Merge pull request #723 from kuwork/main

Support for MokaAI M3E

relay/channel/adapter.go

@@ -15,6 +15,7 @@ type Adaptor interface {
 	SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
 	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
+	ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error)
 	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
 	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)

relay/channel/ali/adaptor.go

@@ -67,6 +67,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	//TODO implement me
 	return nil, errors.New("not implemented")

relay/channel/aws/adaptor.go

@@ -59,6 +59,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return nil, nil
 }

relay/channel/baidu/adaptor.go

@@ -122,6 +122,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/claude/adaptor.go

@@ -73,6 +73,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/cloudflare/adaptor.go

@@ -56,6 +56,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	// 添加文件字段
 	file, _, err := c.Request.FormFile("file")

relay/channel/cohere/adaptor.go

@@ -54,6 +54,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return requestConvertRerank2Cohere(request), nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = cohereRerankHandler(c, resp, info)

relay/channel/deepseek/adaptor.go

@@ -49,6 +49,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/dify/adaptor.go

@@ -48,6 +48,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/gemini/adaptor.go

@@ -68,6 +68,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/jina/adaptor.go

@@ -55,6 +55,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = jinaRerankHandler(c, resp)

relay/channel/mistral/adaptor.go

@@ -50,6 +50,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/mokaai/adaptor.go

@@ -0,0 +1,93 @@
+package mokaai
+
+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"
+	"strings"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return request, nil
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	suffix := "chat/"
+	if strings.HasPrefix(info.UpstreamModelName, "m3e") {
+		suffix = "embeddings"
+	}
+	fullRequestURL := fmt.Sprintf("%s/%s", info.BaseUrl, suffix)
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := embeddingRequestOpenAI2Moka(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		return nil, errors.New("not implemented")
+	}
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+		
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		err, usage = mokaEmbeddingHandler(c, resp)
+	default:
+		// err, usage = mokaHandler(c, resp)
+		
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/mokaai/constants.go

@@ -0,0 +1,9 @@
+package mokaai
+
+var ModelList = []string{
+	"m3e-large",
+	"m3e-base",
+	"m3e-small",
+}
+
+var ChannelName = "mokaai"

relay/channel/mokaai/relay-mokaai.go

@@ -0,0 +1,83 @@
+package mokaai
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func embeddingRequestOpenAI2Moka(request dto.GeneralOpenAIRequest) *dto.EmbeddingRequest {
+	var input []string // Change input to []string
+
+	switch v := request.Input.(type) {
+	case string:
+		input = []string{v} // Convert string to []string
+	case []string:
+		input = v // Already a []string, no conversion needed
+	case []interface{}:
+		for _, part := range v {
+			if str, ok := part.(string); ok {
+				input = append(input, str) // Append each string to the slice
+			}
+		}
+	}
+	return &dto.EmbeddingRequest{
+		Input: input,
+		Model:  request.Model,
+	}
+}
+
+func embeddingResponseMoka2OpenAI(response *dto.EmbeddingResponse) *dto.OpenAIEmbeddingResponse {
+	openAIEmbeddingResponse := dto.OpenAIEmbeddingResponse{
+		Object: "list",
+		Data:   make([]dto.OpenAIEmbeddingResponseItem, 0, len(response.Data)),
+		Model:  "baidu-embedding",
+		Usage:  response.Usage,
+	}
+	for _, item := range response.Data {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, dto.OpenAIEmbeddingResponseItem{
+			Object:    item.Object,
+			Index:     item.Index,
+			Embedding: item.Embedding,
+		})
+	}
+	return &openAIEmbeddingResponse
+}
+
+func mokaEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var baiduResponse dto.EmbeddingResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &baiduResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	// if baiduResponse.ErrorMsg != "" {
+	// 	return &dto.OpenAIErrorWithStatusCode{
+	// 		Error: dto.OpenAIError{
+	// 			Type:    "baidu_error",
+	// 			Param:   "",
+	// 		},
+	// 		StatusCode: resp.StatusCode,
+	// 	}, nil
+	// }
+	fullTextResponse := embeddingResponseMoka2OpenAI(&baiduResponse)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}
+

relay/channel/ollama/adaptor.go

@@ -58,6 +58,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/openai/adaptor.go

@@ -149,6 +149,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	a.ResponseFormat = request.ResponseFormat
 	if info.RelayMode == constant.RelayModeAudioSpeech {

relay/channel/palm/adaptor.go

@@ -49,6 +49,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/perplexity/adaptor.go

