Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Agent Assist menyediakan
residensi data
untuk menjaga data dalam penyimpanan
Anda secara fisik di dalam region atau lokasi geografis tertentu. Saat Anda menentukan
region, data dalam penyimpanan Anda tidak akan disimpan di luar region tersebut. Harga sama untuk semua wilayah.
Menentukan region sangat membantu dalam kasus penggunaan berikut:
Sistem Anda memiliki persyaratan peraturan atau kebijakan yang mengatur lokasi penyimpanan data Anda.
Latensi jaringan Anda mungkin ditingkatkan jika data berada di region yang sama dengan pelanggan Anda. Misalnya, jika pelanggan di Belgia menggunakan europe-west1, mereka dapat mengharapkan latensi yang lebih baik.
global (pilihan) atau tidak ada region (default) ¶
global (multi-region) ¶
Simbol
Deskripsi
*
Vertex AI tidak mendukung lokasi multi-region 'us'. Akibatnya, penggunaan fitur AI Generatif Agent Assist di multi-region 'us' akan mengandalkan endpoint single region AS yang ada.
¶
Panggilan ke wilayah global mungkin memiliki latensi yang lebih tinggi saat dipanggil dari luar Amerika Serikat. Sebaiknya pilih region yang lebih spesifik dan lebih dekat dengan layanan dan pengguna Anda, jika memungkinkan.
Fitur yang tersedia untuk penayangan regional
ID region
Perangkuman dengan bagian kustom v4.0
Perangkuman dengan bagian kustom v3.1/3.0
Analisis Sentimen
(Proaktif) Bantuan Pengetahuan Generatif
Buat Assist Anda Sendiri (Pratinjau)
us-central1
✓
✓
✓
✓
✓
us-east1
✓
✓
✓
✓
✓
us-west1
✓
✓
✓
✓
✓
us
✓
✓
✓
✓
✓
northamerica-northeast1
✓
✓
✓
✓
europe-west1
✓
✓
✓
✓
✓
europe-west2
✓
✓
✓
✓
europe-west3
✓
✓
✓
✓
europe-west4
✓
✓
✓
europe-west6
✓
✓
✓
asia-southeast1
✓
✓
✓
✓
asia-southeast2
✓
✓
✓
asia-northeast1
✓
✓
✓
✓
asia-south1
✓
✓
✓
✓
australia-southeast1
✓
✓
✓
✓
✓
global
✓
✓
✓
✓
✓
Data dalam penyimpanan
Semua data pengguna developer dan pengguna akhir Agent Assist disertakan dalam data saat istirahat.
Contoh:
Transkripsi CCAI hanya mendukung data yang digunakan dan data dalam penyimpanan multi-region (jika tidak menggunakan fitur Adaptasi Ucapan) di Uni Eropa, Amerika Serikat, Amerika Utara (Kanada).
Hanya region berikut yang didukung untuk penyimpanan data, yang digunakan oleh fitur Bantuan Pengetahuan Generatif (Proaktif): global, multi-region us, dan multi-region eu.
Menentukan region menggunakan API
Untuk menggunakan regionalisasi, Anda harus menentukan wilayah untuk setiap permintaan API.
Kolom wajib diisi:
Berikan ID wilayah untuk parameter jalur URL location.
Untuk region global, gunakan dialogflow.googleapis.com untuk
nama host. Untuk semua region lainnya, gunakan [region-id]-dialogflow.googleapis.com
untuk nama host.
Sebaiknya gunakan variabel lingkungan GOOGLE_APPLICATION_CREDENTIALS
untuk memberikan kredensial ke library klien Anda.
Lihat petunjuk penyiapan Dialogflow
untuk mengetahui informasi selengkapnya tentang cara menyetel variabel ini.
