Data Sources

Connect your existing document storage to Outpost

Outpost can sync documents from your existing storage systems. Configure one or more data sources to start processing your documents.

Achtung

These data source configurations are relevant when you operate your own Outpost runtime (on-prem/customer-managed). In the default managed setup, most users configure sources in meinGPT and do not edit app_config.yaml directly.

UI-First Setup (Empfohlen)

Für die meisten Nutzer gilt: Quellen zuerst direkt in meinGPT konfigurieren:

  1. Öffne Data Pools / Data Sources in meinGPT
  2. Quelle im UI hinzufügen
  3. Sync starten und indexierte Inhalte prüfen

Die app_config.yaml-Beispiele pro Quelle brauchst Du nur, wenn Du einen eigenen On-Prem-Outpost betreibst.

Einige Quellen haben keine Managed-/Cloud-Option und sind ausschließlich mit einem eigenen Enterprise Outpost verfügbar: Local Files, IMAP Mailbox und SMB/CIFS. Diese werden nur über die app_config.yaml auf dem Outpost-Server konfiguriert.

Supported Data Sources

Local Files

Mount local folders directly into Outpost (nur Enterprise Outpost)

SharePoint/OneDrive

Connect to SharePoint document libraries and OneDrive

Amazon S3

Connect to AWS S3 buckets or S3-compatible storage

Google Drive

Sync documents from Google Drive

Confluence

Sync pages and attachments from Confluence

Web Crawler

Crawl public or internal websites into a data pool

IMAP Mailbox

Sync emails from IMAP mailboxes (nur Enterprise Outpost)

SMB/CIFS

Connect to Windows/Samba network shares (nur Enterprise Outpost)

WebDAV

Connect to WebDAV servers (Nextcloud, ownCloud, etc.)

Basic Configuration

config/app_config.yaml
data_pools:
  - id: local
    type: local
    base_path: ./data
    
  - id: my-s3
    type: s3
    access_key_id: $AWS_ACCESS_KEY_ID
    secret_access_key: $AWS_SECRET_ACCESS_KEY
    endpoint: https://s3.amazonaws.com
    bucket_name: my-bucket

Hinweis

Security: Always use environment variables for credentials, never hardcode them in configuration files.

Synchronization (How It Works)

For all source types, synchronization follows the same high-level pattern:

  1. Data pool configuration is resolved (from meinGPT and/or local data_pools in app_config.yaml)
  2. Outpost connector fetches files/content into local sync storage
  3. Content is parsed, chunked, embedded, and indexed
  4. Later sync runs update changed content incrementally
War diese Seite hilfreich?