Amazon CloudSearch and Amazon Kendra

Question

I was wondering what are the main differences between Amazon CloudSearch and Kendra? Why are there two different tools from the same company that compete with each other? Both look the same, I am not sure what the differences are in features. How is one being differentiated from the other?

Amazon CloudSearch: Set up, manage, and scale a search solution for your website or application. Amazon CloudSearch enables you to search large collections of data such as web pages, document files, forum posts, or product information. With a few clicks in the AWS Management Console, you can create a search domain, upload the data you want to make searchable to Amazon CloudSearch, and the search service automatically provisions the required technology resources and deploys a highly tuned search index;

Amazon Kendra: Enterprise search service powered by machine learning. It is a highly accurate and easy to use enterprise search service that’s powered by machine learning. It 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.

Jinks

Answer 1

The key difference between the two services is that AWS Cloud Search is based on Solr, a keyword engine, while Amazon Kendra is an ML-powered search engine designed to provide more accurate search results over unstructured data such as Word documents, PDFs, HTML, PPTs, and FAQs. Kendra was designed from the ground up to natively handle natural language queries and return specific answers, instead of just lists of documents like keyword engines do.

Another key difference is that in CloudSearch, to upload data to your domain, it must be formatted as a valid JSON or XML batch. Kendra, on the other hand, provides out of the box connectors that allow customers to automatically index content from popular repositories like Sharepoint Online, S3, Salesforce, Servicenow, etc., directly into the Kendra index. So, depending on your use case, Kendra may be a better choice, especially if you’re considering the service for enterprise search applications, or even web site search where deeper language understanding is important. Hope this helps, happy to address follow-up questions. You can also visit our Kendra FAQ page for more specific answers around the service: https://aws.amazon.com/kendra/faqs/

Stereotypy

Thank you for the explanation. Also, i feel like Amazon CloudSearch is not "Enterprise search" unlike Kendra. – Jinks

Another one disadvantage with Kendra i see is, it doesn't have "VISUALIZATION OF DATA" (For ex: Banana is a visualization tool (a fork of Kibana) that works for Solr and allows admins to monitor events and logs in the dashboard on the fly.) – Jinks