feat: support gpt-4 with vision (#683, #714)

Author: songquanpeng

controller/relay-aiproxy.go

@@ -48,7 +48,7 @@ type AIProxyLibraryStreamResponse struct {
 func requestOpenAI2AIProxyLibrary(request GeneralOpenAIRequest) *AIProxyLibraryRequest {
 	query := ""
 	if len(request.Messages) != 0 {
-		query = request.Messages[len(request.Messages)-1].Content
+		query = request.Messages[len(request.Messages)-1].StringContent()
 	}
 	return &AIProxyLibraryRequest{
 		Model:  request.Model,

controller/relay-ali.go

@@ -88,18 +88,18 @@ func requestOpenAI2Ali(request GeneralOpenAIRequest) *AliChatRequest {
 		message := request.Messages[i]
 		if message.Role == "system" {
 			messages = append(messages, AliMessage{
-				User: message.Content,
+				User: message.StringContent(),
 				Bot:  "Okay",
 			})
 			continue
 		} else {
 			if i == len(request.Messages)-1 {
-				prompt = message.Content
+				prompt = message.StringContent()
 				break
 			}
 			messages = append(messages, AliMessage{
-				User: message.Content,
-				Bot:  request.Messages[i+1].Content,
+				User: message.StringContent(),
+				Bot:  request.Messages[i+1].StringContent(),
 			})
 			i++
 		}

controller/relay-baidu.go

@@ -89,7 +89,7 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 		if message.Role == "system" {
 			messages = append(messages, BaiduMessage{
 				Role:    "user",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, BaiduMessage{
 				Role:    "assistant",
@@ -98,7 +98,7 @@ func requestOpenAI2Baidu(request GeneralOpenAIRequest) *BaiduChatRequest {
 		} else {
 			messages = append(messages, BaiduMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}

controller/relay-openai.go

@@ -132,7 +132,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 	if textResponse.Usage.TotalTokens == 0 {
 		completionTokens := 0
 		for _, choice := range textResponse.Choices {
-			completionTokens += countTokenText(choice.Message.Content, model)
+			completionTokens += countTokenText(choice.Message.StringContent(), model)
 		}
 		textResponse.Usage = Usage{
 			PromptTokens:     promptTokens,

controller/relay-palm.go

@@ -59,7 +59,7 @@ func requestOpenAI2PaLM(textRequest GeneralOpenAIRequest) *PaLMChatRequest {
 	}
 	for _, message := range textRequest.Messages {
 		palmMessage := PaLMChatMessage{
-			Content: message.Content,
+			Content: message.StringContent(),
 		}
 		if message.Role == "user" {
 			palmMessage.Author = "0"

controller/relay-tencent.go

@@ -84,7 +84,7 @@ func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
 		if message.Role == "system" {
 			messages = append(messages, TencentMessage{
 				Role:    "user",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, TencentMessage{
 				Role:    "assistant",
@@ -93,7 +93,7 @@ func requestOpenAI2Tencent(request GeneralOpenAIRequest) *TencentChatRequest {
 			continue
 		}
 		messages = append(messages, TencentMessage{
-			Content: message.Content,
+			Content: message.StringContent(),
 			Role:    message.Role,
 		})
 	}

controller/relay-utils.go

@@ -87,7 +87,7 @@ func countTokenMessages(messages []Message, model string) int {
 	tokenNum := 0
 	for _, message := range messages {
 		tokenNum += tokensPerMessage
-		tokenNum += getTokenNum(tokenEncoder, message.Content)
+		tokenNum += getTokenNum(tokenEncoder, message.StringContent())
 		tokenNum += getTokenNum(tokenEncoder, message.Role)
 		if message.Name != nil {
 			tokenNum += tokensPerName

controller/relay-xunfei.go

@@ -81,7 +81,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 		if message.Role == "system" {
 			messages = append(messages, XunfeiMessage{
 				Role:    "user",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, XunfeiMessage{
 				Role:    "assistant",
@@ -90,7 +90,7 @@ func requestOpenAI2Xunfei(request GeneralOpenAIRequest, xunfeiAppId string, doma
 		} else {
 			messages = append(messages, XunfeiMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}

controller/relay-zhipu.go

@@ -114,7 +114,7 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 		if message.Role == "system" {
 			messages = append(messages, ZhipuMessage{
 				Role:    "system",
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 			messages = append(messages, ZhipuMessage{
 				Role:    "user",
@@ -123,7 +123,7 @@ func requestOpenAI2Zhipu(request GeneralOpenAIRequest) *ZhipuRequest {
 		} else {
 			messages = append(messages, ZhipuMessage{
 				Role:    message.Role,
-				Content: message.Content,
+				Content: message.StringContent(),
 			})
 		}
 	}

controller/relay.go

@@ -12,10 +12,49 @@ import (
 
 type Message struct {
 	Role    string  `json:"role"`
-	Content string  `json:"content"`
+	Content any     `json:"content"`
 	Name    *string `json:"name,omitempty"`
 }
 
+type ImageURL struct {
+	Url    string `json:"url,omitempty"`
+	Detail string `json:"detail,omitempty"`
+}
+
+type TextContent struct {
+	Type string `json:"type,omitempty"`
+	Text string `json:"text,omitempty"`
+}
+
+type ImageContent struct {
+	Type     string    `json:"type,omitempty"`
+	ImageURL *ImageURL `json:"image_url,omitempty"`
+}
+
+func (m Message) StringContent() string {
+	content, ok := m.Content.(string)
+	if ok {
+		return content
+	}
+	contentList, ok := m.Content.([]any)
+	if ok {
+		var contentStr string
+		for _, contentItem := range contentList {
+			contentMap, ok := contentItem.(map[string]any)
+			if !ok {
+				continue
+			}
+			if contentMap["type"] == "text" {
+				if subStr, ok := contentMap["text"].(string); ok {
+					contentStr += subStr
+				}
+			}
+		}
+		return contentStr
+	}
+	return ""
+}
+
 const (
 	RelayModeUnknown = iota
 	RelayModeChatCompletions