Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/706d0ccd-c0ec-423d-88c0-a5716700a855_85de1ef5-b340-4275-924e-4ad340d35a4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for used BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.143, 0.007, 0.189, 0.024] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bf4f465-99cb-483b-aac1-a7512b150755_f6e5cdcb-7b34-4d49-9c97-e74cb6428e87.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hydropack and make the results to show only items that have a capacity of 21 to 35L.\nPrevious actions:\n[button] Camp & Hike -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.24, 0.21, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/01bede1e-91ec-4fe0-a6bc-173826497800_3740da81-2f79-42c0-be33-7f148bf3f1d2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a person by phone number 123456789.\nPrevious actions:\n[link] Find People -> CLICK\n[link] BY PHONE NUMBER -> CLICK\n[input] -> TYPE: 123456789" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.342, 0.225, 0.389, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_d7504220-9487-4929-8b6f-608bf6883e93.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\n[link] 2022 -> CLICK\n[link] Eo -> CLICK\n[button] ​Jerzy Skolimowski -> CLICK\n[button] Add to list -> CLICK\n[menuitem] Create new list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.236, 0.609, 0.261] in the image\nAnd my action is Action: TYPE\nValue: Directors" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_15235466-cb9e-45a0-baf0-c2715e127ad9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[button] Continue -> CLICK\n[textbox] *First Name -> TYPE: John\n[textbox] *Last Name -> TYPE: Mark\n[textbox] *Email Address -> TYPE: [email protected]\n[textbox] *Phone Number -> TYPE: 234567890" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.436, 0.566, 0.476] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_7470ad8d-b2a2-4965-827b-7a794991454e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[button] Unlock deals External Link should open in a new wi... -> CLICK\n[div] Search location -> TYPE: TEXAS CITY\n[div] Texas City, TX -> CLICK\n[textbox] Select a date range. -> CLICK\n[img] Right -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.315, 0.62, 0.33] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/759d1c94-3314-481f-8763-5918b00567c4_1ef99a0e-af72-404c-a371-1815204eea54.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Mexican restaurants in Concord, CA and start an order at La Pinata Mexican Restaurant.\nPrevious actions:\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: Concord\n[span] Concord -> CLICK\n[textbox] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.015, 0.335, 0.025] in the image\nAnd my action is Action: TYPE\nValue: mexican" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_2a60c96b-b69a-4763-9e83-c7ad02c58d8f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[link] Footwear -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.345, 0.397, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_19088135-f0c7-424d-8c4b-c28c88f3c7db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[span] LaGuardia Airport -> CLICK\n[button] Find a Location -> CLICK\n[link] 1 Laguardia Airport (LGA)  -> CLICK\n[combobox] Pick Up Time -> SELECT: midnight\n[textbox] Enter your pick-up location or zip code -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.121, 0.891, 0.145] in the image\nAnd my action is Action: SELECT\nValue: noon" } ]

{ "bytes": "", "path": "./images/4f75897b-8df4-4f4c-88c3-72d440f6a4ee_83ca13ff-29f2-4738-bcd2-859f003ae40d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.63, 0.005, 0.67, 0.023] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/64779409-c396-4779-a574-b219c3b22282_00b8010a-a12a-4481-b961-a21322bb3972.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest skiing activity in August 10\nPrevious actions:\n[textbox] Where to? -> TYPE: skiing" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.21, 0.752, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f567f79-e197-4d7e-9a49-877daae6dde5_eebe61c3-9d1e-450d-a54c-0e428e7c9dd9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\n[combobox] Search for anything -> TYPE: iPhone 12 Pro\n[button] Search -> CLICK\n[link] 128 GB - apply Storage Capacity filter -> CLICK\n[heading] Apple iPhone 12 Pro - 128GB - All Colors - Unlocke... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.458, 0.244, 0.76, 0.256] in the image\nAnd my action is Action: SELECT\nValue: Blue" } ]

