Connect Data Sources

Auteryn can sync knowledge base content from multiple external sources. Once connected, your knowledge base stays up to date automatically.

---

Notion

Sync Notion pages, databases, and workspaces.

1. Go to Knowledge Bases → New Knowledge Base → Notion
2. Click Connect Notion — you’ll be redirected to Notion’s OAuth screen
3. Grant access to the pages or workspaces you want to sync
4. Select which pages or databases to include
5. Click Sync

Note

Auteryn only reads your Notion content. It cannot create or modify pages.

What gets synced: Page titles, body text, inline databases, linked pages. Images are skipped.

Confluence

Sync Confluence spaces and pages.

1. Go to Knowledge Bases → New Knowledge Base → Confluence
2. Click Connect Atlassian and complete the OAuth flow
3. Select your Confluence site and the spaces to sync
4. Click Sync

What gets synced: Page titles, body content, nested pages. Attachments are not synced.

Google Drive

Sync Google Docs, PDFs, and folders from Google Drive.

1. Go to Knowledge Bases → New Knowledge Base → Google Drive
2. Click Connect Google and grant read access
3. Select the folders or files to sync
4. Click Sync

Supported files: Google Docs (converted to text), PDFs, plain text files, Markdown.

GitHub

Sync a repository’s documentation and source files.

1. Go to Knowledge Bases → New Knowledge Base → GitHub
2. Click Connect GitHub and authorize Auteryn
3. Select the repository and branch to sync
4. Optionally filter by directory (e.g., only /docs)
5. Click Sync

What gets synced: README files, Markdown files, code files (optional). Binary files are skipped.

Tip

For code-focused knowledge bases, enable Include source files and specify the extensions (.py, .ts, .go, etc.).

Web Crawler

Crawl any public website and sync its content.

1. Go to Knowledge Bases → New Knowledge Base → Web Crawler
2. Enter the starting URL (e.g., https://docs.yourproduct.com)
3. Set the crawl depth (1 = only that page; 3 = follow links 3 levels deep)
4. Set an optional URL pattern filter
5. Click Start Crawl

Caution

The web crawler only works on publicly accessible pages. It cannot crawl pages behind a login.

---

Sync schedule

For connected sources, configure automatic re-syncing:

1. Open the knowledge base → Sync Settings
2. Set the sync frequency: Manual, Daily, or Weekly

File uploads are static — they only update when you upload new files.