Announcing Amazon Kendra: Reinventing Enterprise Search with Machine Learning
Today, AWS announced Amazon Kendra, a new highly accurate and easy to use enterprise search service powered by machine learning. Kendra provides a more intuitive way to search, using natural language, and returns more accurate answers so your end users can discover information stored within the vast amount of content spread across your company. Users can ask questions like "How long is maternity leave?" and get a specific answer such as "14 weeks", or "How do I configure my VPN?" and get a specific passage extracted from a document describing the process. With Kendra, you can provide pinpoint search accuracy from content within your manuals, research reports, FAQs, HR documentation, customer service guides, and more.
Today, AWS announced Amazon Kendra, a new highly accurate and easy to use enterprise search service powered by machine learning. Kendra provides a more intuitive way to search, using natural language, and returns more accurate answers so your end users can discover information stored within the vast amount of content spread across your company. Users can ask questions like "How long is maternity leave?" and get a specific answer such as "14 weeks", or "How do I configure my VPN?" and get a specific passage extracted from a document describing the process. With Kendra, you can provide pinpoint search accuracy from content within your manuals, research reports, FAQs, HR documentation, customer service guides, and more.
Kendra is available as a console application for setup and administration workflows, as well as APIs for additional flexibility. Kendra’s preview offers built-in connectors for SharePoint Online, Amazon S3, and databases, or you can use the Kendra API to ingest data from other data sources. For GA, Kendra will offer additional connectors for other popular data sources like Box, Dropbox, Salesforce, and OneDrive. Once your data is ingested, you can immediately test your search in the console, and easily deploy search components to your application with code samples Kendra provides in the console. Amazon Kendra is optimized to find accurate answers from specific domains such as IT, pharmaceutical, insurance, energy, industrial, financial services, and more. Kendra's machine learning models are periodically updated for each customer by capturing end-user search patterns and feedback, allowing Kendra's relevance to stay aligned with information trends in the enterprise.
Customers like Woodside, 3M, and Sage are discovering the power of Kendra and reporting significant improvements in accuracy and speed when searching, compared to existing solutions.
To get started, read the documentation where you’ll find details on creating your first index, adding data sources, testing search and deploying Kendra search in your application. We'll also show you how you can tune relevance by boosting field priorities in your index. Kendra Preview is available in today in the AWS console, via the AWS SDKs, and the AWS CLI in the following regions: Northern Virginia, Oregon, and Ireland. See the AWS Region Table for more details.