{ "bytes": "", "path": "./images/51221157-cb79-407e-95c8-b2c730e95e01_df559d9e-9ae9-42b5-833d-1268b513e3db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a music party in Ohio and follow its organizer\nPrevious actions:\n[div] Search for events -> CLICK\n[textbox] Search events -> TYPE: music\n[combobox] autocomplete -> TYPE: ohio" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.137, 0.42, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_cdab6084-b5e6-4dc2-908a-907ef2e36ce8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[link] SHOP HOTELS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.127, 0.42, 0.149] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/24de7f7d-f3f0-41a6-a578-e35b513b46e5_d4441fd5-a932-4be8-9301-89a7764372d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[checkbox] 7.3 cubic foot (5) -> CLICK\n[checkbox] 7.4 cubic foot (6) -> CLICK\n[span] Price -> CLICK\n[img] expand -> CLICK\n[spinbutton] Enter Minimum Price -> TYPE: 0" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.403, 0.121, 0.434] in the image\nAnd my action is Action: TYPE\nValue: 1000" } ]

{ "bytes": "", "path": "./images/6f4e562e-91f9-401d-8730-af947985b821_a8b1678d-bc7c-412c-b9ad-f628c66d0f63.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 3 most rated to watch tv shows or movies on Amazon Prime to watchlist.\nPrevious actions:\n[link] What to Watch on Amazon Prime -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.2, 0.077, 0.217] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/708cbe51-b493-41da-afa8-648564133972_84cfe885-5fe0-4f65-bebd-c0f56bf02c16.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK\n[span] -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.211, 0.492, 0.241] in the image\nAnd my action is Action: TYPE\nValue: ewn" } ]

{ "bytes": "", "path": "./images/d0ce3db1-720b-4333-a487-2bdc8fd74a80_80261cdf-aaba-4a97-976e-a2d72d013c4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show episodes of Alien Worlds and check where to watch Episode 4 of Season 1.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.22, 0.594, 0.246] in the image\nAnd my action is Action: TYPE\nValue: Alien Worlds" } ]

{ "bytes": "", "path": "./images/2a45ede7-6449-40b2-b032-149ddbe205a9_6dfde72b-7747-444c-835b-2feaf91878ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\n[combobox] autocomplete -> TYPE: New Orleans\n[div] LA, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.62, 0.309, 0.683, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e133f6c-155d-4ba4-89f5-16f569d6e918_08739645-479a-4ec6-8ace-d73e2de59ebe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest food tour in Paris which offers free cancellation\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.197, 0.463, 0.204] in the image\nAnd my action is Action: TYPE\nValue: Paris" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_7e7219df-cb90-454e-aeb9-988780eced12.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights one way -> CLICK\n[textbox] From , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.341, 0.29, 0.363] in the image\nAnd my action is Action: TYPE\nValue: JFK" } ]

{ "bytes": "", "path": "./images/277bdab6-e924-45dd-ba26-d659d864d671_b716dec6-b13d-4e4c-bfbb-96a9fbd930ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\n[textbox] Search -> TYPE: dog treats\n[span] dog treats -> CLICK\n[span] View all 20+ items -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.823, 0.16, 0.969, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd2e9403-3201-4bb7-a19d-f475960cf5be_4b07f157-afb9-41cc-bc51-78f88a227dfd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse Thai restaurants that offer delivery and have vegan options available.\nPrevious actions:\n[textbox] Find -> TYPE: thai restaurants\n[span] Thai Restaurants -> CLICK\n[button] Offers Delivery -> CLICK\n[span] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.2, 0.066, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_a2e74740-9137-4289-afcf-e7975501f39d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[button] CHECKOUT -> CLICK\n[button] Pick up in store Shipping: Free -> CLICK\n[searchbox] City, State, or ZIP code -> TYPE: 10005\n[svg] -> CLICK\n[label] UNIQLO SOHO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.571, 0.325, 0.618] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/351568c6-452d-4f32-9375-2b6301f0cb36_18ed8582-6390-4c5e-834d-a8c52a81fd04.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[listitem] Grand Central Terminal, East 42nd Street, New York... -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Bus -> CLICK\n[label] Express Bus -> CLICK\n[label] Rail -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.396, 0.332, 0.848, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_c8172921-931f-4897-badb-a46e41361d4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking with EV charging for month with lowest price in Chicago.