Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Endpoint global dan multi-regional
Cloud Translation - Advanced menawarkan endpoint global serta endpoint multiregional Uni Eropa dan AS:
translate.googleapis.com(global)
translate-eu.googleapis.com
translate-us.googleapis.com
Jika Anda menggunakan endpoint multiwilayah, data dalam penyimpanan dan pemrosesan machine learning Anda akan tetap berada dalam batas kontinental Uni Eropa atau Amerika Serikat. Endpoint multiwilayah ini penting jika lokasi data Anda harus dikontrol untuk mematuhi persyaratan peraturan setempat.
Jika Anda tidak menentukan endpoint, Cloud Translation - Advanced akan menggunakan endpoint global secara default.
Endpoint global versus multi-regional
Saat menggunakan endpoint multi-regional, ada beberapa perbedaan jika dibandingkan dengan menggunakan endpoint global:
Terjemahan teks yang menggunakan model AutoML kustom tidak didukung.
Anda hanya dapat menggunakan model NMT terlatih.
Fitur yang bukan GA (masih dalam Pratinjau) tidak didukung.
Panggilan melalui endpoint global tidak dapat mengakses resource yang dibuat menggunakan endpoint multi-regional. Demikian pula, panggilan melalui endpoint
multi-regional tidak dapat mengakses resource yang dibuat menggunakan endpoint global.
Membatasi lokasi resource
Administrator kebijakan organisasi dapat membatasi region yang tersedia untuk Cloud Translation - Resource lanjutan dengan membuat batasan lokasi resource. Jika ditetapkan, Cloud Translation - Pengguna tingkat lanjut akan dapat membuat resource hanya di lokasi tertentu.
Membatasi penggunaan endpoint API global
Untuk membantu menerapkan penggunaan endpoint regional, administrator kebijakan organisasi dapat menggunakan batasan kebijakan organisasi constraints/gcp.restrictEndpointUsage untuk memblokir permintaan ke endpoint API global. Untuk mengetahui informasi selengkapnya, lihat Membatasi penggunaan endpoint.
Menentukan endpoint
Contoh berikut menunjukkan terjemahan teks yang menggunakan endpoint
multi-regional. Jika Anda menggunakan library klien, tetapkan endpoint API sebagai bagian dari
opsi klien. Untuk beberapa contohnya, lihat Menetapkan lokasi menggunakan library klien dalam panduan Cloud Natural Language API.
REST
Sebelum menggunakan salah satu data permintaan,
lakukan penggantian berikut:
PROJECT_NUMBER_OR_ID: ID numerik atau alfanumerik untuk project Google Cloud Anda
ENDPOINT: Endpoint regional, yang menentukan tempat data Anda berada. Contoh, translate-eu.googleapis.com.
LOCATION: Region tempat Anda ingin menjalankan operasi ini. Anda harus memilih region di dalam batas benua untuk endpoint regional. Misalnya, jika Anda menggunakan endpoint translate-eu.googleapis.com,
tentukan region di Eropa seperti europe-west1.
Metode HTTP dan URL:
POST https://ENDPOINT/v3/projects/PROJECT_NUMBER_OR_ID/locations/LOCATION:translateText
[[["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 2025-09-01 UTC."],[],[],null,["# Global and multi-regional endpoints\n===================================\n\nCloud Translation - Advanced offers a global endpoint as well as EU and US\nmulti-regional endpoints:\n\n- `translate.googleapis.com` (global)\n- `translate-eu.googleapis.com`\n- `translate-us.googleapis.com`\n\nIf you use a multi-regional endpoint, your data at-rest and machine learning\nprocessing stays within the continental boundaries of the EU or US. These\nmulti-regional endpoints are important if your data's location must be\ncontrolled to comply with local regulatory requirements.\n\nIf you don't specify an endpoint, Cloud Translation - Advanced uses the global\nendpoint by default.\n\nGlobal versus multi-regional endpoints\n--------------------------------------\n\nWhen using a multi-regional endpoint, there are some difference when compared to\nusing the global endpoint:\n\n- Text translations that use custom AutoML models are not supported. You can use only the pre-trained NMT model.\n- Features that are not GA (still in [Preview](/products#product-launch-stages)) are not supported.\n- Calls through the global endpoint cannot access resources that were created by using a multi-regional endpoint. Similarly, calls through a multi-regional endpoint cannot access resources that were created by using the global endpoint.