mirror of
https://github.com/browseros-ai/BrowserOS.git
synced 2026-05-13 15:46:22 +00:00
29056226bb
- Add hover_at, type_at, drag_at coordinate tools to server - Add hoverAt, typeAt, dragAt methods to Browser class - Export server internals (browser, tool-loop, registry) for eval imports - Copy eval app from enterprise repo with agents, graders, runner, dashboard - Nest eval-targets inside apps/eval - Adapt sessionExecutionDir → workingDir for current server API - Add biome ignore for dashboard HTML to prevent lint breaking onclick handlers
11 lines
4.5 KiB
JSON
Vendored
11 lines
4.5 KiB
JSON
Vendored
{"query_id": "Amazon--0", "dataset": "webvoyager", "query": "Search an Xbox Wireless controller with green color and rated above 4 stars.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.amazon.com/", "metadata": {"original_task_id": "Amazon--0", "website": "Amazon", "category": "Amazon", "additional": {"ground_truth": "Xbox Core Wireless Gaming Controller - Velocity Green; 4.7-star", "answer_type": "possible"}}}
|
|
{"query_id": "Apple--0", "dataset": "webvoyager", "query": "Compare the prices of the latest models of MacBook Air available on Apple's website.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.apple.com/", "metadata": {"original_task_id": "Apple--0", "website": "Apple", "category": "Apple", "additional": {"ground_truth": "MacBook Air 13-inch M1 chip: from $999; 13-inch M2 chip: from $1099; 15-inch M2 chip: from $1299", "answer_type": "possible"}}}
|
|
{"query_id": "BBC News--0", "dataset": "webvoyager", "query": "Find a report on the BBC News website about recent developments in renewable energy technologies in the UK.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.bbc.com/news/", "metadata": {"original_task_id": "BBC News--0", "website": "BBC News", "category": "BBC News", "additional": {"ground_truth": "<report> (about developments in renewable energy technologies in the UK)", "answer_type": "possible"}}}
|
|
{"query_id": "Booking--0", "dataset": "webvoyager", "query": "Find a Mexico hotel with deals for December 25-26.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.booking.com/", "metadata": {"original_task_id": "Booking--0", "website": "Booking", "category": "Booking", "additional": {"ground_truth": "Be Local", "answer_type": "possible"}}}
|
|
{"query_id": "Coursera--0", "dataset": "webvoyager", "query": "Find a beginner-level online course about '3d printing' which lasts 1-3 months, and is provided by a renowned university.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.coursera.org/", "metadata": {"original_task_id": "Coursera--0", "website": "Coursera", "category": "Coursera", "additional": {"ground_truth": "Rapid Prototyping Using 3D Printing, Specialization", "answer_type": "possible"}}}
|
|
{"query_id": "ESPN--0", "dataset": "webvoyager", "query": "Look up the current standings for the NBA Eastern Conference on ESPN.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.espn.com/", "metadata": {"original_task_id": "ESPN--0", "website": "ESPN", "category": "ESPN", "additional": {"ground_truth": "<standings> (NBA Eastern Conference)", "answer_type": "possible"}}}
|
|
{"query_id": "GitHub--0", "dataset": "webvoyager", "query": "Search for an open-source project related to 'climate change data visualization' on GitHub and report the project with the most stars.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://github.com/", "metadata": {"original_task_id": "GitHub--0", "website": "GitHub", "category": "GitHub", "additional": {"ground_truth": "resource-watch/resource-watch", "answer_type": "golden"}}}
|
|
{"query_id": "Google Map--0", "dataset": "webvoyager", "query": "Find 5 beauty salons with ratings greater than 4.8 in Seattle, WA.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.google.com/maps/", "metadata": {"original_task_id": "Google Map--0", "website": "Google Map", "category": "Google Map", "additional": {"ground_truth": "Beehive Salon, Intermezzo Salon & Spa, Cindy's Beauty Salon, The Red Chair Salon, Ella and Oz Salon", "answer_type": "possible"}}}
|
|
{"query_id": "Huggingface--0", "dataset": "webvoyager", "query": "Find a pre-trained natural language processing model on Hugging Face that can perform sentiment analysis, and make sure the model's last update is within March 2023.", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://huggingface.co/", "metadata": {"original_task_id": "Huggingface--0", "website": "Huggingface", "category": "Huggingface", "additional": {"ground_truth": "distilroberta-finetuned-financial-news-sentiment-analysis", "answer_type": "possible"}}}
|
|
{"query_id": "Wolfram Alpha--0", "dataset": "webvoyager", "query": "derivative of x^2 when x=5.6", "graders": ["webvoyager_grader", "fara_combined"], "start_url": "https://www.wolframalpha.com/", "metadata": {"original_task_id": "Wolfram Alpha--0", "website": "Wolfram Alpha", "category": "Wolfram Alpha", "additional": {"ground_truth": "11.2", "answer_type": "golden"}}}
|