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: Chicago\n[li] Chicago, IL, USA -> CLICK\n[button] Filter -> CLICK\n[checkbox] EV Charging (10) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.607, 0.458, 0.659] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_d27c83d7-a7bf-4035-be1a-7cfe70abd291.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 28, 2023 -> CLICK\n[combobox] Hour -> TYPE: 2\n[combobox] Minute -> TYPE: 30\n[combobox] AM or PM -> SELECT: PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.46, 0.353, 0.487] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f738b393-9234-4c07-8baf-20f05627d5ed_79c44cf2-97a2-4876-8e7d-99b6d5b1855d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[link] Home Services -> HOVER\n[span] Landscaping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.017, 0.564, 0.027] in the image\nAnd my action is Action: TYPE\nValue: WEST HOLLYWOOD" } ]

{ "bytes": "", "path": "./images/2a7f7732-ec9b-4d78-91ad-f0fe10bf7daf_00e89ec7-a6d4-4c75-ae50-335ba459f64d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a gaming pc which can run Call of Duty Warzone at 4k.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK\n[button] 4K -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.518, 0.429, 0.533] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0592744b-ea69-4724-80f8-3924916b7758_e85650b5-205b-4c62-8430-558ab5a7a477.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out the cancellation policy\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.604, 0.01, 0.659, 0.049] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_b2fd1297-19ee-4a76-89d7-39842b79a223.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.129, 0.568, 0.155] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_95c8c608-6806-4dc5-95c1-ebad7ad6b1b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[searchbox] From -> TYPE: brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.174, 0.359, 0.212] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_f5cda11c-d548-456b-a605-5b5857a87848.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[span] Edinburgh (Waverley) -> CLICK\n[combobox] Arrival station, Sheffield selected. -> TYPE: manchester\n[span] Manchester -> CLICK\n[radio] Return -> CLICK\n[textbox] Date use format: 29-Mar-23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.471, 0.179, 0.501, 0.193] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c02c193-2aef-4817-92b4-56722edc6b57_bc3b63a8-06fc-4da6-a5d0-8a80cec2bdc8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: skirt\n[textbox] Search by keyword or web id -> ENTER\n[span] Gender -> CLICK\n[link] Neutral (7) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.241, 0.986, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_0f19dcc1-254d-4a15-a862-941158d86dde.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[gridcell] Friday, April 14, 2023 -> CLICK\n[combobox] Hour -> TYPE: 12\n[combobox] Minute -> TYPE: 00\n[combobox] AM or PM -> SELECT: PM\n[button] Get trip suggestions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.376, 0.342, 0.874, 0.385] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd92cea9-a60f-4e09-90d7-32384ccdd61c_e2a55480-187b-4c9f-8f3a-28a19a3c7931.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show most played games based on daily players.\nPrevious actions:\n[link] New & Noteworthy -> HOVER\n[link] Most Played -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.372, 0.144, 0.548, 0.154] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a10e6232-923d-4635-bdc8-c6d989380e45_be9d5c1e-0aa0-43d7-8dff-c3ea5a77d4f4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a blue iPad to your cart and select the option for free engraving with \"hello world\" with no other accessaries.\nPrevious actions:\n[link] iPad -> CLICK\n[link] Buy iPad 10.9-inch -> CLICK\n[img] Blue -> CLICK\n[span] for 12 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.389, 0.938, 0.446] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc8342f9-3e2e-4f59-b54e-b35cd7285fdb_d05fb7e9-a294-4741-a6df-073f2cd22866.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Purchase the classic bundle for the simulation game Cities Skylines.