Document OCR (Optical Character Recognition)

Document AI allows you to identify and extract text from documents in over 200 languages for printed text and 50 languages for handwritten text.

Before you can send a processing request for a document, you must first create a Document OCR processor. The type of processor you create and use for your request affects the output you receive*.

*	This information applies to API version v1beta3 or higher.

Request document processing from a smaller file (<=5 pages for most processors) using the process method, and larger file requests (files with a large number of pages) use the batchProcess method. The status of batch (asynchronous) requests can be checked using the operations resource.

Processor details

File types supported	PDF, TIFF, GIF
Maximum number of pages (online/synchronous)	10
Maximum number of pages (offline/asynchronous/batch)	500
Maximum file size	20Mb

Small file online processing

Synchronous ("online") requests target a document with a small number of pages and size. Synchronous requests immediately return a response inline.

The following code samples show you how to send a process request to a Document OCR processor.

Note: Zero coordinate values omitted. When the API detects a coordinate ("x" or "y") value of 0, that coordinate is omitted in the JSON response. For example, a response with a bounding poly around the entire image would be "normalizedVertices": [{},{"x": 1},{"x": 1,"y": 1},{"y": 1}], or "vertices": [{},{"x": X_MAX},{"x": X_MAX,"y": Y_MAX},{"y": Y_MAX}]. For more information, see the API Reference documentation.

v1

Select the tab below for your language or environment:

REST & CMD LINE

This sample shows how to use the process method to request small document processing (<=5 pages). The example uses the access token for a service account set up for the project using the Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see Before you begin.

This synchronous requests shows you how to provide document content (raw document content in bytes via a base64 encoded string) in the rawDocument object. You can also provide the file content using the inlineDocument object.

Before using any of the request data below, make the following replacements:

• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• PROJECT_ID: Your GCP project ID.
• PROCESSOR_ID: the ID of your custom processor.
• BOOLEAN (skipHumanReview): A boolean to disable human review: true - skips human review, false - enables human review (default). The skipHumanReview field is supported by Procurement DocAI processors only.
• MIME_TYPE^†: One of the valid MIME type options. For example:
  • application/pdf
  • image/gif
  • image/tiff
• IMAGE_CONTENT^†: One of the valid Inline document content, represented as a stream of bytes. For JSON representations, the base64 encoding (ASCII string) of your binary image data. This string should look similar to the following string:
  • /9j/4QAYRXhpZgAA...9tAVx/zDQDlGxn//2Q==
  Visit Vision API's Base64 encode topic for more information.

† This content can also be specified using base64-encoded content using the inlineDocument object.

HTTP method and URL:

POST https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process

Request JSON body:

{
  "skipHumanReview": BOOLEAN,
  "inlineDocument": {
    "mimeType": "MIME_TYPE",
    "content": "IMAGE_CONTENT"
  }
}

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process" | Select-Object -Expand Content

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format. The response body contains an instance of Document.

Node.js

View on GitHub Feedback

/**
 * 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
const client = new DocumentProcessorServiceClient();

async function processDocument() {
  // 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}`);
  }

  // Form parsing provides additional output about
  // form-formatted PDFs. You  must create a form
  // processor in the Cloud Console to see full field details.
  console.log('\nThe following form key/value pairs were detected:');

  const {formFields} = page1;
  for (const field of formFields) {
    const fieldName = getText(field.fieldName.textAnchor);
    const fieldValue = getText(field.fieldValue.textAnchor);

    console.log('Extracted key value pair:');
    console.log(`\t(${fieldName}, ${fieldValue})`);
  }
}

Python

View on GitHub Feedback

# TODO(developer): Uncomment these variables before running the sample.
# project_id= 'YOUR_PROJECT_ID'
# location = 'YOUR_PROJECT_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID' # Create processor in Cloud Console
# file_path = '/path/to/local/pdf'


def process_document_sample(
    project_id: str, location: str, processor_id: str, file_path: str
):
    from google.cloud import documentai_v1 as documentai

    # You must set the api_endpoint if you use a location other than 'us', e.g.:
    opts = {}
    if location == "eu":
        opts = {"api_endpoint": "eu-documentai.googleapis.com"}

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # 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
    name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"

    with open(file_path, "rb") as image:
        image_content = image.read()

    # Read the file into memory
    document = {"content": image_content, "mime_type": "application/pdf"}

    # Configure the process request
    request = {"name": name, "raw_document": document}

    # Recognizes text entities in the PDF document
    result = client.process_document(request=request)

    document = result.document

    print("Document processing complete.")

