feat: support gpt-4o-audio-preview

common/model-ratio.go

@@ -337,15 +337,15 @@ func GetCompletionRatio(name string) float64 {
 		name = "gpt-4o-gizmo-*"
 	}
 	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
-		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
-			return 3
-		}
 		if strings.HasPrefix(name, "gpt-4o") {
 			if name == "gpt-4o-2024-05-13" {
 				return 3
 			}
 			return 4
 		}
+		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
+			return 3
+		}
 		return 2
 	}
 	if strings.HasPrefix(name, "o1-") {

dto/text_request.go → dto/openai_request.go

@@ -34,6 +34,8 @@ type GeneralOpenAIRequest struct {
 	LogProbs            bool           `json:"logprobs,omitempty"`
 	TopLogProbs         int            `json:"top_logprobs,omitempty"`
 	Dimensions          int            `json:"dimensions,omitempty"`
+	Modalities          any            `json:"modalities,omitempty"`
+	Audio               any            `json:"audio,omitempty"`
 }
 
 type OpenAITools struct {
@@ -83,9 +85,10 @@ type Message struct {
 }
 
 type MediaMessage struct {
-	Type     string `json:"type"`
-	Text     string `json:"text"`
-	ImageUrl any    `json:"image_url,omitempty"`
+	Type       string `json:"type"`
+	Text       string `json:"text"`
+	ImageUrl   any    `json:"image_url,omitempty"`
+	InputAudio any    `json:"input_audio,omitempty"`
 }
 
 type MessageImageUrl struct {
@@ -93,9 +96,15 @@ type MessageImageUrl struct {
 	Detail string `json:"detail"`
 }
 
+type MessageInputAudio struct {
+	Data   string `json:"data"` //base64
+	Format string `json:"format"`
+}
+
 const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeText       = "text"
+	ContentTypeImageURL   = "image_url"
+	ContentTypeInputAudio = "input_audio"
 )
 
 func (m Message) StringContent() string {
@@ -168,11 +177,19 @@ func (m Message) ParseContent() []MediaMessage {
 						},
 					})
 				}
-
+			case ContentTypeInputAudio:
+				if subObj, ok := contentMap["input_audio"].(map[string]any); ok {
+					contentList = append(contentList, MediaMessage{
+						Type: ContentTypeInputAudio,
+						InputAudio: MessageInputAudio{
+							Data:   subObj["data"].(string),
+							Format: subObj["format"].(string),
+						},
+					})
+				}
 			}
 		}
 		return contentList
 	}
-
 	return nil
 }

service/token_counter.go

@@ -223,7 +223,7 @@ func CountTokenMessages(messages []dto.Message, model string, stream bool) (int,
 			} else {
 				arrayContent := message.ParseContent()
 				for _, m := range arrayContent {
-					if m.Type == "image_url" {
+					if m.Type == dto.ContentTypeImageURL {
 						imageUrl := m.ImageUrl.(dto.MessageImageUrl)
 						imageTokenNum, err := getImageToken(&imageUrl, model, stream)
 						if err != nil {
@@ -231,6 +231,9 @@ func CountTokenMessages(messages []dto.Message, model string, stream bool) (int,
 						}
 						tokenNum += imageTokenNum
 						log.Printf("image token num: %d", imageTokenNum)
+					} else if m.Type == dto.ContentTypeInputAudio {
+						// TODO: 音频token数量计算
+						tokenNum += 100
 					} else {
 						tokenNum += getTokenNum(tokenEncoder, m.Text)
 					}