refactor: audio relay

relay/channel/openai/adaptor.go

@@ -1,10 +1,13 @@
 package openai
 
 import (
+	"bytes"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
+	"mime/multipart"
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
@@ -14,21 +17,16 @@ import (
 	"one-api/relay/channel/minimax"
 	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
 	"strings"
 )
 
 type Adaptor struct {
-	ChannelType int
+	ChannelType    int
+	ResponseFormat string
 }
 
-func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
-	return nil, nil
-}
-
-func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
-}
-
-func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 	a.ChannelType = info.ChannelType
 }
 
@@ -83,15 +81,73 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	return request, nil
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	a.ResponseFormat = request.ResponseFormat
+	if info.RelayMode == constant.RelayModeAudioSpeech {
+		jsonData, err := json.Marshal(request)
+		if err != nil {
+			return nil, fmt.Errorf("error marshalling object: %w", err)
+		}
+		return bytes.NewReader(jsonData), nil
+	} else {
+		var requestBody bytes.Buffer
+		writer := multipart.NewWriter(&requestBody)
+
+		writer.WriteField("model", request.Model)
+
+		// 添加文件字段
+		file, header, err := c.Request.FormFile("file")
+		if err != nil {
+			return nil, errors.New("file is required")
+		}
+		defer file.Close()
+
+		part, err := writer.CreateFormFile("file", header.Filename)
+		if err != nil {
+			return nil, errors.New("create form file failed")
+		}
+		if _, err := io.Copy(part, file); err != nil {
+			return nil, errors.New("copy file failed")
+		}
+
+		// 关闭 multipart 编写器以设置分界线
+		writer.Close()
+		c.Request.Header.Set("Content-Type", writer.FormDataContentType())
+		return &requestBody, nil
+	}
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
-	return channel.DoApiRequest(a, c, info, requestBody)
+	if info.RelayMode == constant.RelayModeAudioTranscription || info.RelayMode == constant.RelayModeAudioTranslation {
+		return channel.DoFormRequest(a, c, info, requestBody)
+	} else {
+		return channel.DoApiRequest(a, c, info, requestBody)
+	}
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = OpenaiStreamHandler(c, resp, info)
-	} else {
-		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	switch info.RelayMode {
+	case constant.RelayModeAudioSpeech:
+		err, usage = OpenaiTTSHandler(c, resp, info)
+	case constant.RelayModeAudioTranslation:
+		fallthrough
+	case constant.RelayModeAudioTranscription:
+		err, usage = OpenaiSTTHandler(c, resp, info, a.ResponseFormat)
+	default:
+		if info.IsStream {
+			err, usage = OpenaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
 	}
 	return
 }