创建和管理处理器

您必须先创建自己的处理器实例,然后才能发送文档进行处理。本页面详细介绍了如何创建和管理处理器。

可用的处理器

如需使用 API 创建处理器实例,您需要知道每种处理器类型的名称。请动态获取此列表(使用以下代码),因为您的访问权限可能会发生变化。

公开提供的处理器类型包括:

数字化处理器

  • OCR_PROCESSOR
  • FORM_PARSER_PROCESSOR
  • LAYOUT_PARSER_PROCESSOR

预训练处理器

  • BANK_STATEMENT_PROCESSOR
  • EXPENSE_PROCESSOR
  • FORM_W2_PROCESSOR
  • ID_PROOFING_PROCESSOR
  • INVOICE_PROCESSOR
  • PAYSTUB_PROCESSOR
  • US_DRIVER_LICENSE_PROCESSOR
  • US_PASSPORT_PROCESSOR
  • UTILITY_PROCESSOR

提取 / 分类 / 拆分处理器

  • CUSTOM_EXTRACTION_PROCESSOR
  • CUSTOM_CLASSIFICATION_PROCESSOR
  • CUSTOM_SPLITTING_PROCESSOR
  • SUMMARIZER_PROCESSOR

列出处理器类型

网页界面

  1. 在 Google Cloud 控制台的 Document AI 部分,前往处理器库页面。

    前往处理器库

  2. 查看或搜索处理器类型列表。

REST

此示例展示了如何使用 fetchProcessorTypes 方法列出项目的可用处理器类型。

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:处理器的位置,例如:
    • us - 美国
    • eu - 欧盟
  • PROJECT_ID:您的 Google Cloud 项目 ID。

HTTP 方法和网址:

GET https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION:fetchProcessorTypes

如需发送请求,请选择以下方式之一:

curl

执行以下命令:

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

PowerShell

执行以下命令:

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

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

响应是一个 ProcessorType 列表,其中显示了可用的处理器类型,以及类别和可用位置。

{
  "processorTypes": [
  [
    ...
    {
      "name": "projects/PROJECT_ID/locations/LOCATION/processorTypes/FORM_PARSER_PROCESSOR",
      "type": "FORM_PARSER_PROCESSOR",
      "category": "GENERAL",
      "availableLocations": [
        {
          "locationId": "eu"
        },
        {
          "locationId": "us"
        }
      ],
      "allowCreation": true,
      "launchStage": "GA"
    },
    {
      "name": "projects/PROJECT_ID/locations/LOCATION/processorTypes/OCR_PROCESSOR",
      "type": "OCR_PROCESSOR",
      "category": "GENERAL",
      "availableLocations": [
        {
          "locationId": "eu"
        },
        {
          "locationId": "us"
        }
      ],
      "allowCreation": true,
      "launchStage": "GA"
    },
    {
      "name": "projects/PROJECT_ID/locations/LOCATION/processorTypes/INVOICE_PROCESSOR",
      "type": "INVOICE_PROCESSOR",
      "category": "SPECIALIZED",
      "availableLocations": [
        {
          "locationId": "eu"
        },
        {
          "locationId": "us"
        }
      ],
      "allowCreation": true,
      "launchStage": "GA"
    },
    {
      "name": "projects/PROJECT_ID/locations/LOCATION/processorTypes/US_DRIVER_LICENSE_PROCESSOR",
      "type": "US_DRIVER_LICENSE_PROCESSOR",
      "category": "SPECIALIZED",
      "availableLocations": [
        {
          "locationId": "us"
        },
        {
          "locationId": "eu"
        }
      ],
      "allowCreation": true,
      "launchStage": "GA"
    },
    ...
  ]
}

Python

如需了解详情,请参阅 Document AI Python API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


from google.api_core.client_options import ClientOptions
from google.cloud import documentai  # type: ignore

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'


def fetch_processor_types_sample(project_id: str, location: str) -> None:
    # You must set the api_endpoint if you use a location other than 'us'.
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the location
    # e.g.: projects/project_id/locations/location
    parent = client.common_location_path(project_id, location)

