Creating a Data Source in Generative AI Agents

Important

  1. On the Knowledge Bases list page, select the knowledge base that you want to create a data source for.
    If you need help finding the list page, see Listing Knowledge Bases.
  2. Click Create data source.
  3. Enter the following values:
    • Name: A name that starts with a letter or underscore, followed by letters, numbers, hyphens, or underscores. The length can be from 1 to 255 characters.
    • Description: An optional description
    • Tags: Click Show advanced options and add one or more tags to the agent. If you have permissions to create a resource, then you have permission to update its tags. If you need help, see Tags and Tag Namespace Concepts.
  4. Data source type: Object storage is displayed
    Object storage is the only type of data source that you can create.
  5. Data bucket
    Select inputs for the following fields:
    • bucket: Select the bucket that contains the data for this data source. If you don't see your bucket, ensure that you have
    • Object prefixes: Select the bucket's objects to be included for this data source. You can either select objects one at a time, select one or more folders, or select the Select all in bucket option to include all the objects.
      Important

      • PDF and txt files are the only supported bucket objects in Generative AI Agents.

      • If your data is not ready, you can point the data source to empty folders in a bucket and later, populate the folders with data. After you populate the folders with data, you can ingest the data into the data source.

  6. (Optional) Select the checkbox to start the ingestion job for this data source to add the data to this knowledge base. You can run the ingestion job later.
    The ingestion job adds the files that you selected in step 6 to the knowledge base for this data source.
  7. Click Create.
    Note

    If you run an ingestion job, the data source might take a few minutes to create.