Sign in to your Google Cloud account. If you're new to
Google Cloud,
create an account to evaluate how our products perform in
real-world scenarios. New customers also get $300 in free credits to
run, test, and deploy workloads.
In the Google Cloud console, on the project selector page,
select or create a Google Cloud project.
Roles required to select or create a project
Select a project: Selecting a project doesn't require a specific
IAM role—you can select any project that you've been
granted a role on.
Create a project: To create a project, you need the Project Creator
(roles/resourcemanager.projectCreator), which contains the
resourcemanager.projects.create permission. Learn how to grant
roles.
To enable APIs, you need the Service Usage Admin IAM
role (roles/serviceusage.serviceUsageAdmin), which
contains the serviceusage.services.enable permission. Learn how to grant
roles.
In the Google Cloud console, on the project selector page,
select or create a Google Cloud project.
Roles required to select or create a project
Select a project: Selecting a project doesn't require a specific
IAM role—you can select any project that you've been
granted a role on.
Create a project: To create a project, you need the Project Creator
(roles/resourcemanager.projectCreator), which contains the
resourcemanager.projects.create permission. Learn how to grant
roles.
To enable APIs, you need the Service Usage Admin IAM
role (roles/serviceusage.serviceUsageAdmin), which
contains the serviceusage.services.enable permission. Learn how to grant
roles.
Una vez que hayas configurado tu entorno, podrás crear tu aplicación.
En la Google Cloud consola, una aplicación se representa como un gráfico.
Además, en Vertex AI Vision, un gráfico de aplicación debe tener al menos dos nodos: un nodo de origen de vídeo (flujo) y al menos otro nodo (un modelo de procesamiento o un destino de salida).
Crear una aplicación vacía
Antes de rellenar el gráfico de aplicaciones, debes crear una aplicación vacía.
Consola
Crea una aplicación en la Google Cloud consola.
Abre la pestaña Aplicaciones del panel de control de Vertex AI Vision.
Introduce quickstart-app como nombre de la aplicación y elige tu región.
Haz clic en Crear.
Añadir nodos de componentes de aplicaciones
Después de crear la aplicación vacía, puedes añadir los tres nodos al gráfico de la aplicación: el nodo de ingestión, que puede recibir datos de streaming, el nodo de procesamiento, que realiza una tarea de imagen por ordenador en los datos, y un nodo de destino de datos, que en este ejemplo es un destino de almacenamiento de almacén.
Consola
Añade nodos de componentes a tu aplicación en la consola.
Abre la pestaña Aplicaciones del panel de control de Vertex AI Vision.
En la línea quickstart-app, selecciona
schemaVer gráfico. De esta forma, accederás a la visualización del gráfico de la canalización de procesamiento.
Añadir un nodo de ingestión de datos
Para añadir un nodo de flujo de entrada, selecciona la opción Streams (Flujos) en la sección Connectors (Conectores) del menú lateral.
En la sección Fuente del menú Stream que se abre, selecciona
addAñadir streams.
En el menú Añadir emisiones, elige
radio_button_checkedRegistrar nuevas emisiones y añade quickstart-stream como nombre de la emisión.
Para añadir el flujo al gráfico de la aplicación, haz clic en Añadir flujos.
Añadir un nodo de procesamiento de datos
Para añadir el nodo del modelo de detector de objetos, selecciona la opción Detector de objetos en la sección Modelos preentrenados del menú lateral.
Añadir un nodo de almacenamiento de datos
Para añadir el nodo de destino de salida (almacenamiento), selecciona la opción Vertex AI Vision's Media Warehouse (Almacén de contenido multimedia de Vertex AI Vision) en la sección Connectors (Conectores) del menú lateral.
En el menú Media Warehouse de Vertex AI Vision, haz clic en Conectar almacén.
En el menú Conectar almacén, selecciona
radio_button_checkedCrear almacén. Ponle el nombre quickstart-warehouse al almacén y deja la duración del TTL en 14 días.
Haz clic en el botón Crear para añadir el almacén.
Desplegar una aplicación para usarla
Una vez que hayas creado tu aplicación integral con todos los componentes necesarios, el último paso para usarla es implementarla.
Consola
Abre la pestaña Aplicaciones del panel de control de Vertex AI Vision.
Selecciona Ver gráfico junto a la aplicación quickstart-app de la lista.
En la página del creador de gráficos de aplicaciones, haz clic en el botón play_arrowImplementar.
En el cuadro de diálogo de confirmación que aparece, selecciona Implementar.
La operación de implementación puede tardar varios minutos en completarse. Cuando finalice la implementación, aparecerán marcas de verificación verdes junto a los nodos.
