'browse_website' command will stuck in create WebDriver Chrome instance, when exporting the 'https_proxy' env var in terminal.

[yangjian102621]

Background

OpenAI's API blocks calls from certain countries, so they have to use proxies to access it. Using proxies in the terminal is typically done by exporting the environment variable 'https_proxy'. However, after exporting this variable, webdriver.Chrome get blocked and the program gets stuck.

Changes

Before creating a Chrome instance, remove the 'https_proxy' environment variable. After creating the instance, restore the environment variable so that the OpenAI API can be called normally.

Test Plan

1. Export environment variable export https_ proxy= http://127.0.0.1:1080
2. Run the Auto-GPT program python - m autogpt -- gpt3only
3. Set a simple task: Open a page using a browser, such as: https://platform.openai.com/docs/introduction
4. Verify whether the task can be completed normally

PR Quality Checklist

• [ x ] My pull request is atomic and focuses on a single change.
• [ x ] I have thoroughly tested my changes with multiple different prompts.
• [ x ] I have considered potential risks and mitigations for my changes.
• [ x ] I have documented my changes clearly and comprehensively.
• [ x ] I have not snuck in any "extra" small tweaks changes

[BadwomenzzzZ]

Yes, I have the same problem

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
docs	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 9, 2023 6:55am

[p-i-]

This is a mass message from the AutoGPT core team.
Our apologies for the ongoing delay in processing PRs.
This is because we are re-architecting the AutoGPT core!

For more details (and for infor on joining our Discord), please refer to:
https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting

[vercel]

Deployment failed with the following error:

Resource is limited - try again in 3 hours (more than 100, code: "api-deployments-free-per-day").

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.