1.定制模型調(diào)用接口

1.1 輸入?yún)?shù)

1.2 輸出參數(shù)

示例

輸入：

{
    "ModelId": "532",
    "Content": "你好",
    "ModelVersion": "V1" //可以傳入模型的版本號，例如V1、V2等，不傳默認用最新版本
}
                        

輸出：

{"Data":["hello"],"RequestId":"fweo1j3931jd","Code":0}
                        

定制模型SDK調(diào)用示例

package com.alibaba.nlp.automl.modelcenter.service;
import com.aliyuncs.CommonRequest;
import com.aliyuncs.CommonResponse;
import com.aliyuncs.DefaultAcsClient;
import com.aliyuncs.IAcsClient;
import com.aliyuncs.http.MethodType;
import com.aliyuncs.profile.DefaultProfile;
public class PredictDemo {
    private void predictModel() {
        EnvironmentVariableCredentialsProvider credentialsProvider = CredentialsProviderFactory.newEnvironmentVariableCredentialsProvider();// 從環(huán)境變量讀取訪問憑證。
        String regionId = "cn-hangzhou";
        try {
            // 創(chuàng)建DefaultAcsClient實例并初始化
            DefaultProfile profile = DefaultProfile.getProfile("cn-hangzhou", credentialsProvider); 
            IAcsClient client = new DefaultAcsClient(profile);
            // 創(chuàng)建API請求并設(shè)置參數(shù)
            CommonRequest request = new CommonRequest();
            request.setDomain("automl.cn-hangzhou.aliyuncs.com");
            request.setVersion("2019-07-01");
            request.setAction("PredictMTModel");
            request.setMethod(MethodType.POST);
            request.putQueryParameter("ModelId", "647");
            request.putQueryParameter("ModelVersion", "V1");
            request.putBodyParameter("Content", "hello");
            CommonResponse response = client.getCommonResponse(request);
            System.out.println(response);
        } catch (Exception e) {
          e.printStackTrace();
        }
    }
}
                

2. 干預(yù)接口

• 請求URL：[http|https]://automl.cn-hangzhou.aliyuncs.com/api/automl/addMtIntervenePackage。

• 本接口（AddMtIntervenePackage）通過RPC方式，用于獲取機翻自學習模型產(chǎn)出的結(jié)果。

2.1 輸入?yún)?shù)

2.2 輸出參數(shù)

• 輸入：

{
        "PackageName": "test",
        "ProjectId": "1",
        "SourceLanguage": "zh",
        "TargetLanguage": "en",    
}
                        

• 輸出：

{
          "Code": "200",
          "RequestId": "aare83jnn9wj3",
          "Message": "",
          "PackageId": "1"
}
                        

3 干預(yù)詞新增接口

3.1 輸入?yún)?shù)

3.2 輸出參數(shù)

• 輸入：

{
        "PackageName": "test",
        "ProjectId": "1"
}
                        

• 輸出：

{
        "Code": "200",
        "RequestId": "aare83jnn9wj3",
        "Message": "",
        "PackageId": "1"
}
                        

4 干預(yù)詞包綁定模型接口

• 請求URL：[http|https]:[http|https]://automl.cn-hangzhou.aliyuncs.com/api/automl/bindIntervenePackageAndModel。

• 本接口（BindIntervenePackageAndModel）通過RPC方式，用于獲取機翻自學習模型產(chǎn)出的結(jié)果。

4.1 輸入?yún)?shù)

4.2 輸出參數(shù)

• 輸入：

{
        "PackageId": "1",
        "ProjectId": "1",
        "ModelId": "1",
        "ModelVersion": "V1"
}
                        

• 輸出：

{
        "Code": "200",
        "RequestId": "aare83jnn9wj3",
        "Message": "",
        "Success": "true"
}
                        

4. 錯誤碼