使用Vertex AI NodeJS SDK调用predict接口时遇无效参数错误求助

错误详情 #

⨯ Error: 3 INVALID_ARGUMENT: 0 is out of supported range [1, 1025);  for the maximum number of tokens.
    at callErrorFromStatus (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/call.js:31:19)
    at Object.onReceiveStatus (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/client.js:192:76)
    at Object.onReceiveStatus (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/client-interceptors.js:344:141)
    at Object.onReceiveStatus (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/client-interceptors.js:308:181)
    at eval (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/resolving-call.js:94:78)
    at process.processTicksAndRejections (node:internal/process/task_queues:77:11)
for call at
    at ServiceClientImpl.makeUnaryRequest (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/client.js:162:32)
    at ServiceClientImpl.eval (webpack-internal:///(rsc)/./node_modules/@grpc/grpc-js/build/src/make-client.js:103:19)
    at eval (webpack-internal:///(rsc)/./node_modules/@google-cloud/aiplatform/build/src/v1/prediction_service_client.js:241:33)
    at eval (webpack-internal:///(rsc)/./node_modules/google-gax/build/src/normalCalls/timeout.js:42:16)
    at OngoingCallPromise.call (webpack-internal:///(rsc)/./node_modules/google-gax/build/src/call.js:64:27)
    at NormalApiCaller.call (webpack-internal:///(rsc)/./node_modules/google-gax/build/src/normalCalls/normalApiCaller.js:34:19)
    at eval (webpack-internal:///(rsc)/./node_modules/google-gax/build/src/createApiCall.js:75:30)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5) {
  code: 3,
  details: '0 is out of supported range [1, 1025);  for the maximum number of tokens.',
  metadata: Metadata {
    internalRepr: Map(2) {
      'endpoint-load-metrics-bin' => [Array],
      'grpc-server-stats-bin' => [Array]
    },
    options: {}
  }

问题代码 #

const projectId = process.env.PROJECT_ID;
const zone = process.env.ZONE;

const aiplatform = require('@google-cloud/aiplatform');

const {PredictionServiceClient} = aiplatform.v1 
const {EndpointServiceClient} = aiplatform.v1 
const {helpers} = aiplatform;

const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};
const publisher = 'google';
const model = 'text-bison@001';

const predictionServiceClient = new PredictionServiceClient(clientOptions);

export async function callPredict() {
  // configure parent resource
    const endpoint = `projects/${projectId}/locations/${zone}/publishers/${publisher}/models/${model}`;
  const prompt = {
    prompt: 
    'Give me ten interview questions for a project manager, comapre with a program manager',
  };
   const instanceValue = helpers.toValue(prompt);
    

  const instances = [instanceValue];



  const request = {
    endpoint: endpoint,
    instances,
 
  };
  const test = await predictionServiceClient.apiEndpoint();
  const response = await predictionServiceClient.predict(request);
  console.log(response);
  console.log(test);
  return response;
}

解决方案 #

错误原因是调用text-bison@001模型时未指定maxOutputTokens参数，系统默认值为0，而该模型要求此参数值必须在[1, 1025)范围内。

修改代码，在请求中添加模型参数配置：

const projectId = process.env.PROJECT_ID;
const zone = process.env.ZONE;

const aiplatform = require('@google-cloud/aiplatform');

const {PredictionServiceClient} = aiplatform.v1 
const {EndpointServiceClient} = aiplatform.v1 
const {helpers} = aiplatform;

const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};
const publisher = 'google';
const model = 'text-bison@001';

const predictionServiceClient = new PredictionServiceClient(clientOptions);

export async function callPredict() {
  // configure parent resource
    const endpoint = `projects/${projectId}/locations/${zone}/publishers/${publisher}/models/${model}`;
  const prompt = {
    prompt: 
    'Give me ten interview questions for a project manager, compare with a program manager',
  };
   const instanceValue = helpers.toValue(prompt);
    
  const instances = [instanceValue];

  // 添加模型参数配置
  const parameters = helpers.toValue({
    maxOutputTokens: 256, // 设置在1-1024之间的数值，根据需求调整
    temperature: 0.7, // 可选，控制输出随机性
    topP: 0.9, // 可选，控制采样范围
  });

  const request = {
    endpoint: endpoint,
    instances,
    parameters, // 将参数加入请求
  };
  const test = await predictionServiceClient.apiEndpoint();
  const response = await predictionServiceClient.predict(request);
  console.log(response);
  console.log(test);
  return response;
}

关键修改点：

• 新增parameters对象，通过helpers.toValue转换为模型可识别的格式
• 必选设置maxOutputTokens，值需在1到1024之间
• 可按需添加其他可选参数（如temperature、topP）调整输出效果

内容的提问来源于stack exchange，提问作者Janac Meena