Promote search content material utilizing Featured Outcomes for Amazon Kendra
Amazon Kendra is an clever search service powered by machine studying (ML). We’re excited to announce the launch of Amazon Kendra Featured Outcomes. This new function makes particular paperwork or content material seem on the high of the search outcomes web page at any time when a person points a sure question. You should use Featured Outcomes to enhance the visibility of recent paperwork or to advertise sure paperwork when customers enter sure queries.
For instance, you possibly can specify that in case your customers enter the question “new merchandise 2023,” then choose the paperwork titled “What’s new” and “Coming quickly” will function on the high of the search outcomes web page. Moreover, in case your customers ceaselessly use sure queries, you possibly can specify these queries for Featured Outcomes. For instance, if you happen to have a look at your high queries utilizing Amazon Kendra Analytics and discover that particular queries corresponding to “How does kendra semantically rank outcomes?” and “kendra semantic search” are ceaselessly used, then it is perhaps helpful for the queries to function the doc titled “Amazon Kendra search 101.”
On this submit, we introduce Featured Outcomes and present you the right way to use them.
Overview of resolution
Featured outcomes lets you create direct mappings from precise queries to paperwork in your index, permitting you to bypass the same old Amazon Kendra rating course of. Amazon Kendra naturally handles key phrase kind queries to rank essentially the most helpful paperwork within the search outcomes, avoiding extreme that includes of outcomes primarily based on easy key phrases. Featured outcomes are designed for particular queries, quite than queries which are too broad in scope. You possibly can experiment with that includes completely different paperwork for various queries, or guarantee sure paperwork get the visibility they deserve.
Conditions
To observe alongside, you must have the next stipulations:
You possibly can skip this step in case you have a preexisting index to make use of for this demo.
Add a pattern dataset to your index
Full the next steps so as to add pattern dataset to your index:
- On the Amazon Kendra console, go to your index and select Knowledge sources.
- Select Add knowledge supply.
- Below Out there knowledge sources, choose Pattern AWS documentation and select Add dataset.
- Enter a reputation on your Knowledge supply title (corresponding to
sample-aws-data) and select Add knowledge supply.
Search with out Featured Outcomes
On the Amazon Kendra console, select Search listed content material. Within the question discipline, begin with a question corresponding to “Kendra S3 connectors”.
In search outcomes, “DataSourceConfiguration – Amazon Kendra” is listed as the highest search outcome primarily based on the rating course of. However if you wish to promote “Getting began with an Amazon S3 knowledge supply (Console) – Amazon Kendra,” you possibly can bypass the Amazon Kendra rating course of to function this outcome on the high of the search outcomes web page.
Create a Featured Outcomes set
To function sure outcomes, you will need to specify a precise match of a full textual content question, not a partial match of a question utilizing a key phrase or phrase contained inside a question. For instance, if you happen to solely specify the question “Kendra” in a featured outcome set, queries corresponding to “How does Kendra semantically rank outcomes?” won’t render the Featured Outcomes. For extra data on limits, see Quotas for Amazon Kendra. To create a Featured Outcomes set, full the next steps:
- Within the navigation pane, select Featured outcomes, beneath Enrichments.
- Select Create set.
- Enter a reputation on your set (corresponding to
kendra_connector_feature) and select Subsequent.
- Enter a key phrase to search out objects to function (
kendra s3 connectors). - Choose Getting began with an Amazon S3 knowledge supply (Console) – Amazon Kendra from the search outcomes.
- Select Subsequent.
- Select Add question.
- Enter a question string (corresponding to
kendra s3 connectors) and select Add.
- Select Subsequent.
- On the Evaluate and create web page, select Create.
Your Amazon Kendra index is now prepared for pure language queries.
Search with Featured Outcomes
On the Amazon Kendra console, select Search listed content material. Within the question discipline, enter the key phrase used within the function outcomes set kendra s3 connectors.Now, you must see Getting began with an Amazon S3 knowledge supply (Console) – Amazon Kendra featured as the highest outcome on the search web page
For extra details about querying the index, see Querying an Index.
Clear up
To keep away from incurring future prices and to wash out unused roles and insurance policies, delete the assets you created:
- On the Amazon Kendra index, select Indexes within the navigation pane.
- Choose the index you created and on the Actions menu, select Delete.
- To verify deletion, enter
Deletewhen prompted and select Delete.
Wait till you get the affirmation message; the method can take as much as quarter-hour.
Conclusion
On this submit, you discovered the right way to use Amazon Kendra Featured Outcomes to advertise content material in an enterprise search resolution.
There are lots of extra options that we didn’t cowl. For instance:
- You possibly can allow user-based entry management on your Amazon Kendra index, and prohibit entry to paperwork primarily based on the entry controls you’ve already configured.
- You possibly can map object attributes to Amazon Kendra index attributes, and allow them for faceting, search, and show within the search outcomes.
- You possibly can rapidly discover data from webpages (HTML tables) utilizing Amazon Kendra tabular search.
To study extra about Amazon Kendra, refer Amazon Kendra Developer Guide.
In regards to the Authors
Maran Chandrasekaran is a Senior Options Architect at Amazon Internet Companies, working with our enterprise clients. Outdoors of labor, he likes to journey.
Kartik Mittal is a Software program Engineer at Amazon Internet Companies, engaged on Amazon Kendra, an enterprise search engine. Outdoors of labor, he enjoys mountain climbing and likes to journey.
Surya Ram is a Software program Engineer at Amazon Internet Companies, engaged on Amazon Kendra. Outdoors of labor, he enjoys chess, basketball and cricket.
