Data Sources

Train your AI agent with websites, documents, text snippets, Q&A pairs, and Notion. Learn how to structure training data for optimal agent performance.

Text Snippets

Create custom text snippets for flexible, organized training data. Perfect for maintaining structured information.

Creating Snippets

Add multiple snippets, each with a unique title:

knowledge base sources dashboard with texts source highlighted

Formatting

Each snippet supports rich text:

  • Headings for structure
  • Bold, italic, strikethrough
  • Ordered and bullet lists
  • Hyperlinks
  • Emojis

knowledge base sources texts source form

Website Crawling

The Website Crawling feature in the Data sources tab enables you to train your AI agent using content directly from websites. Whether you're working with a full site, a sitemap, or individual URLs, this tool gives you flexible control over what gets included in your agent's knowledge base.

knowledge base sources dashboard with websites source highlighted knowledge base websites source form knowledge base websites source form

If you're using Shopify, it’s recommended to add your sitemap (/sitemap.xml) instead of crawling the entire website. This reduces total MB usage and avoids duplicate product and collection pages, since Shopify’s sitemap already provides a clean, structured source of your content.

Creating Q&As

knowledge base sources dashboard with question answer source highlighted

  • Each Q&A entry begins with a title, this helps you quickly locate and organize questions.
  • You can associate multiple variations of a question with a single answer, improving recognition and response accuracy.
  • You can bulk upload Q&As up to 100 rows per file in .xlsx format, with a maximum file size of 1MB.

knowledge base sources qa source form

Management & Deletion

  • Delete any Q&A individually.
  • To delete all at once, check the box next to "Q&A sources" and click the delete button that appears.

Notion

Sync your Notion database with your agent. Umiplex automatically imports and indexes your Notion content.

Auto Retrain

Keep your agent updated automatically. Auto Retrain refreshes knowledge weekly.

Available on: Standard and Pro plans. Hobby plan users retrain manually.

Supported Sources

  • Websites — Discovers new pages, updates content
  • Notion — Syncs workspace changes
  • Remote storage — Google Drive, Dropbox, and more

How It Works

  • Runs automatically every 24 hours
  • Fetches latest content from all sources
  • New pages discovered automatically
  • No manual action needed

On this page