ￥0.012 / 1k tokens
 	"ERNIE-Bot-turbo":         0.5715, // ￥0.008 / 1k tokens
+	"Embedding-V1":            0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                  1,
 	"chatglm_pro":             0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":            0.1429, // ￥0.002 / 1k tokens
+	"qwen-v1":                 0.8572, // TBD: https://help.aliyun.com/document_detail/2399482.html?spm=a2c4g.2399482.0.0.1ad347feilAgag
+	"qwen-plus-v1":            0.5715, // Same as above
 }
 
 func ModelRatio2JSONString() string {

controller/model.go

@@ -288,6 +288,15 @@ func init() {
 			Root:       "ERNIE-Bot-turbo",
 			Parent:     nil,
 		},
+		{
+			Id:         "Embedding-V1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "baidu",
+			Permission: permission,
+			Root:       "Embedding-V1",
+			Parent:     nil,
+		},
 		{
 			Id:         "PaLM-2",
 			Object:     "model",
@@ -324,6 +333,24 @@ func init() {
 			Root:       "chatglm_lite",
 			Parent:     nil,
 		},
+		{
+			Id:         "qwen-v1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "ali",
+			Permission: permission,
+			Root:       "qwen-v1",
+			Parent:     nil,
+		},
+		{
+			Id:         "qwen-plus-v1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "ali",
+			Permission: permission,
+			Root:       "qwen-plus-v1",
+			Parent:     nil,
+		},
 	}
 	openAIModelsMap = make(map[string]OpenAIModels)
 	for _, model := range openAIModels {

