Read other web pages in a prompt with {{page}}

Pull text from other pages into a prompt with the {{page}} parameter.

On this page

{{page}} is the text of the page you're on. Give it a URL and it reads another page instead, without opening it in a tab: that turns any prompt or command into a small crawler.

# The options

Options go inside the brackets after page, in any order:

{{page query url limit=20% type=render timeout=5000}}
OptionWhat it does
urlReads this page instead of the open one. Starts with https:// or http://
queryAny other words. If the text doesn't fit, HARPA keeps the passages closest to them
limit=500At most 500 tokens of the page
limit=10%At most 10% of the model's context window
type=renderDefault. Loads the page in a hidden frame, so content drawn by JavaScript is read too
type=fetchDownloads the page's text only: faster, but misses content drawn by JavaScript
type=htmlDownloads the raw HTML
timeout=5000How long to wait for the page, in milliseconds (5000 by default)

For example, this reads the Northwind returns page and keeps the 10% of the context that is most about refunds:

{{page refund policy https://northwind.com/help/returns limit=10%}}

The full list of parameters is in Parameters.

# Fetch or navigate

  • {{page url}} is quick and needs no tab. It works on most sites, but not on sites that block it.
  • A Navigate step opens the page in a tab, like you would. It is slower, but it works on any site you can open, and a Loop can go over a list of links: see Navigate.

Try {{page url}} first; switch to navigating if the text comes back empty or says Failed fetching URL.

# Example: answer questions from a website

This command searches one site, reads the top results and answers from them, with links.

  1. Type / in the chat and click Create.
  2. Add an Ask step that saves the question in {{query}}.
  3. Add a Calc step, Set parameter, that saves {{serp {{query}} site:northwind.com}} in {{data}}.
  4. Add a Calc step, Extract SERP links, from data to links. Each link has a title, url and description.
  5. Add a GPT step:
Answer the question using only the information below. Cite sources as
markdown links, like [[1]](URL). Don't make anything up. Answer in {{language}}.

QUESTION: {{query}}

INFORMATION:
- {{links.0.title}} {{links.0.url}}
{{page {{query}} {{links.0.url}} limit=20%}}

- {{links.1.title}} {{links.1.url}}
{{page {{query}} {{links.1.url}} limit=10%}}

- {{links.2.title}} {{links.2.url}}
{{page {{query}} {{links.2.url}} limit=10%}}
  1. Click Save and run it with a question.

# Good to know

  • The prompt, the pages and the answer all share the model's context window. Keep the pages together under about 40% to leave room for a good answer.
  • A page read by URL is kept for 5 minutes, so reading it again in that time is instant.
  • A YouTube video URL gives its transcript.
  • To read a long page all the way through, piece by piece, see Chunking.