クライアントライブラリを使用したドキュメント処理

このページでは、使い慣れたプログラミング言語で Document AI API を使用する方法を説明します。

始める前に

Google Cloud アカウントにログインします。 Google Cloudを初めて使用する場合は、アカウントを作成して、実際のシナリオでの Google プロダクトのパフォーマンスを評価してください。新規のお客様には、ワークロードの実行、テスト、デプロイができる無料クレジット $300 分を差し上げます。

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Document AI API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

Create a service account:

Ensure that you have the Create Service Accounts IAM role (roles/iam.serviceAccountCreator) and the Project IAM Admin role (roles/resourcemanager.projectIamAdmin). Learn how to grant roles.
In the Google Cloud console, go to the Create service account page.
Go to Create service account
Select your project.
In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

In the Service account description field, enter a description. For example, Service account for quickstart.
Click Create and continue.
Grant the Document AI > Document AI Administrator role to the service account.

To grant the role, find the Select a role list, then select Document AI > Document AI Administrator.

Note: The Role field affects which resources the service account can access in your project. You can revoke these roles or grant additional roles later.
Click Continue.
Click Done to finish creating the service account.

Do not close your browser window. You will use it in the next step.

Create a service account key:

In the Google Cloud console, click the email address for the service account that you created.
Click Keys.
Click Add key, and then click Create new key.
Click Create. A JSON key file is downloaded to your computer.
Click Close.

Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON file that contains your credentials. This variable applies only to your current shell session, so if you open a new session, set the variable again.

Example: Linux or macOS

export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

Example: Windows

For PowerShell:

$env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

$env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

For command prompt:

set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

Replace KEY_PATH with the path of the JSON file that contains your credentials.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Document AI API.

Roles required to enable APIs

To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

Enable the API

Create a service account:

Ensure that you have the Create Service Accounts IAM role (roles/iam.serviceAccountCreator) and the Project IAM Admin role (roles/resourcemanager.projectIamAdmin). Learn how to grant roles.
In the Google Cloud console, go to the Create service account page.
Go to Create service account
Select your project.
In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

In the Service account description field, enter a description. For example, Service account for quickstart.
Click Create and continue.
Grant the Document AI > Document AI Administrator role to the service account.

To grant the role, find the Select a role list, then select Document AI > Document AI Administrator.

Note: The Role field affects which resources the service account can access in your project. You can revoke these roles or grant additional roles later.
Click Continue.
Click Done to finish creating the service account.

Do not close your browser window. You will use it in the next step.

Create a service account key:

In the Google Cloud console, click the email address for the service account that you created.
Click Keys.
Click Add key, and then click Create new key.
Click Create. A JSON key file is downloaded to your computer.
Click Close.

Example: Linux or macOS

export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

Example: Windows

For PowerShell:

$env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

Replace KEY_PATH with the path of the JSON file that contains your credentials.

For example:

$env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

For command prompt:

set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

Replace KEY_PATH with the path of the JSON file that contains your credentials.

クライアントライブラリをインストールする

C#

C# 開発環境の設定の詳細については、C# 開発環境設定ガイドをご覧ください。

Install-Package Google.Cloud.DocumentAI.V1 -Pre

Go

go get cloud.google.com/go/documentai

Java

Java 開発環境の設定の詳細については、Java 開発環境設定ガイドをご覧ください。

Maven を使用している場合は、次のものを pom.xml ファイルに追加します。BOM の詳細については、Google Cloud Platform ライブラリ BOM をご覧ください。

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.79.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-document-ai</artifactId>
  </dependency>
</dependencies>

Gradle を使用している場合は、次のものを依存関係に追加します。

implementation 'com.google.cloud:google-cloud-document-ai:2.95.0'

sbt を使用している場合は、次のものを依存関係に追加します。

libraryDependencies += "com.google.cloud" % "google-cloud-document-ai" % "2.95.0"

Visual Studio Code または IntelliJ を使用している場合は、次の IDE プラグインでプロジェクトにクライアントライブラリを追加できます。

プラグインでは、サービスアカウントのキー管理などの追加機能も提供されます。詳細は各プラグインのドキュメントをご覧ください。

Node.js

Node.js 開発環境の設定の詳細については、Node.js 開発環境設定ガイドをご覧ください。

npm install @google-cloud/documentai

PHP

composer require google/cloud-document-ai

Python

Python 開発環境の設定の詳細については、Python 開発環境設定ガイドをご覧ください。

pip install --upgrade google-cloud-documentai

Ruby

Ruby 開発環境の設定の詳細については、Ruby 開発環境設定ガイドをご覧ください。

gem install google-cloud-document_ai

ドキュメント処理

Document AI API を使用して、ローカル PDF ドキュメントから情報をリクエストします。次のサンプルを実行するには、まず UI でプロセッサを作成する必要があります。

