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

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