Data sources

Which sources an Outpost connects, which meinGPT connects directly, and how a connection is made.

A data source is always created in meinGPT: that is where it gets a name, permissions and a release level. Where its documents live is decided afterwards — and for some sources the answer is "on a machine at your site", which is exactly what the Outpost is for.

Who fetches the files?

SourcesConfigured where
meinGPT directlySharePoint, OneDrive, Google Drive, Confluence, S3, WebDAV, web crawlerEntirely in meinGPT. No machine of your own needed.
Only via an OutpostFolders on a machine, SMB shares, IMAP mailboxes, databases and local MCP serversData source in meinGPT, the link in the Outpost

In the default case you do not need an Outpost

If your documents live in SharePoint or Google Drive, meinGPT connects them directly. An Outpost pays off when files or systems must not leave the building or cannot be reached from the cloud at all — a network drive and a database on your own network cannot.

How an Outpost source comes about

Two halves in two places, in this order:

  1. In meinGPT: create the data source — type Other for a folder, type SMB for a share. That produces a data source ID.
  2. In the Outpost: Data tab → Add data source. Paste the ID and state where on this machine the documents live.

There is no button in the Outpost that creates a data source. If you are looking for one, step 1 is missing.

The dialog in the Outpost offers the source types Other, SMB, S3 storage, WebDAV, Web crawler and IMAP. The three middle ones are also reachable from meinGPT — routing them through the Outpost is only right when the service is not reachable from the internet, e.g. an internal MinIO or a Nextcloud on your own network.

The sources in detail

What is the same for every source

  1. The Outpost fetches the files into its working area on this machine.
  2. It extracts text, splits it into passages, encodes them and stores them in the search index.
  3. Later runs only process what changed.
  4. What it cannot read, it skips — and records it by file extension on the Index tab.

Point 4 is the one to keep an eye on: a skipped file cannot be found, and the search tells nobody. → Console & operations

Permissions are created in meinGPT, not in the file system

File, NTFS, AD and POSIX permissions are not carried into the index. Anyone allowed to see a data source in meinGPT finds everything in it. How you split things into data sources is your permission model.

Was this page helpful?