コンソール

Google Cloud コンソールの Document AI セクションで、[プロセッサ] ページに移動します。

[プロセッサ] ページに移動
[プロセッサを作成] を選択します。
作成するプロセッサタイプをリストからクリックします。
サイドの [プロセッサを作成] ウィンドウで、プロセッサ名を指定します。
リストからリージョンを選択します。
[作成] をクリックして、プロセッサを作成します。

プロセッサを作成してプロセッサ ID を取得したら、次のコードを実行して個々のドキュメント処理をリクエストします。

C#

詳細については、Document AI C# API リファレンスドキュメントをご覧ください。

Document AI に対する認証を行うには、アプリケーションのデフォルト認証情報を設定します。詳細については、ローカル開発環境の認証の設定をご覧ください。


using Google.Cloud.DocumentAI.V1;
using Google.Protobuf;
using System;
using System.IO;

public class QuickstartSample
{
    public Document Quickstart(
        string projectId = "your-project-id",
        string locationId = "your-processor-location",
        string processorId = "your-processor-id",
        string localPath = "my-local-path/my-file-name",
        string mimeType = "application/pdf"
    )
    {
        // Create client
        var client = new DocumentProcessorServiceClientBuilder
        {
            Endpoint = $"{locationId}-documentai.googleapis.com"
        }.Build();

        // Read in local file
        using var fileStream = File.OpenRead(localPath);
        var rawDocument = new RawDocument
        {
            Content = ByteString.FromStream(fileStream),
            MimeType = mimeType
        };

        // Initialize request argument(s)
        var request = new ProcessRequest
        {
            Name = ProcessorName.FromProjectLocationProcessor(projectId, locationId, processorId).ToString(),
            RawDocument = rawDocument
        };

        // Make the request
        var response = client.ProcessDocument(request);

        var document = response.Document;
        Console.WriteLine(document.Text);
        return document;
    }
}

C++

詳細については、Document AI C++ API リファレンスドキュメントをご覧ください。


#include "google/cloud/documentai/v1/document_processor_client.h"
#include "google/cloud/location.h"
#include <fstream>
#include <iostream>
#include <string>

int main(int argc, char* argv[]) try {
  if (argc != 5) {
    std::cerr << "Usage: " << argv[0]
              << " project-id location-id processor-id filename (PDF only)\n";
    return 1;
  }

  std::string const location_id = argv[2];
  if (location_id != "us" && location_id != "eu") {
    std::cerr << "location-id must be either 'us' or 'eu'\n";
    return 1;
  }
  auto const location = google::cloud::Location(argv[1], location_id);

  namespace documentai = ::google::cloud::documentai_v1;
  auto client = documentai::DocumentProcessorServiceClient(
      documentai::MakeDocumentProcessorServiceConnection(
          location.location_id()));

  google::cloud::documentai::v1::ProcessRequest req;
  req.set_name(location.FullName() + "/processors/" + argv[3]);
  req.set_skip_human_review(true);
  auto& doc = *req.mutable_raw_document();
  doc.set_mime_type("application/pdf");
  std::ifstream is(argv[4]);
  doc.set_content(std::string{std::istreambuf_iterator<char>(is), {}});

  auto resp = client.ProcessDocument(std::move(req));
  if (!resp) throw std::move(resp).status();
  std::cout << resp->document().text() << "\n";

  return 0;
} catch (google::cloud::Status const& status) {
  std::cerr << "google::cloud::Status thrown: " << status << "\n";
  return 1;
}

Go

詳細については、Document AI Go API リファレンスドキュメントをご覧ください。

import (
	"context"
	"flag"
	"fmt"
	"os"

	documentai "cloud.google.com/go/documentai/apiv1"
	"cloud.google.com/go/documentai/apiv1/documentaipb"
	"google.golang.org/api/option"
)

func main() {
	projectID := flag.String("project_id", "PROJECT_ID", "Cloud Project ID")
	location := flag.String("location", "us", "The Processor location")
	// Create a Processor before running sample
	processorID := flag.String("processor_id", "aaaaaaaa", "The Processor ID")
	filePath := flag.String("file_path", "invoice.pdf", "The path to the file to parse")
	mimeType := flag.String("mime_type", "application/pdf", "The mimeType of the file")
	flag.Parse()

	ctx := context.Background()

	endpoint := fmt.Sprintf("%s-documentai.googleapis.com:443", *location)
	client, err := documentai.NewDocumentProcessorClient(ctx, option.WithEndpoint(endpoint))
	if err != nil {
		fmt.Println(fmt.Errorf("error creating Document AI client: %w", err))
	}
	defer client.Close()