    # For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document

    document_pages = document.pages

    # Read the text recognition output from the processor
    print("The document contains the following paragraphs:")
    for page in document_pages:
        paragraphs = page.paragraphs
        for paragraph in paragraphs:
            paragraph_text = get_text(paragraph.layout, document)
            print(f"Paragraph text: {paragraph_text}")


# Extract shards from the text field
def get_text(doc_element: dict, document: dict):
    """
    Document AI identifies form fields by their offsets
    in document text. This function converts offsets
    to text snippets.
    """
    response = ""
    # If a text segment spans several lines, it will
    # be stored in different text segments.
    for segment in doc_element.text_anchor.text_segments:
        start_index = (
            int(segment.start_index)
            if segment in doc_element.text_anchor.text_segments
            else 0
        )
        end_index = int(segment.end_index)
        response += document.text[start_index:end_index]
    return response

v1beta3

Select the tab below for your language or environment:

REST & CMD LINE

This sample shows how to use the process method to request small document processing (<=5 pages). The example uses the access token for a service account set up for the project using the Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see Before you begin.

Before using any of the request data below, make the following replacements:

• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• PROJECT_ID: Your GCP project ID.
• PROCESSOR_ID: the ID of your custom processor.
• MIME_TYPE: One of the valid MIME type options. For example:
  • application/pdf
  • image/gif
  • image/tiff
• IMAGE_CONTENT: One of the valid Inline document content, represented as a stream of bytes. For JSON representations, the base64 encoding (ASCII string) of your binary image data. This string should look similar to the following string:
  • /9j/4QAYRXhpZgAA...9tAVx/zDQDlGxn//2Q==
  Visit Vision API's Base64 encode topic for more information.

HTTP method and URL:

POST https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process

Request JSON body:

{
  "document": {
    "mimeType": "MIME_TYPE",
    "content": "IMAGE_CONTENT"
  }
}

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process" | Select-Object -Expand Content

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format. The response body contains an instance of Document.

Java

View on GitHub Feedback

import com.google.cloud.documentai.v1beta3.Document;
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1beta3.ProcessRequest;
import com.google.cloud.documentai.v1beta3.ProcessResponse;
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 ProcessDocumentBeta {
  public static void processDocument()
      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 processerId = "your-processor-id";
    String filePath = "path/to/input/file.pdf";
    processDocument(projectId, location, processerId, filePath);
  }

  public static void processDocument(
      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.
    try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create()) {
      // 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);

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

      // Configure the process request.
      ProcessRequest request =
          ProcessRequest.newBuilder().setName(name).setDocument(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);
      }

      // Form parsing provides additional output about
      // form-formatted PDFs. You  must create a form
      // processor in the Cloud Console to see full field details.
      System.out.println("The following form key/value pairs were detected:");

      for (Document.Page.FormField field : firstPage.getFormFieldsList()) {
        String fieldName = getText(field.getFieldName().getTextAnchor(), text);
        String fieldValue = getText(field.getFieldValue().getTextAnchor(), text);

        System.out.println("Extracted form fields pair:");
        System.out.printf("\t(%s, %s))\n", fieldName, fieldValue);
      }
    }
  }

  // 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]";
  }
}

Large file offline processing

Asynchronous ("offline") requests target longer documents. These types of requests start a long-running operations. When this operation finishes it stores output as a JSON file in a specified Cloud Storage bucket.

The following code samples show you how to send a batch process request to a Document OCR processor.

v1

Select the tab below for your language or environment:

REST & CMD LINE

This sample shows how to send a POST request to the batchProcess method for large document asynchronous processing. The example uses the access token for a service account set up for the project using the Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see Before you begin.

A batchProcess request starts a long-running operation and stores results in a Cloud Storage bucket. This sample also shows how to get the status of this long-running operation after it has started.

