Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Dokumen ini mencantumkan kuota dan batas sistem yang berlaku untuk
Aplikasi AI.
Kuota menentukan jumlah resource bersama yang dapat dihitung yang dapat Anda
gunakan. Kouta ditentukan oleh Google Cloud layanan seperti
Aplikasi AI.
Batas sistem adalah nilai tetap yang tidak dapat diubah.
Google Cloud menggunakan kuota untuk membantu memastikan keadilan dan mengurangi lonjakan penggunaan dan ketersediaan resource. Kuota membatasi jumlah
Google Cloud resource yang dapat digunakan Google Cloud project Anda. Kuota
berlaku untuk berbagai jenis resource, termasuk komponen hardware, software, dan jaringan. Misalnya, kuota dapat membatasi jumlah panggilan API ke suatu layanan, jumlah load balancer yang digunakan secara bersamaan oleh project Anda, atau jumlah project yang dapat Anda buat. Kuota melindungi komunitas penggunaGoogle Cloud dengan mencegah kelebihan beban layanan. Kuota juga membantu Anda mengelola resource Anda sendiri. Google Cloud
Sistem Kuota Cloud melakukan hal berikut:
Memantau penggunaan Google Cloud produk dan layanan
Dalam sebagian besar kasus, saat Anda mencoba menggunakan resource lebih banyak daripada yang diizinkan kuotanya, sistem akan memblokir akses ke resource tersebut, dan tugas yang Anda coba lakukan akan gagal.
Kuota umumnya berlaku di level Google Cloud project. Penggunaan resource dalam satu project tidak memengaruhi kuota yang tersedia di project lain. Dalam project Google Cloud , kuota
dibagikan ke semua aplikasi dan alamat IP.
Ada juga batas sistem pada resource Aplikasi AI.
Batas sistem tidak dapat diubah.
Kuota alokasi
Kuota berikut tidak direset dari waktu ke waktu. Sebaliknya, kuota tersebut akan dilepaskan saat Anda
merilis resource. Anda dapat meminta penambahan kuota
jika kuota default tidak cukup.
Kuota
Nilai
Jumlah dokumen per project
10.000.000
Jumlah penyimpanan data per project
100*
Jumlah mesin per project
150†
Jumlah operasi lama impor yang tertunda per project
300
Jumlah operasi yang berjalan lama untuk menghapus dokumen yang tertunda per project
100
Jumlah kontrol penayangan per project
1.000
Jumlah kontrol inferensi peningkat per konfigurasi inferensi
100
Jumlah kontrol penayangan filter per konfigurasi penayangan
100
Jumlah kontrol penayangan pengalihan per konfigurasi penayangan
100
Jumlah kontrol penayangan sinonim per konfigurasi penayangan
100
Jumlah peristiwa pengguna per project
40.000.000.000
Jumlah penyimpanan data regional per project per lokasi untuk Global atau global
100
Jumlah penyimpanan data regional per project per lokasi untuk multi-region Uni Eropa atau eu
100
Jumlah penyimpanan data regional per project per lokasi untuk multi-region AS atau us
100
Jumlah dokumen regional per project per lokasi untuk Global atau global
10.000.000
Jumlah dokumen regional per project per lokasi untuk multi-region Uni Eropa atau eu
10.000.000
Jumlah dokumen regional per project per lokasi untuk multi-region AS atau us
10.000.000
Jumlah mesin regional per project per lokasi untuk Global atau global
150
Jumlah mesin per project per lokasi regional untuk multi-region Uni Eropa atau eu
150
Jumlah mesin per project per lokasi regional untuk multi-region AS atau us
150
Jumlah peristiwa pengguna regional per project per lokasi untuk Global atau global
40.000.000.000
Jumlah peristiwa pengguna regional per project per lokasi untuk multi-region Uni Eropa atau eu
40.000.000.000
Jumlah peristiwa pengguna regional per project per lokasi untuk multi-region AS atau us
40.000.000.000
* Karena keterbatasan teknis, kuota maksimum untuk penyimpanan data adalah
500 per project. Jika Anda memerlukan penyimpanan data lainnya, gunakan project baru.
† Karena keterbatasan teknis, kuota maksimum untuk mesin adalah 500 per project. Jika Anda memerlukan lebih banyak mesin, gunakan project baru.
Kuota kapasitas
Kuota berikut berlaku untuk permintaan AI Applications API. Anda dapat meminta penambahan kuota jika kuota default tidak mencukupi.