    # Fetch all processor types
    response = client.fetch_processor_types(parent=parent)

    print("Processor types:")
    # Print the available processor types
    for processor_type in response.processor_types:
        if processor_type.allow_creation:
            print(processor_type.type_)

Go

如需了解详情,请参阅 Document AI Go API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


//go:build examples

package main

import (
	"context"

	documentai "cloud.google.com/go/documentai/apiv1"
	documentaipb "cloud.google.com/go/documentai/apiv1/documentaipb"
)

func main() {
	ctx := context.Background()
	// This snippet has been automatically generated and should be regarded as a code template only.
	// It will require modifications to work:
	// - It may require correct/in-range values for request initialization.
	// - It may require specifying regional endpoints when creating the service client as shown in:
	//   https://pkg.go.dev/cloud.google.com/go#hdr-Client_Options
	c, err := documentai.NewDocumentProcessorClient(ctx)
	if err != nil {
		// TODO: Handle error.
	}
	defer c.Close()

	req := &documentaipb.FetchProcessorTypesRequest{
		// TODO: Fill request struct fields.
		// See https://pkg.go.dev/cloud.google.com/go/documentai/apiv1/documentaipb#FetchProcessorTypesRequest.
	}
	resp, err := c.FetchProcessorTypes(ctx, req)
	if err != nil {
		// TODO: Handle error.
	}
	// TODO: Use resp.
	_ = resp
}

Java

如需了解详情,请参阅 Document AI Java API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1.FetchProcessorTypesRequest;
import com.google.cloud.documentai.v1.FetchProcessorTypesResponse;
import com.google.cloud.documentai.v1.LocationName;

public class SyncFetchProcessorTypes {

  public static void main(String[] args) throws Exception {
    syncFetchProcessorTypes();
  }

  public static void syncFetchProcessorTypes() throws Exception {
    // This snippet has been automatically generated and should be regarded as a code template only.
    // It will require modifications to work:
    // - It may require correct/in-range values for request initialization.
    // - It may require specifying regional endpoints when creating the service client as shown in
    // https://cloud.google.com/java/docs/setup#configure_endpoints_for_the_client_library
    try (DocumentProcessorServiceClient documentProcessorServiceClient =
        DocumentProcessorServiceClient.create()) {
      FetchProcessorTypesRequest request =
          FetchProcessorTypesRequest.newBuilder()
              .setParent(LocationName.of("[PROJECT]", "[LOCATION]").toString())
              .build();
      FetchProcessorTypesResponse response =
          documentProcessorServiceClient.fetchProcessorTypes(request);
    }
  }
}

Ruby

如需了解详情,请参阅 Document AI Ruby API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

require "google/cloud/document_ai/v1"

##
# Snippet for the fetch_processor_types call in the DocumentProcessorService service
#
# This snippet has been automatically generated and should be regarded as a code
# template only. It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in https://cloud.google.com/ruby/docs/reference.
#
# This is an auto-generated example demonstrating basic usage of
# Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client#fetch_processor_types.
#
def fetch_processor_types
  # Create a client object. The client can be reused for multiple calls.
  client = Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client.new

  # Create a request. To set request fields, pass in keyword arguments.
  request = Google::Cloud::DocumentAI::V1::FetchProcessorTypesRequest.new

  # Call the fetch_processor_types method.
  result = client.fetch_processor_types request

  # The returned object is of type Google::Cloud::DocumentAI::V1::FetchProcessorTypesResponse.
  p result
end

C#

如需了解详情,请参阅 Document AI C# API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

using Google.Api.Gax.ResourceNames;
using Google.Cloud.DocumentAI.V1;

