Safety, RAG & search
Amazon Kendra / Amazon Bedrock Knowledge Bases vs Azure AI Search
Amazon Kendra maps to Azure AI Search, but Kendra is in maintenance mode (no new customers since July 30, 2026), and AWS now points new search workloads to Bedrock Managed Knowledge Base.
Side-by-side comparison
| Aspect | Amazon Web Services | Microsoft Azure |
|---|---|---|
| Service | Amazon Kendra Maintenance Amazon Bedrock Knowledge Bases | Azure AI Search |
| Lifecycle | Maintenance Mode from June 30, 2026. No longer open to new customers from July 30, 2026. AWS recommends Bedrock Managed Knowledge Base. Generally available | The product docs still say "Azure AI Search", but the Azure pricing page for it is now titled "Foundry IQ". |
| What it is | ML-powered enterprise search with connectors and relevance tuning. 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). | 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 | Kendra is billed per index-hour by edition, plus connector usage. | Billed per search unit per hour by tier (Free, Basic, Standard, Storage Optimized), plus semantic ranker usage. |
| Docs | Amazon Kendra docs Amazon Bedrock Knowledge Bases docs | Azure AI Search docs |
| Pricing page | Amazon Kendra pricing Amazon Bedrock Knowledge Bases pricing | Azure AI Search pricing |
| Exams | Generative AI Developer – Professional | AI-103 |
Key differences
- Kendra is a turnkey search service (connectors, FAQs, relevance tuning). Azure AI Search is a more general engine. You build indexes with indexers, skillsets, and integrated vectorization, and you get full-text, vector, and hybrid search plus semantic reranking.
- For log analytics or OpenSearch-style workloads, Azure AI Search isn't a replacement (per Microsoft's AWS comparison guide).
- Migration note. AWS's Kendra-to-Bedrock-Managed-KB guide lists feature gaps and workarounds.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Kendra is billed per index-hour by edition, plus connector usage. Amazon Kendra pricing → Amazon Bedrock Knowledge Bases pricing →
- Azure
- Billed per search unit per hour by tier (Free, Basic, Standard, Storage Optimized), plus semantic ranker usage. 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. |
| 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 Kendra and Amazon Bedrock Knowledge Bases?
Amazon Kendra maps to Azure AI Search, but Kendra is in maintenance mode (no new customers since July 30, 2026), and AWS now points new search workloads to Bedrock Managed Knowledge Base.
How does pricing compare between Amazon Kendra and Amazon Bedrock Knowledge Bases and Azure AI Search?
AWS: Kendra is billed per index-hour by edition, plus connector usage. Azure: Billed per search unit per hour by tier (Free, Basic, Standard, Storage Optimized), plus semantic ranker usage. Check the official pricing pages for current rates.
Which certification exams cover this topic?
AWS Certified Generative AI Developer – Professional; Microsoft Certified – Azure AI Apps and Agents Developer Associate (AI-103).