Question structured knowledge from Amazon Q Enterprise utilizing Amazon QuickSight integration

Amazon Q Enterprise is a generative AI-powered assistant that may reply questions, present summaries, generate content material, and securely full duties based mostly on knowledge and knowledge in your enterprise techniques. Though generative AI is fueling transformative improvements, enterprises should still expertise sharply divided knowledge silos in the case of enterprise data, specifically between unstructured content material (similar to PDFs, Phrase paperwork, and HTML pages), and structured knowledge (real-time knowledge and stories saved in databases or knowledge lakes). Each classes of information are usually queried and accessed utilizing separate instruments, from in-product browse and search performance for unstructured knowledge, to enterprise intelligence (BI) instruments like Amazon QuickSight for structured content material.

Amazon Q Enterprise gives an efficient resolution for shortly constructing conversational functions over unstructured content material, with over 40 knowledge connectors to common content material and storage administration techniques similar to Confluence, SharePoint, and Amazon Easy Storage Service (Amazon S3), to combination enterprise data. Prospects are additionally in search of a unified conversational expertise throughout all their data repositories, whatever the format the content material is saved and arranged as.

On December 3, 2024, Amazon Q Enterprise introduced the launch of its integration with QuickSight, permitting you to shortly join your structured sources to your Amazon Q Enterprise functions, making a unified conversational expertise to your end-users. The QuickSight integration gives an in depth set of over 20 structured knowledge supply connectors, together with Amazon Redshift, PostgreSQL, MySQL, and Oracle, enabling you to shortly broaden the conversational scope of your Amazon Q Enterprise assistants to cowl a wider vary of data sources. For the end-users, solutions are returned in actual time out of your structured sources, mixed with different related data present in unstructured repositories. Amazon Q Enterprise makes use of the analytics and superior visualization engine in QuickSight to generate correct and simple-to-understand solutions from structured sources.

On this put up, we present you easy methods to configure the QuickSight connection from Amazon Q Enterprise after which ask inquiries to get real-time knowledge and visualizations from QuickSight for structured knowledge along with unstructured content material.

Resolution overview

The QuickSight function in Amazon Q Enterprise is offered on the Amazon Q Enterprise console in addition to by way of Amazon Q Enterprise APIs. This function is applied as a plugin inside Amazon Q Enterprise. After it’s enabled, this plugin will behave otherwise than different Amazon Q Enterprise plugins—it can question QuickSight robotically for each consumer immediate, in search of related solutions.

For AWS accounts that aren’t subscribed to QuickSight already, the Amazon Q Enterprise admin completes the next steps:

1. Create a QuickSight account.
2. Join your database in QuickSight to create a dataset.
3. Create a subject in QuickSight, which is then used to make it searchable out of your Amazon Q Enterprise utility.

When the function is activated, Amazon Q Enterprise will use your unstructured knowledge sources configured in Amazon Q Enterprise, in addition to your structured content material out there utilizing QuickSight, to generate a wealthy reply that features narrative and visualizations. Relying on the query and knowledge in QuickSight, Amazon Q Enterprise might generate a number of visualizations as a response.

Conditions

It is best to have the next stipulations:

• An AWS account the place you’ll be able to observe the directions on this put up.
• AWS IAM Identification Heart arrange for use with Amazon Q Enterprise. For extra data, see Configure Amazon Q Enterprise with AWS IAM Identification Heart trusted id propagation.
• A minimum of one Amazon Q Enterprise Professional consumer that has admin permissions to arrange and configure Amazon Q Enterprise. For pricing data, see Amazon Q Enterprise pricing.
• An IAM Identification Heart group that will probably be assigned the QuickSight Admin Professional function, for customers who will handle and configure QuickSight.
• If a QuickSight account exists, then it must be in the identical AWS account and AWS Area as Amazon Q Enterprise, and configured with IAM Identification Heart.
• A database that’s put in and may be reached from QuickSight to load structured knowledge (or you possibly can create a dataset by importing a CSV or XLS file). The database additionally wants credentials to create tables and insert knowledge.
• Pattern structured knowledge to load into the database (together with insert statements).

Create an Amazon Q Enterprise utility

To make use of this function, it is advisable to have an Amazon Q Enterprise utility. Should you don’t have an present utility, observe the steps in Uncover insights from Amazon S3 with Amazon Q S3 connector to create an utility together with an Amazon S3 knowledge supply. Add the non-structured doc(s) to Amazon S3 and sync the info supply.

Create and configure a brand new QuickSight account

You possibly can skip this part if you have already got an present QuickSight account. To create a QuickSight account, full the next steps:

1. On the Amazon Q Enterprise console, navigate to your utility.
2. Select Amazon QuickSight within the navigation pane.

3. Select Create QuickSight account.

4. Beneath QuickSight account data, enter your account identify and an e mail for account notifications.
5. Beneath Assign QuickSight Admin Professional roles, select the IAM Identification Heart group you created as a prerequisite.
6. Select Subsequent.

7. Beneath Service entry, choose Create and use a brand new service function.
8. Select Authorize.

It will create a QuickSight account, assign the IAM Identification Heart group as QuickSight Admin Professional, and authorize Amazon Q Enterprise to entry QuickSight.

You will notice a dashboard with particulars for QuickSight. At the moment, it can present zero datasets and subjects.

