Skip to main content

SharePoint (Knowledge Base)

This section explains how to connect SharePoint Online as a Knowledge Base data source in DataDios. It is a read-only connector: you browse a site's document libraries, folders, and files, and the platform ingests file content into RAG so it is searchable through Hybrid Search.

The connector targets SharePoint Online (not SharePoint Server / on-prem) and reads document-library files — Word, PDF, PowerPoint, and similar. Site Pages and Lists are not ingested.

Prerequisites​

SharePoint is authenticated app-only through Azure AD (Microsoft Entra ID) client credentials and the Microsoft Graph API. Register an app once in the Azure portal:

  1. Register an application (Microsoft Entra ID → App registrations → New registration). Note its Application (client) ID and Directory (tenant) ID.
  2. Add a client secret (Certificates & secrets → New client secret) and copy its value.
  3. Grant the Sites.Read.All application permission (API permissions → Add a permission → Microsoft Graph → Application permissions → Sites.Read.All), then click Grant admin consent.

You'll also need the site URL of the SharePoint site whose libraries you want to read, e.g. https://contoso.sharepoint.com/sites/Engineering.

Steps to Create and Test a SharePoint Data Source​

Step 1: Create a Data Source​

  1. Navigate to the Data Sources tab in DataDios
  2. Click + CREATE SOURCE
  3. In the data source type dropdown, expand Knowledge Base and select SharePoint

Step 2: Fill Connection Details​

  • site_url: The SharePoint site URL, e.g. https://contoso.sharepoint.com/sites/Engineering (required)
  • tenant_id: Your Azure AD Directory (tenant) ID (required)
  • client_id: The registered app's Application (client) ID (required)
  • client_secret: The app's client secret (required, stored encrypted)
  • schedule_sync: (Optional) 15 Minutes, Hourly, or Daily for metadata synchronization

JSON Configuration​

{
   "site_url": "https://contoso.sharepoint.com/sites/Engineering",
   "tenant_id": "00000000-0000-0000-0000-000000000000",
   "client_id": "11111111-1111-1111-1111-111111111111",
   "client_secret": "your-client-secret",
   "schedule_sync": ""
}

Step 3: Test Connection​

  1. Click TEST CONNECTION
  2. Correct credentials with admin consent resolve the site and return Status: OK. The client secret is never echoed back in any response or log.
  3. If the test fails, verify the Sites.Read.All permission has admin consent granted and that the site URL points to an existing site.

Step 4: Save Data Source​

  1. Click CREATE to save the data source
  2. It appears on the Data Sources listing page under Knowledge Base
  1. Expand the data source to browse the site's document libraries → folders → files.
  2. Document-library files are ingested into RAG and become searchable through Hybrid Search.