Send the process request

Before using any of the request data below, make the following replacements:

• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• PROJECT_ID: Your GCP project ID.
• PROCESSOR_ID: the ID of your custom processor.
• STORAGE_URI^†: The URI of the document you want to process stored in a Cloud Storage bucket, including the gs:// prefix. You must at least have read privileges to the file. Example:

  • gs://cloud-samples-data/documentai/loan_form.pdf

• MIME_TYPE: One of the valid MIME type options. For example:
  • application/pdf
  • image/gif
  • image/tiff
• OUTPUT_BUCKET: A Cloud Storage bucket/directory to save output files to, expressed in the following form:
  • gs://bucket/directory/
  The requesting user must have write permission to the bucket.
• BOOLEAN (skipHumanReview): A boolean to disable human review: true - skips human review, false - enables human review (default). The skipHumanReview field is supported by Procurement DocAI processors only.

† This is currently the only input option; gcsPrefix is unavailable.

HTTP method and URL:

POST https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess

Request JSON body:

{
  "inputDocuments": {
    "gcsDocuments": {
      "documents": [
        {
          "gcsUri": "STORAGE_URI",
          "mimeType": "MIME_TYPE"
        },
        {
          "gcsUri": "STORAGE_URI",
          "mimeType": "MIME_TYPE"
        }
      ]
    }
  },
  "documentOutputConfig": {
    "gcsOutputConfig": {
      "gcsUri": "OUTPUT_BUCKET"
    }
  },
  "skipHumanReview": BOOLEAN
}

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID"
}

If the request is successful, the Document AI returns the name for your operation.

Get the results

To get the results of your request, you must send a GET request to the operations resource. The following shows how to send such a request.

Before using any of the request data below, make the following replacements:

• PROJECT_ID: Your GCP project ID.
• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• OPERATION_ID: The ID of your operation. The ID is the last element of the name of your operation. For example:
  • operation name: projects/PROJECT_ID/locations/LOCATION/operations/bc4e1d412863e626
  • operation id: bc4e1d412863e626

HTTP method and URL:

GET https://documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Execute the following command:

curl -X GET \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
https://documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method GET `
  -Headers $headers `
  -Uri "https://documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID" | Select-Object -Expand Content

You should receive a successful status code (2xx) and an empty response.

The response body contains an instance of Document in its standard format with any information relevant to batch processing (shardInfo).

Node.js

View on GitHub Feedback

/**
 * 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';
// const gcsInputUri = 'YOUR_SOURCE_PDF';
// const gcsOutputUri = 'YOUR_STORAGE_BUCKET';
// const gcsOutputUriPrefix = 'YOUR_STORAGE_PREFIX';

// Imports the Google Cloud client library
const {
  DocumentProcessorServiceClient,
} = require('@google-cloud/documentai').v1;
const {Storage} = require('@google-cloud/storage');

// Instantiates Document AI, Storage clients
const client = new DocumentProcessorServiceClient();
const storage = new Storage();

const {default: PQueue} = require('p-queue');

async function batchProcessDocument() {
  const name = `projects/${projectId}/locations/${location}/processors/${processorId}`;

  // Configure the batch process request.
  const request = {
    name,
    inputDocuments: {
      gcsDocuments: {
        documents: [
          {
            gcsUri: gcsInputUri,
            mimeType: 'application/pdf',
          },
        ],
      },
    },
    documentOutputConfig: {
      gcsOutputConfig: {
        gcsUri: `${gcsOutputUri}/${gcsOutputUriPrefix}/`,
      },
    },
  };

  // Batch process document using a long-running operation.
  // You can wait for now, or get results later.
  // Note: first request to the service takes longer than subsequent
  // requests.
  const [operation] = await client.batchProcessDocuments(request);

  // Wait for operation to complete.
  await operation.promise();
  console.log('Document processing complete.');

  // Query Storage bucket for the results file(s).
  const query = {
    prefix: gcsOutputUriPrefix,
  };

  console.log('Fetching results ...');

  // List all of the files in the Storage bucket
  const [files] = await storage.bucket(gcsOutputUri).getFiles(query);