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Simulation -> CLICK\n[link] CITIES: SKYLINES -> CLICK\n[link] Bundle info -> CLICK\n[link] Add to Cart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.441, 0.467, 0.466] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_ac2eb761-67e0-413a-8388-b0e85e06601f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: belo horizonte\n[div] Belo Horizonte, Minas Gerais, Brazil -> CLICK\n[tab] Flexible dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.292, 0.471, 0.325] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7e501a4-5dee-406e-b6ba-00eed783df0c_5aa3d6d6-e7b6-429c-815d-85b1df8eaab9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a KOA campground in California that has RV sites.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.198, 0.771, 0.213] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92869590-839d-4dfd-8884-4c52bef3b328_c5ef9f3a-728c-4744-bc1d-d112a9d73d99.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pasta restaurant in Sydney and save it\nPrevious actions:\n[button] Location Columbus, OH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.347, 0.102, 0.47, 0.124] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_0af4d0bf-3b98-45b8-b7a4-a0c99d68398c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request a refund for the traveler Ian Lo and, his document number is 12345678912345 and email [email protected]\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Request a refund -> CLICK\n[button] Add trip -> CLICK\n[textbox] Last Name* -> TYPE: Lo" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.226, 0.162, 0.443, 0.192] in the image\nAnd my action is Action: TYPE\nValue: 12345678912345" } ]

{ "bytes": "", "path": "./images/4c997e24-d185-4730-84d6-f8cb512f4c03_c6c213c6-e9c9-4ebd-b779-19fd733f7453.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car options to pick up at any location near 10023 on april 12 at 3 am\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.206, 0.5, 0.237] in the image\nAnd my action is Action: TYPE\nValue: 10023" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_350fd79e-7572-4e46-b13c-7bb569bebc81.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] Log in later -> CLICK\n[button] - -> CLICK\n[div] Mr -> CLICK\n[textbox] First name -> TYPE: Joe\n[textbox] Last name -> TYPE: Bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.784, 0.671, 0.934, 0.737] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_7624a77c-25cb-456d-96d6-a8f4841f7a30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.101, 0.914, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1fa9bb3-6e2c-485b-90f1-2a54510bf358_f5afe3cb-9632-40a4-a9e5-07bb9894e599.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking near Disneyland that has EV charging.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Disneyland\n[combobox]   Enter an Address or Venue to find parking -> ENTER\n[strong] Filters -> CLICK\n[checkbox] EV Charging -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.282, 0.328, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_ad396ee3-8490-4f70-9196-6da9a1d68166.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Gift Cards  -> CLICK\n[link] Browse Gift Cards -> CLICK\n[button] Our Brands -> CLICK\n[img] Travel Reinvented. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.311, 0.693, 0.331] in the image\nAnd my action is Action: TYPE\nValue: 150" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_9a76e93b-f2bc-4cad-ab30-cd3ffbbd96c5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\n[textbox] Maximum Value in $ -> TYPE: 400\n[button] Submit price range -> CLICK\n[input] -> CLICK\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.628, 0.185, 0.792, 0.198] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_b44a010e-fd15-4659-a3e5-e01c7fd86c81.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[tab] Rail Passes -> CLICK\n[link] EXPLORE MULTI-RIDE PASSES -> CLICK\n[textbox] From -> TYPE: WASHINGTON\n[option] Washington, DC - Union Station (WAS) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.35, 0.554, 0.364] in the image\nAnd my action is Action: TYPE\nValue: NEW YORK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_d13147e2-afaf-4608-bd27-65d8b4520f52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.398, 0.0, 0.465, 0.057] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/60e7ffd3-dda8-4ec6-9c10-115a5ab1bf90_8a3768a1-8b90-4fe8-ad47-a109170ea6c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the latest news from rotten tomatoes.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.79, 0.064, 0.82, 0.07] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/759d1c94-3314-481f-8763-5918b00567c4_4ac7cf83-cd41-4c71-b91e-f48fa542319a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Mexican restaurants in Concord, CA and start an order at La Pinata Mexican Restaurant.