controller/relay-ali.go

@@ -0,0 +1,240 @@
+package controller
+
+import (
+	"bufio"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"strings"
+)
+
+// https://help.aliyun.com/document_detail/613695.html?spm=a2c4g.2399480.0.0.1adb778fAdzP9w#341800c0f8w0r
+
+type AliMessage struct {
+	User string `json:"user"`
+	Bot  string `json:"bot"`
+}
+
+type AliInput struct {
+	Prompt  string       `json:"prompt"`
+	History []AliMessage `json:"history"`
+}
+
+type AliParameters struct {
+	TopP         float64 `json:"top_p,omitempty"`
+	TopK         int     `json:"top_k,omitempty"`
+	Seed         uint64  `json:"seed,omitempty"`
+	EnableSearch bool    `json:"enable_search,omitempty"`
+}
+
+type AliChatRequest struct {
+	Model      string        `json:"model"`
+	Input      AliInput      `json:"input"`
+	Parameters AliParameters `json:"parameters,omitempty"`
+}
+
+type AliError struct {
+	Code      string `json:"code"`
+	Message   string `json:"message"`
+	RequestId string `json:"request_id"`
+}
+
+type AliUsage struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+}
+
+type AliOutput struct {
+	Text         string `json:"text"`
+	FinishReason string `json:"finish_reason"`
+}
+
+type AliChatResponse struct {
+	Output AliOutput `json:"output"`
+	Usage  AliUsage  `json:"usage"`
+	AliError
+}
+
+func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
+	messages := make([]AliMessage, 0, len(request.Messages))
+	prompt := ""
+	for i := 0; i < len(request.Messages); i++ {
+		message := request.Messages[i]
+		if message.Role == "system" {
+			messages = append(messages, AliMessage{
+				User: message.Content,
+				Bot:  "Okay",
+			})
+			continue
+		} else {
+			if i == len(request.Messages)-1 {
+				prompt = message.Content
+				break
+			}
+			messages = append(messages, AliMessage{
+				User: message.Content,
+				Bot:  request.Messages[i+1].Content,
+			})
+			i++
+		}
+	}
+	return &AliChatRequest{
+		Model: request.Model,
+		Input: AliInput{
+			Prompt:  prompt,
+			History: messages,
+		},
+		//Parameters: AliParameters{  // ChatGPT's parameters are not compatible with Ali's
+		//	TopP: request.TopP,
+		//	TopK: 50,
+		//	//Seed:         0,
+		//	//EnableSearch: false,
+		//},
+	}
+}
+
+func responseAli2OpenAI(response *AliChatResponse) *OpenAITextResponse {
+	choice := OpenAITextResponseChoice{
+		Index: 0,
+		Message: Message{
+			Role:    "assistant",
+			Content: response.Output.Text,
+		},
+		FinishReason: response.Output.FinishReason,
+	}
+	fullTextResponse := OpenAITextResponse{
+		Id:      response.RequestId,
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Choices: []OpenAITextResponseChoice{choice},
+		Usage: Usage{
+			PromptTokens:     response.Usage.InputTokens,
+			CompletionTokens: response.Usage.OutputTokens,
+			TotalTokens:      response.Usage.InputTokens + response.Usage.OutputTokens,
+		},
+	}
+	return &fullTextResponse
+}
+
+func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *ChatCompletionsStreamResponse {
+	var choice ChatCompletionsStreamResponseChoice
+	choice.Delta.Content = aliResponse.Output.Text
+	choice.FinishReason = aliResponse.Output.FinishReason
+	response := ChatCompletionsStreamResponse{
+		Id:      aliResponse.RequestId,
+		Object:  "chat.completion.chunk",
+		Created: common.GetTimestamp(),
+		Model:   "ernie-bot",
+		Choices: []ChatCompletionsStreamResponseChoice{choice},
+	}
+	return &response
+}
+
+func aliStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+	var usage Usage
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
+		if atEOF && len(data) == 0 {
+			return 0, nil, nil
+		}
+		if i := strings.Index(string(data), "\n"); i >= 0 {
+			return i + 1, data[0:i], nil
+		}
+		if atEOF {
+			return len(data), data, nil
+		}
+		return 0, nil, nil
+	})
+	dataChan := make(chan string)
+	stopChan := make(chan bool)
+	go func() {
+		for scanner.Scan() {
+			data := scanner.Text()
+			if len(data) < 5 { // ignore blank line or wrong format
+				continue
+			}
+			if data[:5] != "data:" {
+				continue
+			}
+			data = data[5:]
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	c.Writer.Header().Set("Content-Type", "text/event-stream")
+	c.Writer.Header().Set("Cache-Control", "no-cache")
+	c.Writer.Header().Set("Connection", "keep-alive")
+	c.Writer.Header().Set("Transfer-Encoding", "chunked")
+	c.Writer.Header().Set("X-Accel-Buffering", "no")
+	lastResponseText := ""
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			var aliResponse AliChatResponse
+			err := json.Unmarshal([]byte(data), &aliResponse)
+			if err != nil {
+				common.SysError("error unmarshalling stream response: " + err.Error())
+				return true
+			}
+			usage.PromptTokens += aliResponse.Usage.InputTokens
+			usage.CompletionTokens += aliResponse.Usage.OutputTokens
+			usage.TotalTokens += aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
+			response := streamResponseAli2OpenAI(&aliResponse)
+			response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
+			lastResponseText = aliResponse.Output.Text
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	err := resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	return nil, &usage
+}
+
+func aliHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+	var aliResponse AliChatResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &aliResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if aliResponse.Code != "" {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: OpenAIError{
+				Message: aliResponse.Message,
+				Type:    aliResponse.Code,
+				Param:   aliResponse.RequestId,
+				Code:    aliResponse.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := responseAli2OpenAI(&aliResponse)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}

controller/relay-baidu.go

@@ -54,6 +54,25 @@ type BaiduChatStreamResponse struct {
 	IsEnd      bool `json:"is_end"`
 }
 
