Top pages with a real browser, 3 results

What this example returns

This example returns up to 3 results.

The dataset’s “Overview” view shows 4 columns: Page URL, Page title, Result type, and Extracted Markdown. See every output field.

What each setting does

The input this example runs RAG Web Browser with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Search term or URL query

history of the printing press

Google Search keywords or the URL of a specific page. Search operators work, e.g. san francisco weather, https://www.cnn.com or function calling site:openai.com.

Maximum results maxResults

3

The maximum number of top organic Google Search results whose web pages will be extracted, up to 100: the run keeps every extracted page in memory until it returns. If `query` is a URL, then this field is ignored and the Actor only fetches the specific web page.

Default: 5 → this example uses 3

Google Search retries serpMaxRetries

2

Browser mode only. How many more browser sessions to try when Google answers a results page with a consent or unusual-traffic page. If the last one is blocked too, the run fails with that reason.

Select a scraping tool scrapingTool

Browser

Select a scraping tool for extracting the target web pages. The Browser tool is more powerful and can handle JavaScript heavy websites, while the Plain HTML tool can't handle JavaScript but is about two times faster.

Default: Raw HTTP → this example uses Browser

Target page dynamic content timeout dynamicContentWaitSecs

10

The maximum time in seconds to wait for dynamic page content to load. The Actor considers the web page as fully loaded once this time elapses or when the network becomes idle.

Remove cookie warnings removeCookieWarnings

Yes

If enabled, the Actor attempts to close or remove cookie consent dialogs to improve the quality of extracted text. Note that this setting increases the latency.

Remove HTML elements (CSS selector) removeElementsCssSelector

nav, footer, script, style, noscript, svg, img[src^='data:'], [role="alert"], [role="banner"], [role="dialog"], [role="alertdialog"], [role="region"][aria-label*="skip" i], [aria-modal="true"]

CSS selector for elements removed before the page is converted to text, Markdown or HTML. The default removes navigation, headers, footers, modals, scripts and inline images. Set it to a selector that matches nothing (e.g. dummy_keep_everything) to keep everything. When nothing is removed from a page that way (with…

Target page max retries maxRequestRetries

1

The maximum number of times the Actor will retry loading the target web page on error. If the last attempt fails, the page will be skipped in the results.

Output formats outputFormats

markdown

Select one or more formats to which the target web pages will be extracted and saved in the resulting dataset.

Request timeout requestTimeoutSecs

240

The maximum time in seconds available for the request, including querying Google Search and scraping the target web pages. For example, OpenAI allows only 45 seconds for custom actions. If the search or the page fetches are still unfinished when this time ends, the run stops and does not write a partial set.

HTML transformer htmlTransformer

none

How to extract the main content. None only removes the elements from Remove HTML elements. Readable text keeps the main content and falls back to the cleaned HTML when it isn't confident.

Desired browsing concurrency desiredConcurrency

5

The desired number of web browsers running in parallel. The system automatically scales the number based on the CPU and memory usage. If the initial value is `0`, the Actor picks the number automatically based on the available memory.

{
  "query": "history of the printing press",
  "maxResults": 3,
  "serpMaxRetries": 2,
  "scrapingTool": "browser",
  "dynamicContentWaitSecs": 10,
  "removeCookieWarnings": true,
  "removeElementsCssSelector": "nav, footer, script, style, noscript, svg, img[src^='data:'],\n[role=\"alert\"],\n[role=\"banner\"],\n[role=\"dialog\"],\n[role=\"alertdialog\"],\n[role=\"region\"][aria-label*=\"skip\" i],\n[aria-modal=\"true\"]",
  "maxRequestRetries": 1,
  "outputFormats": [
    "markdown"
  ],
  "requestTimeoutSecs": 240,
  "htmlTransformer": "none",
  "desiredConcurrency": 5
}

What it costs

You pay for the events the actor reports, such as each result or page it produces. Platform usage is included, except when a run renders pages in a browser: such runs also pay their platform usage (compute, browser, proxy) at your plan's rates.

• SERP pagefrom $0.00302One page of Google search results
• Fetched pagefrom $0.00119One stored page for a direct URL query; pages found by a search are covered by the SERP page event

Full pricing

Other ways to run RAG Web Browser

• Top pages for a search as Markdown, 3 resultsSearches Google and returns the top pages as clean Markdown.
• One web page as Markdown, 1 resultFetches a URL and converts it to Markdown.

All examples of RAG Web Browser

About RAG Web Browser

Web browser for AI agents and RAG pipelines: search Google, fetch the top result pages, and return clean Markdown or text ready for LLMs. Also accepts a single URL.

Price:

from $3.02 / 1,000 results

Developer:

Querystone

Categories:

AI, Agents, Developer tools

RAG Web Browser pageOutput fieldsPricing