¡Enhorabuena! Acabas de crear y desplegar tu primera aplicación de Vertex AI Vision. Crear y desplegar una aplicación son los primeros pasos para ingerir y usar datos multimedia procesados con Vertex AI Vision.
Limpieza
Para evitar que los recursos utilizados en esta guía de inicio rápido se cobren en tu cuenta de Google Cloud, elimina el proyecto que contiene los recursos o conserva el proyecto y elimina los recursos.
Eliminar el proyecto
In the Google Cloud console, go to the Manage resources page.
[[["Es fácil de entender","easyToUnderstand","thumb-up"],["Me ofreció una solución al problema","solvedMyProblem","thumb-up"],["Otro","otherUp","thumb-up"]],[["Es difícil de entender","hardToUnderstand","thumb-down"],["La información o el código de muestra no son correctos","incorrectInformationOrSampleCode","thumb-down"],["Me faltan las muestras o la información que necesito","missingTheInformationSamplesINeed","thumb-down"],["Problema de traducción","translationIssue","thumb-down"],["Otro","otherDown","thumb-down"]],["Última actualización: 2025-09-11 (UTC)."],[],[],null,["# Quickstart: Build an app in the console\n\nBuild an app in the console\n===========================\n\nLearn how to create a simple Vertex AI Vision object detector app in the\nGoogle Cloud console.\n\n*** ** * ** ***\n\nTo follow step-by-step guidance for this task directly in the\nGoogle Cloud console, click **Guide me**:\n\n[Guide me](https://console.cloud.google.com/freetrial?redirectPath=/?walkthrough_id=vertex-ai-vision--build-app-console-quickstart)\n\n*** ** * ** ***\n\nBefore you begin\n----------------\n\n- Sign in to your Google Cloud account. If you're new to Google Cloud, [create an account](https://console.cloud.google.com/freetrial) to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.\n- In the Google Cloud console, on the project selector page,\n select or create a Google Cloud project.\n\n | **Note**: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.\n\n [Go to project selector](https://console.cloud.google.com/projectselector2/home/dashboard)\n-\n [Verify that billing is enabled for your Google Cloud project](/billing/docs/how-to/verify-billing-enabled#confirm_billing_is_enabled_on_a_project).\n\n-\n\n\n Enable the Vision AI API.\n\n\n [Enable the API](https://console.cloud.google.com/flows/enableapi?apiid=visionai.googleapis.com)\n\n- In the Google Cloud console, on the project selector page,\n select or create a Google Cloud project.\n\n | **Note**: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.\n\n [Go to project selector](https://console.cloud.google.com/projectselector2/home/dashboard)\n-\n [Verify that billing is enabled for your Google Cloud project](/billing/docs/how-to/verify-billing-enabled#confirm_billing_is_enabled_on_a_project).\n\n-\n\n\n Enable the Vision AI API.\n\n\n [Enable the API](https://console.cloud.google.com/flows/enableapi?apiid=visionai.googleapis.com)\n\nCreate an object detector application\n-------------------------------------\n\nAfter you have set up your environment, you can create your app.\n\nIn the Google Cloud console, an app is represented as a graph.\nAdditionally, in Vertex AI Vision, an app graph must have at least two nodes: a\nvideo source node (stream), and *at least* one more node (a processing model or\noutput destination).\n\n### Create an empty app\n\nBefore you can populate the app graph, you must first create an empty app. \n\n### Console\n\nCreate an app in the Google Cloud console.\n\n1. Open the **Applications** tab of the Vertex AI Vision dashboard.\n\n [Go to the Applications tab](https://console.cloud.google.com/ai/vision-ai/applications)\n2. Click the add**Create** button.\n\n3. Enter `quickstart-app` as the app name and choose your region.\n\n4. Click **Create**.\n\n \u003cbr /\u003e\n\n### Add app component nodes\n\nAfter you have created the empty application, you can then add the three nodes\nto the app graph: the **ingestion node** that can receive stream data, the\n**processing node** that performs a computer image task on data, and a **data\ndestination node**, a warehouse storage destination in this example. \n\n### Console\n\nAdd component nodes to your app in the console.\n\n1. Open the **Applications** tab of the Vertex AI Vision dashboard.\n\n [Go to the Applications tab](https://console.cloud.google.com/ai/vision-ai/applications)\n2. In the `quickstart-app` line, select\n schema**View graph**. This takes you\n to the graph visualization of the processing pipeline.\n\n**Add a data ingestion node**\n\n1. To add an input stream node, select the **Streams** option in the\n **Connectors** section of the side menu.\n\n2. In the **Source** section of the **Stream** menu that opens, select\n add**Add streams**.\n\n3. In the **Add streams** menu, choose\n radio_button_checked**Register new\n streams** and add `quickstart-stream` as the stream name.