Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
Serviço que realiza a deteção e a anotação de imagens para um lote de ficheiros. Agora, apenas são suportados os tipos "application/pdf", "image/tiff" e "image/gif".
Este serviço extrai, no máximo, 5 frames (GIF) ou páginas (PDF ou TIFF) de cada ficheiro fornecido e realiza a deteção e a anotação de cada imagem extraída. Os clientes podem especificar que 5 frames ou páginas querem no AnnotateFileRequest.pages.
Pedido HTTP
POST https://{VISION_GDC_ENDPOINT}/v1/files:annotate
Corpo do pedido
O corpo do pedido contém dados com a seguinte estrutura:
[[["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"]],["Última atualização 2025-08-21 UTC."],[[["\u003cp\u003eThis service performs image detection and annotation on batches of files, currently supporting PDF, TIFF, and GIF formats.\u003c/p\u003e\n"],["\u003cp\u003eIt extracts a maximum of five frames or pages per file for analysis, with the option for users to specify which pages via \u003ccode\u003eAnnotateFileRequest.pages\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe service is accessed via a POST HTTP request to \u003ccode\u003ehttps://{VISION_GDC_ENDPOINT}/v1/files:annotate\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eRequests must include an \u003ccode\u003eAnnotateFileRequest\u003c/code\u003e object within a \u003ccode\u003eBatchAnnotateFilesRequest\u003c/code\u003e and optionally a target \u003ccode\u003eparent\u003c/code\u003e project and location.\u003c/p\u003e\n"],["\u003cp\u003eAuthorization requires either \u003ccode\u003ehttps://www.googleapis.com/auth/cloud-platform\u003c/code\u003e or \u003ccode\u003ehttps://www.googleapis.com/auth/cloud-vision\u003c/code\u003e OAuth scopes.\u003c/p\u003e\n"]]],[],null,["# Method: files.annotate\n\nService that performs image detection and annotation for a batch of files. Now only \"application/pdf\", \"image/tiff\" and \"image/gif\" are supported.\n\nThis service will extract at most 5 (customers can specify which 5 in AnnotateFileRequest.pages) frames (gif) or pages (pdf or tiff) from each file provided and perform detection and annotation for each image extracted.\n\n### HTTP request\n\n`POST https://{VISION_GDC_ENDPOINT}/v1/files:annotate`\n\n### Request body\n\nThe request body contains data with the following structure:\n\n### Response body\n\nIf successful, the response body contains an instance of [BatchAnnotateFilesResponse](/distributed-cloud/hosted/docs/latest/gdch/apis/vertex-ai/ocr/rest/v1/BatchAnnotateFilesResponse).\n\n### Authorization Scopes\n\nRequires one of the following OAuth scopes:\n\n- `https://www.googleapis.com/auth/cloud-platform`\n- `https://www.googleapis.com/auth/cloud-vision`"]]
