Wondering what’s next for npm?Check out our public roadmap! »

    TypeScript icon, indicating that this package has built-in type declarations

    2.10.0 • Public • Published

    Google Cloud Platform logo

    Document AI: Node.js Client

    release level npm version codecov

    Document AI client for Node.js

    A comprehensive list of changes in each version may be found in the CHANGELOG.

    Read more about the client libraries for Cloud APIs, including the older Google APIs Client Libraries, in Client Libraries Explained.

    Table of contents:


    Before you begin

    1. Select or create a Cloud Platform project.
    2. Enable billing for your project.
    3. Enable the Document AI API.
    4. Set up authentication with a service account so you can access the API from your local workstation.

    Installing the client library

    npm install @google-cloud/documentai

    Using the client library

     * TODO(developer): Uncomment these variables before running the sample.
    // const projectId = 'YOUR_PROJECT_ID';
    // const location = 'YOUR_PROJECT_LOCATION'; // Format is 'us' or 'eu'
    // const processorId = 'YOUR_PROCESSOR_ID'; // Create processor in Cloud Console
    // const filePath = '/path/to/local/pdf';
    const {DocumentProcessorServiceClient} =
    // Instantiates a client
    const client = new DocumentProcessorServiceClient();
    async function quickstart() {
      // The full resource name of the processor, e.g.:
      // projects/project-id/locations/location/processor/processor-id
      // You must create new processors in the Cloud Console first
      const name = `projects/${projectId}/locations/${location}/processors/${processorId}`;
      // Read the file into memory.
      const fs = require('fs').promises;
      const imageFile = await fs.readFile(filePath);
      // Convert the image data to a Buffer and base64 encode it.
      const encodedImage = Buffer.from(imageFile).toString('base64');
      const request = {
        rawDocument: {
          content: encodedImage,
          mimeType: 'application/pdf',
      // Recognizes text entities in the PDF document
      const [result] = await client.processDocument(request);
      const {document} = result;
      // Get all of the document text as one big string
      const {text} = document;
      // Extract shards from the text field
      const getText = textAnchor => {
        if (!textAnchor.textSegments || textAnchor.textSegments.length === 0) {
          return '';
        // First shard in document doesn't have startIndex property
        const startIndex = textAnchor.textSegments[0].startIndex || 0;
        const endIndex = textAnchor.textSegments[0].endIndex;
        return text.substring(startIndex, endIndex);
      // Read the text recognition output from the processor
      console.log('The document contains the following paragraphs:');
      const [page1] = document.pages;
      const {paragraphs} = page1;
      for (const paragraph of paragraphs) {
        const paragraphText = getText(paragraph.layout.textAnchor);
        console.log(`Paragraph text:\n${paragraphText}`);


    Samples are in the samples/ directory. Each sample's README.md has instructions for running its sample.

    Sample Source Code Try it
    Batch-parse-form.v1beta2 source code Open in Cloud Shell
    Batch-parse-table.v1beta2 source code Open in Cloud Shell
    Batch-process-document source code Open in Cloud Shell
    Parse-form.v1beta2 source code Open in Cloud Shell
    Parse-table.v1beta2 source code Open in Cloud Shell
    Parse-with-model.v1beta2 source code Open in Cloud Shell
    Process-document source code Open in Cloud Shell
    Quickstart source code Open in Cloud Shell
    Set-endpoint.v1beta2 source code Open in Cloud Shell

    The Document AI Node.js Client API Reference documentation also contains samples.

    Supported Node.js Versions

    Our client libraries follow the Node.js release schedule. Libraries are compatible with all current active and maintenance versions of Node.js.

    Client libraries targeting some end-of-life versions of Node.js are available, and can be installed via npm dist-tags. The dist-tags follow the naming convention legacy-(version).

    Legacy Node.js versions are supported as a best effort:

    • Legacy versions will not be tested in continuous integration.
    • Some security patches may not be able to be backported.
    • Dependencies will not be kept up-to-date, and features will not be backported.

    Legacy tags available

    • legacy-8: install client libraries from this dist-tag for versions compatible with Node.js 8.


    This library follows Semantic Versioning.

    This library is considered to be in beta. This means it is expected to be mostly stable while we work toward a general availability release; however, complete stability is not guaranteed. We will address issues and requests against beta libraries with a high priority.

    More Information: Google Cloud Platform Launch Stages


    Contributions welcome! See the Contributing Guide.

    Please note that this README.md, the samples/README.md, and a variety of configuration files in this repository (including .nycrc and tsconfig.json) are generated from a central template. To edit one of these files, make an edit to its template in this directory.


    Apache Version 2.0





    npm i @google-cloud/documentai

    DownloadsWeekly Downloads






    Unpacked Size

    6.56 MB

    Total Files


    Last publish


    • avatar
    • avatar
    • avatar
    • avatar