# Amazon Kendra

Cloud service · AWS. Updated 2026-11-12. Page: https://blowstack.com/tools/cloud-services-hub/amazon-kendra

> Amazon Kendra is a highly accurate and easy to use enterprise search service powered by machine learning, designed to enable organizations to index and search internal documents and data across various sources using natural language queries.

Practice exams covering Amazon Kendra: [AIP-C01 AWS Certified Generative AI Developer - Professional](https://blowstack.com/practice-exams/aws-certified-generative-ai-developer-professional).

## 8 key features of Amazon Kendra

Amazon Kendra provides a highly accurate and scalable enterprise search service, leveraging natural language processing, machine learning, and document understanding to deliver relevant search results from diverse data sources securely and efficiently.

1. **Natural Language Search**: Amazon Kendra utilizes natural language processing (NLP) to understand the meaning of content and user queries, allowing it to return more accurate and relevant search results.
2. **Machine Learning**: Employs machine learning models to continuously improve search outcomes based on user interactions and feedback, ensuring the most relevant results are prioritized over time.
3. **Document Understanding**: Kendra is capable of understanding complex documents, extracting useful information, and indexing content from various formats including PDFs, HTML, MS Word, and PowerPoint.
4. **Highly Scalable**: Designed to scale with your enterprise needs, supporting quick and reliable searches across large volumes of documents without compromising on performance.
5. **Secure Data Handling**: Ensures data security and compliance by offering features like encryption at rest and in transit, alongside fine-grained access control to manage who can access your documents.
6. **Integration and Connectivity**: Offers seamless integration with a wide range of AWS services and third-party applications, allowing for easy implementation and connectivity to various data sources.
7. **Passage Retrieval API**: The retrieve API returns relevant passages or text excerpts for an input query, while the query API searches an index.
8. **Intelligent Ranking**: Amazon Kendra Intelligent Ranking uses Kendra's semantic search capabilities to re-rank another search service's results.

## Where Amazon Kendra is used

Amazon Kendra facilitates information retrieval across enterprises, enhances customer service, aids in compliance and risk management, and accelerates research and development by allowing natural language queries to find relevant information quickly.

1. **Enterprise Search**: Amazon Kendra revolutionizes the way employees access information within an organization, empowering them to find internal documents, such as reports, manuals, and HR policies, using natural language queries. This drastically reduces the time spent searching for information and boosts productivity.
2. **Customer Service Enhancement**: By integrating Amazon Kendra with customer service portals or chatbots, businesses can provide instant, accurate answers to customer inquiries. This not only elevates the customer experience by offering self-service options but also reduces the workload on customer service representatives.
3. **Compliance and Risk Management**: Kendra can analyze and understand complex documents, making it an invaluable tool for organizations that need to stay compliant with regulations. Legal teams and compliance officers can quickly find relevant information for audits, reducing the risk of non-compliance penalties.
4. **Research and Development**: Research teams can leverage Amazon Kendra to sift through vast amounts of scientific papers, patents, and technical documentation, identifying relevant information quickly. This accelerates the innovation process by helping researchers stay on top of current findings and historical data.

## How Amazon Kendra is priced

Amazon Kendra offers on-demand pricing based on usage and an Enterprise Edition for dedicated instances, both designed to scale with customer needs.

- **Provisioned Index Capacity**: Storage and query capacity are billed by provisioned unit-hours from index creation until deletion, rather than by the actual number of queries executed or documents indexed. Charges continue even when provisioned capacity is unused.
- **Basic Enterprise Edition**: The base index costs $1.40 per hour. Additional storage units and query units each cost $0.70 per hour.
- **GenAI Enterprise Edition**: The base index costs $0.32 per hour. Additional storage units cost $0.25 per hour each, and additional query units cost $0.07 per hour each.
- **Basic Developer Edition**: The base index costs $1.125 per hour and includes up to 10,000 documents or 3 GB of extracted text, whichever comes first, and 0.05 queries per second.
- **Connector Charges**: GenAI Enterprise Edition connectors cost a flat $30 per index per month. Basic Enterprise Edition and Basic Developer Edition connectors cost $0.35 per syncing hour plus $1 per million documents scanned during syncing.
- **Free Trial**: Basic Developer Edition and GenAI Enterprise Edition offer up to 750 hours of free usage during the first 30 days. Connector usage is excluded, and usage beyond the trial limits is billed at standard rates.
- **High-Volume Discounts**: Discounted pricing is available for high-volume workloads by requesting a price quote.

