Significant-Gravitas / AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
https://agpt.co
Other
168.37k stars 44.41k forks source link

browse_website command returns error #5073

Closed Hotch-C closed 1 year ago

Hotch-C commented 1 year ago

⚠️ Search for existing issues first ⚠️

Which Operating System are you using?

Windows

Which version of Auto-GPT are you using?

Latest Release

Do you use OpenAI GPT-3 or GPT-4?

GPT-3.5

Which area covers your issue best?

Commands

Describe your issue.

Windows11 Home, running inside VertualBox.

When Auto-GPT tries the COMMAND = 'browse_website' ARGUEMENT = {url ..., It returns the Error: expected string or byte-like object, got 'NoneType' Both commands 'Google' and 'web_search' work correctly.

Upload Activity Log Content

No response

Upload Error Log Content

No response

Georgeroa73 commented 1 year ago

I am having the same issue!

Georgeroa73 commented 1 year ago

NEXT ACTION: COMMAND = browse_website ARGUMENTS = {'url': 'https://www.zillow.com/zebulon-nc/sold/', 'question': 'Can you provide recently sold homes in Zebulon, NC?'} Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for RealEstateGPT... Asking user via keyboard... Input:y -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= SYSTEM: Command browse_website returned: Error: There is no such driver by url https://chromedriver.storage.googleapis.com/LATEST_RELEASE_115.0.5790

Wiser2001 commented 1 year ago

Same issue here. Windows 10 running in PowerShell, both 3.5 and 4 (I have paid API)

VectorZhao commented 1 year ago
CRITICISM:  I should ensure that I thoroughly review each study and extract the most relevant information to provide accurate and concise summaries.
SPEAK:  To gather more detailed information and analyze the key findings, methodologies, and limitations of the identified studies on atmosphere retrieval of exoplanets, I will use the 'browse_website' command to access the websites of the papers.

NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://link.springer.com/article/10.1007/s10686-021-09791-z', 'question': ''}

SYSTEM:  Command browse_website returned: Error: There is no such driver by url https://chromedriver.storage.googleapis.com/LATEST_RELEASE_115.0.5790
gabeturner06 commented 1 year ago

I have the same issue, only I'm running MacOS, with OpenAI GPT-3.5. "Input:-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= SYSTEM: Command browse_website returned: Error: There is no such driver by url https://chromedriver.storage.googleapis.com/LATEST_RELEASE_115.0.5790"

otteb commented 1 year ago

Any ideas on how to fix this? I have the same error on my MacOS M1 chip

frenchdevartist commented 1 year ago

It is the same for me with my Mac M1. No way to use Auto-GPT without fixing this issue.

syrsteven commented 1 year ago

The problem is in the file 'Auto-GPT/autogpt/commands/web_selenium.py' 116 chromium_driver_path = Path("/usr/bin/chromedriver") Change "/usr/bin/chromedriver" to the path where you store your chromedriver. However there is no chromedriver for version >114 on the official website, you can search for chromedriver115, chromedriver116 on Google. Here is the download address of chromedriver116.

Hotch-C commented 1 year ago

The problem is in the file 'Auto-GPT/autogpt/commands/web_selenium.py' 116 chromium_driver_path = Path("/usr/bin/chromedriver") Change "/usr/bin/chromedriver" to the path where you store your chromedriver. However there is no chromedriver for version >114 on the official website, you can search for chromedriver115, chromedriver116 on Google. Here is the download address of chromedriver116.

I like this answer, it was helpful and clearly explained with enough info for my layman brain to understand and follow. But it didn't work for me. GPT kept saying driver 116.0.5845.97 didn't exist, even though I changed the path to the driver location,

It seems I've fixed my problem by changing the browser to Edge. We'll see if that causes issues down the road. It's pulling website info correctly so far.

github-actions[bot] commented 1 year ago

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

github-actions[bot] commented 1 year ago

This issue was closed automatically because it has been stale for 10 days with no activity.