如何通过Java代码为VertexAI设置GoogleCredentials

我通过CLI执行gcloud auth login使用默认认证时，代码可以正常运行，但现在希望为VertexAI配置自定义的GoogleCredentials令牌（比如通过GoogleCredentials credentials = GoogleCredentials.create(token);创建的令牌）。我注意到VertexAI类只有getCredentials方法，没有setter，但VertexAI.Builder类提供了setCredentials方法，却不清楚具体用法。现有使用默认认证的代码如下，请帮忙修改为通过自定义GoogleCredentials执行的版本：

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.ResponseHandler;

public class QuestionAnswer {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    String output = simpleQuestion(projectId, location, modelName);
    System.out.println(output);
  }

  // Asks a question to the specified Vertex AI Gemini model and returns the generated answer.
  public static String simpleQuestion(String projectId, String location, String modelName)
      throws Exception {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String output;
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      // Send the question to the model for processing.
      GenerateContentResponse response = model.generateContent("Why is the sky blue?");
      // Extract the generated text from the model's response.
      output = ResponseHandler.getText(response);
      return output;
    }
  }
}

解决方案 #

要使用自定义GoogleCredentials，你需要通过VertexAI.Builder构建VertexAI实例，而非直接调用构造方法。核心步骤是先创建好自定义的GoogleCredentials对象，再通过Builder的setCredentials方法传入，同时指定项目ID和区域，最后调用build()生成实例。

修改后的完整代码如下：

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import com.google.auth.oauth2.GoogleCredentials;

public class QuestionAnswer {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";
    // 替换为你的令牌创建逻辑，比如从文件、环境变量获取令牌
    String token = "your-custom-auth-token";
    GoogleCredentials credentials = GoogleCredentials.create(token);

    String output = simpleQuestion(projectId, location, modelName, credentials);
    System.out.println(output);
  }

  public static String simpleQuestion(String projectId, String location, String modelName, GoogleCredentials credentials)
      throws Exception {
    // 使用Builder构建VertexAI实例并传入自定义credentials
    try (VertexAI vertexAI = new VertexAI.Builder()
            .setProjectId(projectId)
            .setLocation(location)
            .setCredentials(credentials)
            .build()) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent("Why is the sky blue?");
      return ResponseHandler.getText(response);
    }
  }
}

关键修改说明

• 新增GoogleCredentials参数传入业务方法，也可在方法内部直接创建该对象（根据你的令牌获取逻辑调整）
• 用VertexAI.Builder替代原有的直接构造，依次配置项目ID、区域、自定义凭证后构建实例
• 保留try-with-resources语法，确保VertexAI客户端资源能自动释放

内容的提问来源于stack exchange，提问作者Sarada Chelluboyena