> ## Documentation Index
> Fetch the complete documentation index at: https://elephas.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# How to Add a Web Page to a Brain

> Add a web page to an Elephas Brain by its address and ask about it next to your documents. Elephas saves a copy once. Limits and pages that cannot be read.

Open a Brain, choose **Add › Web Page…** (⇧⌘O on Mac, Ctrl+Shift+O on Windows), paste the page's address and click **Add**. Elephas saves a copy of the page and indexes it on your computer, so you can ask about it alongside your PDFs, notes and reports.

## Before you start

* You need an internet connection to fetch the page. Once it is saved, it stays readable offline.
* The page must be public. Elephas cannot sign in to sites, so pages behind a login, a paywall or a cookie wall usually cannot be read.
* In a Team workspace, you need a role on the Team Brain that lets you add files.

## Steps

<Steps>
  <Step title="Open the Brain">
    Click the Brain in the sidebar, or open it from the **Brains** page.
  </Step>

  <Step title="Choose Add Web Page">
    Click **Add**, then **Web Page…**. You can also choose **File › Add Web Page…**, or press ⇧⌘O on Mac or Ctrl+Shift+O on Windows.
  </Step>

  <Step title="Paste the address">
    In **Web address**, paste the full address, starting with `https://` or `http://`, for example `https://example.com/article`. Click **Add** or press Return (Mac) or Enter (Windows). Press Escape or click **Cancel** to close the form.
  </Step>

  <Step title="Wait for it to be fetched">
    The form shows **Fetching…** while the page downloads. Then the page appears in the Brain's list, named after the page's title, and gets ready like any other document.
  </Step>
</Steps>

If the fetch fails, the form stays open with the reason, so you can correct the address and try again.

## How it works

### Elephas saves a copy, once

Elephas downloads the page once and keeps that copy. The copy is what gets indexed, what your citations open, and what syncs if you use Personal Sync. Elephas never fetches the page again on its own, so your answers do not change because a website changed.

To pick up a newer version of the page, add the same address to the same Brain again. If the page changed, Elephas adds it as a new version of the same document. If it did not change, nothing happens. See [update documents](/docs/brains-and-documents/update-documents-and-versions).

### What Elephas reads

* The page's main text and headings. Menus, headers, footers, sidebars and scripts are left out.
* If the address points to a PDF, Elephas saves and reads it as a PDF, with page numbers in its citations.
* Only the one page you entered. Elephas does not follow links or crawl the rest of the site.

Citations to a web page point to paragraphs, for example "paragraphs 12–14". See [citations and sources](/docs/ask/citations-and-sources).

### Limits

| Limit | Value |
| - | - |
| Page size | 20 MB |
| Time to load | 30 seconds |
| Redirects | Up to 5 |
| Addresses | `http://` and `https://` only |

### Privacy

Fetching the page is a normal web request from your computer to that website. It sends no cookies and no sign-in details. After that, reading and indexing happen on your computer. Asking about the page works like any other document: see [what data is sent to AI](/docs/privacy-and-security/what-data-is-sent-to-ai).

## Troubleshooting

| Message | What to do |
| - | - |
| **Enter a full web address starting with http\:// or https\://.** | Paste the whole address from your browser's address bar, including `https://`. |
| **The page could not be reached. Check your connection and retry.** | Check you are online and the address opens in your browser. |
| **The website did not return the page.** | The site returned an error, such as page not found or access denied. Check the address, or try a public version of the page. |
| **The page took too long to load.** | The site did not respond within 30 seconds. Try again later. |
| **The page redirected too many times.** | Open the address in your browser and copy the final address it lands on. |
| **This page is larger than the import limit.** | The page is over 20 MB. Save it as a PDF from your browser and add the PDF instead. |
| **This address is not a web page or a PDF.** | The address points to something else, such as an image, a video or a download. Download the file and add it with **Files…** if it is a [supported type](/docs/brains-and-documents/supported-file-types). |
| **No readable text was found in this file.** | The page builds its text with JavaScript after it loads. Save it as a PDF from your browser and add the PDF. |

For more, see [file import errors](/docs/troubleshooting/file-import-errors).

## Related articles

<CardGroup cols={2}>
  <Card title="Add files and folders" href="/docs/brains-and-documents/add-files-and-folders" />

  <Card title="Supported file types" href="/docs/brains-and-documents/supported-file-types" />

  <Card title="Update documents" href="/docs/brains-and-documents/update-documents-and-versions" />

  <Card title="Citations and sources" href="/docs/ask/citations-and-sources" />
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.