什么参数对于 Node.js 的 Google Document AI 客户端库无效？

Question

我正在尝试使用 Node.js 应用程序运行 Google 的文档 OCR。所以我使用了 Node JavaScript 的客户端库@google-cloud/documentai

我做了像文档示例中那样的一切

有我的代码

const projectId = '*******';
const location = 'eu'; // Format is 'us' or 'eu'
const processor = '******'; // Create processor in Cloud Console
const keyFilename = './secret/******.json';

const { DocumentProcessorServiceClient } = require('@google-cloud/documentai').v1beta3;

const client = new DocumentProcessorServiceClient({projectId, keyFilename});

async function start(encodedImage) {

  console.log("Google AI Started")
  const name = `projects/${projectId}/locations/${location}/processors/${processor}`;

  const request = {
    name,
    document: {
      content: encodedImage,
      mimeType: 'application/pdf',
    },
  }

  try {
    const [result] = await client.processDocument(request);

    const { document } = result;

    const { text } = document;

    const getText = textAnchor => {
      if (!textAnchor.textSegments || textAnchor.textSegments.length === 0) {
        return '';
      }

      // First shard in document doesn't have startIndex property
      const startIndex = textAnchor.textSegments[0].startIndex || 0;
      const endIndex = textAnchor.textSegments[0].endIndex;

      return text.substring(startIndex, endIndex);
    };

    const [page1] = document;
    const { paragraphs } = page1;

    for (const paragraph of paragraphs) {
      const paragraphText = getText(paragraph.layout.textAnchor);
      console.log(`Paragraph text:\n${paragraphText}`);
    }
    return paragraphs;
  }
  catch (error) {
    console.error(error);
  }
}

module.exports = {
  start
}

图像编码在这里

const {start: google} = require('./document-ai/index')

if (mimeType === 'application/pdf') {
        pdf = true;
        encoded = Buffer.from(file).toString('base64');
      }

await google(encoded);

结果我得到这个错误

const projectId = '*******';
const location = 'eu'; // Format is 'us' or 'eu'
const processor = '******'; // Create processor in Cloud Console
const keyFilename = './secret/******.json';

const { DocumentProcessorServiceClient } = require('@google-cloud/documentai').v1beta3;

const client = new DocumentProcessorServiceClient({projectId, keyFilename});

async function start(encodedImage) {

  console.log("Google AI Started")
  const name = `projects/${projectId}/locations/${location}/processors/${processor}`;

  const request = {
    name,
    document: {
      content: encodedImage,
      mimeType: 'application/pdf',
    },
  }

  try {
    const [result] = await client.processDocument(request);

    const { document } = result;

    const { text } = document;

    const getText = textAnchor => {
      if (!textAnchor.textSegments || textAnchor.textSegments.length === 0) {
        return '';
      }

      // First shard in document doesn't have startIndex property
      const startIndex = textAnchor.textSegments[0].startIndex || 0;
      const endIndex = textAnchor.textSegments[0].endIndex;

      return text.substring(startIndex, endIndex);
    };

    const [page1] = document;
    const { paragraphs } = page1;

    for (const paragraph of paragraphs) {
      const paragraphText = getText(paragraph.layout.textAnchor);
      console.log(`Paragraph text:\n${paragraphText}`);
    }
    return paragraphs;
  }
  catch (error) {
    console.error(error);
  }
}

module.exports = {
  start
}

我的请求中有哪些无效参数？

环境详情

• 操作系统：Windows 10
• Node.js 版本：12.18.3
• NPM版本：6.14.8
• @google-cloud/documentai版本：2.2.1

Answer 1

我也为此苦苦挣扎，结果证明解决方案非常简单：apiEndpoint当您的位置不是 时，您必须设置参数"us"。

这是位置的示例"eu"：

const client = new DocumentProcessorServiceClient({ 
  keyFilename, 
  apiEndpoint: 'eu-documentai.googleapis.com' 
});

更多信息请参见：GitHub：googleapis/nodejs-document-ai