Kuota
Nilai
Permintaan kueri lengkap per menit per project
300
Permintaan baca penelusuran percakapan per menit per project
300
Permintaan tulis penelusuran percakapan per menit per project
300
Permintaan batch dokumen (seperti impor dan penghapusan langsung) per menit per project
100
Mendokumentasikan permintaan impor asinkron (Cloud Storage, BigQuery, dll.) per menit per project
5
Permintaan penghapusan dokumen per menit per project
100
Permintaan baca dokumen per menit per project
300
Permintaan tulis dokumen per menit per project
12.000
Permintaan pembuatan evaluasi per hari per project
5
Permintaan baca evaluasi per menit per project
100
Permintaan tulis evaluasi per menit per project
100
Permintaan kueri LLM (ringkasan penelusuran, penelusuran multi-turn) per menit per project
60
Jumlah penulisan streaming FHIR atau BigQuery yang tertunda per menit
6.000
Jumlah set kueri contoh per project
100
Permintaan Ranking API per menit per project
500
Permintaan rekomendasi per menit per project
60.000
Contoh permintaan baca kueri per menit per project
200
Permintaan baca set kueri contoh per menit per project
100
Permintaan tulis set kueri contoh per menit per project
100
Contoh permintaan tulis kueri per menit per project
200
Permintaan baca skema per menit per project
100
Permintaan tulis skema per menit per project
100
Permintaan penelusuran per menit per project
300
Permintaan batch peristiwa pengguna (seperti impor dan penghapusan) per menit per project
100
Permintaan pengumpulan peristiwa pengguna per menit per project per pengguna
240
Permintaan tulis peristiwa pengguna per menit per project
60.000
Kuota untuk pengindeksan halaman web
Jika Anda memiliki penyimpanan data dengan
Pengindeksan situs lanjutan
diaktifkan, setiap halaman web yang Anda indeks akan diperhitungkan dalam kuota "Jumlah dokumen per project" dalam daftar Kuota alokasi. Anda juga dapat melihat jumlah halaman dalam project dan kuota halaman untuk project tersebut di kolom Halaman project vs. kuota di halaman Data untuk penyimpanan data.
Jika Anda menambahkan situs ke penyimpanan data dalam project dan halaman web di situs tersebut melebihi kuota project, situs tersebut tidak akan diindeks. Jika Anda memiliki situs di penyimpanan data yang sudah diindeks, situs tersebut akan terus diindeks seperti sebelumnya. Anda dapat meminta untuk mengupgrade kuota kapan saja.
Meminta penambahan kuota
Untuk menyesuaikan sebagian besar kuota, gunakan konsol Google Cloud .
Untuk mengetahui informasi selengkapnya, lihat
Meminta penyesuaian kuota.
[[["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\u003eQuotas define the amount of shared resources, like hardware, software, and network components, that a Google Cloud project can use within Vertex AI Agent Builder, and they are set by Google Cloud services to ensure fairness and prevent overloading.\u003c/p\u003e\n"],["\u003cp\u003eSystem limits are fixed constraints on Vertex AI Agent Builder resources that cannot be altered, unlike quotas, which can be increased upon request.\u003c/p\u003e\n"],["\u003cp\u003eThere are two types of quotas detailed: allocation quotas, which are released when the resource is no longer in use and include limits like the number of documents or data stores per project, and request quotas, which apply to API requests and involve limits on requests like document read/write, search, and user events per minute.\u003c/p\u003e\n"],["\u003cp\u003eIndexing web pages in a data store with Advanced website indexing enabled counts towards the "Number of documents per project" quota, and exceeding this quota will prevent new web pages from being indexed, though already indexed pages will continue as before.\u003c/p\u003e\n"],["\u003cp\u003eYou can request increases to most quotas, but system limits cannot be modified, and you can go to the "Request a quota adjustment" page on the Google cloud console for more information.\u003c/p\u003e\n"]]],[],null,["This document lists the quotas and system limits that apply to\nAI Applications.\n\n- *Quotas* specify the amount of a countable, shared resource that you can use. Quotas are defined by Google Cloud services such as AI Applications.\n- *System limits* are fixed values that cannot be changed.\n\nGoogle Cloud uses quotas to help ensure fairness and reduce\nspikes in resource use and availability. A quota restricts how much of a\nGoogle Cloud resource your Google Cloud project can use. Quotas\napply to a range of resource types, including hardware, software, and network\ncomponents. For example, quotas can restrict the number of API calls to a\nservice, the number of load balancers used concurrently by your project, or the\nnumber of projects that you can create. Quotas protect the community of\nGoogle Cloud users by preventing the overloading of services. Quotas also\nhelp you to manage your own Google Cloud resources.\n\nThe Cloud Quotas system does the following:\n\n- Monitors your consumption of Google Cloud products and services\n- Restricts your consumption of those resources\n- Provides a way to [request changes to the quota value](/docs/quotas/help/request_increase) and [automate quota adjustments](/docs/quotas/quota-adjuster)\n\nIn most cases, when you attempt to consume more of a resource than its quota\nallows, the system blocks access to the resource, and the task that\nyou're trying to perform fails.