Organiza tus páginas con colecciones
Guarda y categoriza el contenido según tus preferencias.
En esta página, se te guía a través del proceso de configuración para acceder a las APIs previamente entrenadas de Vertex AI dentro de la infraestructura aislada de Google Distributed Cloud (GDC), lo que te permite integrar funciones basadas en IA en tu aplicación aislada. Puedes encontrar detalles sobre los requisitos previos y los pasos para habilitar y desactivar las APIs de Vertex AI a través de la consola de GDC.
Esta página está dirigida a los desarrolladores de aplicaciones que forman parte de grupos de operadores de aplicaciones y que son responsables de optimizar las aplicaciones aisladas con funciones basadas en IA. Para obtener más información, consulta Audiences for GDC air-gapped documentation (Públicos para la documentación de GDC aislada del aire).
Vertex AI en Distributed Cloud incluye varias APIs que debes habilitar desde la consola de GDC para permitir que los usuarios de tu organización interactúen con los modelos de AA y las capacidades de IA. Para obtener más información sobre estas APIs, consulta la siguiente documentación:
Antes de comenzar, verifica que hayas realizado los siguientes pasos previos:
Debes tener el rol de administrador de AI Platform (ai-platform-admin) para configurar el acceso a las APIs de Vertex AI. Si aún no tienes el rol, puedes comunicarte con el administrador de IAM de tu organización o el administrador de IAM del proyecto para solicitarlo. También puedes pedirle a tu administrador que habilite las APIs de Vertex AI por ti. Para obtener información sobre este rol, consulta Cómo preparar permisos de IAM.
Configura el sistema de nombres de dominio (DNS) de GDC. Si no configuraste el DNS, trabaja con tu operador de infraestructura (IO) para completar este requisito previo.
Si traes tu propio modelo porque deseas usar la predicción en línea o ejecutar notebooks de inteligencia artificial (IA) y aprendizaje automático (AA) en un entorno de GPU, asegúrate de asignar máquinas con GPU para los tipos de clúster correctos.
Habilita las APIs previamente entrenadas
Puedes habilitar los modelos y las APIs de los servicios de Vertex AI con la consola de GDC.
La alerta VAI-A0001 (Enabling State Time Limit Reached) se activa si los servicios tardan mucho en habilitarse. En este caso, tu IO debe revisar el manual de ejecución VAI-R0001 para obtener más detalles.
Cómo desactivar las APIs previamente entrenadas
Puedes desactivar las APIs previamente entrenadas con la consola de GDC.
En el menú de navegación, haz clic en Vertex AI>APIs previamente entrenadas.
En la página APIs previamente entrenadas, haz clic en Inhabilitar en un servicio específico para desactivar esa API.
En el cuadro de diálogo de confirmación, ingresa disable en el campo de texto para confirmar que deseas realizar esa acción. Luego, haz clic en Inhabilitar. Aparecerá un mensaje de progreso.
[[["Fácil de comprender","easyToUnderstand","thumb-up"],["Resolvió mi problema","solvedMyProblem","thumb-up"],["Otro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Información o código de muestra incorrectos","incorrectInformationOrSampleCode","thumb-down"],["Faltan la información o los ejemplos que necesito","missingTheInformationSamplesINeed","thumb-down"],["Problema de traducción","translationIssue","thumb-down"],["Otro","otherDown","thumb-down"]],["Última actualización: 2025-09-04 (UTC)"],[[["\u003cp\u003eThis page outlines how to provision GPU resources on a container for AI/ML workloads and enable Vertex AI pre-trained APIs on Google Distributed Cloud (GDC) air-gapped.\u003c/p\u003e\n"],["\u003cp\u003eAdministrator access is generally required to configure GPU resources and manage Vertex AI pre-trained APIs, so you may need to request these actions if lacking the necessary permissions.\u003c/p\u003e\n"],["\u003cp\u003eVertex AI on GDC offers pre-trained APIs for Optical Character Recognition (OCR), Speech-to-Text, and Translation, along with services like Online Prediction and Vertex AI Workbench.\u003c/p\u003e\n"],["\u003cp\u003eProvisioning GPUs involves setting up DNS, creating a GPU-supporting cluster, and configuring containers to utilize GPU resources.\u003c/p\u003e\n"],["\u003cp\u003eThe GDC console is used to enable, deactivate, and monitor the status of the OCR, Speech-to-Text, and Vertex AI Translation pre-trained APIs.\u003c/p\u003e\n"]]],[],null,["# Enable Vertex AI APIs\n\nThis page guides you through the setup process for accessing Vertex AI pre-trained APIs within the Google Distributed Cloud (GDC) air-gapped infrastructure, allowing you to integrate AI features into your air-gapped application. You can find details about the prerequisites and the steps for enabling and deactivating the Vertex AI APIs through the GDC console console.\n\nThis page is for application developers within application operator groups who are responsible for optimizing air-gapped applications with AI features. For more information, see [Audiences for GDC air-gapped documentation](/distributed-cloud/hosted/docs/latest/gdch/resources/audiences).