\n\n \u003cbr /\u003e\n\n4. To add the stream to the app graph, click **Add streams**.\n\n**Add a data processing node**\n\n1. To add the object detector model node, select the **Object detector**\n option in the **Pre-trained models** section of the side menu.\n\n**Add a data storage node**\n\n1. To add the output destination (storage) node, select the\n **Vertex AI Vision's Media Warehouse** option in the **Connectors** section of the side\n menu.\n\n2. In the **Vertex AI Vision's Media Warehouse** menu, click **Connect warehouse**.\n\n3. In the **Connect warehouse** menu, select\n radio_button_checked**Create new\n warehouse** . Name the warehouse `quickstart-warehouse`, and leave\n the TTL duration at 14 days.\n\n4. Click the **Create** button to add the warehouse.\n\nDeploy your app for use\n-----------------------\n\nAfter you have built your end-to-end app with all the necessary components, the last step to using the app is to deploy it.\n\n\u003cbr /\u003e\n\n### Console\n\n1. Open the **Applications** tab of the Vertex AI Vision dashboard.\n\n [Go to the Applications tab](https://console.cloud.google.com/ai/vision-ai/applications)\n2. Select **View graph** next to the `quickstart-app` app in the list.\n\n3. From the application graph builder page, click the\n play_arrow**Deploy** button.\n\n4. In the following confirmation dialog, select **Deploy**.\n\n The deploy operation might take several minutes to complete. After\n deployment finishes, green check marks appear next to the nodes.\n\n\nCongratulations! You've just created and deployed your first Vertex AI Vision\napp. Creating and deploying an app are the first steps in ingesting and using\nprocessed media data with Vertex AI Vision.\n\nClean up\n--------\n\nTo avoid incurring charges to your Google Cloud account for the resources used\nin this quickstart, either delete the project that contains the resources, or\nkeep the project and delete the individual resources. \n\n### Delete the project\n\n| **Caution** : Deleting a project has the following effects:\n|\n| - **Everything in the project is deleted.** If you used an existing project for the tasks in this document, when you delete it, you also delete any other work you've done in the project.\n| - **Custom project IDs are lost.** When you created this project, you might have created a custom project ID that you want to use in the future. To preserve the URLs that use the project ID, such as an `appspot.com` URL, delete selected resources inside the project instead of deleting the whole project.\n|\n|\n| If you plan to explore multiple architectures, tutorials, or quickstarts, reusing projects\n| can help you avoid exceeding project quota limits.\n1. In the Google Cloud console, go to the **Manage resources** page.\n\n [Go to Manage resources](https://console.cloud.google.com/iam-admin/projects)\n2. In the project list, select the project that you want to delete, and then click **Delete**.\n3. In the dialog, type the project ID, and then click **Shut down** to delete the project. \n\n### Delete individual resources\n\n#### Delete a warehouse\n\n1. In the Google Cloud console, go to the **Warehouses** page.\n\n [Go to the Warehouses tab](https://console.cloud.google.com/ai/vision-ai/media-warehouse)\n2. Locate your `quickstart-warehouse` warehouse.\n3. To delete the warehouse, click more_vert **Actions** , click **Delete warehouse**, and then follow the instructions.\n\n#### Delete a stream\n\n1. In the Google Cloud console, go to the **Streams** page.\n\n [Go to the Streams tab](https://console.cloud.google.com/ai/vision-ai/video-streams)\n2. Locate your `quickstart-stream` stream.\n3. To delete the stream, click more_vert **Actions** , click **Delete stream**, and then follow the instructions.\n\n#### Delete an app\n\n1. In the Google Cloud console, go to the **Applications** page.\n\n [Go to the Applications tab](https://console.cloud.google.com/ai/vision-ai/applications)\n | **Note:** You must first undeploy your app before you can delete it.\n2. Locate your `quickstart-app` app.\n3. To delete the app, click more_vert **Actions** , click **Delete application**, and then follow the instructions.\n\nWhat's next\n-----------\n\n- Read [Set up a project and a development environment](/vision-ai/docs/cloud-environment) before you use the command line tools.\n- Learn how to [ingest data](/vision-ai/docs/create-manage-streams#ingest-videos) into your new app and read about other components you can add in [Build an app](/vision-ai/docs/build-app).\n- Learn about other output storage and processing options in [Connect app output to a data destination](/vision-ai/docs/connect-data-destination).\n- Read about how to [Search Warehouse data in the console](/vision-ai/docs/search-streaming-warehouse).\n- Read more about [Responsible AI practices](https://ai.google/responsibilities/responsible-ai-practices/)."]]