  // Add all asynchronous downloads to queue for execution.
  const queue = new PQueue({concurrency: 15});
  const tasks = files.map((fileInfo, index) => async () => {
    // Get the file as a buffer
    const [file] = await fileInfo.download();

    console.log(`Fetched file #${index + 1}:`);

    // The results stored in the output Storage location
    // are formatted as a document object.
    const document = JSON.parse(file.toString());
    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}`);
    }

    // Form parsing provides additional output about
    // form-formatted PDFs. You  must create a form
    // processor in the Cloud Console to see full field details.
    console.log('\nThe following form key/value pairs were detected:');

    const {formFields} = page1;
    for (const field of formFields) {
      const fieldName = getText(field.fieldName.textAnchor);
      const fieldValue = getText(field.fieldValue.textAnchor);

      console.log('Extracted key value pair:');
      console.log(`\t(${fieldName}, ${fieldValue})`);
    }
  });
  await queue.addAll(tasks);
}

Python

View on GitHub Feedback

import re

from google.cloud import documentai_v1 as documentai
from google.cloud import storage

# TODO(developer): Uncomment these variables before running the sample.
# project_id= 'YOUR_PROJECT_ID'
# location = 'YOUR_PROJECT_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID' # Create processor in Cloud Console
# gcs_input_uri = "YOUR_INPUT_URI"
# gcs_output_uri = "YOUR_OUTPUT_BUCKET_URI"
# gcs_output_uri_prefix = "YOUR_OUTPUT_URI_PREFIX"


def batch_process_documents(
    project_id,
    location,
    processor_id,
    gcs_input_uri,
    gcs_output_uri,
    gcs_output_uri_prefix,
    timeout: int = 300,
):

    # You must set the api_endpoint if you use a location other than 'us', e.g.:
    opts = {}
    if location == "eu":
        opts = {"api_endpoint": "eu-documentai.googleapis.com"}

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    destination_uri = f"{gcs_output_uri}/{gcs_output_uri_prefix}/"

    gcs_documents = documentai.GcsDocuments(
        documents=[{"gcs_uri": gcs_input_uri, "mime_type": "application/pdf"}]
    )

    # 'mime_type' can be 'application/pdf', 'image/tiff',
    # and 'image/gif', or 'application/json'
    input_config = documentai.BatchDocumentsInputConfig(gcs_documents=gcs_documents)

    # Where to write results
    output_config = documentai.DocumentOutputConfig(
        gcs_output_config={"gcs_uri": destination_uri}
    )

    # Location can be 'us' or 'eu'
    name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"
    request = documentai.types.document_processor_service.BatchProcessRequest(
        name=name,
        input_documents=input_config,
        document_output_config=output_config,
    )

    operation = client.batch_process_documents(request)

    # Wait for the operation to finish
    operation.result(timeout=timeout)

    # Results are written to GCS. Use a regex to find
    # output files
    match = re.match(r"gs://([^/]+)/(.+)", destination_uri)
    output_bucket = match.group(1)
    prefix = match.group(2)

    storage_client = storage.Client()
    bucket = storage_client.get_bucket(output_bucket)
    blob_list = list(bucket.list_blobs(prefix=prefix))
    print("Output files:")

    for i, blob in enumerate(blob_list):
        # If JSON file, download the contents of this blob as a bytes object.
        if ".json" in blob.name:
            blob_as_bytes = blob.download_as_bytes()

            document = documentai.types.Document.from_json(blob_as_bytes)
            print(f"Fetched file {i + 1}")

            # For a full list of Document object attributes, please reference this page:
            # https://cloud.google.com/document-ai/docs/reference/rpc/google.cloud.documentai.v1beta3#document

            # Read the text recognition output from the processor
            for page in document.pages:
                for form_field in page.form_fields:
                    field_name = get_text(form_field.field_name, document)
                    field_value = get_text(form_field.field_value, document)
                    print("Extracted key value pair:")
                    print(f"\t{field_name}, {field_value}")
                for paragraph in document.pages:
                    paragraph_text = get_text(paragraph.layout, document)
                    print(f"Paragraph text:\n{paragraph_text}")
        else:
            print(f"Skipping non-supported file type {blob.name}")


# Extract shards from the text field
def get_text(doc_element: dict, document: dict):
    """
    Document AI identifies form fields by their offsets
    in document text. This function converts offsets
    to text snippets.
    """
    response = ""
    # If a text segment spans several lines, it will
    # be stored in different text segments.
    for segment in doc_element.text_anchor.text_segments:
        start_index = (
            int(segment.start_index)
            if segment in doc_element.text_anchor.text_segments
            else 0
        )
        end_index = int(segment.end_index)
        response += document.text[start_index:end_index]
    return response

v1beta3

Select the tab below for your language or environment:

REST & CMD LINE

This sample shows how to send a POST request to the batchProcess method for large document asynchronous processing. The example uses the access token for a service account set up for the project using the Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see Before you begin.

