Zeema
New design
Catalogue / search-index

Vertex AI Search

gcpSearch indexgoogle-vertex-ai-search

Managed data store with semantic search over websites, documents, structured records and media.

Provider
gcp
Kind
Search index
Category
Data
Official docs
https://cloud.google.com/generative-ai-app-builder/docs/introduction
Properties · 5 set by this component
propertytypevaluesrequiredkind defaultthis component
customerManagedKeys · component propertyboolean—nofalseinherited
dataStoreType · component propertyenumwebsite | unstructured | structured | media | healthcareno—inherited
edition · component propertyenumstandard | enterpriseno—inherited
geoScheme · advancedenumnone | s2 | h3 | geohash | quadtreenonone▸ none
indexingenumsync | async | batchnoasync▸ async
managedboolean—nofalse▸ true
rebuildCadenceHours · advancedinteger—no—inherited
replicasinteger—no—inherited
semanticSearch · component propertyboolean—notrueinherited
shardingStrategy · advancedenumnone | hash | geo | time | prefix-rangenonone▸ none
structureenuminverted | trie | vector | geo-cellnoinverted▸ vector
Rules that apply · 1

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.

Search index without an asynchronous feederror
derived-store-without-cdc-or-rebuild

A search index is derived data and needs an asynchronous feed from a stream, change data capture or an indexing worker. Without one it is written inline on the request path, and it can never be rebuilt after it drifts.

  • — this does not hold:
  • — the node has at least one asynchronous incoming edge from a stream, change-data-capture or worker
Use it in a design
nodes:
  - { id: "vertex-ai-search", component: "google-vertex-ai-search" }
Other Search index products · 31
Alibaba Cloud Elasticsearchalibaba-elasticsearchalibabacloudsearch-indexOpenSearchalibaba-open-searchalibabacloudsearch-indexAmazon Bedrock Knowledge Basesaws-bedrock-knowledge-baseawssearch-indexAmazon CloudSearchaws-cloudsearchawssearch-indexAmazon Kendraaws-kendraawssearch-indexAmazon OpenSearch Serviceaws-opensearchawssearch-indexAzure AI Searchazure-ai-searchazuresearch-indexFoundry IQazure-foundry-iqazuresearch-indexAI Searchcloudflare-ai-searchcloudflaresearch-indexAlgoliaalgoliasearch-indexCoveocoveosearch-indexElastic Cloudelastic-cloudsearch-indexElasticsearchelasticsearchsearch-indexGeo cell indexgeo-cell-indexsearch-indexManticore Searchmanticoresearch-indexMeilisearchmeilisearchsearch-indexOpenSearchopensearchsearch-indexQuickwitquickwitsearch-indexGeneric search indexsearch-indexsearch-indexApache Solrsolrsearch-indexSonicsonicsearch-indexSphinxsphinxsearch-indexTrie indextrie-indexsearch-indexTypesensetypesensesearch-indexVespavespasearch-indexCloud Talent Solutiongoogle-cloud-talent-solutiongcpsearch-indexAI Commerce Searchgoogle-vertex-ai-search-commercegcpsearch-indexVision API Product Searchgoogle-vision-product-searchgcpsearch-indexIBM Cloud Databases for Elasticsearchibm-databases-for-elasticsearchibmsearch-indexIBM Watson Discoveryibm-watson-discoveryibmsearch-indexOCI Search with OpenSearchoci-opensearchocisearch-index
Source
# yaml-language-server: $schema=../../schema/component.schema.json
# Vertex AI Search (Agent Search) data store: a managed index over websites, unstructured documents,
# structured records, media or FHIR data, with out-of-the-box natural language understanding and
# semantic search ("AI Applications introduction"). Documents are indexed after import, so indexing is async.
schemaVersion: "1"
type: "component"
id: "google-vertex-ai-search"
kind: "search-index"
provider: "gcp"
docs: "https://cloud.google.com/generative-ai-app-builder/docs/introduction"
defaults:
  managed: true
  structure: "vector"
  indexing: "async"
  shardingStrategy: "none"
  geoScheme: "none"
properties:
  dataStoreType:
    type: "enum"
    values: ["website", "unstructured", "structured", "media", "healthcare"]
  semanticSearch:
    type: "boolean"
    default: true
  edition:
    type: "enum"
    values: ["standard", "enterprise"]
  customerManagedKeys:
    type: "boolean"
    default: false

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