Create views with Data explorer using natural language

You can now create views in books with the new Data explorer feature using natural language. The Data explorer feature uses generative AI to analyze your query and matches it to the relevant data in TM1 to recommend views. An explanation for the logic behind the recommendation accompanies each recommended view. You can make changes to the view and add it to the book or insert it as-is.

The initial release of Data explorer is available in English only.
Important: The Data explorer feature is part of the Planning Analytics AI assistant add-on, which requires a separate license purchase; it is not included in a standard Planning Analytics Workspace license. To purchase a license, contact your IBM® sales representative or go directly to your IBM account.
Creating views in the Data explorer is a two-part process:
Analyze cube
For Data explorer to recommend views, you need analyzed cubes. Cube analysis takes place in the modeling workbench, which allows AI to review the structure of a cube and understand the data.
Submit query
Once cube analysis is complete, you can go to a book and enter your query in the Data explorer to get recommended views.

Prerequisites

Before you can use Data explorer, you need to have access to the analyzed cube, access to all of the dimensions and hierarchies in the cube, and read access to:
  • CubeSecurity
    • }CubeAttributes
    • }DimensionAttributes
    • }ElementAttributes_<dim> (For each dimension in the cube)
    • }SubsetAttributes_<dim> (For each dimension in the cube)
  • DimensionSecurity
    • }Cubes
    • }CubeAttributes
    • }Dimensions
    • }DimensionAttributes
    • }ElementAttributes_<dim> (for each dimension in the cube)
    • }SubsetAttributes_<dim> (for each dimension in the cube)
    • }Subsets_<dim> (for each dimension in the cube)

Creating views in Data explorer

Follow these steps to run a cube analysis and then create a view in Data explorer:
  1. In the modeling workbench data tree, go to the cube that you want to analyze.
  2. From the cube's menu, click AI operations > Analyze cube and click Analyze.
    Note: You can check the status of a cube analysis by clicking AI operations > Analyze log.
  3. After the cube analysis completes, go to the book where you want to create the view.
  4. Click AI operations and select Data explorer.
  5. Select the database and analyzed cube with the data that you want to use to create a view.
    Note: If you choose Auto-select for the analyzed cube, the most relevant cube is automatically selected to create a view, based on your query.
  6. Enter your query in natural language. For example, you can enter Show me sales performance trends over the last year or Show me 2024 sales of mobile devices in north america.
  7. Click Submit.

A view generates along with an explanation for the recommended view and the cube chosen to generate the view. You can add the view to the book in edit mode.

You can also make certain changes to the view such as switch rows and columns, move dimensions to the context area, edit the set, and change levels.

If there are other analyzed cubes with data that match your query, they are listed next to Alternative cubes. Click an alternative cube to see a recommended view from that cube.

AI-generated views

The Data explorer feature uses granite-3-8b-instruct from the Granite family of IBM foundation models to create the view and the explanation of its recommendation.

The Granite models are decoder-only models that can efficiently predict and generate language. These models were built with trusted data that has the following characteristics:
  • Sourced from quality data sets in domains such as finance (SEC Filings), law (Free Law), technology (Stack Exchange), science (arXiv, DeepMind Mathematics), literature (Project Gutenberg (PG-19)), and more.
  • Compliant with rigorous IBM data clearance and governance standards.
  • Scrubbed of hate, abuse, and profanity, data duplication, and blocklisted URLs, among other things.
Note: IBM is committed to building AI that is open, trusted, targeted, and empowering. For more information about contractual protections that are related to IBM indemnification, see the IBM Client Relationship Agreement and IBM watsonx.ai service description.