Skip to content
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

Implement webvoyager benchmark #140

Open
2 of 4 tasks
lynchee-owo opened this issue Apr 23, 2024 · 0 comments
Open
2 of 4 tasks

Implement webvoyager benchmark #140

lynchee-owo opened this issue Apr 23, 2024 · 0 comments
Assignees

Comments

@lynchee-owo
Copy link
Contributor

lynchee-owo commented Apr 23, 2024

Use WebVoyager benchmark.

  • Set up Selenium with Chrome. Configure Selenium to launch Chrome with the WebWand extension loaded.
  • Write a Python script to automate task execution. Tasks are contained in tasks_test.jsonl file from WebVoyager. Refer to run.py in WebVoyager and replace any agent related logic with WebWand's API. Need to handle async operations such as waiting for task completion. Save results in the "results" folder
  • Use WebVoyager's GPT4V auto-evaluator to automatically assess the performance of WebWand against the dataset.
  • Analyze the evaluation results
@lynchee-owo lynchee-owo changed the title Implement benchmark Implement webvoyager benchmark Apr 26, 2024
@lynchee-owo lynchee-owo self-assigned this May 1, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant