Create a Zendesk Unstructured Data Stream (Beta)
Create an unstructured data lake object in Data Cloud to ingest your Zendesk Knowledge articles 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 connect unstructured data: | Data Cloud Architect |
Before you begin:
- Make sure you've set up a Zendesk connection.
-
From App Launcher, select Data Cloud.
-
Click Data Lake Objects and then click New.
-
To choose a method for creating your data lake object, select From External Files, and click Next.
-
Choose the Zendesk connector, and click Next.
-
To specify what content is ingested into Data Cloud, from the Select Connection dropdown list, select the Zendesk connection you previously created. Data Cloud auto-populates the source based on the connection that you select.
-
Configure what Zendesk Knowledge articles you want to ingest.
- Included Categories, Enter the category numbers for the Zendesk Knowledge articles you want to ingest. Separate multiple categories with a comma, for example:
33947411893029, 45247421893041
. - Included Sections, Enter the category section numbers for the Zendesk Knowledge articles you want to ingest. Separate multiple sections with a comma, for example:
36947911883069, 75957411893379
. Each section you enter must have a parent category under “Included Categories”, otherwise the section is ignored. Leave this field blank to include all the sections in your specified categories.
- Set the filters you prepared to refine which Zendesk Knowledge articles to ingest. Each filter you set narrows the filtering criteria. For example, if you include a label and filter by creation date, then only articles from your specified category that have this label and that were created on or after the date you specify, are included in the ingestion.
- Included Tags, Enter the Zendesk Knowledge tags for articles you want to ingest. Separate multiple tags with a comma, for example:
Tag1, Tag2
. - Excluded Tags, Enter the Zendesk Knowledge tags for articles you don’t want to ingest. Separate multiple tags with a comma, for example:
Tag1, Tag2
. - Included Labels, Enter the Zendesk Knowledge labels for articles you want to ingest. Separate multiple tags with a comma, for example:
Label1,Label2
. - Excluded Labels, Enter the Zendesk Knowledge labels for articles you don’t want to ingest. Separate multiple tags with a comma, for example:
Label1, Label2
.
If an article has both an excluded and an included tag or label, it’s not ingested.
- Created On or After Date, Select a creation date on or after which Zendesk articles are ingested.
- Last Updated On or After, Select a “Last Update” date on or after which Zendesk articles are ingested.
-
Click Next. The connector refreshes the ingestion every hour. To view sync status, go to your Data Stream status.
-
To set up your unstructured lake object and its associated data model object, add an Object Name and an Object API Name for the UDLO. See Data Lake Object Naming Standards.
-
Map the UDLO to a UDMO.
- To create a new UDMO, click New. Then select from the Data Space dropdown list a data space in which to create it. Add an Object Name and an Object API Name for the UDLO. See Data Lake Object Naming Standards.
- To use an existing UDMO, click Existing, and select a data space and a UDMO from the list from which to select the existing UDMO.
-
Optionally, leave the checkbox selected to create a search index configuration for the UDMO using system defaults that automatically selects 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.
-
Click Next, or if you created a search index configuration, review the details, and save your work.
The data stream now ingests your Zendesk Knowledge data into an unstructured data lake object, and maps it to an unstructured data model object (UDMO). From this UDMO, a search index is created which can now be used to ground AI-generated responses.