Safety, RAG & search
Amazon Bedrock Knowledge Bases vs Foundry IQ (knowledge bases) / Azure AI Search
The Azure equivalent of Amazon Bedrock Knowledge Bases is Foundry IQ knowledge bases, which run on Azure AI Search with agentic retrieval.
Side-by-side comparison
| Aspect | Amazon Web Services | Microsoft Azure |
|---|---|---|
| Service | Amazon Bedrock Knowledge Bases | Foundry IQ (knowledge bases) Preview Azure AI Search |
| Lifecycle | Generally available | Some features are GA and some are preview, depending on the Search REST API version. The portals expose preview-only access. The product docs still say "Azure AI Search", but the Azure pricing page for it is now titled "Foundry IQ". |
| What it is | Managed RAG. Managed Knowledge Base (AWS runs ingestion, storage, and agentic retrieval) or customer-managed (bring your own vector store, such as OpenSearch Serverless, Aurora, or Neptune). | Multi-source, permission-aware knowledge bases for agents, using agentic retrieval on Azure AI Search, with sources such as Blob, SharePoint, OneLake, and the web. Search and retrieval engine. Full-text, vector, and hybrid search, semantic ranker, integrated vectorization and AI enrichment (indexers and skillsets), and agentic retrieval. |
| Pricing model | Managed KB is billed on ingested size, query volume, and LLM usage. Customer-managed KBs bill for the underlying vector store plus embedding and generation tokens. | Azure AI Search tier (search units per hour), plus semantic ranker/agentic retrieval usage and embedding/LLM tokens. |
| Docs | Amazon Bedrock Knowledge Bases docs | Foundry IQ (knowledge bases) docs Azure AI Search docs |
| Pricing page | Amazon Bedrock Knowledge Bases pricing | Foundry IQ (knowledge bases) pricing Azure AI Search pricing |
| Exams | Generative AI Developer – Professional AIF-C01 | AI-103 |
Key differences
- Bedrock offers a Managed Knowledge Base (AWS runs ingestion, storage, and agentic multi-hop retrieval) or customer-managed vector stores (OpenSearch Serverless, Aurora, Neptune Analytics graphs, Kendra GenAI index, structured data stores).
- Foundry IQ is a multi-source knowledge base on Azure AI Search. It covers Blob, SharePoint, OneLake, and web sources, syncs ACLs, honors Microsoft Purview sensitivity labels, and enforces permissions at query time under the caller's Entra identity.
- Foundry IQ is partly GA and partly preview depending on the Search REST API version. Bedrock Knowledge Bases is GA.
- Both support hybrid search, reranking, and citations. Bedrock also supports image queries with multimodal embeddings.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Managed KB is billed on ingested size, query volume, and LLM usage. Customer-managed KBs bill for the underlying vector store plus embedding and generation tokens. Amazon Bedrock Knowledge Bases pricing →
- Azure
- Azure AI Search tier (search units per hour), plus semantic ranker/agentic retrieval usage and embedding/LLM tokens. Foundry IQ (knowledge bases) pricing → Azure AI Search pricing →
Certification exam mapping
| Exam | Provider | Level | Status |
|---|---|---|---|
| AWS Certified Generative AI Developer – Professional | AWS | Professional | current Exam code not confirmed from the official page at build time; shown by name only. |
| AWS Certified AI Practitioner AIF-C01 | AWS | Foundational | current Italian and German versions retire after Oct 15, 2026 (per AWS cert page). |
| Microsoft Certified – Azure AI Apps and Agents Developer Associate AI-103 | Azure | Associate | current Generative AI and agentic solutions with Microsoft Foundry using Python. Successor in scope to the retired AI-102. |
Relevance is based on each exam's published scope, not a line-by-line objective match. Check the official study guide.
FAQ
What is the Azure equivalent of Amazon Bedrock Knowledge Bases?
The Azure equivalent of Amazon Bedrock Knowledge Bases is Foundry IQ knowledge bases, which run on Azure AI Search with agentic retrieval.
How does pricing compare between Amazon Bedrock Knowledge Bases and Foundry IQ (knowledge bases) and Azure AI Search?
AWS: Managed KB is billed on ingested size, query volume, and LLM usage. Customer-managed KBs bill for the underlying vector store plus embedding and generation tokens. Azure: Azure AI Search tier (search units per hour), plus semantic ranker/agentic retrieval usage and embedding/LLM tokens. Check the official pricing pages for current rates.
Which certification exams cover this topic?
AWS Certified Generative AI Developer – Professional; AWS Certified AI Practitioner (AIF-C01); Microsoft Certified – Azure AI Apps and Agents Developer Associate (AI-103).
Is Azure AI Search the same as Bedrock Knowledge Bases?
Not exactly. Azure AI Search is the index and retrieval engine. Foundry IQ is the knowledge-base layer on top of it that maps most closely to Bedrock Knowledge Bases.