Treinar uma versão do processador
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
Iniciar um novo job de treinamento para um processador
Mais informações
Para ver a documentação detalhada que inclui este exemplo de código, consulte:
Exemplo de código
Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Informações incorretas ou exemplo de código","incorrectInformationOrSampleCode","thumb-down"],["Não contém as informações/amostras de que eu preciso","missingTheInformationSamplesINeed","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Outro","otherDown","thumb-down"]],[],[[["\u003cp\u003eThis code sample demonstrates how to initiate a new training job for a Document AI processor using the Python API.\u003c/p\u003e\n"],["\u003cp\u003eThe code utilizes the \u003ccode\u003edocumentai\u003c/code\u003e library to set up and train a new processor version, specifying project, location, and processor identifiers.\u003c/p\u003e\n"],["\u003cp\u003eYou can optionally configure the training and test data by providing URIs for Google Cloud Storage (GCS) buckets containing your documents, otherwise the Cloud Console defaults will be used.\u003c/p\u003e\n"],["\u003cp\u003eAuthentication with Document AI is required, using Application Default Credentials as detailed in the provided link.\u003c/p\u003e\n"],["\u003cp\u003eUpon successful execution, the code will output the operation details, the new processor version, and the validation results for both training and test datasets.\u003c/p\u003e\n"]]],[],null,["# Train a processor version\n\nStart a new training job for a processor\n\nExplore further\n---------------\n\n\nFor detailed documentation that includes this code sample, see the following:\n\n- [Train and evaluate](/document-ai/docs/training-overview)\n\nCode sample\n-----------\n\n### Python\n\n\nFor more information, see the\n[Document AI Python API\nreference documentation](/python/docs/reference/documentai/latest).\n\n\nTo authenticate to Document AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n\n from typing import Optional\n\n from google.api_core.client_options import ClientOptions\n from google.cloud import documentai # type: ignore\n\n # TODO(developer): Uncomment these variables before running the sample.\n # project_id = 'YOUR_PROJECT_ID'\n # location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'\n # processor_id = 'YOUR_PROCESSOR_ID'\n # processor_version_display_name = 'new-processor-version'\n # train_data_uri = 'gs://bucket/directory/' # (Optional)\n # test_data_uri = 'gs://bucket/directory/' # (Optional)\n\n\n def train_processor_version_sample(\n project_id: str,\n location: str,\n processor_id: str,\n processor_version_display_name: str,\n train_data_uri: Optional[str] = None,\n test_data_uri: Optional[str] = None,\n ) -\u003e None:\n # You must set the api_endpoint if you use a location other than 'us', e.g.:\n opts = ClientOptions(api_endpoint=f\"{location}-documentai.googleapis.com\")\n\n client = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.services.document_processor_service.DocumentProcessorServiceClient.html(client_options=opts)\n\n # The full resource name of the processor\n # e.g. `projects/{project_id}/locations/{location}/processors/{processor_id}\n parent = client.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.services.document_processor_service.DocumentProcessorServiceClient.html#google_cloud_documentai_v1_services_document_processor_service_DocumentProcessorServiceClient_processor_path(project_id, location, processor_id)\n\n processor_version = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.ProcessorVersion.html(\n display_name=processor_version_display_name\n )\n\n # If train/test data is not supplied, the default sets in the Cloud Console will be used\n input_data = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.TrainProcessorVersionRequest.html.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.TrainProcessorVersionRequest.InputData.html(\n training_documents=documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.BatchDocumentsInputConfig.html(\n gcs_prefix=documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.GcsPrefix.html(gcs_uri_prefix=train_data_uri)\n ),\n test_documents=documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.BatchDocumentsInputConfig.html(\n gcs_prefix=documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.GcsPrefix.html(gcs_uri_prefix=test_data_uri)\n ),\n )\n\n request = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.TrainProcessorVersionRequest.html(\n parent=parent, processor_version=processor_version, input_data=input_data\n )\n\n operation = client.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.services.document_processor_service.DocumentProcessorServiceClient.html#google_cloud_documentai_v1_services_document_processor_service_DocumentProcessorServiceClient_train_processor_version(request=request)\n # Print operation details\n print(operation.operation.name)\n # Wait for operation to complete\n response = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.TrainProcessorVersionResponse.html(operation.result())\n\n metadata = documentai.https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.TrainProcessorVersionMetadata.html(operation.metadata)\n\n print(f\"New Processor Version:{response.processor_version}\")\n print(f\"Training Set Validation: {metadata.training_dataset_validation}\")\n print(f\"Test Set Validation: {metadata.test_dataset_validation}\")\n\nWhat's next\n-----------\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=documentai)."]]