Vertex AI RAG Engine

gcp AI servicegoogle-vertex-ai-rag-engine

Managed retrieval corpus that indexes documents for grounding generative model responses.

Provider: gcp
Kind: AI service
Category: Compute
Official docs: https://cloud.google.com/vertex-ai/generative-ai/docs/rag-overview

Properties · 4 set by this component

property	type	values	required	kind default	this component
auth	enum	api-key \| oauth \| iam \| none	no	—	▸ iam
contentFiltering	boolean	—	no	—	inherited
customerManagedKeys	boolean	—	no	—	▸ false
dataResidency · advanced	enum	us \| eu \| asia \| global	no	—	inherited
dataRetentionDays	integer	—	no	—	inherited
grounding · component property	boolean	—	no	true	inherited
keyStore	boolean	—	no	false	inherited
managed	boolean	—	no	false	▸ true
modality	enum	text \| vision \| speech \| multimodal \| structured \| image \| video \| audio \| embedding \| rerank	no	—	▸ text
publicEndpoint	boolean	—	no	—	inherited
quotaUnitsPerMinute	integer	—	no	—	inherited
rateLimitRpm · advanced	integer	—	no	—	inherited
rateLimitTpm · advanced	integer	—	no	—	inherited
vectorDatabase · component property	enum	rag-managed-db \| vertex-vector-search \| pinecone \| weaviate	no	rag-managed-db	inherited
viaGateway	boolean	—	no	false	inherited

Rules that apply · 2

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

AI API key not managedwarning

ai-api-key-unmanaged

This AI vendor is reached with an API key, and nothing in the design holds or rotates that key. It ends up in environment files or code, every caller shares it, and a single leak runs up the vendor bill until someone notices. Put the key in a key-management component, or say it is held there with keyStore.

— all of these hold:
— the node's `auth` is "api-key"
— the node's `keyStore` is false
— the node has at least one incoming edge from an app-server, worker or client
— this does not hold:
— the design contains a node of kind key-management

Stateful node without zone redundancyerror

stateful-node-without-zone-redundancy

A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.

— all of these hold:
— the node's `stateless` is false
— the node sits inside exactly 1 availability-zone group
— this does not hold:
— the node sits inside at least one cell group

Use it in a design

nodes:
  - { id: "vertex-ai-rag-engine", component: "google-vertex-ai-rag-engine" }

Other AI service products · 125

and 85 more → AI service page

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Vertex AI RAG Engine corpus: a fully managed retrieval index over documents, backed by the
3# RAG Engine managed vector database unless another one is attached ("RAG Engine overview").
4# The corpus indexes and retrieves text passages for grounding Gemini calls.
5schemaVersion: "1"
6type: "component"
7id: "google-vertex-ai-rag-engine"
8kind: "ai-service"
9provider: "gcp"
10docs: "https://cloud.google.com/vertex-ai/generative-ai/docs/rag-overview"
11defaults:
12  auth: "iam"
13  managed: true
14  modality: "text"
15  customerManagedKeys: false
16properties:
17  vectorDatabase:
18    type: "enum"
19    values: ["rag-managed-db", "vertex-vector-search", "pinecone", "weaviate"]
20    default: "rag-managed-db"
21  grounding:
22    type: "boolean"
23    default: true

The same page as markdown, for an agent: /catalogue/components/google-vertex-ai-rag-engine.md