\nPrevious actions:\n[textbox] Near -> TYPE: Concord\n[span] Concord -> CLICK\n[textbox] Find -> CLICK\n[textbox] Find -> TYPE: mexican\n[span] Mexican -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.532, 0.709, 0.631, 0.736] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/82c5913d-8392-44a2-8873-6627a281fa23_82d66396-a339-49bf-94d7-e088d54ab356.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate monthly payment for car value of $50,000 and downpayment of $10,000 with interest rate of 4% for 60 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK\n[input] -> TYPE: 50000\n[input] -> TYPE: 10000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.333, 0.473, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_e499aff5-fada-4a43-a168-d2465e48c36f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[link] BABY -> HOVER\n[tab] Toddler (6M-5Y) -> CLICK\n[link] All Toddler (6M-5Y) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.23, 0.236, 0.277, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ea8737b0-0ff4-4476-b97d-5677d4f526dc_4e1fe0be-da2a-4005-8084-67028e46af25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\n[span] Locksmiths -> CLICK\n[textbox] Near -> TYPE: SAN FRANSISCO\n[span] San Francisco, CA -> CLICK\n[button] All -> CLICK\n[radio] Key extraction -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.519, 0.048, 0.535] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_51aa7294-0daa-44c7-adc5-04a136b43a7a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[textbox] To -> TYPE: new york\n[a] NYC - New York, NY -> CLICK\n[combobox] Number of passengers -> SELECT: 2\n[textbox] Depart (date format mm/dd/yyyy) -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.127, 0.373, 0.153, 0.387] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ba150cb-3b4a-4f0a-bff0-b448c78608ae_1755a651-6a6c-470d-8c28-8470e6038b82.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hotel deals in Las Vegas for four adults starting on May 17 and ending on May 20, and if deal is not available, set an alert for the same.\nPrevious actions:\n[textbox] Where? -> TYPE: las vegas\n[div] Las Vegas, NV -> CLICK\n[textbox] When? -> CLICK\n[link] 17 -> CLICK\n[link] 20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.713, 0.114, 0.902, 0.164] in the image\nAnd my action is Action: SELECT\nValue: 4 Guests" } ]

{ "bytes": "", "path": "./images/13a676be-2f4f-4abf-83fb-4ab641793801_ce4602ee-4097-4c4d-a52e-dd181d2ca5eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a list of Administrative and Clerical jobs MTA is currently recruiting for in Brooklyn\nPrevious actions:\n[link] Careers -> CLICK\n[link] See all open MTA positions. -> CLICK\n[textbox] Enter a Location -> TYPE: brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.675, 0.493, 0.743, 0.536] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03e45ce0-4375-44aa-b57f-cf439ccbe363_073152ad-a25b-4229-b88e-710c06a9e4cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest news article and send an email about it.\nPrevious actions:\n[link] Jets signing former Packers QB Boyle to 1-year dea... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.743, 0.26, 0.768, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b4aa5a9-79c5-49a3-9cc6-ead02159a3dd_92ef851f-5e36-4b3b-826d-730a35f6816d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Queen size memory foam mattress with lowest price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.029, 0.045, 0.06, 0.078] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_ae3dbbe1-426e-4fff-9667-43fe2d1f382e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[combobox] Child 1 age -> SELECT: 4\n[combobox] Infant 1 age -> SELECT: Under 1\n[button] Done -> CLICK\n[button] Preferred flight class Economy -> CLICK\n[menuitem] First class -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.207, 0.931, 0.242] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_ca703888-1346-4c10-af36-2ecd3a7f5fcd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[div] -> CLICK\n[button] close -> CLICK\n[button] Price -> CLICK\n[textbox] $ -> TYPE: 5\n[textbox] $$$ -> TYPE: 10" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.963, 0.007, 0.988, 0.022] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f27bb47e-3aba-439a-b98a-2cf9b0e25e9c_b1062855-4c2b-4283-9b44-d7dc68373578.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse Tokyo's best tea related attractions in the morning.\nPrevious actions:\n[span] Explore the World -> HOVER\n[span] Tokyo -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.233, 0.104, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eeeee9d8-5387-46bc-a741-5bcb66b46f31_ab08133d-0fb2-4fe2-abe7-fc145167b9b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a job opening in sales in San Fransisco, and if found, apply for the job.