How is Auto-GPT able to access the internet?

[JustinHinh]

I only have access to GPT-3.5-Turbo. I see that there is a browse_website function in commands.py

def browse_website(url, question):
    summary = get_text_summary(url, question)
    links = get_hyperlinks(url)

    # Limit links to 5
    if len(links) > 5:
        links = links[:5]

    result = f"""Website Content Summary: {summary}\n\nLinks: {links}"""

    return result

I'm not sure how this works though. Can someone explain the mechanism behind this?

[Sycosplat]

It looks like they are using BeautifulSoup for the web scraping:
https://beautiful-soup-4.readthedocs.io/en/latest/

You can have a look at browse.py to look at the implementation.