Foundry IQ
Permission-aware knowledge base that answers agent queries by agentic retrieval over connected enterprise data sources.
- Provider
- azure
- Kind
- Search index
- Category
- Data
| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| citations | boolean | — | no | true | inherited |
| geoScheme | enum | none | s2 | h3 | geohash | quadtree | no | none | inherited |
| indexing | enum | sync | async | batch | no | async | ▸ batch |
| knowledgeSourceType | enum | azure-blob | sharepoint | onelake | web | search-index | no | — | inherited |
| managed | boolean | — | no | false | ▸ true |
| permissionEnforcement | boolean | — | no | true | inherited |
| rebuildCadenceHours | integer | — | no | — | inherited |
| replicas | integer | — | no | — | inherited |
| retrievalReasoningEffort | enum | minimal | low | medium | no | — | inherited |
| semanticReranking | boolean | — | no | true | inherited |
| shardingStrategy | enum | none | hash | geo | time | prefix-range | no | none | inherited |
| structure | enum | inverted | trie | vector | geo-cell | no | inverted | inherited |
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.
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
nodes:
- { id: "foundry-iq", component: "azure-foundry-iq" }Alibaba Cloud Elasticsearchalibaba-elasticsearchOpenSearchalibaba-open-searchAmazon Bedrock Knowledge Basesaws-bedrock-knowledge-baseAmazon CloudSearchaws-cloudsearchAmazon Kendraaws-kendraAmazon OpenSearch Serviceaws-opensearchAzure AI Searchazure-ai-searchAI Searchcloudflare-ai-searchAlgoliaalgoliaCoveocoveoElastic Cloudelastic-cloudElasticsearchelasticsearchGeo cell indexgeo-cell-indexManticore SearchmanticoreMeilisearchmeilisearchOpenSearchopensearchQuickwitquickwitGeneric search indexsearch-indexApache SolrsolrSonicsonicSphinxsphinxTrie indextrie-indexTypesensetypesenseVespavespaCloud Talent Solutiongoogle-cloud-talent-solutionVertex AI Searchgoogle-vertex-ai-searchAI Commerce Searchgoogle-vertex-ai-search-commerceVision API Product Searchgoogle-vision-product-searchIBM Cloud Databases for Elasticsearchibm-databases-for-elasticsearchIBM Watson Discoveryibm-watson-discoveryOCI Search with OpenSearchoci-opensearch
# yaml-language-server: $schema=../../schema/component.schema.json # Foundry IQ: a knowledge base over enterprise knowledge sources that agents query through agentic retrieval, built on Azure AI Search indexing. # "What is Foundry IQ?" states indexed sources are chunked, embedded and refreshed by scheduled indexer runs, that results are semantically reranked and returned with citations, and that permissions are enforced at query time under the caller's Entra identity. schemaVersion: "1" type: "component" id: "azure-foundry-iq" kind: "search-index" provider: "azure" docs: "https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/what-is-foundry-iq" defaults: managed: true indexing: "batch" properties: knowledgeSourceType: type: "enum" values: ["azure-blob", "sharepoint", "onelake", "web", "search-index"] retrievalReasoningEffort: type: "enum" values: ["minimal", "low", "medium"] permissionEnforcement: type: "boolean" default: true semanticReranking: type: "boolean" default: true citations: type: "boolean" default: true