\n\nRestricting resource locations\n------------------------------\n\nOrganization policy administrators can restrict the regions available for\nCloud Translation - Advanced resources by [creating a resource locations\nconstraint](/resource-manager/docs/organization-policy/defining-locations). If\nset, Cloud Translation - Advanced users would be able to create resources only in a\nparticular location.\n\nRestricting global API endpoint usage\n-------------------------------------\n\nTo help enforce the use of regional endpoints, organization policy\nadministrators can use the `constraints/gcp.restrictEndpointUsage` organization\npolicy constraint to block requests to the global API endpoint. For more\ninformation, see [Restricting endpoint\nusage](/assured-workloads/docs/restrict-endpoint-usage).\n\nSpecify an endpoint\n-------------------\n\nThe following example shows a text translation that uses a multi-regional\nendpoint. If you use the client libraries, set the API endpoint as part of the\nclient options. For some examples, see [Setting the location using client\nlibraries](/natural-language/docs/locations#setting_the_location_using_client_libraries)\nin the Cloud Natural Language API guide. \n\n### REST\n\n\nBefore using any of the request data,\nmake the following replacements:\n\n- \u003cvar translate=\"no\"\u003ePROJECT_NUMBER_OR_ID\u003c/var\u003e: the numeric or alphanumeric ID of your Google Cloud project\n- \u003cvar translate=\"no\"\u003eENDPOINT\u003c/var\u003e: Regional endpoint, which determines where your data resides. For example, `translate-eu.googleapis.com`.\n- \u003cvar translate=\"no\"\u003eLOCATION\u003c/var\u003e: Region where you want to run this operation. You must pick a region inside the continental boundary of the regional endpoint. For example, if you use the `translate-eu.googleapis.com` endpoint, specify a region in Europe such as `europe-west1`.\n\n\nHTTP method and URL:\n\n```\nPOST https://ENDPOINT/v3/projects/PROJECT_NUMBER_OR_ID/locations/LOCATION:translateText\n```\n\n\nRequest JSON body:\n\n```\n{\n \"model\": \"projects/PROJECT_NUMBER_OR_ID/locations/LOCATION/models/general/base\",\n \"sourceLanguageCode\": \"en\",\n \"targetLanguageCode\": \"de\",\n \"contents\": [\"Come here!\"]\n}\n```\n\nTo send your request, choose one of these options: \n\n#### curl\n\n| **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](/sdk/gcloud/reference/init) or [`gcloud auth login`](/sdk/gcloud/reference/auth/login) , or by using [Cloud Shell](/shell/docs), which automatically logs you into the `gcloud` CLI . You can check the currently active account by running [`gcloud auth list`](/sdk/gcloud/reference/auth/list).\n\n\nSave the request body in a file named `request.json`,\nand execute the following command:\n\n```\ncurl -X POST \\\n -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n -H \"x-goog-user-project: PROJECT_NUMBER_OR_ID\" \\\n -H \"Content-Type: application/json; charset=utf-8\" \\\n -d @request.json \\\n \"https://ENDPOINT/v3/projects/PROJECT_NUMBER_OR_ID/locations/LOCATION:translateText\"\n```\n\n#### PowerShell\n\n| **Note:** The following command assumes that you have logged in to the `gcloud` CLI with your user account by running [`gcloud init`](/sdk/gcloud/reference/init) or [`gcloud auth login`](/sdk/gcloud/reference/auth/login) . You can check the currently active account by running [`gcloud auth list`](/sdk/gcloud/reference/auth/list).\n\n\nSave the request body in a file named `request.json`,\nand execute the following command:\n\n```\n$cred = gcloud auth print-access-token\n$headers = @{ \"Authorization\" = \"Bearer $cred\"; \"x-goog-user-project\" = \"PROJECT_NUMBER_OR_ID\" }\n\nInvoke-WebRequest `\n -Method POST `\n -Headers $headers `\n -ContentType: \"application/json; charset=utf-8\" `\n -InFile request.json `\n -Uri \"https://ENDPOINT/v3/projects/PROJECT_NUMBER_OR_ID/locations/LOCATION:translateText\" | Select-Object -Expand Content\n```\n\nYou should receive a JSON response similar to the following:\n\n```\n{\n \"translations\": [\n {\n \"translatedText\": \"Komm her!\",\n \"model\": \"projects/PROJECT_NUMBER_OR_ID/locations/LOCATION/models/general/base\"\n }\n ]\n}\n```\n\n\u003cbr /\u003e"]]