public sealed partial class GeneratedDocumentProcessorServiceClientSnippets
{
    /// <summary>Snippet for FetchProcessorTypes</summary>
    /// <remarks>
    /// This snippet has been automatically generated and should be regarded as a code template only.
    /// It will require modifications to work:
    /// - It may require correct/in-range values for request initialization.
    /// - It may require specifying regional endpoints when creating the service client as shown in
    ///   https://cloud.google.com/dotnet/docs/reference/help/client-configuration#endpoint.
    /// </remarks>
    public void FetchProcessorTypesRequestObject()
    {
        // Create client
        DocumentProcessorServiceClient documentProcessorServiceClient = DocumentProcessorServiceClient.Create();
        // Initialize request argument(s)
        FetchProcessorTypesRequest request = new FetchProcessorTypesRequest
        {
            ParentAsLocationName = LocationName.FromProjectLocation("[PROJECT]", "[LOCATION]"),
        };
        // Make the request
        FetchProcessorTypesResponse response = documentProcessorServiceClient.FetchProcessorTypes(request);
    }
}

创建处理器

网页界面

  1. 在 Google Cloud 控制台的 Document AI 部分,前往处理器库页面。

    前往处理器库

  2. 查看或搜索处理器库,找到要创建的处理器。

  3. 点击要创建的处理器类型。

  4. 在侧边创建处理器窗口中,指定处理器名称。

  5. 从列表中选择您的区域

  6. 点击创建以创建处理器。

    系统会将您转到处理器的概览标签页,其中包含名称ID类型预测端点等信息。您可以使用此端点发送请求

REST

此示例展示了如何使用 processors.create 方法创建新的 processor

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:处理器的位置,例如:
    • us - 美国
    • eu - 欧盟
  • PROJECT_ID:您的 Google Cloud 项目 ID。
  • PROCESSOR_TYPE:处理器的类型,例如:
    • OCR_PROCESSOR
    • FORM_PARSER_PROCESSOR
    • INVOICE_PROCESSOR
    • US_DRIVER_LICENSE_PROCESSOR
  • DISPLAY_NAME:处理器的显示名称。

HTTP 方法和网址:

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

请求 JSON 正文:

{
  "type": "PROCESSOR_TYPE",
  "displayName": "DISPLAY_NAME"
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth 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"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$cred = gcloud auth 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" | Select-Object -Expand Content

如果请求成功,服务器将返回一个 200 OK HTTP 状态代码以及 JSON 格式的响应。响应包含有关新创建的处理器的信息,例如 processEndpoint 和完整处理器名称。 这两个字符串都包含发送请求所需的唯一处理器 ID(例如 aa22ec60216f6ccc)。

{
  "name": "projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID",
  "type": "PROCESSOR_TYPE",
  "displayName": "DISPLAY_NAME",
  "state": "ENABLED",
  "processEndpoint": "https://LOCATION-documentai.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID:process",
  "createTime": "2022-03-02T22:50:31.395849Z",
  "defaultProcessorVersion": "projects/PROJECT_ID/locations/LOCATION/processors/PROCESSOR_ID/processorVersions/pretrained"
}

Python

如需了解详情,请参阅 Document AI Python API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


from google.api_core.client_options import ClientOptions
from google.cloud import documentai  # type: ignore

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
# processor_display_name = 'YOUR_PROCESSOR_DISPLAY_NAME' # Must be unique per project, e.g.: 'My Processor'
# processor_type = 'YOUR_PROCESSOR_TYPE' # Use fetch_processor_types to get available processor types


def create_processor_sample(
    project_id: str, location: str, processor_display_name: str, processor_type: str
) -> None:
    # You must set the api_endpoint if you use a location other than 'us'.
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the location
    # e.g.: projects/project_id/locations/location
    parent = client.common_location_path(project_id, location)

    # Create a processor
    processor = client.create_processor(
        parent=parent,
        processor=documentai.Processor(
            display_name=processor_display_name, type_=processor_type
        ),
    )

    # Print the processor information
    print(f"Processor Name: {processor.name}")
    print(f"Processor Display Name: {processor.display_name}")
    print(f"Processor Type: {processor.type_}")

Go

如需了解详情,请参阅 Document AI Go API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


