Siapkan project Google Cloud , aktifkan Aplikasi AI, dan siapkan kontrol akses untuk project Anda. Anda dapat menggunakan project Google Cloud yang sudah ada jika sudah menggunakannya.
Siapkan data Anda untuk diimpor ke Vertex AI Search.
Aplikasi penelusuran media menggunakan data berikut:
Data media terstruktur. Wajib. Upload informasi metadata tentang
konten media Anda, seperti judul, deskripsi, dan URI ke lokasi
media Anda. Vertex AI Search menyediakan skema standar untuk media.
Atau, Anda dapat menggunakan skema Anda sendiri.
Peristiwa pengguna. Wajib. Peristiwa pengguna membantu menentukan peringkat hasil penelusuran.
Buat aplikasi dan penyimpanan data, lalu impor data media Anda.
Cara mengimpor data media bergantung pada tempat Anda mengimpornya. Misalnya, jika data Anda berada di Cloud Storage, Anda dapat mengimpornya menggunakan
konsol atau API dengan memberikan lokasi bucket data Anda.
Vertex AI Search menyediakan banyak opsi konfigurasi. Beberapa opsi
bergantung pada apakah Anda berencana men-deploy widget penelusuran.
Tindakan
Bergantung pada kasus penggunaan Anda dan apakah Anda berencana men-deploy widget penelusuran
yang siap pakai atau mengintegrasikan panggilan API penelusuran ke dalam kode Anda sendiri,
Vertex AI Search menyediakan beberapa opsi untuk konfigurasi.
Anda dapat menyematkan widget penelusuran ke dalam situs Anda sehingga otomatis menyediakan kotak penelusuran dan antarmuka penelusuran yang dapat diperluas. Jika Anda berencana men-deploy widget penelusuran, konfigurasikan hal berikut:
Jika Anda berencana untuk mengintegrasikan panggilan API penelusuran ke server atau aplikasi,
bukan menggunakan widget, Anda dapat mengonfigurasi setelan penelusuran menggunakan
opsi berikut:
Setelan kolom. Untuk data terstruktur atau data tidak terstruktur dengan
metadata, perbarui setelan kolom untuk meningkatkan cara Vertex AI Search
menggunakan metadata untuk penelusuran. Lihat Mengonfigurasi kolom untuk
penelusuran.
Pelengkapan otomatis. Bergantung pada data Anda, siapkan saran pelengkapan otomatis berdasarkan konten dokumen, kolom, histori penelusuran, atau peristiwa pengguna. Lihat
Mengonfigurasi pelengkapan otomatis.
Kontrol penayangan. Mengontrol kapan hasil penelusuran
dioptimalkan, disembunyikan, difilter, atau dialihkan, atau apakah kueri tertentu
dikaitkan dengan kueri lain. Lihat Mengonfigurasi kontrol
penayangan untuk penelusuran.
Jika berencana men-deploy aplikasi dengan mengintegrasikan panggilan API penelusuran ke dalam kode
Anda sendiri, Anda dapat mengonfigurasi pemfilteran dan peningkatan untuk hasil penelusuran.
Anda dapat melihat pratinjau hasil penelusuran untuk memeriksa apakah konfigurasi aplikasi Anda berfungsi seperti yang diharapkan.
Tindakan
Untuk melihat pratinjau hasil penelusuran, gunakan konsol atau API.
Konsol. Gunakan halaman Pratinjau konsol Aplikasi AI untuk melihat pratinjau
pengaruh konfigurasi widget penelusuran terhadap hasil Anda. Lihat petunjuk Konsol
di Mendapatkan hasil
penelusuran untuk media.
API. Jika Anda mengintegrasikan panggilan API ke dalam aplikasi,
buat panggilan API untuk melihat pratinjau konfigurasi penelusuran Anda. Lihat petunjuk REST
di Mendapatkan hasil
penelusuran untuk media.
Jika Anda puas dengan versi pratinjau aplikasi penelusuran media, bagikan
kepada pengguna dengan men-deploy-nya ke situs Anda.
