Websites
Open in CMSThe Websites screen lists the web pages your agent uses as references when it answers, and is where you add a website by its URL. Found in the agent sidebar under Knowledge → Websites. Clicking a website opens its detail page.
Websites List
| New Website | Opens the Add New Website form. |
| Search Websites | Shows or hides the search panel below the buttons. |
| Sort By | Sorts the list by Code, Title or State, in Ascending or Descending order. |
| Grid View / List View | Switches between thumbnail cards and a compact list. Your choice is remembered. |
| Website card | Shows the thumbnail, a state badge, the title, the code, the author and how many chunks are active. Click it to open the detail page. |
| Load more data | Loads the next page of websites. |
Search Websites
| Title | Finds websites by title. |
| Code | Finds websites by code. |
| Author | Limits the list to one registered author. |
| State | Limits the list to one state (for example Active or Failed). |
| Apply | Runs the search. |
| Reset | Clears every search field. |
Add New Website: Source and Extraction
| Website Source | The starting URL, including http:// or https:// (required). |
| Guidelines | Expands the URL rules: HTTP and HTTPS only, a valid domain, at most 2048 characters, and large websites take longer to process. |
| Get Metadata | Reads the page to fill in the title and thumbnail, and opens the rest of the form. |
| Ingestion Mode | How the collected content is split into chunks (required). Options: Semantic or Skimming. See the Ingestion Modes on the Documents page. |
... button (Ingestion Mode) | Opens Ingestion Mode Parameters for the selected mode. |
| Content Extraction | Whether to extract only the starting page or follow links: Single Page or Related Pages. |
... button (Content Extraction) | Shown for Related Pages. Opens Content Extraction Parameters. |
Content Extraction Parameters
Used when Content Extraction is Related Pages. In create mode the dialog closes with Set Parameters.
| Max Depth | How many link levels to follow from the starting page (required). |
| Max Pages | The most pages to extract from the website. Fewer pages are faster and cheaper; more pages give wider coverage. |
| Keywords | Optional words that focus the crawl on relevant pages. Press Enter after each one (up to 10 keywords, 50 characters each). Leave empty to extract all pages. |
| Process The Whole Domain | When the starting URL has a path (for example example.com/docs/), only that path is processed by default. Turn this on to follow links across the whole domain. |
| Cache Mode | Advanced. How previously visited pages are handled: Bypass, Enabled, Disabled, Read Only or Write Only. Bypass always fetches fresh content; Enabled reuses cached results. |
| Word Count Threshold | Advanced. Pages with fewer words than this are skipped. |
| Excluded Tags | Advanced. HTML elements whose links are ignored while crawling, such as navigation menus. |
| Strip Tags | Advanced. HTML elements removed from the page before extraction, such as headers, footers and sidebars. |
Website Details
| Title | The main name of the website (required). |
| Author | A registered author, shown as code and name (required). Authors are managed under Citations → Authors. |
| Code | Your own unique identifier for the website (required). |
| Thumbnail Source | Choose URL (paste an HTTPS image link and click Preview) or Upload (pick an image file). |
| Permissions | Permission codes that restrict this website to authorized users only. |
| Website Source | A link to the source or website location. |
| Save / Cancel | Save creates the website and starts processing. |
Website Detail
| Resource State | The current state of the website and the number of active chunks. |
| View Chunks | Opens Chunks filtered to this website. |
| Chunking Process | The chunking status, with a View Log button that opens the Chunking Log. |
| Editing | The details can only be edited while the website is Inactive. |
Detail Actions
The buttons in the page header depend on the website's state.
| Deactivate | Shown when the website is Active. Stops the agent from using it. |
| Activate | Shown when the website is Inactive. Puts it back into use. |
| Retrain | Shown when Inactive. Lets you change the ingestion and extraction settings, then collects and processes the website again. |
| Retrain as New | Available in retrain mode. Processes a copy of the website as a new website. |
| Delete | Shown when Inactive. Deletes the website after confirmation. |
| Cancel Chunking | Shown while the website is processing. Stops the processing. |
| Retry Chunking | Shown when processing was Cancelled or Failed. You confirm by typing the website title. |
| Purge Web | Shown for Deleted, Failed or Cancelled websites. Removes it permanently after you type the website title. |
Related guide: Websites