How to Configure Sharepoint Knowledge Ingestion

Sharepoint Knowledge ingestion allows you to ingest the site content from your Sharepoint pages.

Pre-Requisites

  • Please ensure the required SharePoint Connector has been created with the necessary permissions. Please refer the SharePoint API Access Requirements Doc for details.
  • Please ensure the Service Account being used for connecting to SharePoint has access to the Sites we want to ingest from.

Configuration

Start by creating a new Ingestion under Answers > Ingestion > Internal Knowledge Settings

  • First, select the Connector which was created for the ingestion and then provide a name for the ingestion. under Ingestion Name.

  • Then, choose a Domain. The domain is the functional areas of employee service that is most related to the knowledge being ingested for this configuration.

  • In order to ingest articles from a SharePoint Site, users would need to define the Start URL. They commonly follow the below structure :

    • Site Pages
      • https://<instance-name>.sharepoint.com/sites/<site-name>/_api/SitePages/Pages?$top=10&$skip=0
      • https://graph.microsoft.com/beta/sites/<instance-name>.sharepoint.com:/sites/<site-name>:/pages
    • Teams Site Pages
      • https://graph.microsoft.com/beta/sites/<instance-name>.sharepoint.com:/teams/<teams-site-name>:/pages_
      • https://<instance-name>.sharepoint.com/teams/<teams-site-name>/_api/SitePages/Pages?$top=100&$skip=0

  • Users also need to provide the Article Url in order for us to generate this for all the ingested Articles. The field that controls this is the Article Url Override filed under Field Overrides.

Validation

  • Once you have submitted the Knowledge ingestion configuration, it will kick off the Ingestion pipeline in the background, the status of the same can be tracked on the Ingested Knowledge View
  • You can search for the Articles with their Title's here, and if they are listing on the Console that means they have been ingested successfully.
  • Please note, only Site Pages in the Published state are ingested into the AI Assistant. See Microsoft documentation for more details on Sharepoint page lifecycle.