Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
This page shows you how to enable CMEK to work with
Vertex AI RAG Engine.
Overview
Vertex AI RAG Engine provides robust options for managing how
your data at rest is encrypted. By default, all user data within RagManagedDb
is encrypted using a Google-owned and Google-managed encryption key, which is the default
setting. This default setting helps you to verify that your data is secure
without requiring any specific configuration.
If you require more control over your keys used for encryption,
Vertex AI RAG Engine supports Customer-managed encryption keys
(CMEK). With CMEK, you can use your
cryptographic keys, managed within Cloud Key Management Service (KMS), to protect your RAG
corpus data.
CMEK is only supported on RagVectorDbConfig of type RagManagedDb.
The encryption_spec field defines the KMS key, and the field is immutable,
which means that CMEK can't be enabled or disabled after the RAG corpus is
created.
No more than 50 unique KMS keys can be used to create RAG corpora per project
per region.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Use CMEK with Vertex AI RAG Engine\n\n| The [VPC-SC security controls](/vertex-ai/generative-ai/docs/security-controls) and\n| CMEK are supported by Vertex AI RAG Engine. Data residency and AXT security controls aren't\n| supported.\n\nThis page shows you how to enable CMEK to work with\nVertex AI RAG Engine.\n\nOverview\n--------\n\nVertex AI RAG Engine provides robust options for managing how\nyour data at rest is encrypted. By default, all user data within `RagManagedDb`\nis encrypted using a Google-owned and Google-managed encryption key, which is the default\nsetting. This default setting helps you to verify that your data is secure\nwithout requiring any specific configuration.\n\nIf you require more control over your keys used for encryption,\nVertex AI RAG Engine supports [Customer-managed encryption keys\n(CMEK)](/kms/docs/cmek). With CMEK, you can use your\ncryptographic keys, managed within Cloud Key Management Service (KMS), to protect your RAG\ncorpus data.\n\nSet up the encryption key with your RAG corpus\n----------------------------------------------\n\nTo set up an encryption key, follow the steps at [Set up your KMS key and grant permissions](/vertex-ai/generative-ai/docs/rag-engine/use-ragmanageddb-with-rag#set_up_your_kms_key_and_grant_permissions).\n\nCMEK limitations for Vertex AI RAG Engine\n-----------------------------------------\n\nVertex AI RAG Engine supports CMEK with the following limitations:\n\n- Before creating a RAG corpus, you must manually enable the RAG Service account. For detailed instructions, see [Grant Permissions to the Vertex AI RAG Engine service agent](/vertex-ai/generative-ai/docs/rag-engine/use-ragmanageddb-with-rag#grant_permissions_to_the_vertex_ai_rag_engine_service_agent).\n\n- CMEK is only supported on `RagVectorDbConfig` of type `RagManagedDb`.\n\n- The `encryption_spec` field defines the KMS key, and the field is immutable,\n which means that CMEK can't be enabled or disabled after the RAG corpus is\n created.\n\n- No more than 50 unique KMS keys can be used to create RAG corpora per project\n per region.\n\nWhat's next\n-----------\n\n- For information about managing your encryption, see [Manage your\n encryption](/vertex-ai/generative-ai/docs/rag-engine/use-ragmanageddb-with-rag#manage_your_encryption).\n- For more information on Vertex AI RAG Engine, see [Vertex AI RAG Engine\n overview](/vertex-ai/generative-ai/docs/rag-engine/rag-overview).\n- To learn more about data at rest, see [Data\n residency](/vertex-ai/generative-ai/docs/learn/data-residency).\n- To learn more about the RAG API, see [RAG Engine\n API](/vertex-ai/generative-ai/docs/model-reference/rag-api)."]]