Amazon Kendra
Amazon Kendra is a highly accurate and easy to use enterprise search service that’s powered by machine learning. Kendra delivers powerful natural language search capabilities to your websites and applications so your end users can more easily find the information they need within the vast amount of content spread across your company.
Ask natural language questions, get immediate answers
Use natural language questions instead of just simple keywords to get the answers you’re looking for, whether that is a precise answer, an FAQ, or an entire document. Say goodbye to sifting through long lists of links and hoping one has the information you need.
Bring all of your data together in a few clicks
Get rid of information silos. Kendra lets you easily add content from file systems, SharePoint, intranet sites, file sharing services, and more, into a centralized location so you can quickly search all of your information to find the best answer.
Constantly improving search results
Your results get better over time search, because Kendra’s machine learning algorithms learn which results your users find most valuable. You also have the option to fine-tune results by manually adjusting the importance of certain data sources or document freshness.
Get better answers upfront…
Use natural language questions instead of just simple keywords to get the answers you’re looking for. Kendra will connect the dots within your files to return answers, whether that is a text snippet, FAQ, or document. Instead of sifting through long lists of documents to find specific answers, Kendra can provide a suggested answer upfront. See the difference between the search experience before and after Kendra.
…using natural language
Natural language enables you to get more specific answers from anywhere in your data. Ask questions like, “Is the IT help desk open at noon?” or “How do I connect to my VPN?” so you can get more precise answers.
Customer stories
“When our material scientists lead new research, they need access to information from prior relevant research—information that’s buried in the many patents we hold in our huge knowledge base… Kendra lets our scientists find the information they need by handling natural language queries quickly and accurately.”
"Our goal is to help our customers get to the answers they need faster - even when the right answers may be buried within documents over 100 pages long - so they can understand regulatory information faster and make decisions more quickly and confidently"
Bring all of your data together in a few clicks
Combine previously-siloed data sources into a central location, or index, with just a few clicks. Go from months of work to implementation in less than a week.
Step 1: Create an index
Create an index where you'll add your data sources.
Step 2: Add data sources
Use Kendra's connectors for popular sources like S3, SharePoint, Salesforce, Servicenow, RDS databases, One Drive and many more coming later this year.
Step 3: Test and deploy
Test the search experience directly in the console. Plus, access sample code for each component of the search experience so you can easily deploy to new or existing applications.
Constantly improving search results
Incremental learning (coming soon)
Kendra actively retrains deep learning models built for your data set and employee usage patterns to improve search accuracy. As end-users interact with search results, Kendra fine tunes its results. This means that if you click on a result or give it a ‘thumbs up’ or ‘thumbs down’, Kendra will learn which results are more relevant and surface those first.
Relevance tuning
Kendra gives you the option to manually tune relevance; you can boost certain fields in your index like document freshness, view counts, or specific data sources. For example, you could boost documents that are not only viewed more often but that are also more recent, like trending news or updates.
Natural language understanding for multiple domains
Kendra uses deep learning models to understand natural language queries and document content and structures for a wide range of internal use cases like HR, operations, support, and R&D. Kendra is also optimized to understand complex language from domains like IT, financial services, insurance, pharmaceuticals, industrial manufacturing, energy, legal, media and entertainment, travel and hospitality, healthcare, HR, news, telecommunications, and automotive. This means that you can ask a question like “Can I add children as dependents on HMO?” and Kendra will provide answers related to your healthcare options.
Amazon Kendra Developer Edition
Kendra Developer Edition provides developers with a lower- cost option to build proof of concepts (POCs) and experiment more with Amazon Kendra. Kendra Developer Edition has the same features as Kendra Enterprise Edition, but limited to 4,000 queries per day, up to 10k searchable documents across 5 data sources, and runs on a single availability zone. Kendra Developer Edition does not offer the scaling options available in the Enterprise Edition. Therefore this edition is ideal for development purposes, not recommended for production.
Get started with Kendra today
Experience reimagined search for yourself. With Amazon Kendra, you can now connect your own data sources and start testing the search experience on your own content in minutes.
Preview Trials: Customers who began using the Free Tier 30-day trial during the Preview of Amazon Kendra Enterprise Edition, which ended on 5/10/2020, will continue to have access with no changes to the original terms.