+type BaiduEmbeddingRequest struct {
+	Input []string `json:"input"`
+}
+
+type BaiduEmbeddingData struct {
+	Object    string    `json:"object"`
+	Embedding []float64 `json:"embedding"`
+	Index     int       `json:"index"`
+}
+
+type BaiduEmbeddingResponse struct {
+	Id      string               `json:"id"`
+	Object  string               `json:"object"`
+	Created int64                `json:"created"`
+	Data    []BaiduEmbeddingData `json:"data"`
+	Usage   Usage                `json:"usage"`
+	BaiduError
+}
+
 func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 	messages := make([]BaiduMessage, 0, len(request.Messages))
 	for _, message := range request.Messages {
@@ -112,6 +131,36 @@ func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *ChatCom
 	return &response
 }
 
+func embeddingRequestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduEmbeddingRequest {
+	baiduEmbeddingRequest := BaiduEmbeddingRequest{
+		Input: nil,
+	}
+	switch request.Input.(type) {
+	case string:
+		baiduEmbeddingRequest.Input = []string{request.Input.(string)}
+	case []string:
+		baiduEmbeddingRequest.Input = request.Input.([]string)
+	}
+	return &baiduEmbeddingRequest
+}
+
+func embeddingResponseBaidu2OpenAI(response *BaiduEmbeddingResponse) *OpenAIEmbeddingResponse {
+	openAIEmbeddingResponse := OpenAIEmbeddingResponse{
+		Object: "list",
+		Data:   make([]OpenAIEmbeddingResponseItem, 0, len(response.Data)),
+		Model:  "baidu-embedding",
+		Usage:  response.Usage,
+	}
+	for _, item := range response.Data {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, OpenAIEmbeddingResponseItem{
+			Object:    item.Object,
+			Index:     item.Index,
+			Embedding: item.Embedding,
+		})
+	}
+	return &openAIEmbeddingResponse
+}
+
 func baiduStreamHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
 	var usage Usage
 	scanner := bufio.NewScanner(resp.Body)
@@ -212,3 +261,39 @@ func baiduHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCo
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &fullTextResponse.Usage
 }
+
+func baiduEmbeddingHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
+	var baiduResponse BaiduEmbeddingResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &baiduResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if baiduResponse.ErrorMsg != "" {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: OpenAIError{
+				Message: baiduResponse.ErrorMsg,
+				Type:    "baidu_error",
+				Param:   "",
+				Code:    baiduResponse.ErrorCode,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := embeddingResponseBaidu2OpenAI(&baiduResponse)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}

controller/relay-text.go

@@ -20,6 +20,7 @@ const (
 	APITypePaLM
 	APITypeBaidu
 	APITypeZhipu
+	APITypeAli
 )
 