Tindakan
Anda dapat men-deploy aplikasi penelusuran dengan salah satu cara berikut:
Sematkan widget penelusuran ke situs Anda. Vertex AI Search
menyediakan kode yang dapat Anda salin ke situs atau aplikasi web Anda. Tindakan ini akan men-deploy widget penelusuran. Anda dapat melihat pratinjau hasil penelusuran di konsol.
Lihat Menambahkan widget penelusuran ke halaman web.
Integrasikan panggilan API penelusuran ke server atau aplikasi Anda. Untuk kontrol penuh
atas cara hasil penelusuran ditampilkan, Anda dapat mengintegrasikan panggilan
API ke server atau aplikasi. Untuk informasi selengkapnya tentang cara melakukan
panggilan API, lihat Mendapatkan hasil penelusuran. Untuk referensi library klien, lihat library klien Aplikasi AI.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-19 UTC."],[[["\u003cp\u003eThis page outlines the steps to implement a media search application using Vertex AI Search, including project setup, data preparation, and app creation.\u003c/p\u003e\n"],["\u003cp\u003ePreparing data involves uploading structured media data and user events, following specified schemas for effective search result ranking.\u003c/p\u003e\n"],["\u003cp\u003eThe process includes creating a media app and data store, importing media data from various sources like Cloud Storage, and setting up real-time and historical user event recording.\u003c/p\u003e\n"],["\u003cp\u003eVertex AI Search offers flexible configuration options for search settings, allowing for deployment of a search widget or integration of search API calls into existing code.\u003c/p\u003e\n"],["\u003cp\u003eAfter configuring and previewing search results, you can deploy the app by embedding the search widget or integrating API calls and maintain the app by regularly updating the structured data.\u003c/p\u003e\n"]]],[],null,["# Media search checklist\n\nThis page provides a checklist of the steps required to implement a media search app.\n\n\u003cbr /\u003e\n\nIf you're new to Vertex AI Search, consider following the [Get started\nwith media search](/generative-ai-app-builder/docs/try-media-search) quickstart\ntutorial to create a sample app. \n\n\n### [Set up a Google Cloud\nproject](#set-up-project)\n\nSet up a Google Cloud project, turn on AI Applications, and set up access\ncontrol for your project. You can use an existing Google Cloud project if you\nhave one already.\n\n### Actions\n\n1. Complete the steps in [Before you begin](/generative-ai-app-builder/docs/before-you-begin). \n\n### [Prepare your data](#prepare-data)\n\nPrepare your data for importing to Vertex AI Search.\n\nMedia search apps use the following data:\n\n- **Structured media data.** Required. Upload metadata information about your\n media content, such as titles, descriptions, and URIs to the location of your\n media. Vertex AI Search provides a predefined schema for media.\n Alternatively, you can use your own schema.\n\n- **User events.** Required. User events help rank search results.\n\n### Actions\n\n1. Review information about media data and data stores and prepare your data\n according to the required schemas and fields in [About media documents and\n data stores](/generative-ai-app-builder/docs/media-documents). If you are\n using your own schema, also see [Example schema as a JSON\n object](/generative-ai-app-builder/docs/provide-schema#example-schema) and\n [structured data](/generative-ai-app-builder/docs/prepare-data#structured).\n\n2. Review media user event requirements in [About media user\n events](/generative-ai-app-builder/docs/media-user-events).\n\n### [Create your app and import your data](#import-data)\n\nCreate an app and data store and then import your media data.\n\nHow you import media data depends on where you're importing it from. For\nexample, if your data is in Cloud Storage, you can import it using the\nconsole or the API by providing the bucket location of your data.\n\n### Actions\n\n1. [Create a media data store](/generative-ai-app-builder/docs/create-data-store-media).\n\n2. [Create media apps](/generative-ai-app-builder/docs/create-app-media).\n\n3. [Bulk import historical user events](/generative-ai-app-builder/docs/import-user-events) so that\n your app can start training.\n\n4. [Set up real-time user event recording](/generative-ai-app-builder/docs/record-user-events).\n\n### [Configure your search\nsettings](#configure-settings)\n\nVertex AI Search provides many configuration options. Some options\ndepend on whether you plan to deploy a search widget.