Skip to main content Skip to complementary content
Qlik Resources
Loading SearchUnify's search If you need assistance with your product, please contact Qlik Support.
Qlik Customer Portal
Loading SearchUnify's search If you need assistance with your product, please contact Qlik Support.
Qlik Customer Portal

Analyzing business intelligence questions using Amazon Bedrock

This Job uses the tBedrockClient component to send a business intelligence question to Amazon Bedrock using the Titan Text Lite model to generate insights, and displays the AI-generated answer in the console.

Before you begin

Before running this Job, ensure you have:

  • An active AWS account with Amazon Bedrock enabled.
  • Amazon Bedrock API keys configured in your AWS account. For more information, see How Amazon Bedrock API keys work.
  • Access to the amazon.titan-text-lite-v1 model in your AWS region.
  • Your AWS access key and secret key stored securely.

Linking the components

Procedure

  1. Create a new Standard Job and add the following components by typing their names in the design workspace or dragging them from the Palette: tBedrockClient, and tLogRow.
  2. Connect tBedrockClient to tLogRow using a Row > FLOW connection.
    Job design showing tBedrockClient connected to tLogRow.

Configuring the components

Procedure

  1. Double-click tBedrockClient to open its Component view.
  2. In the Basic settings tab, configure the following parameters:
    • In the Credential provider list, select API keys.

      Make sure the API key is set as an environment variable. For more information, see Use an Amazon Bedrock API key.

    • In the Region field, select or enter your AWS region (for example, "us-east-1").
    • In the Model ID field, click the [...] button and select amazon.titan-text-lite-v1 from the list.
    • In the Request template field, enter the following JSON: 
      {
  "inputText": "As a Qlik analytics expert, provide a detailed answer to this question: What are the top 3 key performance indicators (KPIs) that a SaaS company should track to measure customer success?"
}
    tBedrockClient Basic settings showing Credential provider set to API keys, Model ID as amazon.titan-text-lite-v1, and the request template with the Qlik-focused prompt.
  3. Click Edit schema and define the following output column:
    • content (String)

    This column will store the AI-generated answer from Amazon Bedrock.

  4. Click OK to close the schema editor and OK to close the component view.
  5. Double-click tLogRow to open its Component view.
  6. In the Basic settings tab, set the Mode as Vertical.
  7. Click OK to close the component view.

Executing the Job

Procedure

  1. Press Ctrl+S to save the Job.
  2. Press F6 to execute the Job.

Results

The Job sends the business intelligence question to Amazon Bedrock using the Titan Text Lite model with a Qlik Analytics expert context, and displays the AI-generated detailed answer in the console.

Run console showing the execution result with the AI-generated expert answer displayed in table format.

The console output displays the detailed AI-generated answer identifying the top three customer success KPIs with explanations tailored for Qlik Analytics users.

Related reference
Related information

Did this page help you?

If you find any issues with this page or its content – a typo, a missing step, or a technical error – please let us know!

Leave your feedback here