Jika Anda perlu memberikan kredensial manual dalam kode, satu langkah tambahan diperlukan sebelum Anda dapat memanggil endpoint yang dilokalkan. Anda harus menyetel
cakupan ke https://www.googleapis.com/auth/cloud-platform saat Anda membuat
kredensial autentikasi. Contoh berikut menunjukkan cara melakukannya di Java saat membuat objek GoogleCredentials:
[[["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."],[[["\u003cp\u003eAgent Assist offers data residency, ensuring your data-at-rest is stored within a specified geographical region you select.\u003c/p\u003e\n"],["\u003cp\u003eSpecifying a region can be crucial for systems with regulatory data location requirements or for improving network latency for customers in a specific area.\u003c/p\u003e\n"],["\u003cp\u003eData residency only applies to data-at-rest; it does not cover data-in-use or data-in-transit, so these will not be covered by this regionality.\u003c/p\u003e\n"],["\u003cp\u003eTo implement regionalization, you must specify a region ID in every API request and adjust the hostname accordingly, such as using \u003ccode\u003e[region-id]-dialogflow.googleapis.com\u003c/code\u003e instead of \u003ccode\u003edialogflow.googleapis.com\u003c/code\u003e for the global region.\u003c/p\u003e\n"],["\u003cp\u003eThe Agent Assist Console and Model training do not support regionalization, so it can only be done by calling the API directly, and model training may send data outside of the region.\u003c/p\u003e\n"]]],[],null,["# Regionalization and data residency\n\nAgent Assist provides\n[data residency](https://cloud.google.com/blog/products/identity-security/meet-data-residency-requirements-with-google-cloud)\nto keep your [data-at-rest](https://en.wikipedia.org/wiki/Data_at_rest)\nphysically within a specified geographical region or location. When you specify\na region, your data-at-rest is not stored outside that region. Pricing is the\nsame for all regions.\n\nSpecifying a region is particularly helpful in the following use cases:\n\n- Your system has regulatory or policy requirements that govern where your data must reside.\n- Your network latencies might be improved when the data is in the same region as your customers. For example, if Belgium customers use `europe-west1`, they can expect better latency.\n\n| **Important:** The [AI/ML data location](/terms/data-residency) (data residency for ML processing, or DRZ) commitment is only supported in locations in the US and EU. When requests are made to multi-region APIs, ML processing for generative models may occur in any of those regions. For non-AI/ML data (in use or transit) or data outside US and EU multi-regions, the DRZ commitment doesn't apply. For details, see the [Vertex AI documentation](/vertex-ai/generative-ai/docs/learn/locations).\n\nAvailable regions\n-----------------\n\nAvailable features for regional serving\n---------------------------------------\n\nData-at-rest\n------------\n\nAll Agent Assist developer user and end-user data is included in data-at-rest.\nFor example:\n\n- [Knowledge bases](/agent-assist/docs/knowledge-base) and [knowledge documents](/agent-assist/docs/knowledge-documents).\n- [Conversation profiles](/agent-assist/docs/basics#conversation_profiles).\n- [Conversation](/agent-assist/docs/basics#conversations) and message histories.\n- [Conversion participants](/agent-assist/docs/basics#participants).\n- Suggestions returned by Agent Assist.\n- [Feedbacks](/agent-assist/docs/feedback).\n\nLimitations\n-----------\n\nThe following limitations apply:\n\n- The **Agent Assist console** doesn't support regionalization. You can only implement regionalization by calling the API directly.\n- [Model training](/agent-assist/docs/model-training) does not support regionalization. Your data may get routed outside the region during this process.\n- [API Explorer](https://developers.google.com/explorer-help/), found on many\n [REST reference documents](/dialogflow/es/docs/reference/rest), only supports\n the `global` region for API calls.\n\n- [CCAI Transcription](/agent-assist/docs/transcription) only\n supports multi-region data in use and data at rest (if not using the Speech\n Adaptation feature) in EU, US, North America (Canada).\n\n- Only the following regions are supported for data stores, used by (Proactive) Generative Knowledge Assist feature: `global`, `us` multi-region, and `eu` multi-region.\n\nSpecify a region using the API\n------------------------------\n\nTo use regionalization you must specify a region for every API request.\n\nRequired fields:\n\n- Provide the region ID for the `location` URL path parameter.\n\n- For the `global` region, use `dialogflow.googleapis.com` for the\n hostname. For all other regions, use `[region-id]-dialogflow.googleapis.com`\n for the hostname.\n\nFor example:\n\n- `dialogflow.googleapis.com/v2/projects/project_id/locations/global/knowledgeBases/knowledge_base_id`\n\n- `us-central1-dialogflow.googleapis.com/v2/projects/project_id/locations/us-central1/knowledgeBases/knowledge_base_id`\n\nTo use [client libraries](/agent-assist/docs/reference-index), the following\nsteps are required:\n\n- Set the service endpoint to: `REGION_ID-dialogflow.googleapis.com`.\n- Set the resource name with the correct location, for example:\n\n projects/project_id/locations/region_id/knowledgeBases/knowledge_base_id\n\nCredentials\n-----------\n\nWe recommend that you use the \u003cvar translate=\"no\"\u003eGOOGLE_APPLICATION_CREDENTIALS\u003c/var\u003e\nenvironment variable to provide your client libraries with credentials.\nSee the [Dialogflow setup instructions](/dialogflow/es/docs/quick/setup#auth-env)\nfor more information about setting this variable.\n\nIf you instead need to provide manual credentials in your code, one additional\nstep is required before you can call a regionalized endpoint. You must set\nthe scope to https://www.googleapis.com/auth/cloud-platform when you generate\nyour authentication credentials. The following example demonstrates how to do\nthis in Java when creating a `GoogleCredentials` object: \n\n GoogleCredentials.fromStream(new FileInputStream(\"credential_file\"))\n .createScoped(\"https://www.googleapis.com/auth/cloud-platform\")\n\nCloud Logging\n-------------\n\nSee the [Cloud Logging documentation](/dialogflow/es/docs/logging) to control\nthe region where your logs are stored."]]