@@ -52,6 +52,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/siliconflow/adaptor.go

@@ -58,6 +58,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeRerank:

relay/channel/tencent/adaptor.go

@@ -73,6 +73,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/vertex/adaptor.go

@@ -151,6 +151,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/xunfei/adaptor.go

@@ -50,6 +50,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	// xunfei's request is not http request, so we don't need to do anything here
 	dummyResp := &http.Response{}

relay/channel/zhipu/adaptor.go

@@ -56,6 +56,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/zhipu_4v/adaptor.go

@@ -53,6 +53,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/constant/api_type.go

@@ -27,7 +27,7 @@ const (
 	APITypeVertexAi
 	APITypeMistral
 	APITypeDeepSeek
-
+	APITypeMokaAI
 	APITypeDummy // this one is only for count, do not add any channel after this
 )
 
@@ -78,6 +78,8 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeMistral
 	case common.ChannelTypeDeepSeek:
 		apiType = APITypeDeepSeek
+	case common.ChannelTypeMokaAI:
+		apiType = APITypeMokaAI
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false

relay/relay_adaptor.go

@@ -14,6 +14,7 @@ import (
 	"one-api/relay/channel/gemini"
 	"one-api/relay/channel/jina"
 	"one-api/relay/channel/mistral"
+	"one-api/relay/channel/mokaai"
 	"one-api/relay/channel/ollama"
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
@@ -74,6 +75,8 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &mistral.Adaptor{}
 	case constant.APITypeDeepSeek:
 		return &deepseek.Adaptor{}
+	case constant.APITypeMokaAI:
+		return &mokaai.Adaptor{}
 	}
 	return nil
 }

relay/relay_embedding.go

@@ -0,0 +1,127 @@
+package relay
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
+	"one-api/setting"
+)
+
+func getEmbeddingPromptToken(embeddingRequest dto.EmbeddingRequest) int {
+	token, _ := service.CountTokenInput(embeddingRequest.Input, embeddingRequest.Model)
+	return token
+}
+
+func EmbeddingHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorWithStatusCode) {
+	relayInfo := relaycommon.GenRelayInfo(c)
+
+	var embeddingRequest *dto.EmbeddingRequest
+	err := common.UnmarshalBodyReusable(c, &embeddingRequest)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidateTextRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapperLocal(err, "invalid_text_request", http.StatusBadRequest)
+	}
+	if relayMode == relayconstant.RelayModeModerations && embeddingRequest.Model == "" {
+		embeddingRequest.Model = "m3e-base"
+	}
+	if relayMode == relayconstant.RelayModeEmbeddings && embeddingRequest.Model == "" {
+		embeddingRequest.Model = c.Param("model")
+	}
+	if embeddingRequest.Input == nil || len(embeddingRequest.Input) == 0 {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("input is empty"), "invalid_input", http.StatusBadRequest)
+	}
+	// map model name
+	modelMapping := c.GetString("model_mapping")
+	//isModelMapped := false
+	if modelMapping != "" && modelMapping != "{}" {
+		modelMap := make(map[string]string)
+		err := json.Unmarshal([]byte(modelMapping), &modelMap)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+		}
+		if modelMap[embeddingRequest.Model] != "" {
+			embeddingRequest.Model = modelMap[embeddingRequest.Model]
+			// set upstream model name
+			//isModelMapped = true
+		}
+	}
+
+	relayInfo.UpstreamModelName = embeddingRequest.Model
+	modelPrice, success := common.GetModelPrice(embeddingRequest.Model, false)
+	groupRatio := setting.GetGroupRatio(relayInfo.Group)
+
+	var preConsumedQuota int
+	var ratio float64
+	var modelRatio float64
+
+	promptToken := getEmbeddingPromptToken(*embeddingRequest)
+	if !success {
+		preConsumedTokens := promptToken
+		modelRatio = common.GetModelRatio(embeddingRequest.Model)
+		ratio = modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	relayInfo.PromptTokens = promptToken
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
+
+	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)
+
+	convertedRequest, err := adaptor.ConvertEmbeddingRequest(c,relayInfo,*embeddingRequest)
+	
+	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)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+	}
+
+	var httpResp *http.Response
+	if resp != nil {
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
+		}
+	}
+
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
+	if openaiErr != nil {
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
+	postConsumeQuota(c, relayInfo, embeddingRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
+	return nil
+}