//go:build examples

package main

import (
	"context"

	documentai "cloud.google.com/go/documentai/apiv1"
	documentaipb "cloud.google.com/go/documentai/apiv1/documentaipb"
)

func main() {
	ctx := context.Background()
	// This snippet has been automatically generated and should be regarded as a code template only.
	// It will require modifications to work:
	// - It may require correct/in-range values for request initialization.
	// - It may require specifying regional endpoints when creating the service client as shown in:
	//   https://pkg.go.dev/cloud.google.com/go#hdr-Client_Options
	c, err := documentai.NewDocumentProcessorClient(ctx)
	if err != nil {
		// TODO: Handle error.
	}
	defer c.Close()

	req := &documentaipb.CreateProcessorRequest{
		// TODO: Fill request struct fields.
		// See https://pkg.go.dev/cloud.google.com/go/documentai/apiv1/documentaipb#CreateProcessorRequest.
	}
	resp, err := c.CreateProcessor(ctx, req)
	if err != nil {
		// TODO: Handle error.
	}
	// TODO: Use resp.
	_ = resp
}

Java

如需了解详情,请参阅 Document AI Java API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

import com.google.cloud.documentai.v1.CreateProcessorRequest;
import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
import com.google.cloud.documentai.v1.LocationName;
import com.google.cloud.documentai.v1.Processor;

public class SyncCreateProcessor {

  public static void main(String[] args) throws Exception {
    syncCreateProcessor();
  }

  public static void syncCreateProcessor() throws Exception {
    // This snippet has been automatically generated and should be regarded as a code template only.
    // It will require modifications to work:
    // - It may require correct/in-range values for request initialization.
    // - It may require specifying regional endpoints when creating the service client as shown in
    // https://cloud.google.com/java/docs/setup#configure_endpoints_for_the_client_library
    try (DocumentProcessorServiceClient documentProcessorServiceClient =
        DocumentProcessorServiceClient.create()) {
      CreateProcessorRequest request =
          CreateProcessorRequest.newBuilder()
              .setParent(LocationName.of("[PROJECT]", "[LOCATION]").toString())
              .setProcessor(Processor.newBuilder().build())
              .build();
      Processor response = documentProcessorServiceClient.createProcessor(request);
    }
  }
}

Ruby

如需了解详情,请参阅 Document AI Ruby API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

require "google/cloud/document_ai/v1"

##
# Snippet for the create_processor call in the DocumentProcessorService service
#
# This snippet has been automatically generated and should be regarded as a code
# template only. It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in https://cloud.google.com/ruby/docs/reference.
#
# This is an auto-generated example demonstrating basic usage of
# Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client#create_processor.
#
def create_processor
  # Create a client object. The client can be reused for multiple calls.
  client = Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client.new

  # Create a request. To set request fields, pass in keyword arguments.
  request = Google::Cloud::DocumentAI::V1::CreateProcessorRequest.new

  # Call the create_processor method.
  result = client.create_processor request

  # The returned object is of type Google::Cloud::DocumentAI::V1::Processor.
  p result
end

C#

如需了解详情,请参阅 Document AI C# API 参考文档

如需向 Document AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

using Google.Api.Gax.ResourceNames;
using Google.Cloud.DocumentAI.V1;

public sealed partial class GeneratedDocumentProcessorServiceClientSnippets
{
    /// <summary>Snippet for CreateProcessor</summary>
    /// <remarks>
    /// This snippet has been automatically generated and should be regarded as a code template only.
    /// It will require modifications to work:
    /// - It may require correct/in-range values for request initialization.
    /// - It may require specifying regional endpoints when creating the service client as shown in
    ///   https://cloud.google.com/dotnet/docs/reference/help/client-configuration#endpoint.
    /// </remarks>
    public void CreateProcessorRequestObject()
    {
        // Create client
        DocumentProcessorServiceClient documentProcessorServiceClient = DocumentProcessorServiceClient.Create();
        // Initialize request argument(s)
        CreateProcessorRequest request = new CreateProcessorRequest
        {
            ParentAsLocationName = LocationName.