	// Open local file.
	data, err := os.ReadFile(*filePath)
	if err != nil {
		fmt.Println(fmt.Errorf("os.ReadFile: %w", err))
	}

	req := &documentaipb.ProcessRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/processors/%s", *projectID, *location, *processorID),
		Source: &documentaipb.ProcessRequest_RawDocument{
			RawDocument: &documentaipb.RawDocument{
				Content:  data,
				MimeType: *mimeType,
			},
		},
	}
	resp, err := client.ProcessDocument(ctx, req)
	if err != nil {
		fmt.Println(fmt.Errorf("processDocument: %w", err))
	}

	// Handle the results.
	document := resp.GetDocument()
	fmt.Printf("Document Text: %s", document.GetText())
}

Java

詳細については、Document AI Java API リファレンスドキュメントをご覧ください。

import com.google.cloud.documentai.v1.Document;
import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
import com.google.cloud.documentai.v1.ProcessRequest;
import com.google.cloud.documentai.v1.ProcessResponse;
import com.google.cloud.documentai.v1.RawDocument;
import com.google.protobuf.ByteString;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeoutException;

public class QuickStart {
  public static void main(String[] args)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String location = "your-project-location"; // Format is "us" or "eu".
    String processorId = "your-processor-id";
    String filePath = "path/to/input/file.pdf";
    quickStart(projectId, location, processorId, filePath);
  }

  public static void quickStart(
      String projectId, String location, String processorId, String filePath)
      throws IOException, InterruptedException, ExecutionException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs
    // to be created
    // once, and can be reused for multiple requests. After completing all of your
    // requests, call
    // the "close" method on the client to safely clean up any remaining background
    // resources.
    String endpoint = String.format("%s-documentai.googleapis.com:443", location);
    DocumentProcessorServiceSettings settings =
        DocumentProcessorServiceSettings.newBuilder().setEndpoint(endpoint).build();
    try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create(settings)) {
      // 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
      String name =
          String.format("projects/%s/locations/%s/processors/%s", projectId, location, processorId);

      // Read the file.
      byte[] imageFileData = Files.readAllBytes(Paths.get(filePath));

      // Convert the image data to a Buffer and base64 encode it.
      ByteString content = ByteString.copyFrom(imageFileData);

      RawDocument document =
          RawDocument.newBuilder().setContent(content).setMimeType("application/pdf").build();

      // Configure the process request.
      ProcessRequest request =
          ProcessRequest.newBuilder().setName(name).setRawDocument(document).build();

      // Recognizes text entities in the PDF document
      ProcessResponse result = client.processDocument(request);
      Document documentResponse = result.getDocument();

      // Get all of the document text as one big string
      String text = documentResponse.getText();

      // Read the text recognition output from the processor
      System.out.println("The document contains the following paragraphs:");
      Document.Page firstPage = documentResponse.getPages(0);
      List<Document.Page.Paragraph> paragraphs = firstPage.getParagraphsList();

      for (Document.Page.Paragraph paragraph : paragraphs) {
        String paragraphText = getText(paragraph.getLayout().getTextAnchor(), text);
        System.out.printf("Paragraph text:\n%s\n", paragraphText);
      }
    }
  }

  // Extract shards from the text field
  private static String getText(Document.TextAnchor textAnchor, String text) {
    if (textAnchor.getTextSegmentsList().size() > 0) {
      int startIdx = (int) textAnchor.getTextSegments(0).getStartIndex();
      int endIdx = (int) textAnchor.getTextSegments(0).getEndIndex();
      return text.substring(startIdx, endIdx);
    }
    return "[NO TEXT]";
  }
}

Node.js

詳細については、Document AI Node.js API リファレンスドキュメントをご覧ください。

/**
 * 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} =
  require('@google-cloud/documentai').v1;

// Instantiates a client
// apiEndpoint regions available: eu-documentai.googleapis.com, us-documentai.googleapis.com (Required if using eu based processor)
// const client = new DocumentProcessorServiceClient({apiEndpoint: 'eu-documentai.googleapis.com'});
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 = {
    name,
    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}`);
  }
}

PHP

詳細については、Document AI PHP API リファレンスドキュメントをご覧ください。

# Include the autoloader for libraries installed with Composer.
require __DIR__ . '/vendor/autoload.php';

# Import the Google Cloud client library.
use Google\Cloud\DocumentAI\V1\Client\DocumentProcessorServiceClient;
use Google\Cloud\DocumentAI\V1\RawDocument;
use Google\Cloud\DocumentAI\V1\ProcessRequest;

# TODO(developer): Update the following lines before running the sample.
# Your Google Cloud Platform project ID.
$projectId = 'YOUR_PROJECT_ID';

# Your Processor Location.
$location = 'us';

# Your Processor ID as hexadecimal characters.
# Not to be confused with the Processor Display Name.
$processorId = 'YOUR_PROCESSOR_ID';