\nPrevious actions:\n[link] Our Team -> CLICK\n[menuitem] olink -> CLICK\n[link] See Open Roles -> CLICK\n[textbox] Select Department -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.258, 0.25, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_fb6ad166-2b4e-4439-bcb9-4024694fe8fc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check flight status for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\n[link] Flight status -> CLICK\n[generic] Apr 7, 2023 -> CLICK\n[option] Apr 9, 2023 -> CLICK\n[combobox] Airline. Enter to change collapsed list. Selected ... -> CLICK\n[option] United Airlines (UA) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.087, 0.295, 0.35, 0.322] in the image\nAnd my action is Action: TYPE\nValue: belo horizonte" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_05bed7b6-3573-4132-93c1-7cfe12b02c17.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[combobox] Pick Up Time -> SELECT: 11:00 AM\n[textbox] mm/dd/yyyy -> CLICK\n[select] June 2023 -> SELECT: June 2023\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 1:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.391, 0.567, 0.431] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_da3ddac9-4749-42d8-9fab-3cd56b1ac44a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[span] New Orleans, Louisiana, United States -> CLICK\n[textbox] Drop-off location -> TYPE: new york\n[span] New York, United States -> CLICK\n[generic] Saturday March 25th -> CLICK\n[button] Saturday March 25, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.744, 0.083, 0.881, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/930803d7-4032-4144-89a2-e44f3c5c9ccf_2bfdc2d3-8e60-435d-9e21-c63207b3c90d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy tickets for a group at Hurricane harbor Phoenix on April 22\nPrevious actions:\n[span] Hurricane Harbor Phoenix -> CLICK\n[button] Go! -> CLICK\n[link] Groups  -> CLICK\n[span] Buy Now -> CLICK\n[button] April 22, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.401, 0.099, 0.464, 0.129] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_336e6fd2-269d-493a-b7dc-c6c145b02503.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[textbox] Going to -> TYPE: changi\n[button] Singapore (SIN - Changi) Singapore -> CLICK\n[button] Departing April 5, 2023 -> CLICK\n[button] Apr 11, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.176, 0.568, 0.2] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a92a83ca-25ff-4751-8754-c65ef858699d_ed54258d-f01a-4eb0-8b28-5c6b95d348fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Lava Hot Springs East KOA photo gallery.\nPrevious actions:\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: Lave Hot Springs East KOA\n[list] KOA Logo Icon Lava Hot Springs West KOA Holiday La... -> CLICK\n[button] FIND A KOA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.487, 0.49, 0.541, 0.511] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1e46885-62b3-42ae-837a-474b1541348a_235eb14d-9210-4c53-a3d1-0afe2b3c737a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking passes for New York Yankees game on April 14\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.124, 0.782, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_ed212c71-ebb3-483a-8e55-dee589fad20b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[a] NYC - New York, NY -> CLICK\n[combobox] Number of passengers -> SELECT: 2\n[textbox] Depart (date format mm/dd/yyyy) -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 9 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.599, 0.35, 0.614, 0.361] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_14af7c4c-eb5c-4ec0-bb9f-33a24e6fcc22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] Military & Veterans -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: nevada city" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.268, 0.209, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8082086a-10a7-4631-9792-b57337426f9a_0c859da4-62dd-45c1-9935-aad323de8426.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a SUV with automatic transmission in New York drop off at March 30.