feat(model/ocr): support new task type

Author: kevinlin09

samples/MultiModalConversationQwenVLOcr.java

@@ -9,6 +9,7 @@
 import com.alibaba.dashscope.exception.ApiException;
 import com.alibaba.dashscope.exception.NoApiKeyException;
 import com.alibaba.dashscope.exception.UploadFileException;
+import com.alibaba.dashscope.utils.JsonUtils;
 import com.google.gson.JsonObject;
 import io.reactivex.Flowable;
 
@@ -18,7 +19,7 @@
 import java.util.Map;
 
 public class MultiModalConversationQwenVLOcr {
-    private static final String modelName = "qwen-vl-ocr-2025-02-18";
+    private static final String modelName = "qwen-vl-ocr-2025-08-28";
     public static void videoImageListSample() throws ApiException, NoApiKeyException, UploadFileException {
         MultiModalConversation conv = new MultiModalConversation();
         MultiModalMessage systemMessage = MultiModalMessage.builder()
@@ -28,20 +29,20 @@ public static void videoImageListSample() throws ApiException, NoApiKeyException
 
         Map<String, Object> imageContent = new HashMap<>();
         imageContent.put("type", "image");
-        imageContent.put("image", "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/public_data/POIE/test_subset/nf0986.jpg");
-        imageContent.put("min_pixels", "3136");
-        imageContent.put("max_pixels", "2007040");
+        imageContent.put("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg");
+        imageContent.put("min_pixels", "401408");
+        imageContent.put("max_pixels", "6422528");
         imageContent.put("enable_rotate", false);
 
         Map<String, Object> textContent = new HashMap<>();
         textContent.put("type", "text");
-        textContent.put("text", "提取图像中的文字。");
+        textContent.put("text", "定位所有的文字行，并且返回旋转矩形([cx, cy, width, height, angle])的坐标结果。");
 
         JsonObject resultSchema = new JsonObject();
         resultSchema.addProperty("Calories", "");
 
         OcrOptions ocrOptions = OcrOptions.builder()
-                .task(OcrOptions.Task.KEY_INFORMATION_EXTRACTION)
+                .task(OcrOptions.Task.ADVANCED_RECOGNITION)
                 .taskConfig(OcrOptions.TaskConfig.builder()
                         .resultSchema(resultSchema)
                         .build())
@@ -65,6 +66,7 @@ public static void videoImageListSample() throws ApiException, NoApiKeyException
 
         MultiModalConversationResult result = conv.call(param);
         System.out.println(result);
+        System.out.println(JsonUtils.toJson(result));
 //        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
 //        result.blockingForEach(System.out::println);
     }

src/main/java/com/alibaba/dashscope/aigc/multimodalconversation/OcrOptions.java

@@ -34,7 +34,10 @@ public enum Task {
     FORMULA_RECOGNITION,
 
     @SerializedName("multi_lan")
-    MULTI_LAN
+    MULTI_LAN,
+
+    @SerializedName("advanced_recognition")
+    ADVANCED_RECOGNITION
   }
 
   @Data

src/main/java/com/alibaba/dashscope/common/MultiModalMessageAdapter.java

@@ -37,8 +37,12 @@ private void writeValue(JsonWriter out, Object value) throws IOException {
       out.value((String) value);
     } else if (value instanceof Integer) {
       out.value((Integer) value);
+    } else if (value instanceof Long) {
+      out.value((Long) value);
     } else if (value instanceof Double) {
       out.value((Double) value);
+    } else if (value instanceof Float) {
+      out.value((Float) value);
     } else if (value instanceof Boolean) {
       out.value((Boolean) value);
     } else if (value instanceof Character) {