# Path for the file to read.
$documentPath = 'resources/invoice.pdf';

# Create Client.
$client = new DocumentProcessorServiceClient();

# Read in file.
$handle = fopen($documentPath, 'rb');
$contents = fread($handle, filesize($documentPath));
fclose($handle);

# Load file contents into a RawDocument.
$rawDocument = (new RawDocument())
    ->setContent($contents)
    ->SetMimeType('application/pdf');

# Get the Fully-qualified Processor Name.
$fullProcessorName = $client->processorName($projectId, $location, $processorId);

# Send a ProcessRequest and get a ProcessResponse.
$request = (new ProcessRequest())
    ->setName($fullProcessorName)
    ->setRawDocument($rawDocument);

$response = $client->processDocument($request);

# Show the text found in the document.
printf('Document Text: %s', $response->getDocument()->getText());

Python

詳細については、Document AI Python API リファレンスドキュメントをご覧ください。

from google.api_core.client_options import ClientOptions
from google.cloud import documentai_v1

# TODO(developer): Create a processor of type "OCR_PROCESSOR".

# TODO(developer): Update and uncomment these variables before running the sample.
# project_id = "MY_PROJECT_ID"

# Processor ID as hexadecimal characters.
# Not to be confused with the Processor Display Name.
# processor_id = "MY_PROCESSOR_ID"

# Processor location. For example: "us" or "eu".
# location = "MY_PROCESSOR_LOCATION"

# Path for file to process.
# file_path = "/path/to/local/pdf"

# Set `api_endpoint` if you use a location other than "us".
opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

# Initialize Document AI client.
client = documentai_v1.DocumentProcessorServiceClient(client_options=opts)

# Get the Fully-qualified Processor path.
full_processor_name = client.processor_path(project_id, location, processor_id)

# Get a Processor reference.
request = documentai_v1.GetProcessorRequest(name=full_processor_name)
processor = client.get_processor(request=request)

# `processor.name` is the full resource name of the processor.
# For example: `projects/{project_id}/locations/{location}/processors/{processor_id}`
print(f"Processor Name: {processor.name}")

# Read the file into memory.
with open(file_path, "rb") as image:
    image_content = image.read()

# Load binary data.
# For supported MIME types, refer to https://cloud.google.com/document-ai/docs/file-types
raw_document = documentai_v1.RawDocument(
    content=image_content,
    mime_type="application/pdf",
)

# Send a request and get the processed document.
request = documentai_v1.ProcessRequest(name=processor.name, raw_document=raw_document)
result = client.process_document(request=request)
document = result.document

# Read the text recognition output from the processor.
# For a full list of `Document` object attributes, reference this page:
# https://cloud.google.com/document-ai/docs/reference/rest/v1/Document
print("The document contains the following text:")
print(document.text)

Ruby

詳細については、Document AI Ruby API リファレンスドキュメントをご覧ください。

require "google/cloud/document_ai/v1"

##
# Document AI quickstart
#
# @param project_id [String] Your Google Cloud project (e.g. "my-project")
# @param location_id [String] Your Processor Location (e.g. "us")
# @param processor_id [String] Your Processor ID (e.g. "a14dae8f043b60bd")
# @param file_path [String] Path to Local File (e.g. "invoice.pdf")
# @param mime_type [String] Refer to https://cloud.google.com/document-ai/docs/file-types (e.g. "application/pdf")
#
def quickstart project_id:, location_id:, processor_id:, file_path:, mime_type:
  # Create the Document AI client.
  client = ::Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client.new do |config|
    config.endpoint = "#{location_id}-documentai.googleapis.com"
  end

  # Build the resource name from the project.
  name = client.processor_path(
    project: project_id,
    location: location_id,
    processor: processor_id
  )

  # Read the bytes into memory
  content = File.binread file_path

  # Create request
  request = Google::Cloud::DocumentAI::V1::ProcessRequest.new(
    skip_human_review: true,
    name: name,
    raw_document: {
      content: content,
      mime_type: mime_type
    }
  )

  # Process document
  response = client.process_document request

  # Handle response
  puts response.document.text
end

これで完了です。Document AI への最初のリクエストを送信しました。

いかがでしたか

クリーンアップ

このクイックスタートで使用したリソースについて、Google アカウントに課金されないようにするには、次の手順を行います。

不要になったプロジェクトを Google Cloud console で削除します。

次のステップ

Document AI API クライアントライブラリの詳細を確認する。

プロセッサを作成して管理する

プロセスリクエストを送信する

クライアント ライブラリを使用したドキュメント処理

始める前に

クライアント ライブラリをインストールする

C#

Go

Java

Node.js

PHP

Python

Ruby

ドキュメント処理

コンソール

C#

C++

Go

Java

Node.js

PHP

Python

Ruby

いかがでしたか

クリーンアップ

次のステップ

クライアントライブラリを使用したドキュメント処理

クライアントライブラリをインストールする