 var httpClient *http.Client
@@ -73,7 +74,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	// map model name
 	modelMapping := c.GetString("model_mapping")
 	isModelMapped := false
-	if modelMapping != "" {
+	if modelMapping != "" && modelMapping != "{}" {
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
 		if err != nil {
@@ -94,6 +95,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		apiType = APITypePaLM
 	case common.ChannelTypeZhipu:
 		apiType = APITypeZhipu
+	case common.ChannelTypeAli:
+		apiType = APITypeAli
+
 	}
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
@@ -135,6 +139,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
 		case "BLOOMZ-7B":
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
+		case "Embedding-V1":
+			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
 		}
 		apiKey := c.Request.Header.Get("Authorization")
 		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
@@ -153,6 +159,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			method = "sse-invoke"
 		}
 		fullRequestURL = fmt.Sprintf("https://open.bigmodel.cn/api/paas/v3/model-api/%s/%s", textRequest.Model, method)
+	case APITypeAli:
+		fullRequestURL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation"
 	}
 	var promptTokens int
 	var completionTokens int
@@ -206,12 +214,20 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		}
 		requestBody = bytes.NewBuffer(jsonStr)
 	case APITypeBaidu:
-		baiduRequest := requestOpenAI2Baidu(textRequest)
-		jsonStr, err := json.Marshal(baiduRequest)
+		var jsonData []byte
+		var err error
+		switch relayMode {
+		case RelayModeEmbeddings:
+			baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(textRequest)
+			jsonData, err = json.Marshal(baiduEmbeddingRequest)
+		default:
+			baiduRequest := requestOpenAI2Baidu(textRequest)
+			jsonData, err = json.Marshal(baiduRequest)
+		}
 		if err != nil {
 			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
 		}
-		requestBody = bytes.NewBuffer(jsonStr)
+		requestBody = bytes.NewBuffer(jsonData)
 	case APITypePaLM:
 		palmRequest := requestOpenAI2PaLM(textRequest)
 		jsonStr, err := json.Marshal(palmRequest)
@@ -226,6 +242,13 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
 		}
 		requestBody = bytes.NewBuffer(jsonStr)
+	case APITypeAli:
+		aliRequest := requestOpenAI2Ali(textRequest)
+		jsonStr, err := json.Marshal(aliRequest)
+		if err != nil {
+			return errorWrapper(err, "marshal_text_request_failed", http.StatusInternalServerError)
+		}
+		requestBody = bytes.NewBuffer(jsonStr)
 	}
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
@@ -250,6 +273,11 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	case APITypeZhipu:
 		token := getZhipuToken(apiKey)
 		req.Header.Set("Authorization", token)
+	case APITypeAli:
+		req.Header.Set("Authorization", "Bearer "+apiKey)
+		if textRequest.Stream {
+			req.Header.Set("X-DashScope-SSE", "enable")
+		}
 	}
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
@@ -280,7 +308,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			if strings.HasPrefix(textRequest.Model, "gpt-4") {
 				completionRatio = 2
 			}
-			if isStream && apiType != APITypeBaidu && apiType != APITypeZhipu {
+			if isStream && apiType != APITypeBaidu && apiType != APITypeZhipu && apiType != APITypeAli {
 				completionTokens = countTokenText(streamResponseText, textRequest.Model)
 			} else {
 				promptTokens = textResponse.Usage.PromptTokens
@@ -368,7 +396,14 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			}
 			return nil
 		} else {
-			err, usage := baiduHandler(c, resp)
+			var err *OpenAIErrorWithStatusCode
+			var usage *Usage
+			switch relayMode {
+			case RelayModeEmbeddings:
+				err, usage = baiduEmbeddingHandler(c, resp)
+			default:
+				err, usage = baiduHandler(c, resp)
+			}
 			if err != nil {
 				return err
 			}
@@ -415,6 +450,26 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			}
 			return nil
 		}
+	case APITypeAli:
+		if isStream {
+			err, usage := aliStreamHandler(c, resp)
+			if err != nil {
+				return err
+			}
+			if usage != nil {
+				textResponse.Usage = *usage
+			}
+			return nil
+		} else {
+			err, usage := aliHandler(c, resp)
+			if err != nil {
+				return err
+			}
+			if usage != nil {
+				textResponse.Usage = *usage
+			}
+			return nil
+		}
 	default:
 		return errorWrapper(errors.New("unknown api type"), "unknown_api_type", http.StatusInternalServerError)
 	}

controller/relay.go

@@ -99,6 +99,19 @@ type OpenAITextResponse struct {
 	Usage   `json:"usage"`
 }
 
+type OpenAIEmbeddingResponseItem struct {
+	Object    string    `json:"object"`
+	Index     int       `json:"index"`
+	Embedding []float64 `json:"embedding"`
+}
+
+type OpenAIEmbeddingResponse struct {
+	Object string                        `json:"object"`
+	Data   []OpenAIEmbeddingResponseItem `json:"data"`
+	Model  string                        `json:"model"`
+	Usage  `json:"usage"`
+}
+
 type ImageResponse struct {
 	Created int `json:"created"`
 	Data    []struct {

