🛠️ How-to guide

<aside> 🗂️

WHAT IT DOES

Once content is in, the Sources area is where you keep it healthy — check what processed, open any item to preview it, tag and organize it, retry anything that failed, and remove what's out of date.

</aside>

Viewing your content

The Sources list shows every item with its type, status, and last update. Use the All / Ready / Processing / Failed tabs, search, and filters to find what you need, or group by a tag. Select any item to open its detail view.

The Sources list groups content by status — Ready, Processing, and Failed — so you can spot and fix anything that didn't process.

The detail view shows the original source (file or URL), a preview of the extracted content, its metadata (which knowledge base it's in, source type, status, last updated), and — for crawled pages — a history of when it was fetched and indexed.

What the statuses mean

• Ready — processed and available for your agents to answer from.
• Processing — still being converted and indexed; check back shortly.
• Failed — something went wrong. Open the item to see the reason, and use the Failed tab to find everything that needs attention.

Editing and organizing

• Tag items one at a time or in bulk to keep them organized (see Sources).
• Add to knowledge base — select items and add them to a knowledge base (you can create a new one on the spot). This just files the content — nothing is re-uploaded.
• Crawled and uploaded text isn't edited word-by-word here — to change it, update the original source and refresh, or recompose a manual entry.

Retrying and deleting

• Retry — select failed items (or use the Failed tab) and retry processing.
• Delete — remove an item from its detail view, or select several and delete in bulk. The confirmation offers "Don't re-add these on the next crawl / re-ingest" so a website, SharePoint, or cloud source won't recreate them. You can reverse this later from the crawl's Blocked URLs list.

FAQ

• An item is stuck on Processing — what do I do? Large files and big crawls take longer; if it lands on Failed, open it to see why, fix the source, and retry.
• I deleted a crawled page but it came back. Re-delete it and tick "Don't re-add…" so it's added to the crawl's Blocked URLs.