Amazon Kendra

Amazon Kendra Cheat Sheet

• Amazon Kendra is a highly scalable, intelligent enterprise search service.
• It utilizes machine learning to search unstructured data and improve accuracy in search results.

• It’s tightly integrated with other AWS services, such as Amazon S3 and Amazon Lex.
• It offers enterprise-grade security.

Features

• Natural Language Processing (NLP): Amazon Kendra uses NLP to get highly accurate answers without the need for machine learning (ML) expertise.
• Fine-tuning Search Results: You can fine-tune your search results based on content attributes, freshness, user behavior, and more.
• ML-powered Instant Answers: Amazon Kendra delivers ML-powered instant answers, FAQs, and document ranking as a fully managed service.

Benefits

• Amazon Kendra can increase employee productivity by 25%.
• It can lower the 5-year Total Cost of Ownership (TCO) by 82% compared to a traditional Enterprise Search Tool.
• It can reduce the Total Cost of Ownership (TCO) in year one by 75% compared to a traditional Enterprise Search Tool.
• It can reduce development costs by 80%.

Use Cases

• Boosting Employee Search Capabilities: Enhance the efficiency of your workforce by providing a unified search interface that enables them to access the insights they need for data-driven decision making.
• Optimizing Customer Engagement: Lower the expenses of your contact center by implementing user-friendly self-service bots, assistance solutions for agents, and seamless access to documents.
• Incorporating Search into SaaS Applications: Accelerate your information retrieval process with search features powered by machine learning within your applications.

Document Types and Formats Supported

• Amazon Kendra can handle a variety of document types and formats, including PDF, HTML, Word, PowerPoint, and others.
• It also supports additional formats like RTF, JSON, Markdown, CSV, MS Excel, XML, and XSLT.

Data Sources

• Amazon Kendra can connect to a wide range of data sources, such as Adobe Experience Manager, Alfresco, Aurora, Amazon FSx, Amazon RDS, Amazon S3 buckets, Amazon WorkDocs, Box, Confluence, Dropbox, Drupal, GitHub, and more.

Querying Data

• Users can query data using natural language. The response includes information like the title, a text excerpt, and the location of the most relevant documents in the index.

Use of Tags

• You can organize your indexes, data sources, and FAQs by assigning tags. Tags can be used to categorize your Amazon Kendra resources in different ways, such as by purpose, owner, or application.

Pricing

• Kendra Enterprise Edition (KEE): This is a highly reliable service designed for production workloads. It costs $1,008 per month.
• Kendra Developer Edition (KDE): This is a more affordable option at $810 per month, intended for developers to build a proof-of-concept. However, it’s not recommended for production workloads.
• Upon initiating the Kendra Enterprise Edition, customers are provided with a foundational capacity that encompasses 100,000 documents that can be searched and a daily limit of up to 8,000 queries.
• Customers have the option to scale their usage up or down by adding capacity units. This allows them to support more documents or more queries per day.
• For those new to Amazon Kendra Developer Edition, there’s an offer to get started for free. This offer includes up to 750 hours of free usage for the first 30 days. However, this does not apply to connector usage; standard pricing for run time and scanning will still apply.
• Discounted pricing options are available for customers who are willing to commit to a certain minimum volume.

Amazon Kendra Cheat Sheet References:

https://docs.aws.amazon.com/kendra/latest/dg/what-is-kendra.html

https://aws.amazon.com/kendra/pricing/

https://aws.amazon.com/kendra/