## Services Amazon Kendra works with

- **[Amazon S3](https://blowstack.com/tools/cloud-services-hub/amazon-s3)**: Integrate with Amazon S3 to index documents stored in S3 buckets and enable intelligent search across the content.
- **[Amazon RDS](https://blowstack.com/tools/cloud-services-hub/amazon-rds)**: Integrate with Amazon RDS to index structured data stored in relational databases and provide advanced search capabilities.
- **[Amazon CloudWatch](https://blowstack.com/tools/cloud-services-hub/amazon-cloudwatch)**: Use Amazon CloudWatch integration to monitor the performance and health of Kendra indexes and search applications.
- **[Amazon DynamoDB](https://blowstack.com/tools/cloud-services-hub/amazon-dynamodb)**: Integrate with Amazon DynamoDB to index NoSQL databases, allowing Kendra to search through unstructured and semi-structured data stored in DynamoDB tables.
- **[Amazon Data Firehose](https://blowstack.com/tools/cloud-services-hub/amazon-kinesis-data-firehose)**: Stream data into Amazon Kendra for indexing in near-real-time using Amazon Kinesis Data Firehose.
- **[AWS Lambda](https://blowstack.com/tools/cloud-services-hub/aws-lambda)**: Use AWS Lambda for custom data preprocessing and transformation before indexing the data with Amazon Kendra.
- **[Amazon Aurora](https://blowstack.com/tools/cloud-services-hub/amazon-aurora)**: Amazon Kendra's database connector can index records from supported Aurora MySQL and Aurora PostgreSQL databases. You configure the tables and columns that supply document text, identifiers, and metadata, then synchronize them with a Kendra index.
- **[Amazon Bedrock](https://blowstack.com/tools/cloud-services-hub/amazon-bedrock)**: Amazon Kendra GenAI Enterprise Edition indexes can serve as retrieval sources for Amazon Bedrock Knowledge Bases. Bedrock uses passages retrieved from the index to ground generated answers in your organization's documents.
- **[Amazon Cognito](https://blowstack.com/tools/cloud-services-hub/amazon-cognito)**: Amazon Kendra supports user-context filtering with JWTs issued by Amazon Cognito user pools. Configuring the token issuer and claim mappings lets Kendra filter search results using the authenticated user's identity and groups.
- **[Amazon EventBridge](https://blowstack.com/tools/cloud-services-hub/amazon-eventbridge)**: Amazon Kendra API activity recorded by CloudTrail can be matched by EventBridge rules. For example, a rule can initiate an operational workflow when someone creates or deletes a Kendra index.
- **[Amazon FSx](https://blowstack.com/tools/cloud-services-hub/amazon-fsx-(for-all-types))**: Amazon Kendra's Amazon FSx connector indexes documents stored on FSx for Windows File Server file systems. It can also crawl access-control information so search results respect document permissions.
- **[Amazon Lex](https://blowstack.com/tools/cloud-services-hub/amazon-lex)**: Amazon Kendra can answer questions for Amazon Lex bots through the built-in Kendra search intent. When a conversation needs information from enterprise documents, Lex can query the configured Kendra index and return an answer.
- **[Amazon Q Business](https://blowstack.com/tools/cloud-services-hub/amazon-q-business)**: Amazon Kendra indexes can supply enterprise content to Amazon Q Business through a Kendra retriever configuration. This lets a Q Business application use an existing compatible Kendra index to retrieve information for conversational answers.
- **[Amazon VPC](https://blowstack.com/tools/cloud-services-hub/amazon-vpc)**: Amazon Kendra data source connectors can use configured VPC subnets and security groups to reach private repositories, such as databases without public endpoints. Kendra creates network interfaces to provide this connectivity.
- **[AWS CloudFormation](https://blowstack.com/tools/cloud-services-hub/aws-cloudformation)**: Amazon Kendra indexes, data sources, and FAQs can be provisioned as CloudFormation resources. Templates can define an index and its connector configuration together for repeatable deployment.
- **[AWS CloudTrail](https://blowstack.com/tools/cloud-services-hub/aws-cloudtrail)**: Amazon Kendra integrates with CloudTrail to record supported API activity, including who made a request and when it occurred. These records help audit changes to indexes, data sources, and other Kendra resources.
- **[AWS IAM Identity Center (AWS Single Sign-On)](https://blowstack.com/tools/cloud-services-hub/aws-iam-identity-center-(aws-single-sign-on))**: Amazon Kendra Experience Builder uses IAM Identity Center to authenticate users and manage access to search experiences. Administrators can assign users and groups to an experience without building a separate sign-in system.
- **[AWS Identity and Access Management (IAM)](https://blowstack.com/tools/cloud-services-hub/aws-identity-and-access-management-(iam))**: Amazon Kendra uses IAM policies to control access to its APIs and service roles to access data sources and other required resources. For example, an index role can grant Kendra permission to read documents from a specific S3 bucket.
- **[AWS Key Management Service (AWS KMS)](https://blowstack.com/tools/cloud-services-hub/aws-key-management-service-(aws-kms))**: Amazon Kendra supports customer-managed KMS keys for encrypting index data at rest. KMS key policies and grants control Kendra's ability to use those keys.
- **[AWS PrivateLink](https://blowstack.com/tools/cloud-services-hub/aws-privatelink)**: Amazon Kendra supports interface VPC endpoints through AWS PrivateLink. Applications can access supported Kendra API endpoints privately from a VPC without using an internet gateway or NAT device.
- **[AWS Secrets Manager](https://blowstack.com/tools/cloud-services-hub/aws-secrets-manager)**: Amazon Kendra data source connectors retrieve repository credentials from Secrets Manager. Kendra can use a configured secret to authenticate to a database or another supported repository during synchronization.
- **[AWS Step Functions](https://blowstack.com/tools/cloud-services-hub/aws-step-functions)**: Amazon Kendra operations can be orchestrated through Step Functions AWS SDK integrations. A workflow can start a data source synchronization job and check its execution history before proceeding to subsequent processing.

