feat(model/vl): support thingking mode

Author: kevinlin09

samples/MultiModalConversationQwenVL.java

@@ -10,9 +10,11 @@
 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 io.reactivex.Flowable;
 
 public class MultiModalConversationQwenVL {
-    private static final String modelName = "qwen-vl-max-latest";
+    private static final String modelName = System.getenv("MODEL_NAME");
     public static void videoImageListSample() throws ApiException, NoApiKeyException, UploadFileException {
         MultiModalConversation conv = new MultiModalConversation();
         MultiModalMessage systemMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
@@ -25,10 +27,18 @@ public static void videoImageListSample() throws ApiException, NoApiKeyException
         Collections.singletonMap("text", "描述这个视频的具体过程"))).build();
 
         MultiModalConversationParam param = MultiModalConversationParam.builder()
-                .model(MultiModalConversationQwenVL.modelName).message(systemMessage)
+                .model(MultiModalConversationQwenVL.modelName)
+                .enableThinking(true)
+                .thinkingBudget(20)
+                .message(systemMessage)
                 .message(userMessage).build();
-        MultiModalConversationResult result = conv.call(param);
-        System.out.print(result);
+//        MultiModalConversationResult result = conv.call(param);
+//        System.out.print(result);
+
+        Flowable<MultiModalConversationResult> results = conv.streamCall(param);
+        results.blockingForEach(result -> {
+            System.out.println(JsonUtils.toJson(result));
+        });
     }
 
     public static void main(String[] args) {

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

@@ -150,6 +150,12 @@ public class MultiModalConversationParam extends HalfDuplexServiceParam {
   /** language type for tts */
   private String languageType;
 
+  /** enable thinking */
+  private Boolean enableThinking;
+
+  /** thinking budget */
+  private Integer thinkingBudget;
+
   @Override
   public JsonObject getHttpBody() {
     JsonObject requestObject = new JsonObject();
@@ -283,6 +289,14 @@ public Map<String, Object> getParameters() {
       params.put("n", n);
     }
 
+    if (enableThinking != null) {
+      params.put("enable_thinking", enableThinking);
+    }
+
+    if (thinkingBudget != null) {
+      params.put("thinking_budget", thinkingBudget);
+    }
+
     params.putAll(parameters);
     return params;
   }

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

@@ -16,4 +16,7 @@ public class MultiModalConversationTokensDetails {
 
   @SerializedName("video_tokens")
   private Integer videoTokens;
+
+  @SerializedName("reasoning_tokens")
+  private Integer reasoningTokens;
 }

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

@@ -36,6 +36,7 @@ public class MultiModalMessage {
   String name;
 
   /** chain of thought content */
+  @SerializedName("reasoning_content")
   String reasoningContent;
 
   /** annotations result for message */