SharePoint/OneDrive

In meinGPT (UI)

For most teams, setup is done directly in meinGPT without editing local config files.

Open admin settings in meinGPT
Go to Data Pools / Data Sources
Click Add Source and choose this source type
Configure credentials and scope in the UI
Save and trigger the first sync

If you do not run your own DataVault runtime, this is usually all you need.

On-Prem Runtime Configuration (Advanced)

data_pools:
  - id: onedrive
    type: onedrive
    client_id: "4306c62e-d96d-41a0-9f59-f577e3707aba"
    refresh_token: $ONEDRIVE_REFRESH_TOKEN
    drive_id: $ONEDRIVE_DRIVE_ID
    drive_type: "personal"

Configuration Options

Field	Type	Default	Required	Description
`id`	string	-	✅	Unique identifier for the data pool
`type`	string	-	✅	Must be "onedrive"
`client_id`	string	"4306c62e-d96d-41a0-9f59-f577e3707aba"	❌	Application client ID
`client_secret`	string	null	❌	Application client secret
`refresh_token`	string	-	✅	OAuth refresh token
`drive_id`	string	-	✅	OneDrive ID
`drive_type`	string	-	✅	Drive type ("personal", "business", "documentLibrary")
`tenant_id`	string	null	❌	Optional custom tenant
`base_path`	string	"/"	❌	Optional folder path

Synchronization

Vault uses OAuth refresh token based access to OneDrive/SharePoint content.
Sync runs pull files from the selected drive scope and ingest incrementally.
If tokens rotate, runtime refresh updates are applied automatically during operation.

Setup

Register Azure app: Azure Portal → App registrations
Configure permissions: Microsoft Graph API permissions
Get refresh token: OAuth2 authorization flow
Add to environment: ONEDRIVE_REFRESH_TOKEN and ONEDRIVE_DRIVE_ID

→ Microsoft Graph Documentation

On-prem only: this source page is relevant when you operate your own DataVault runtime and configure data_pools yourself.