Local Files

In meinGPT (UI)

Für die meisten Teams erfolgt die Einrichtung direkt in meinGPT, ohne lokale Config-Dateien.

Öffne die Admin-Einstellungen in meinGPT
Gehe zu Data Pools / Data Sources
Klicke Add Source und wähle diesen Source-Typ
Hinterlege Zugangsdaten und Scope im UI
Speichere und starte den ersten Sync

Wenn Du keinen eigenen DataVault betreibst, ist das in der Regel ausreichend.

On-Prem Runtime Configuration (Advanced)

data_pools:
  - id: local
    type: local
    base_path: ./data

Configuration Options

Field	Type	Default	Required	Description
`id`	string	-	✅	Unique identifier for the data pool
`type`	string	-	✅	Must be "local"
`base_path`	string	"./"	❌	Directory path to sync from

Synchronization

Vault scans base_path and syncs files into local ingest storage.
Changes are picked up in later sync runs (new/updated/deleted files).
Use read-only mounts when possible to reduce operational risk.

Docker Setup

docker-compose.yml

services:
  vault:
    volumes:
      - ./data:/data/vault              # Local directory
      - /mnt/network:/data/network:ro   # Network drive (read-only)

Basic Operations

# Add files to sync
mkdir -p data
cp your-documents.pdf data/

# Check processing
docker compose logs vault | grep -i local

→ Local File System Documentation

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