What is Amazon Kendra?
Amazon Kendra is a managed information retrieval and intelligent search service that uses natural language processing and deep learning models. Unlike traditional keyword search, Kendra evaluates semantic and contextual similarity to decide whether a text chunk or document is relevant to a query.
Important notice: Amazon Kendra has been closed to new customers since July 30, 2026. Existing customers can continue using the service unchanged. For comparable capabilities, AWS recommends Amazon Bedrock Knowledge Bases; the Kendra GenAI index is also used internally by Amazon Q Business and Bedrock Knowledge Bases for retrieval-augmented generation applications.
Kendra indexes content from various data sources such as S3, SharePoint, Salesforce, ServiceNow, Confluence, and databases. The three index editions (GenAI Enterprise, Basic Enterprise, Basic Developer) let you configure the service based on accuracy and scaling requirements.
Core Features
Natural Language Understanding: Kendra answers factoid questions, descriptive questions, and ambiguous queries by understanding the meaning of the question rather than just matching keywords.
GenAI Index for RAG: The GenAI Enterprise Index delivers highly accurate retrieval results for retrieval-augmented generation applications and can be used directly within Amazon Q Business and Amazon Bedrock Knowledge Bases.
Intelligent Ranking: Kendra can be used as a re-ranking layer for results from other search services to improve their relevance ordering.
Connectors: Native connections to data sources such as SharePoint, Salesforce, ServiceNow, Confluence, Google Drive, OneDrive, databases (JDBC), and web crawlers; custom sources via the Custom Data Source API.
Access Control: Kendra respects existing access rights from connected data sources, so users only see results from documents they are authorized to access.
Typical Use Cases
Enterprise-Wide Knowledge Search: Employees search the intranet, SharePoint, Confluence, and document archives through a single entry point and get the most relevant answer regardless of storage location.
Customer Self-Service: Customer portals use the Kendra Search API to search FAQs, product documentation, and knowledge base articles to reduce support requests.
Retrieval-Augmented Generation: The GenAI index serves as a knowledge base for generative AI applications in Amazon Q Business or Amazon Bedrock, grounding answers in company-specific data.
Benefits
- Semantic understanding instead of plain keyword search
- Direct use as a knowledge base for RAG applications in Amazon Q Business and Bedrock
- Broad connector ecosystem for common enterprise data sources
- Inherits existing access rights for compliance and data privacy
Integration with innFactory
As an AWS reseller, innFactory supports you with Amazon Kendra and with migrating to Amazon Bedrock Knowledge Bases: architecture design, connector integration, access control concepts, and cost optimization for enterprise search and RAG solutions on AWS.
Typical Use Cases
Frequently Asked Questions
What is Amazon Kendra?
Amazon Kendra is a managed information retrieval and intelligent search service that uses natural language processing and semantic models to understand search queries. Kendra searches connected data sources such as SharePoint, Salesforce, or S3 and returns relevant answers instead of plain keyword matches.
Is Amazon Kendra still available to new customers?
Amazon Kendra has been closed to new customers since July 30, 2026. Existing customers can continue using the service. For comparable capabilities, AWS recommends Amazon Bedrock Knowledge Bases and Amazon Q Business, which can use the Kendra GenAI index internally.
What does Amazon Kendra cost?
Kendra is billed hourly per index, tiered by edition (GenAI Enterprise, Basic Enterprise, Basic Developer), plus optional storage and query capacity units and connector fees. Billing runs from index creation regardless of actual usage. Exact prices are on the official AWS pricing page.
What editions does Kendra offer?
Kendra offers three index types: the GenAI Enterprise Edition with the highest accuracy for RAG applications and enterprise search, the Basic Enterprise Edition for production workloads with classic semantic search, and the Basic Developer Edition for proof-of-concept projects, not recommended for production.
Can I integrate Kendra with generative AI and chatbots?
Yes. The Kendra GenAI index can be used directly within Amazon Q Business and Amazon Bedrock Knowledge Bases for retrieval-augmented generation applications. Kendra also integrates natively with Amazon Lex for chatbots and offers Kendra Intelligent Ranking to re-rank results from other search services.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of AWS (official documentation). This page does not represent an offer by AWS.