Integrate unstructured data into Amazon QuickSight using Amazon Q Business

Amazon QuickSight is a comprehensive business intelligence (BI) platform that offers a range of advanced features for data analysis and visualization. It combines interactive dashboards, natural language query capabilities, pixel-perfect reporting, machine learning (ML) driven insights, and scalable embedded analytics in a single, unified service. Amazon Q in QuickSight brings natural language capabilities, helping both data analysts and business users get insights needed to inform decisions fast. Two key capabilities Amazon Q provides business users are the ability to ask and answer questions beyond their dashboards with data Q&A, and to build documents and slides explaining data using stories. Amazon Q capabilities draw from your existing enterprise data in QuickSight, maintaining organizational data governance and security rules.

Amazon Q Business is an enterprise AI assistant, allowing business users to discover and summarize insights from unstructured enterprise data sources, including document management systems, internal websites, and business applications.

This new integration automatically finds and summarizes relevant data insights from users’ documents, websites, and applications into data Q&A answers and generative story narratives, giving you a more complete picture of your business.

In this post, we discuss how to get started with this new feature.

Solution overview

The following key capabilities are now available to integrate structured and unstructured data in QuickSight:

• Enhanced Q&A with Amazon Q Business integration – Amazon Q in QuickSight data Q&A now presents summarized insights from Amazon Q Business as part of multi-visual answers, enriching multi-visual responses with additional business context.
• Enriched data stories with unstructured data insights – Amazon Q in QuickSight now automatically includes summarized information from Amazon Q Business when creating data stories in QuickSight, and allows you to upload your own documents to bring additional narrative context. This allows Amazon Q to generate more complete, relevant, and personalized narratives incorporating data from both structured and unstructured sources.
• Transparency – Both data Q&A and data stories provide links to unstructured source material, allowing you to verify sources to gain confidence in the insights you see.

In the following sections, we demonstrate how these new features work and how to put them to use for your own use cases.

Prerequisites

You need the following prerequisites:

• An AWS account.
• A QuickSight account with at least 1 Admin Pro user.
• A QuickSight dataset connecting to a relational data source or a file flat with structured data uploaded as a dataset. To create a QuickSight dataset, see Creating datasets.
• A QuickSight topic created from the dataset above. To create a topic, see Creating Amazon QuickSight Q topics.
• A QuickSight dashboard built on the dataset. To build your dashboard, see Build your first dashboard.
• A few documents in PDF or Word containing unstructured data related to the data being analyzed in QuickSight.

Create a new Amazon Q Business application from QuickSight

1. On the QuickSight console, choose Manage QuickSight on the dropdown menu.
   
2. Choose Security & permissions in the navigation pane, then choose Manage.

3. Select Amazon Q Business
4. On the dropdown menu for your preferred AWS Region, choose Create.
   The Amazon Q Business application will be created in the same Region as QuickSight.
   
   If you have an Amazon Q Business application already configured using AWS IAM Identity Center, your QuickSight account will also need to have IAM Identity Center in the same Region. If so, you will be able to link to your existing Amazon Q Business application here.
5. Enter a name for your new application (for this post, we name it New_QuickSight_application), then choose Done.
   

Configure your Amazon Q Business application

1. This will now open up the application you created (New_QuickSight_application) in the Amazon Q Business console automatically.
   
2. Go to Data sources and click on Select retriever.

3. For Retrievers, select Native.
4. For Index provisioning, select Enterprise or Starter (depending on your use case).
5. Choose Confirm.
   
   Amazon Q Business supports its own index where you can add and sync documents.
6. Choose Add data source
7. Choose Upload files or use any of the connectors to connect to your data repository.

8. Choose your files to upload, then choose Upload. In this example, we uploaded three files: Coffee Growth Plan for 2025, Coffee Sales, and Coffee Type Definitions.
   
9. When the upload is complete, choose Done.
   The index creation process will take a few minutes to complete. You can refresh the page to see its status.

Query structured and unstructured data using Amazon Q in QuickSight

In this example, we use a topic called coffee sales in QuickSight. The topic is created using an Excel file that contains coffee sales by customer, product, and region. To learn more on how to create a QuickSight dataset, see Creating datasets. To learn how to create a topic, see Creating Amazon QuickSight Q topics.

In the coffee sales topic details page, ensure Allow insight summaries from Amazon Q Business in Q&A is enabled as shown below.

Using Amazon Q in QuickSight, enter the query “bottom performing products.” You will see an additional section in the left pane that shows Insights from Q Business. This information is coming from the documents that were uploaded into the Amazon Q Business index.

Integrate unstructured data in data stories

In this example, we use a QuickSight dashboard that was created on coffee sales data. To learn more on how to build dashboards, see Build your first dashboard.

Create your story for the prompt and select visuals. You now have additional options to upload relevant documents from your computer and link to your company repository of documents stored in Amazon Q Business. When you build your story, you will see that the insights are now being retrieved from both structured data in QuickSight as well as unstructured data stored within Amazon Q Business.

Conclusion

In this post, we discussed how you are now able to bring in unstructured data from Amazon Q Business into QuickSight Q&A to ask questions about your data and obtain relevant insights from your company documents as well as get enriched insights in data stories.

This feature is available to all Amazon Q Business Pro Users. Try it out for your own use case, and share your feedback and questions in the comments.

Check out the other new exciting Amazon Q in QuickSight feature launches in Revolutionizing business intelligence: Amazon Q in QuickSight introduces powerful new capabilities.

About the authors

Priya Mysore is a Senior Worldwide GenAI Specialist at AWS, with over two decades of experience in data and analytics. Priya is passionate about helping customers unlock the true potential of their data using AI/ML capabilities in Amazon QuickSight. Priya excels at empowering both business and technical users to harness the full potential of their data through self-service analytics. She guides organizations in implementing intuitive, AI-driven solutions that democratize data access, enabling users across all levels to uncover actionable insights, make data-driven decisions, and drive business value. Priya’s deep knowledge of business intelligence, combined with her enthusiasm for AI services in the application layer, drives her to deliver innovative solutions that meet the evolving needs of AWS customers.

Rahul Easwar is a Senior Product Manager with Amazon QuickSight, bringing over 15 years of experience in implementing and leading global Analytics programs across various industry verticals. His expertise has been instrumental in shaping the future of business intelligence within the AWS ecosystem. As the product leader for Amazon QuickSight Pixel-Perfect Reporting, Easwar spearheaded the successful launch of this groundbreaking feature in 2022. Currently, Easwar is focused on pushing the boundaries of AI-powered analytics with Q in QuickSight. This cutting-edge initiative aims to democratize data insights by leveraging natural language processing and machine learning to make data exploration more intuitive and accessible to all users, regardless of their technical expertise.