Mendapatkan hasil penjelajahan yang dipersonalisasi
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Penjelajahan menggunakan metode navigasi untuk menampilkan hasil penelusuran yang cocok dengan kategori atau filter yang dipilih pengguna akhir. Penjelajahan menampilkan hasil yang dapat dipersonalisasi.
Halaman ini menjelaskan cara mendapatkan hasil penjelajahan untuk penyimpanan data penelusuran umum.
Tentang penjelajahan
Di aplikasi penelusuran AI Applications, menjelajah berarti menelusuri tanpa kueri atau dengan kueri kosong. Jika Anda memiliki penyimpanan data penelusuran umum yang
berisi data terstruktur, data tidak terstruktur dengan metadata, atau data situs, Anda
dapat mengirim kueri
penelusuran kosong untuk menerima hasil penjelajahan.
Saat Anda mengirim permintaan penjelajahan, dokumen di penyimpanan data Anda yang cocok dengan filter akan ditampilkan sesuai dengan sinyal berbasis peristiwa. Anda dapat
memberikan pengalaman penjelajahan yang lebih baik dengan melakukan hal berikut:
Gunakan filter dalam permintaan penelusuran Anda untuk mempersempit hasil penelusuran. Jika Anda menggunakan pengindeksan situs lanjutan, lihat Menggunakan data terstruktur untuk pengindeksan situs lanjutan untuk memahami cara menambahkan metadata dalam skema dan menggunakannya untuk memperkaya filter dan kolom boost.
Tambahkan spesifikasi peningkat untuk memengaruhi urutan hasil yang ditampilkan dengan
meningkatkan atau menyembunyikan hasil tertentu.
Pahami peristiwa pengguna dan catat peristiwa tersebut. Google menggunakan peristiwa pengguna Anda untuk mengoptimalkan peringkat hasil berdasarkan rasio klik-tayang.
Perbedaan antara penjelajahan dan penelusuran
Tabel berikut menyajikan perbedaan antara penelusuran dan penjelajahan.
Fitur
Telusuri
Jelajahi
Tujuan
Menemukan informasi tertentu
Menjelajahi dan menemukan konten
Contoh
Menelusuri "restoran Korea terbaik di Vancouver" di Google Penelusuran
Menjelajahi restoran berdasarkan kategori tempat restoran tersebut berada, seperti "Restoran > Korea > Vancouver > Bintang 4 ke atas"
User
Intent
Biasanya berorientasi pada sasaran
Eksploratif
Titik
awal
Kueri atau kata kunci
biasanya ada di kotak penelusuran
Situs atau platform tertentu biasanya menggunakan menu, breadcrumb, link, atau metode navigasi lainnya seperti aspek
Metode
Memasukkan kata kunci atau frasa dan menerapkan konfigurasi penelusuran dan penayangan
Menelusuri dengan kueri kosong, menerapkan
konfigurasi penelusuran dan penayangan
Hasil
Daftar hasil yang relevan
Semua dokumen di penyimpanan data yang
cocok dengan filter
Mendapatkan hasil penjelajahan untuk aplikasi dengan data situs
Untuk menggunakan API guna mendapatkan hasil penjelajahan untuk aplikasi dengan data situs,
Temukan ID aplikasi Anda. Jika Anda sudah memiliki ID aplikasi, lanjutkan ke langkah berikutnya.
Di konsol Google Cloud , buka halaman AI Applications.