## Practice Amazon Kendra in a full exam

Questions on Amazon Kendra in each practice exam, with every answer option and an explanation for each:

- [AIP-C01](https://blowstack.com/practice-exams/aws-certified-generative-ai-developer-professional): 3 questions

## What is Amazon Kendra

Amazon Kendra is a highly innovative and powerful search service powered by machine learning, designed to facilitate the retrieval of accurate information across various content repositories within an organization. It represents a significant leap beyond traditional search technologies, which often struggle to understand the true intent behind a user's query or to sift through the complexities of human language in documents.

Amazon Kendra has been in maintenance since June 30, 2026. It is closed to new customers; existing customers can continue using it. It should not be selected for new workloads.

Kendra, through its advanced natural language processing (NLP) capabilities, enables users to find precise answers to their questions, not just by returning relevant documents but by pinpointing the exact pieces of text that answer their queries.

Kendra offers three index types: GenAI Enterprise Edition, Basic Enterprise Edition, and Basic Developer Edition. GenAI Enterprise Edition uses the latest information retrieval technologies and semantic models for the highest accuracy and provides high availability for production workloads. Basic Enterprise Edition provides highly available semantic search for production workloads, while Basic Developer Edition is intended for proof-of-concept solutions rather than production.

Kendra's GenAI index supports retrieval augmented generation (RAG) as well as enterprise search. GenAI indexes can be used in Amazon Q Business and Amazon Bedrock knowledge bases to build generative AI applications using proprietary data.

Deleting an index also deletes all of its data source connectors and permanently deletes all document information in that index from Amazon Kendra.

At its core, Amazon Kendra is built to understand the nuances of human language, making it possible for users to ask questions in their natural, conversational tone. This approach breaks away from the keyword-based searches that require users to guess the right combination of terms present in the documents. Instead, Kendra comprehends the intent and context of the query, which allows for a more intuitive search experience and significantly improves the chances of retrieving the most relevant information.

One of the remarkable features of Amazon Kendra is its ability to continuously learn and improve over time. As it is exposed to more queries and content, it refines its understanding of the organization's data and user needs, thereby enhancing its accuracy and efficiency. This self-learning capability ensures that the search experience keeps evolving and remains aligned with the dynamic nature of information and user expectations.

Amazon Kendra supports a wide range of data sources, including popular cloud storage services, web applications, and databases. This versatility makes it an ideal solution for businesses and organizations with diverse and dispersed data ecosystems. By integrating Kendra, they can create a unified, searchable index of all their content, regardless of where it resides, enabling employees to access needed information swiftly and efficiently. Moreover, Kendra offers a suite of features to customize and secure the search experience.

The maximum extracted text size that can be ingested from a file is 5 MB, and this quota is not adjustable.

Administrators can define access control policies to ensure that users only see search results relevant to their roles and permissions. Furthermore, Kendra allows for the customization of the search results and the addition of FAQs to anticipate and directly answer common queries, enhancing user satisfaction.

In summary, Amazon Kendra represents a transformative approach to enterprise search, leveraging the power of machine learning to deliver a more natural, efficient, and precise way to find information. Its ability to understand the context of queries, learn from interactions, and support a broad spectrum of data sources, all while ensuring a customizable and secure search experience, makes it an invaluable tool for organizations looking to harness the full potential of their knowledge assets.

## Learn Amazon Kendra in lessons

2 short lessons on Amazon Kendra in 1 certification course.

- AIP-C01: Amazon Kendra: passage retrieval and relevance tuning (Premium), https://app.blowstack.com/lessons/amazon-kendra-passage-retrieval-and-relevance-tuning-aip-c01
- AIP-C01: Amazon Kendra vs Amazon OpenSearch Service: retrieval responsibilities (Premium), https://app.blowstack.com/lessons/amazon-kendra-vs-amazon-opensearch-service-retrieval-responsibilities-aip-c01