web/src/components/ChannelsTable.js

@@ -363,9 +363,12 @@ const ChannelsTable = () => {
                   </Table.Cell>
                   <Table.Cell>
                     <Popup
-                      content={channel.balance_updated_time ? renderTimestamp(channel.balance_updated_time) : '未更新'}
-                      key={channel.id}
-                      trigger={renderBalance(channel.type, channel.balance)}
+                      trigger={<span onClick={() => {
+                        updateChannelBalance(channel.id, channel.name, idx);
+                      }} style={{ cursor: 'pointer' }}>
+                      {renderBalance(channel.type, channel.balance)}
+                    </span>}
+                      content="点击更新"
                       basic
                     />
                   </Table.Cell>
@@ -380,16 +383,16 @@ const ChannelsTable = () => {
                       >
                         测试
                       </Button>
-                      <Button
-                        size={'small'}
-                        positive
-                        loading={updatingBalance}
-                        onClick={() => {
-                          updateChannelBalance(channel.id, channel.name, idx);
-                        }}
-                      >
-                        更新余额
-                      </Button>
+                      {/*<Button*/}
+                      {/*  size={'small'}*/}
+                      {/*  positive*/}
+                      {/*  loading={updatingBalance}*/}
+                      {/*  onClick={() => {*/}
+                      {/*    updateChannelBalance(channel.id, channel.name, idx);*/}
+                      {/*  }}*/}
+                      {/*>*/}
+                      {/*  更新余额*/}
+                      {/*</Button>*/}
                       <Popup
                         trigger={
                           <Button size='small' negative>

web/src/components/UsersTable.js

@@ -227,7 +227,7 @@ const UsersTable = () => {
                       content={user.email ? user.email : '未绑定邮箱地址'}
                       key={user.username}
                       header={user.display_name ? user.display_name : user.username}
-                      trigger={<span>{renderText(user.username, 10)}</span>}
+                      trigger={<span>{renderText(user.username, 15)}</span>}
                       hoverable
                     />
                   </Table.Cell>

web/src/constants/channel.constants.js

@@ -4,6 +4,7 @@ export const CHANNEL_OPTIONS = [
   { key: 3, text: 'Azure OpenAI', value: 3, color: 'olive' },
   { key: 11, text: 'Google PaLM2', value: 11, color: 'orange' },
   { key: 15, text: '百度文心千帆', value: 15, color: 'blue' },
+  { key: 17, text: '阿里通义千问', value: 17, color: 'orange' },
   { key: 16, text: '智谱 ChatGLM', value: 16, color: 'violet' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
   { key: 2, text: '代理：API2D', value: 2, color: 'blue' },
@@ -14,5 +15,5 @@ export const CHANNEL_OPTIONS = [
   { key: 6, text: '代理：OpenAI Max', value: 6, color: 'violet' },
   { key: 9, text: '代理：AI.LS', value: 9, color: 'yellow' },
   { key: 12, text: '代理：API2GPT', value: 12, color: 'blue' },
-  { key: 13, text: '代理：AIGC2D', value: 13, color: 'purple' }
+  { key: 13, text: '代理：AIGC2D', value: 13, color: 'purple' },
 ];

web/src/constants/toast.constants.js

@@ -1,5 +1,5 @@
 export const toastConstants = {
-  SUCCESS_TIMEOUT: 500,
+  SUCCESS_TIMEOUT: 1500,
   INFO_TIMEOUT: 3000,
   ERROR_TIMEOUT: 5000,
   WARNING_TIMEOUT: 10000,

