Google Drive

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: google-drive
    type: drive
    refresh_token: $GOOGLE_REFRESH_TOKEN
    scope: "drive.readonly"
    root_folder_id: null
    team_drive: null

Configuration Options

Field	Type	Default	Required	Description
`id`	string	-	✅	Unique identifier for the data pool
`type`	string	-	✅	Must be "drive"
`refresh_token`	string	-	✅	OAuth refresh token
`scope`	string	"drive.readonly"	❌	Access scope
`root_folder_id`	string	null	❌	Optional specific folder ID
`team_drive`	string	null	❌	Shared drive ID
`client_id`	string	null	❌	Optional custom client ID
`client_secret`	string	null	❌	Optional custom client secret
`base_path`	string	"/"	❌	Optional folder path

Synchronization

Vault uses the OAuth refresh token to access Google Drive content.
Sync runs fetch documents from the selected root scope (root_folder_id / base_path).
Later runs process only changed content.

Setup

Create Google Cloud project: Google Cloud Console
Enable Drive API: Enable Google Drive API
Create OAuth credentials: Download client credentials
Get refresh token: Complete OAuth2 flow
Add to environment: GOOGLE_REFRESH_TOKEN

→ Google Drive API Documentation

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