0 / 0
Preparing data
Last updated: Oct 23, 2024
Preparing data

After you create a project, or join one, the next step is to add data to the project and prepare the data for analysis.

Required permissions
You must have the Admin or Editor role in a project to add or prepare data.

You can add data assets from your local system, from a catalog, from the Resource hub, or from connections to data sources. See Adding data to a project.

You can add these types of data assets to a project:

  • Data assets from files from your local system, including structured data, unstructured data, and images. The files are stored in the project's IBM Cloud Object Storage bucket.
  • Connection assets that contain information for connecting to data sources. You can add connections to IBM or third-party data sources. See Connectors.
  • Connected data assets that specify a table, view, or file that is accessed through a connection to a data source.
  • Connected folder assets that specify a path in IBM Cloud Object Storage.

To get started quickly, take a tutorial. See Quick start tutorials.

To refine data by cleansing and shaping it, you can:

  • Select the Prepare data tile on your watsonx home page.
  • Add the data to the project, then open the data asset and click Prepare data.

To manage feature groups for a data asset, open the data asset and go to its Feature group page.

To create synthetic data, you can:

  • Select the Prepare data tile on your watsonx home page.
  • Select the Generate synthetic tabular data tile.

To associate grounding documents with a foundation model prompt to help with retrieval-augmented generation tasks, you can:

  • From the project overview, click the Assets tab, and then choose New asset > Ground gen AI with vectorized documents.

Learn more

Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more