-
Notifications
You must be signed in to change notification settings - Fork 44.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implemented Selenium based web browsing. #1397
Conversation
Replaced the default web browsing function with one that uses selenium to gather information with a visual and an overlay. Included a small bug fix for the missing google api key that would attempt to use official google with default api keys from the template.
Noticed issues with flake8 formatting and fixed them.
Since this commit, autogpt fails to start up;
I think you need to update |
def create_message(chunk, question): | ||
return { | ||
"role": "user", | ||
"content": f"\"\"\"{chunk}\"\"\" Using the above text, please answer the following question: \"{question}\" -- if the question cannot be answered using the text, please summarize the text." |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need “please” in the prompt?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we must be kind to the algos
…ing each others efforts in many aspects. * added a new config parameter in .env to control which kind of browser the user wants: headless or full Selenium with Chrome * restored browse_website() to commands.py * PR Significant-Gravitas#1397 introduced a working Selenium adapter, but inadvertently clobbered PR Significant-Gravitas#968, and replicated most of the stuff in browse.py, but based on an old version, without any merge conflicts. This is now rectified by moving Selenium code into browse.py, and reducing duplication as much as possible. * there was a small typo, because an object reference was also returned along with the links in the link scraper. * listed the PROs and CONs of each browser in the source code
* Implemented Selenium based web browing. Replaced the default web browsing function with one that uses selenium to gather information with a visual and an overlay. Included a small bug fix for the missing google api key that would attempt to use official google with default api keys from the template. * Fixed flake8 issues.
Replaced the default web browsing function with one that uses selenium to gather information with a visual and an overlay.
Included a small bug fix for the missing google api key that would attempt to use official google with default api keys from the template.
Background
Changes
Documentation
Test Plan
PR Quality Checklist