A batchProcess request starts a long-running operation and stores results in a Cloud Storage bucket. This sample also shows how to get the status of this long-running operation after it has started.

Send the process request

Before using any of the request data below, make the following replacements:

• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• PROJECT_ID: Your GCP project ID.
• PROCESSOR_ID: the ID of your custom processor.
• STORAGE_URI^†: The URI of the document you want to process stored in a Cloud Storage bucket, including the gs:// prefix. You must at least have read privileges to the file. Example:

  • gs://cloud-samples-data/documentai/loan_form.pdf

• MIME_TYPE: One of the valid MIME type options. For example:
  • application/pdf
  • image/gif
  • image/tiff
• OUTPUT_BUCKET: A Cloud Storage bucket/directory to save output files to, expressed in the following form:
  • gs://bucket/directory/
  The requesting user must have write permission to the bucket.

HTTP method and URL:

POST https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess

Request JSON body:

{
  "inputConfigs": [
    {
      "gcsSource": "STORAGE_URI",
      "mimeType": "MIME_TYPE"
    }
  ],
  "outputConfig": {
    "gcsDestination": "OUTPUT_BUCKET"
  }
}

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Save the request body in a file called request.json, and execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:batchProcess" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID"
}

If the request is successful, the Document AI returns the name for your operation.

Get the results

To get the results of your request, you must send a GET request to the operations resource. The following shows how to send such a request.

Before using any of the request data below, make the following replacements:

• LOCATION: one of the following regional processing options:
  • us - United States
  • eu - European Union
• PROJECT_ID: Your GCP project ID.
• OPERATION_ID: The ID of your operation. The ID is the last element of the name of your operation. For example:
  • operation name: projects/PROJECT_ID/locations/LOCATION/operations/bc4e1d412863e626
  • operation id: bc4e1d412863e626

HTTP method and URL:

GET https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID

To send your request, choose one of these options:

curl

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Execute the following command:

curl -X GET \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID

PowerShell

Note: Ensure you have set the GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account private key file path.

Execute the following command:

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method GET `
  -Headers $headers `
  -Uri "https://LOCATION-documentai.googleapis.com/v1beta3/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/BUCKET_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.documentai.v1beta3.OperationMetadata",
    "state": "SUCCEEDED",
    "createTime": "2019-11-19T00:36:37.310474834Z",
    "updateTime": "2019-11-19T00:37:10.682615795Z"
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.documentai.v1beta3.BatchProcessDocumentsResponse",
    "responses": [
      {
        "inputConfig": {
          "gcsSource": {
            "uri": "gs://INPUT_FILE"
          },
          "mimeType": "application/pdf"
        },
        "outputConfig": {
          "gcsDestination": {
            "uri": "gs://OUTPUT_BUCKET/"
          }
        }
      }
    ]
  }
}

The response body contains an instance of Document in its standard format with any information relevant to batch processing (shardInfo).

Java

View on GitHub Feedback

import com.google.api.gax.longrunning.OperationFuture;
import com.google.api.gax.paging.Page;
import com.google.cloud.documentai.v1beta3.BatchProcessMetadata;
import com.google.cloud.documentai.v1beta3.BatchProcessRequest;
import com.google.cloud.documentai.v1beta3.BatchProcessResponse;
import com.google.cloud.documentai.v1beta3.Document;
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
import com.google.cloud.storage.Blob;
import com.google.cloud.storage.BlobId;
import com.google.cloud.storage.Bucket;
import com.google.cloud.storage.Storage;
import com.google.cloud.storage.StorageOptions;
import com.google.protobuf.util.JsonFormat;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class BatchProcessDocumentBeta {
  public static void batchProcessDocument()
      throws IOException, InterruptedException, TimeoutException, ExecutionException {
    // 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 processerId = "your-processor-id";
    String outputGcsBucketName = "your-gcs-bucket-name";
    String outputGcsPrefix = "PREFIX";
    String inputGcsUri = "gs://your-gcs-bucket/path/to/input/file.pdf";
    batchProcessDocument(
        projectId, location, processerId, inputGcsUri, outputGcsBucketName, outputGcsPrefix);
  }

