Siapkan project, aktifkan Aplikasi AI, dan siapkan kontrol akses untuk project Anda. Google Cloud Anda dapat menggunakan project yang sudah ada jika Anda sudah memilikinya. Google Cloud
Tindakan
Tinjau Sebelum memulai dan pastikan Anda telah menyelesaikan langkah-langkahnya.
Bersiap untuk mengimpor data FHIR R4 sumber dari penyimpanan data Cloud Healthcare API ke penyimpanan data Vertex AI Search.
Tindakan
Tinjau informasi tentang data yang didukung dan hubungan antara aplikasi penelusuran layanan kesehatan dan penyimpanan data di Tentang aplikasi dan penyimpanan data.
Vertex AI Search menyediakan opsi untuk menyesuaikan widget penelusuran Anda.
Tindakan
Bergantung pada kasus penggunaan Anda dan apakah Anda berencana men-deploy widget penelusuran siap pakai atau mengintegrasikan panggilan API penelusuran ke dalam kode Anda sendiri, Vertex AI Search menyediakan beberapa opsi untuk konfigurasi.
Hasil widget penelusuran. Pilih apakah akan melakukan penelusuran dasar atau
menelusuri dengan jawaban menggunakan LLM. Berlaku untuk widget penelusuran. Lihat
Mengonfigurasi hasil untuk widget penelusuran.
Pelengkapan otomatis. Siapkan saran pelengkapan otomatis untuk menerima saran kueri yang bermanfaat. Lihat
Mengonfigurasi perlengkapan otomatis.
Lihat pratinjau hasil penelusuran Anda untuk memeriksa apakah konfigurasi aplikasi Anda berfungsi seperti yang diharapkan. Anda dapat melakukan penelusuran menggunakan kata kunci dan kueri bahasa alami.
Anda juga dapat memilih untuk mendapatkan jawaban AI generatif.
Lihat pratinjau hasil penelusuran Anda, menggunakan konsol atau API.
Konsol. Gunakan halaman Pratinjau konsol Aplikasi AI untuk melihat pratinjau pengaruh konfigurasi widget penelusuran terhadap hasil Anda. Lihat petunjuk Console
di Menelusuri data layanan kesehatan.
API. Jika Anda mengintegrasikan panggilan API ke dalam aplikasi, lakukan panggilan API untuk melihat pratinjau konfigurasi penelusuran Anda. Lihat petunjuk REST
di Menelusuri data layanan kesehatan.
Jika Anda berencana men-deploy aplikasi dengan mengintegrasikan panggilan API penelusuran ke dalam kode Anda sendiri, Vertex AI Search memungkinkan Anda menyesuaikan hasilnya.
Tindakan
Konfigurasi permintaan penelusuran Anda dengan opsi berikut:
Jika Anda puas dengan versi pratinjau aplikasi penelusuran, 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 Anda. Untuk mengetahui informasi selengkapnya tentang melakukan panggilan API, lihat Menelusuri data kesehatan. Untuk
resource library klien, lihat Library klien Aplikasi AI.
Anda dapat memelihara aplikasi untuk memastikan data terbaru dan yang diperlukan tersedia
di penyimpanan data Anda.
Tindakan
Untuk memperbarui data Anda, lihat Memperbarui data layanan kesehatan.
Perbarui data hanya jika Anda melakukan impor batch. Anda dapat melewati langkah ini jika telah menyiapkan impor streaming.