[[["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."],[],[],null,["# Get personalized browse results\n\nBrowsing uses navigational methods to display search results that match\nthe end user's selected categories or filters. Browsing returns results that can be\npersonalized.\nThis page describes how to get browse results for generic search data stores.\n\nAbout browse\n------------\n\nIn an AI Applications search app, to browse is to search with\nno query or an empty query. If you have a generic search data store that\ncontains structured data, unstructured data with metadata, or website data, you\ncan send an empty search\nquery to receive browse results.\n\nWhen you send a browse request, the documents in your data store that match\nthe filters are returned according to event-based signals. You can\ndeliver an enhanced browsing experience by doing the following:\n\n- Use filters in your search request to narrow down the search results. If you use advanced website indexing, see [Use structured data for advanced website\n indexing](/generative-ai-app-builder/docs/add-website-metadata) to understand how to add metadata in your schema and use it to enrich your filter and boost fields.\n- Add a boost specification to influence the order of the returned results by boosting or burying specific results.\n- Understand user events and record them. Google uses your user events to optimize result ranking for click-through rate.\n\nHow browse differs from search\n------------------------------\n\nThe following table presents the differences between searching and browsing.\n\nGet browse results for an app with website data\n-----------------------------------------------\n\nTo use the API to get browse results for an app with website data,\n\n1. Find your app ID. If you already have your app ID, skip to the next step.\n\n 1. In the Google Cloud console, go to the **AI Applications** page.\n\n [Go to Apps](https://console.cloud.google.com/gen-app-builder/engines)\n 2. On the **Apps** page, find the name of your app and get the app's ID from\n the **ID** column.\n\n2. Call the [`engines.servingConfigs.search`](/generative-ai-app-builder/docs/reference/rest/v1/projects.locations.collections.engines.servingConfigs/search) method with an\n empty query or no query as follows:\n\n\n ### REST\n\n \u003cbr /\u003e\n\n **Key Term:** In Vertex AI Search, the term *app* can be used interchangeably with the term *engine* in the context of APIs. \n\n curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n -H \"Content-Type: application/json\" \\\n \"https://discoveryengine.googleapis.com/v1/projects/\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e/locations/global/collections/default_collection/engines/\u003cvar translate=\"no\"\u003eAPP_ID\u003c/var\u003e/servingConfigs/default_search:search\" \\\n -d '{\n \"servingConfig\": \"projects/\u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e/locations/global/collections/default_collection/engines/\u003cvar translate=\"no\"\u003eAPP_ID\u003c/var\u003e/servingConfigs/default_search\",\n \"orderBy\": \"\u003cvar translate=\"no\"\u003eORDER_BY\u003c/var\u003e\",\n \"params\": {\n \"searchType\": \"0\"\n },\n \"filter\": \"\u003cvar translate=\"no\"\u003eFILTER\u003c/var\u003e\",\n \"boostSpec\": \"\u003cvar translate=\"no\"\u003eBOOST_SPEC\u003c/var\u003e\",\n }'\n\n Replace the following:\n - \u003cvar translate=\"no\"\u003ePROJECT_ID\u003c/var\u003e: the ID of your Google Cloud project.\n - \u003cvar translate=\"no\"\u003eAPP_ID\u003c/var\u003e: the ID of the Vertex AI Search app that you want to query.\n - \u003cvar translate=\"no\"\u003eORDER_BY\u003c/var\u003e: optional. The order in which the results are arranged. The attribute to sort on must have a numerical interpretation---for example, `date`. For more information, see [Order web search\n results](/generative-ai-app-builder/docs/order-web-search-results).\n - \u003cvar translate=\"no\"\u003eFILTER\u003c/var\u003e: optional but recommended. A text field for filtering your search using a filter expression. The default value is an empty string. For more information about using the `filter` field, see [Filter generic search\n for structured or unstructured data](/generative-ai-app-builder/docs/filter-search-metadata) and [Filter website search](/generative-ai-app-builder/docs/filter-website-search).\n - \u003cvar translate=\"no\"\u003eBOOST_SPEC\u003c/var\u003e: optional. A specification to boost or bury documents. Values:\n - `BOOST`: a floating point number in the range \\[-1,1\\]. When the value is negative, results are demoted (they appear lower down in the results). When the value is positive, results are promoted (they appear higher up in the results).\n - `CONDITION`: a [text filter expression](/generative-ai-app-builder/docs/filter-search-metadata#filter-expression-syntax) to select the documents to which boost is applied. The filter must evaluate to a boolean value. To learn about boost for structured search, see [Boost search results](/generative-ai-app-builder/docs/boost-search-results).\n\n You should receive a JSON response similar to the following truncated response.\n The response contains itemized search results listed in the order that's\n determined by the fields set in the search request.\n\n #### Response\n\n ```\n {\n \"results\": [\n {\n \"id\": \"DOCUMENT_ID\",\n \"document\": {\n \"name\": \"projects/PROJECT_ID/locations/global/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/documents/DOCUMENT_ID\",\n \"id\": \"DOCUMENT_ID\",\n \"structData\": {},\n \"derivedStructData\": {\n \"displayLink\": \"LINK_TO_BE_DISPLAYED\",\n \"link\": \"DOCUMENT_URL\",\n …\n }\n }\n },\n {\n \"id\": \"DOCUMENT_ID\",\n \"document\": {\n \"name\": \"projects/PROJECT_ID/locations/global/collections/default_collection/dataStores/DATA_STORE_ID/branches/0/documents/DOCUMENT_ID\",\n \"id\": \"DOCUMENT_ID\",\n \"structData\": {},\n \"derivedStructData\": {\n \"displayLink\": \"LINK_TO_BE_DISPLAYED\",\n \"link\": \"DOCUMENT_URL\",\n …\n }\n }\n }\n …\n ]\n }\n ```\n\n \u003cbr /\u003e\n\n\u003cbr /\u003e"]]