\n\nVertex AI on Distributed Cloud includes various APIs that\nyou must enable from the GDC console to let users from your\norganization interact with ML models and AI capabilities. To learn more about\nthese APIs, see the following documentation:\n\n- **Generative AI** : [Learn about Generative AI capabilities and available models](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/genai/genai-overview).\n- **Online Prediction** : [Learn about online predictions](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-online-predictions).\n- **Optical Character Recognition (OCR)** : [Learn about character recognition features](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-ocr).\n- **Speech-to-Text** : [Learn about speech recognition features](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-stt).\n- **Vertex AI Translation** : [Learn about translation features](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-translation).\n- **Vertex AI Workbench** : [Learn about Vertex AI Workbench](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-workbench-intro).\n\nBefore you begin\n----------------\n\nBefore you begin, check that you've done the following prerequisite steps:\n\n1. You must have the AI Platform Admin (`ai-platform-admin`) role to set up access to the Vertex AI APIs. You can contact your Organization IAM Admin or Project IAM Admin to request the role if you don't already have it. Alternatively, you can ask your administrator to enable Vertex AI APIs on your behalf. For information about this role, see [Prepare IAM permissions](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-ao-permissions).\n2. Set up the GDC domain name system (DNS). If you haven't set up the DNS, work with your Infrastructure Operator (IO) to complete this prerequisite.\n3. [Set up a project to use Vertex AI](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-set-up-project).\n4. If you bring your own model because you want to use\n [Online Prediction](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-online-predictions)\n or run artificial intelligence (AI) and machine learning (ML) notebooks in a\n GPU environment, make sure to\n [allocate GPU machines](/distributed-cloud/hosted/docs/latest/gdch/platform/pa-user/create-user-cluster#gpu)\n for the correct cluster types.\n\n | **Note:** Pre-trained APIs run on a shared service Kubernetes cluster managed by the infrastructure.\n\nEnable pre-trained APIs\n-----------------------\n\nYou can enable Vertex AI service APIs and models using the\nGDC console.\n\nAfter [meeting the prerequisites](#before-you-enable-apis), follow these steps\nto enable APIs:\n\n1. [Sign in to the GDC console](/distributed-cloud/hosted/docs/latest/gdch/platform/pa-user/iam/sign-in). If you can't sign in, see [Connect to an identity provider](/distributed-cloud/hosted/docs/latest/gdch/platform/pa-user/iam/connect-identity).\n2. In the navigation menu, click **Vertex AI** \\\u003e **Pre-trained APIs**.\n3. On the **Pre-trained APIs** page, click **Enable** on a specific service to\n enable that API.\n\n | **Note:** The GDC console doesn't display the buttons to enable the pre-trained APIs if you don't have the correct permissions.\n4. In the confirmation dialog, click **Enable**. A progress message displays.\n\nThe enablement duration varies. It might take between 15 and 45 minutes to\nfinish, depending on the state of the cluster.\n\nIf you want to view the status of the pre-trained APIs,\n[view the service status and endpoints](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-api-status).\n\nThe VAI-A0001 alert (`Enabling State Time Limit Reached`) triggers if the\nservices take a long time to be enabled. In this case, your IO must review the\nVAI-R0001 runbook for details.\n| **Note:** You can't enable an API while you wait for another API to finish deactivating.\n\nDeactivate pre-trained APIs\n---------------------------\n\nYou can deactivate pre-trained APIs using the GDC console.\n\nAfter [meeting the prerequisites](#before-you-enable-apis), follow these steps\nto deactivate APIs:\n\n1. [Sign in to the GDC console](/distributed-cloud/hosted/docs/latest/gdch/platform/pa-user/iam/sign-in).\n2. In the navigation menu, click **Vertex AI** \\\u003e **Pre-trained APIs**.\n3. On the **Pre-trained APIs** page, click **Disable** on a specific service to\n deactivate that API.\n\n | **Note:** The GDC console doesn't display the buttons to deactivate the pre-trained APIs if you don't have the correct permissions.\n4. In the confirmation dialog, enter *disable* in the text field to confirm\n that you want to take that action. Then, click **Disable**. A progress\n message displays.\n\nIf you want to view the status of the pre-trained APIs,\n[view the service status and endpoints](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-api-status).\n| **Note:** You can't deactivate an API while you wait for another API to finish enabling."]]
