Create a Guru Unstructured Data Connection (Beta)

Create an unstructured data lake object (DLO) in Data Cloud to ingest your organization’s content from Guru into Data Cloud.

See the Unstructured Data Reference for a list of supported file formats.

This feature is a Beta Service. A customer may opt to try a Beta Service in its sole discretion. Any use of the Beta Service is subject to the applicable Beta Services Terms provided at Agreements and Terms. If you have questions or feedback about this Beta Service, contact the Data Cloud Connector team at datacloud-connectors-beta@salesforce.com.
User Permissions Needed 
To create a connection:System Admin profile or Data Cloud Architect permission set

Before you begin:

  • Make sure that you’ve set up a Guru connection and you know its name.
  • Verify you have a list of tags you want to use to filter your Guru cards.
  • Verify you have a list of Guru collections and folders that you want to ingest.

  1. From App Launcher, select Data Cloud.

  2. Select Data Lake Objects and then select New.

  3. Select the From External Files tile, and select Next.

  4. From the New Data Lake Object screen, choose the Guru connector tile and select Next.

  5. From the Connection Details dropdown, choose the Guru connection you previously created.

  6. In the Guru Collections and Folders Section, in the Included Collections field, enter the list of Collection IDs you created earlier as a comma-separated list. Without filtering applied, all knowledge base articles from all specified collections are ingested. If you leave the field blank, all cards in all collections are ingested.

  7. In the Guru Collections and Folders section, in the Included Folders field, enter the list of folders you collected earlier. Specify each folder as a comma-separated list in the following format: collection/folder. If you don't apply filters, all knowledge base articles from all specified folders are ingested. If you leave the field blank, all cards in all folders are ingested.

    • If the folder isn't in the specified collection, but the collection name is valid, the entire collection is ingested.
    • If an invalid collection is listed, no content is ingested.
    • If the folder and collection are valid, only the contents in the folder are ingested.

  8. If you want to include only verified Guru cards, check the Ingest only verified cards checkbox. If you leave the checkbox unchecked, unverified cards are ingested.

  9. In the Apply Filters section, you can apply filters to limit ingestion to the articles you want. There are several filters available. If you leave any filter field blank, all applicable items are ingested. When you apply more than one filter (even more than one filter of the same type), each filter removes or includes content from the number of files that are ingested. If you apply filters and no content is ingested, your filters are probably too restrictive. If you see content you didn’t intend to ingest, your filters are probably too broad.

    Apply any or all of the following filters:

    • Included Tags: Provide a comma-separated list of tags. Any card tagged with the provided tag is included. If multiple tags are listed, any cards tagged with any included tag is ingested. This field is case-sensitive. If you misspell a tag, it is ignored.
    • Excluded Tags: Provide a comma-separated list of tags. Any card tagged with the provided tag is excluded. If multiple tags are listed, all cards tagged any excluded tag is excluded. This field is case-sensitive. If you misspell a tag, it is ignored.
    • Creation Date: Select one date from the calendar widget. Any card created on or after the provided date is ingested.
    • Last Update Date: Select one date from the calendar widget. Any card updated on or after the provided date is ingested.

  10. In the Guru Card Access Levels to Include section, select the radio button to restrict the ingestion of Guru cards to: Default is Both.

    • Only Public cards
    • Non-public (teammates and restricted) cards
    • Both public and non-public (teammates and restricted) cards

    Select Next. By default, the connector runs every two hours. You can monitor sync status in Data Stream status.

  11. To set up your unstructured data lake object (UDLO) and its associated data model object, add an Object Name and an Object API Name for the UDLO. See Data Lake Object Naming Standards.

  12. Map the UDLO to a UDMO.

    1. To create a new UDMO, click New. Then select from the Data Space dropdown list a data space in which to create the UDMO. Add an Object Name and an Object API Name for the UDLO. See Data Lake Object Naming Standards.
    2. To use an existing UDMO, click Existing, and select a data space and a UDMO from the list of existing UDMOs.

  13. Leave the checkbox selected to create a search index configuration for the UDMO using system defaults that automatically select text fields and a chunking strategy for each field. You can deselect the checkbox and create a search index configuration later if you choose not to do so now.

  14. Click Next if you didn’t create a search index configuration. Otherwise, review the details and save your work.

The data stream ingests cards from Guru into a UDLO and maps them to a UDMO. From this UDMO, a search index is created which can now be used to ground AI-generated responses.

If you have any connection or ingestion issues look at the Troubleshooting information.