Google Drive · Connector
How do we connect Google Drive to AI agents on our own infrastructure?
Katonic connects to Google Drive, reads the files in the drive or the folder you name and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from those files with a model you serve, so the files and the questions are not sent to a public AI service.
What it reads.
From Google Drive.
- 01Google Workspace files and other files in Drive
- 02A single folder, where you give its URL or ID
Through: Google Drive API v3
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
OAuth 2.0, or a service account.
The set-up dialog asks for
- Folder URL or ID (optional)
Permissions
Access is set on the source in Katonic. In addition, Katonic reads the permissions of each item from Google Drive and re-syncs them, every 24 hours by default. Whether an item's own permissions restrict who can retrieve it, or only add to the access set on the source, is a setting an administrator turns on for the cluster.
Katonic reads the permission list of each file: users, groups, domain sharing and link sharing. A file shared with anyone who has the link is blocked by default, and a file shared with the whole domain is flagged.
Sync
Incremental, by modified time, and full.
You set how often the source is read again, in minutes, hours, days or weeks.
Use case pages that name Google Drive.
Does Katonic read Google Drive sharing settings?
Yes. It reads the permission list of each file and re-syncs it, every 24 hours by default. Whether those permissions restrict retrieval, or only add to the access set on the source in Katonic, is a setting an administrator turns on for the cluster.
What happens to files shared by link?
A file shared with anyone who has the link is blocked by default.
Where are the files indexed?
In the Knowledge Engine, on infrastructure you own or control. They are not sent to a public AI service.