web/src/pages/Channel/EditChannel.js

@@ -35,6 +35,27 @@ const EditChannel = () => {
   const [customModel, setCustomModel] = useState('');
   const handleInputChange = (e, { name, value }) => {
     setInputs((inputs) => ({ ...inputs, [name]: value }));
+    if (name === 'type' && inputs.models.length === 0) {
+      let localModels = [];
+      switch (value) {
+        case 14:
+          localModels = ['claude-instant-1', 'claude-2'];
+          break;
+        case 11:
+          localModels = ['PaLM-2'];
+          break;
+        case 15:
+          localModels = ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'Embedding-V1'];
+          break;
+        case 17:
+          localModels = ['qwen-v1', 'qwen-plus-v1'];
+          break;
+        case 16:
+          localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
+          break;
+      }
+      setInputs((inputs) => ({ ...inputs, models: localModels }));
+    }
   };
 
   const loadChannel = async () => {
@@ -132,7 +153,10 @@ const EditChannel = () => {
       localInputs.base_url = localInputs.base_url.slice(0, localInputs.base_url.length - 1);
     }
     if (localInputs.type === 3 && localInputs.other === '') {
-      localInputs.other = '2023-03-15-preview';
+      localInputs.other = '2023-06-01-preview';
+    }
+    if (localInputs.model_mapping === '') {
+      localInputs.model_mapping = '{}';
     }
     let res;
     localInputs.models = localInputs.models.join(',');
@@ -192,7 +216,7 @@ const EditChannel = () => {
                   <Form.Input
                     label='默认 API 版本'
                     name='other'
-                    placeholder={'请输入默认 API 版本，例如：2023-03-15-preview，该配置可以被实际的请求查询参数所覆盖'}
+                    placeholder={'请输入默认 API 版本，例如：2023-06-01-preview，该配置可以被实际的请求查询参数所覆盖'}
                     onChange={handleInputChange}
                     value={inputs.other}
                     autoComplete='new-password'
@@ -270,8 +294,8 @@ const EditChannel = () => {
             }}>清除所有模型</Button>
             <Input
               action={
-                <Button type={'button'} onClick={()=>{
-                  if (customModel.trim() === "") return;
+                <Button type={'button'} onClick={() => {
+                  if (customModel.trim() === '') return;
                   if (inputs.models.includes(customModel)) return;
                   let localModels = [...inputs.models];
                   localModels.push(customModel);
@@ -279,9 +303,9 @@ const EditChannel = () => {
                   localModelOptions.push({
                     key: customModel,
                     text: customModel,
-                    value: customModel,
+                    value: customModel
                   });
-                  setModelOptions(modelOptions=>{
+                  setModelOptions(modelOptions => {
                     return [...modelOptions, ...localModelOptions];
                   });
                   setCustomModel('');
@@ -297,7 +321,7 @@ const EditChannel = () => {
           </div>
           <Form.Field>
             <Form.TextArea
-              label='模型映射'
+              label='模型重定向'
               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={handleInputChange}
@@ -323,7 +347,7 @@ const EditChannel = () => {
                 label='密钥'
                 name='key'
                 required
-                placeholder={inputs.type === 15 ? "请输入 access token，当前版本暂不支持自动刷新，请每 30 天更新一次" : '请输入渠道对应的鉴权密钥'}
+                placeholder={inputs.type === 15 ? '请输入 access token，当前版本暂不支持自动刷新，请每 30 天更新一次' : '请输入渠道对应的鉴权密钥'}
                 onChange={handleInputChange}
                 value={inputs.key}
                 autoComplete='new-password'
@@ -354,7 +378,7 @@ const EditChannel = () => {
               </Form.Field>
             )
           }
-          <Button type={isEdit ? "button" : "submit"} positive onClick={submit}>提交</Button>
+          <Button type={isEdit ? 'button' : 'submit'} positive onClick={submit}>提交</Button>
         </Form>
       </Segment>
     </>

web/src/pages/Token/EditToken.js

@@ -83,7 +83,7 @@ const EditToken = () => {
       if (isEdit) {
         showSuccess('令牌更新成功！');
       } else {
-        showSuccess('令牌创建成功！');
+        showSuccess('令牌创建成功，请在列表页面点击复制获取令牌！');
         setInputs(originInputs);
       }
     } else {