  public static void batchProcessDocument(
      String projectId,
      String location,
      String processorId,
      String gcsInputUri,
      String gcsOutputBucketName,
      String gcsOutputUriPrefix)
      throws IOException, InterruptedException, TimeoutException, ExecutionException {
    // 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.
    try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create()) {
      // 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);

      BatchProcessRequest.BatchInputConfig batchInputConfig =
          BatchProcessRequest.BatchInputConfig.newBuilder()
              .setGcsSource(gcsInputUri)
              .setMimeType("application/pdf")
              .build();

      String fullGcsPath = String.format("gs://%s/%s/", gcsOutputBucketName, gcsOutputUriPrefix);
      BatchProcessRequest.BatchOutputConfig outputConfig =
          BatchProcessRequest.BatchOutputConfig.newBuilder().setGcsDestination(fullGcsPath).build();

      // Configure the batch process request.
      BatchProcessRequest request =
          BatchProcessRequest.newBuilder()
              .setName(name)
              .addInputConfigs(batchInputConfig)
              .setOutputConfig(outputConfig)
              .build();

      OperationFuture<BatchProcessResponse, BatchProcessMetadata> future =
          client.batchProcessDocumentsAsync(request);

      // Batch process document using a long-running operation.
      // You can wait for now, or get results later.
      // Note: first request to the service takes longer than subsequent
      // requests.
      System.out.println("Waiting for operation to complete...");
      future.get(180, TimeUnit.SECONDS);

      System.out.println("Document processing complete.");

      Storage storage = StorageOptions.newBuilder().setProjectId(projectId).build().getService();
      Bucket bucket = storage.get(gcsOutputBucketName);

      // List all of the files in the Storage bucket.
      Page<Blob> blobs = bucket.list(Storage.BlobListOption.prefix(gcsOutputUriPrefix + "/"));
      int idx = 0;
      for (Blob blob : blobs.iterateAll()) {
        if (!blob.isDirectory()) {
          System.out.printf("Fetched file #%d\n", ++idx);
          // Read the results

          // Download and store json data in a temp file.
          File tempFile = File.createTempFile("file", ".json");
          Blob fileInfo = storage.get(BlobId.of(gcsOutputBucketName, blob.getName()));
          fileInfo.downloadTo(tempFile.toPath());

          // Parse json file into Document.
          FileReader reader = new FileReader(tempFile);
          Document.Builder builder = Document.newBuilder();
          JsonFormat.parser().merge(reader, builder);

          Document document = builder.build();

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

          // Read the text recognition output from the processor
          System.out.println("The document contains the following paragraphs:");
          Document.Page page1 = document.getPages(0);
          List<Document.Page.Paragraph> paragraphList = page1.getParagraphsList();
          for (Document.Page.Paragraph paragraph : paragraphList) {
            String paragraphText = getText(paragraph.getLayout().getTextAnchor(), text);
            System.out.printf("Paragraph text:%s\n", paragraphText);
          }

          // Form parsing provides additional output about
          // form-formatted PDFs. You  must create a form
          // processor in the Cloud Console to see full field details.
          System.out.println("The following form key/value pairs were detected:");

          for (Document.Page.FormField field : page1.getFormFieldsList()) {
            String fieldName = getText(field.getFieldName().getTextAnchor(), text);
            String fieldValue = getText(field.getFieldValue().getTextAnchor(), text);

            System.out.println("Extracted form fields pair:");
            System.out.printf("\t(%s, %s))", fieldName, fieldValue);
          }

          // Clean up temp file.
          tempFile.deleteOnExit();
        }
      }
    }
  }

  // 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]";
  }
}