\n\nQuotas generally apply at the Google Cloud project\nlevel. Your use of a resource in one project doesn't affect\nyour available quota in another project. Within a Google Cloud project, quotas\nare shared across all applications and IP addresses.\n\n\nThere are also *system limits* on AI Applications resources.\nSystem limits can't be changed.\n| **Note:** Google Cloud products that use the Discovery Engine API, AI Applications (also known as Vertex AI Search) and Google Agentspace, share quotas. This means that your search and recommendations apps in Vertex AI Search share quotas with your apps in Google Agentspace.\n\nAllocation quotas\n\nThe following quotas don't reset over time. Instead, they're released when you\nrelease the resource. You can [request a quota increase](#request-a-quota-increase)\nif the default quota isn't enough.\n\n| Quota | Value |\n|--------------------------------------------------------------------------|----------------|\n| Total number of data stores per project | 100^\\*^ |\n| Total number of engines per project | 150^†^ |\n| Number of pending import long running operations per project | 300 |\n| Number of pending purge documents long running operations per project | 100 |\n| Number of serving controls per project | 1,000 |\n| Number of boost serving controls per serving config | 100 |\n| Number of filter serving controls per serving config | 100 |\n| Number of redirect serving controls per serving config | 100 |\n| Number of synonym serving controls per serving config | 100 |\n| Regional number of data stores per project per location (Global, US, EU) | 100 |\n| Regional number of documents per project per location (Global, US, EU) | 10,000,000 |\n| Regional number of engines per project per location (Global, US, EU) | 150 |\n| Regional number of user events per project per location (Global, US, EU) | 40,000,000,000 |\n\n\n^\\*^ Due to a technical limitation, the maximum quota for data stores is\n500 per project. If you need more data stores, use new projects.\n\n\n^†^ Due to a technical limitation, the maximum quota for engines is 500\nper project. If you need more engines, use new projects.\n| **Note:** The number of data stores, documents, user events, and engines across all locations can't exceed the total per-project quota for that resource. For example, if you already have 60 data stores in the `eu` multi-region and 40 in the `us` multi-region, you can't create another data store because the overall data store quota for the project is 100.\n\nRate quotas\n\nThe following quotas apply to AI Applications API requests. You can\n[request a quota increase](#request-a-quota-increase) if the default quota\nisn't enough.\n\n| Quota | Value |\n|---------------------------------------------------------------------------------------|--------|\n| Complete query requests per minute per project | 300 |\n| Conversational search read requests per minute per project | 300 |\n| Conversational search write requests per minute per project | 300 |\n| Document batch requests (such as inline import and purge) per minute per project | 100 |\n| Document async import (Cloud Storage, BigQuery, etc.) requests per minute per project | 5 |\n| Document purge requests per minute per project | 100 |\n| Document read requests per minute per project | 300 |\n| Document write requests per minute per project | 12,000 |\n| Evaluation create requests per day per project | 5 |\n| Evaluation read requests per minute per project | 100 |\n| Evaluation write requests per minute per project | 100 |\n| LLM query requests (search summarization, multi-turn search) per minute per project | 60 |\n| Number of pending FHIR or BigQuery streaming writes per minute | 6,000 |\n| Number of sample query sets per project | 100 |\n| Ranking API requests per minute per project | 500 |\n| Recommend requests per minute per project | 60,000 |\n| Sample query read requests per minute per project | 200 |\n| Sample query set read requests per minute per project | 100 |\n| Sample query set write requests per minute per project | 100 |\n| Sample query write requests per minute per project | 200 |\n| Schema read requests per minute per project | 100 |\n| Schema write requests per minute per project | 100 |\n| Regional search requests per minute per project per location (Global, US, EU) | 300 |\n| User event batch requests (such as import and purge) per minute per project | 100 |\n| User event collect requests per minute per project per user | 240 |\n| User event write requests per minute per project | 60,000 |\n\nQuota for web page indexing\n\nWhen you have a data store with\n[Advanced website indexing](/generative-ai-app-builder/docs/about-advanced-features#advanced-website-indexing)\nturned on, every web page that you index counts towards the \"Number of documents\nper project\" quota in the [Allocation quotas](#allocation-quotas) list. You can\nalso see the number of pages in your project and the page quota for that project\nin the **Project pages vs quota** field in the **Data** page for a data store.\n\nIf you add websites to a data store in a project and the web pages in those\nwebsites exceed the project's quota, the websites are not\nindexed. If you have websites in your data store that are already indexed, those\nwebsites continue to be indexed as before. You can request to [upgrade your\nquota](#request-a-quota-increase) at any time.\n\nRequest a quota increase\n\nTo adjust most quotas, use the Google Cloud console.\nFor more information, see\n[Request a quota adjustment](/docs/quotas/help/request_increase)."]]