[[["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 2025-09-03 UTC."],[[["\u003cp\u003eThis page outlines the steps to build a healthcare search app using Vertex AI Search, beginning with setting up a Google Cloud project.\u003c/p\u003e\n"],["\u003cp\u003eThe process involves preparing and importing FHIR R4 data from a Cloud Healthcare API data store into a Vertex AI Search data store.\u003c/p\u003e\n"],["\u003cp\u003eAfter creating the app and connecting it to the data store, users can configure search settings, including widget results and autocomplete suggestions.\u003c/p\u003e\n"],["\u003cp\u003eUsers can preview search results and tailor them to fit specific requirements, such as filtering, before deploying the app to a website or integrating it with other code.\u003c/p\u003e\n"],["\u003cp\u003eThe final step is to maintain the app by refreshing data, which is necessary when performing batch imports, but can be skipped when using a streaming import setup.\u003c/p\u003e\n"]]],[],null,["# Healthcare search checklist\n\nThis page provides a checklist of the steps required to implement a healthcare search 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. Review [Before you begin](/generative-ai-app-builder/docs/before-you-begin) and confirm that you have completed the steps. \n\n### [Prepare your data](#prepare-data)\n\nPrepare to import your source FHIR R4 data from a Cloud Healthcare API data store\nto your Vertex AI Search data store.\n\n### Actions\n\n1. Review the information about supported data and the relationship between\n healthcare search apps and data stores in [About apps and data\n stores](/generative-ai-app-builder/docs/create-datastore-ingest).\n\n2. Prepare your source data according to the requirements in\n [Prepare data for ingestion](/generative-ai-app-builder/docs/prepare-data#hc-fhir-data).\n\n### [Import your data](#import-data)\n\nCreate a data store and then import your data into it. You can perform a\none-time batch import or set up a streaming import.\n\n### Actions\n\n1. To create a data store and import data into it and later connect it to a healthcare search app, follow the instructions in [Create a healthcare search data\nstore](/generative-ai-app-builder/docs/create-data-store-hc). \n\n### [Create your app](#create-app)\n\nCreate your healthcare search app and connect it to your new data store.\n\n### Actions\n\n1. [Create a healthcare search app](/generative-ai-app-builder/docs/create-app-hc). \n\n### [Configure your search\nsettings](#configure-settings)\n\nVertex AI Search provides options to customize your 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\n- **Search widget results.** Select the whether to perform a basic search or\n to search with an answer using LLMs. Applicable for a search widget. See\n [Configure results for the search widget](/generative-ai-app-builder/docs/configure-widget-attributes).\n\n- **Autocomplete.** Set up autocomplete suggestions to receive helpful query\n suggestions. See\n [Configure autocomplete](/generative-ai-app-builder/docs/configure-autocomplete).\n\n### [Preview search\nresults](#preview-results)\n\nPreview your search results to check if your app configurations are\nworking as expected. You can search using keywords and natural language queries.\nYou can also choose to get a generative AI answer.\n\n### Actions\n\n1. Review the subset of FHIR resources, resource references, and elements that\n Vertex AI Search supports. See\n [Healthcare FHIR R4 data schema reference](/generative-ai-app-builder/docs/fhir-schema-reference).\n\n2. Preview your search results, using the console or the API.\n\n - **Console.** Use the AI Applications console **Preview** page to preview how\n search widget configurations affect your results. See the **Console**\n instructions in [Search healthcare data](/generative-ai-app-builder/docs/search-hc-data).\n\n - **API** . If you're integrating API calls into your application, make\n API calls to preview your search configurations. See the **REST**\n instructions in [Search healthcare data](/generative-ai-app-builder/docs/search-hc-data).\n\n### [Filter your search\nresults](#configure-results)\n\nIf you plan to deploy your app by integrating search API calls into your own\ncode, Vertex AI Search lets you customize the results.\n\n### Actions\n\nConfigure your search requests with the following options:\n\n- **Filter results.** See [Filter healthcare search](/generative-ai-app-builder/docs/filter-hc-search). \n\n### [Deploy your search\napp](#preview-results)\n\nWhen you are happy with the preview version of your search app, share it with\nyour 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. See\n [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 API\n calls, see [Search healthcare data](/generative-ai-app-builder/docs/search-hc-data). For\n 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. To refresh your data, see [Refresh healthcare data](/generative-ai-app-builder/docs/refresh-hc-data). Refresh your data only if you perform batch imports. You can skip this step if you have set up a streaming import."]]
