Current Page Document Loader

Load the text of the page in your current tab, ready to index into a knowledge base.

What it does

Current Page Document Loader reads the text of the active browser tab and puts it in one output field, named by Output field name (text by default). It reads the page as you see it, so pages behind a login and content added by scripts are included.

Set DOM Selector to read only part of the page, such as the main article. It uses the same text extraction as Get All Text, and is meant to feed the Indexer.

When to use it

• Save the article, document or internal tool page you are looking at into a knowledge base.
• Index pages that need you to be signed in, which URL Document Loader cannot reach.
• Start it from a right-click so you can index any page as you browse.

Inputs and settings

Réglage	Type	Ce que cela fait
Output field name	Text	The name of the output field that will hold the loaded text. Par défaut : text
DOM Selector	Page element	The selector of the DOM element to interact with.
Options	Group	The options for the node.
Options › Visible text only	Toggle	Only return text from visible elements. Par défaut : Off
Options › Include input fields	Toggle	Whether to include the input fields in the output. Par défaut : Off

• Leave DOM Selector empty to read the whole page. Use the picker to click the part you want, or type a selector such as article or main.
• Turn on Visible text only to skip hidden menus, collapsed sections and other text you can’t see.

Outputs

• Output

Each item has the page text in the field you named (default text). With Include input fields on, the incoming fields are kept next to it. Pass it to the Indexer’s Input as {{ $input.text }}.

Dependencies and credentials

None. This node needs no connection and has no slots for other nodes.

Example workflow

1. Context Menu with Menu Contexts Page, so you can right-click any page to run the workflow.
2. Current Page Document Loader with DOM Selector article, Visible text only on and Output field name text.
3. Indexer with Input {{ $input.text }}. Connect Local Knowledge to Knowledge and Recursive Character Text Splitter to Text Splitter.

Common issues

• “No content found”. The page, or the element matched by DOM Selector, has no text. Run the workflow once the page has loaded, and check or clear DOM Selector.
• The node doesn’t run in the web app. This node runs in the browser extension; install it or run the workflow from the extension.
• Menus and footers end up in the knowledge base. Set DOM Selector to the main content, and turn on Visible text only.

Related nodes

• Indexer: save the text into a knowledge base.
• Get All Text: the same page text, when you don’t need to index.
• URL Document Loader: load a page by its address, without opening it.