\n\n### Actions\n\nDepending on your use case and whether you plan to deploy the out-of-the-box\nsearch widget or integrate search API calls into your own code,\nVertex AI Search provides several options for configuration.\n\n1. You can embed a search widget into your website that automatically provides\n a search bar and expandable search interface. If you plan to deploy the\n search widget, configure the following:\n\n - **Search widget results.** See [Configure results for the\n search widget](/generative-ai-app-builder/docs/configure-widget-attributes).\n\n - **Search widget facets.** See [Configure facets\n for the search widget](/generative-ai-app-builder/docs/configure-widget-facets).\n\n2. If you plan to integrate search API calls into your server or application\n instead of using the widget, you can configure your search settings using\n the following options:\n\n - **Field settings.** For structured data or for unstructured data with\n metadata, update field settings to refine how Vertex AI Search\n uses metadata for search. See [Configure fields for\n search](/generative-ai-app-builder/docs/configure-search-attributes).\n\n - **Autocomplete.** Depending on your data, set up autocomplete suggestions\n based on document content, fields, search history, or user events. See\n [Configure autocomplete](/generative-ai-app-builder/docs/configure-autocomplete).\n\n - **Serving controls.** Control when search results\n are boosted, buried, filtered, or redirected, or whether certain queries\n are associated with other queries. See [Configure serving\n controls for search](/generative-ai-app-builder/docs/configure-serving-controls).\n\n - **Search-as-you-type.** If your app uses awkward input devices such as TV\n remote controls, you can enable the search-as-you-type feature. See [Get\n search-as-you-type results for a media\n app](/generative-ai-app-builder/docs/preview-search-results#media-search).\n\n### [Filter and boost your\nsearch results](#configure-results)\n\nIf you plan to deploy your app by integrating search API calls into your own\ncode, you can configure filtering and boosting for your search results.\n\n### Actions\n\n1. [Filter media search](/generative-ai-app-builder/docs/filter-media-search).\n\n2. [Boost search results](/generative-ai-app-builder/docs/boost-search-results).\n\n### [Preview search\nresults](#preview-results)\n\nYou can preview your search results to check if your app configurations are\nworking as expected.\n\n### Actions\n\n1. To preview your search results, use the console or the API.\n\n - **Console.** Use the AI Applications console **Preview** page to preview\n how search widget configurations affect your results. See the **Console**\n instructions in [Get search\n results for media](/generative-ai-app-builder/docs/get-media-search-results).\n\n - **API** . If you're integrating API calls into your application,\n make API calls to preview your search configurations. See the **REST**\n instructions in [Get search\n results for media](/generative-ai-app-builder/docs/get-media-search-results).\n\n### [Deploy your\napp](#preview-results)\n\nWhen you're happy with the preview version of your media search app, share it\nwith your users by deploying it to your website.\n\n### Actions\n\n1. You can deploy your search app in either of the following ways:\n\n - **Embed the search widget into your website.** Vertex AI Search\n provides code that you can copy into your website or web application. This\n deploys the search widget. You can preview search results in the console.\n See [Add the search widget to a webpage](/generative-ai-app-builder/docs/add-widget).\n\n - **Integrate search API calls into your server or application.** For full\n control over how your search results are displayed, you can integrate API\n calls into your server or applications. For more information about making\n API calls, see [Get search results](/generative-ai-app-builder/docs/preview-search-results). For client library resources, see [AI Applications client\n libraries](/generative-ai-app-builder/docs/libraries).\n\n### [Maintain your app](#maintain-data)\n\nYou can maintain your app to ensure that latest and necessary data is available\nin your data store.\n\n### Actions\n\n1. [Refresh your structured\n data](/generative-ai-app-builder/docs/refresh-data#refresh-structured)."]]