9. Select Go to QuickSight.

Now you can proceed to the subsequent part to arrange your knowledge.

Configure an present QuickSight account

You possibly can skip this part in case you adopted the earlier steps and created a brand new QuickSight account.

In case your present QuickSight account is just not on IAM Identification Heart, think about using a unique AWS account with no QuickSight subscription for the aim of testing this function. From that account, you create an Amazon Q Enterprise utility on IAM Identification Heart and undergo the QuickSight integration setup steps on the Amazon Q Enterprise console that may create the QuickSight account for you in IAM Identification Heart. Keep in mind to delete that new QuickSight account and Amazon Q Enterprise utility after your testing is finished to keep away from additional billing.

Full the next steps to arrange the QuickSight connector from Amazon Q Enterprise for an present QuickSight account:

1. On the Amazon Q Enterprise console, navigate to your utility.
2. Select Amazon QuickSight within the navigation pane.

3. Select Authorize QuickSight solutions.

4. Beneath Assign QuickSight Admin Professional roles, select the IAM Identification Heart group you created as a prerequisite.
5. Beneath Service Entry, choose Create and use a brand new service function.
6. Select Save.

You will notice a dashboard with particulars for QuickSight. If you have already got a dataset and subjects, they may present up right here.

You’re now prepared so as to add a dataset and subjects within the subsequent part.

Add knowledge in QuickSight

On this part, we create an Amazon Redshift knowledge supply. You possibly can as an alternative create an information supply from the database of your alternative, use recordsdata in Amazon S3, or carry out a direct add of CSV recordsdata and hook up with it. Consult with Making a dataset from a database for extra particulars.

To configure your knowledge, full the next steps:

1. Create a brand new dataset with Amazon Redshift as an information supply.

Configuring this connection gives a number of decisions; select the one that most closely fits your wants.

2. Create a subject from the dataset. For extra data, see Creating a subject.

3. Optionally, create dashboards from the subject. If created, Amazon Q Enterprise can use them.

Ask queries to Amazon Q Enterprise

To start out chatting with Amazon Q Enterprise, full the next steps:

1. On the Amazon Q Enterprise console, navigate to your utility.
2. Select Amazon QuickSight within the navigation pane.

It is best to see the datasets and subjects populated with values.

3. Select the hyperlink below Deployed URL.

We uploaded AWS Price and Utilization Reviews for a particular AWS account in QuickSight utilizing Amazon Redshift. We additionally uploaded Amazon service documentation into an information supply utilizing Amazon S3 into Amazon Q Enterprise as unstructured knowledge. We are going to ask questions associated to our AWS prices and present how Amazon Q Enterprise solutions questions from each structured and unstructured knowledge.

The next screenshot exhibits an instance query that returns a response from solely unstructured knowledge.

The next screenshot exhibits an instance query that returns a response from solely structured knowledge.

The next screenshot exhibits an instance query that returns a response from each structured and unstructured knowledge.

The next screenshot exhibits an instance query that returns a number of visualizations from each structured and unstructured knowledge.

Clear up

Should you not need to use this Amazon Q Enterprise function, delete the assets you created to keep away from future expenses:

1. Delete the Amazon Q Enterprise utility:
   1. On the Amazon Q Enterprise console, select Purposes within the navigation pane.
   2. Choose your utility and on the Actions menu, select Delete.
   3. Enter delete to verify and select Delete.

The method can take as much as quarter-hour to finish.

2. Delete the S3 bucket:
   1. Empty your S3 bucket.
   2. Delete the bucket.
3. Delete the QuickSight account:
   1. On the Amazon QuickSight console, select Handle Amazon QuickSight.
   2. Select Account setting and Handle.
   3. Delete the account.
4. Delete your IAM Identification Heart occasion.

Conclusion

On this put up, we confirmed easy methods to embrace solutions out of your structured sources in your Amazon Q Enterprise functions, utilizing the QuickSight integration. This creates a unified conversational expertise to your end-users that saves them time, helps them make higher choices by way of extra full solutions, and improves their productiveness.

At AWS re:Invent 2024, we additionally introduced the same unified expertise enabling entry to insights from unstructured knowledge sources in Amazon Q in QuickSight powered by Amazon Q Enterprise.

To study in regards to the new capabilities Amazon Q in QuickSight gives, see QuickSight Plugin.

To study extra about Amazon Q Enterprise, consult with the Amazon Q Enterprise Consumer Information.

To study extra about configuring a QuickSight dataset, see Handle your Amazon QuickSight datasets extra effectively with the brand new consumer interface.

QuickSight additionally gives querying unstructured knowledge. For extra particulars, consult with Combine unstructured knowledge into Amazon QuickSight utilizing Amazon Q Enterprise.

Concerning the authors

Jiten Dedhia is a Sr. AIML Options Architect with over 20 years of expertise within the software program business. He has helped Fortune 500 corporations with their AIML/Generative AI wants.

Jean-Pierre Dodel is a Principal Product Supervisor for Amazon Q Enterprise, accountable for delivering key strategic product capabilities together with structured knowledge assist in Q Enterprise, RAG. and total product accuracy optimizations. He brings intensive AI/ML and Enterprise search expertise to the group with over 7 years of product management at AWS.