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.275, 0.446, 0.31] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e133e56-ac17-41dc-987a-257078d770c3_b0cd091e-32b2-4506-9cb9-8259c8d63ce5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find on the water activities in Dubai from 5pm to 12am with a maximum duration of four hours\nPrevious actions:\n[button] Dubai United Arab Emirates -> CLICK\n[path] -> CLICK\n[button] -> CLICK\n[div] On the Water -> CLICK\n[label] Up to 1 hour -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.319, 0.105, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f14fb44-31d8-49f3-b5fb-95826175bcb8_cdddded4-b437-467d-99c4-8f76f89e0aaa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search new books from Jk Rowling available for kids within the age from 3 to 5 that are below $20\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: Jk rowling\n[link] Jk rowling -> CLICK\n[select] Most popular -> SELECT: Publication date, new to old\n[div] Age range -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.267, 0.196, 0.292] in the image\nAnd my action is Action: SELECT\nValue: Ages 3-5 (31)" } ]

{ "bytes": "", "path": "./images/bd32af6e-9fae-4968-b3e6-d143f148f5b8_313db28f-e14f-4a5d-af0a-7fca3e4fcd49.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a copy of the Gorillaz first studio album.\nPrevious actions:\n[combobox] Search artists, albums and more... -> TYPE: gorillaz\n[link] Gorillaz Gorillaz Artist -> CLICK\n[link] Gorillaz -> CLICK\n[link] Buy a copy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.884, 0.155, 0.97, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_329d8cfe-b9b5-4cb7-a9ed-bf622f9a3a98.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[textbox] From -> TYPE: new york\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: washington" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.327, 0.129, 0.559, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_648bdb7d-6268-4937-afe4-50036e127c4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[button] Transit  -> CLICK\n[link] Parking -> CLICK\n[link] Find Parking Lots -> CLICK\n[button] Stations G–K  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.353, 0.417, 0.361] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1267fbd8-54c8-4f2e-8471-b13c4de332c7_b5988297-2c7c-4904-b027-838dccd562f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a tiny home anywhere for an adult and 2 pets to stay in from april 10 to april 12\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.905, 0.069, 0.956, 0.091] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_78c3abc0-517b-4da4-b4eb-ce0788ed923a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[label] Pick-up location -> TYPE: Heathrow" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.121, 0.438, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31c12c59-d9b8-4d9a-8456-9f1107d0e5f8_75bcd0ba-31a7-43c4-a6a9-c9eb75258065.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the reservation made by James Smith in the United States with Confirmation Number 123456\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.019, 0.535, 0.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d78e3aac-c01b-4ebb-957d-e70f8bb378f3_ad2ccb9e-f110-417f-97cb-e2595afe0dd7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the design tool for a new home office.\nPrevious actions:\n[link] Design -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.053, 0.693, 0.245, 0.713] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_bc8a2b0a-b824-4d31-996a-98da91c17d68.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Brooklyn\n[span] Brooklyn, New York, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.156, 0.302, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_fa8985dc-a6b2-4b61-8ee1-b532dff08e13.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] Check-in April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] 1 room, 2 travelers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.262, 0.853, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_b8806818-06e9-467c-8a42-067311698bfc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[polyline] -> CLICK\n[link] Cars for sale near Tampa, FL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.604, 0.277, 0.632] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fa2828c5-44b3-446e-ae42-a26438ed8343_974c432b-99eb-42e8-a5a5-9ff19f60d0bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the upcoming departures for the oak grove station going southbound direction\nPrevious actions:\n[combobox] Search MBTA.com -> TYPE: oak grove station\n[button] search -> CLICK\n[link] T orange line bus commuter rail Zone 1A Oak Grove -> CLICK\n[link] Go to route -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.514, 0.429, 0.532] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c2a17420-ceb4-4324-ae8f-60cf845a144b_b0495a6e-1270-4d11-8868-2413bc8f1272.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open Canyon de Chelly schedule calendar.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.182, 0.539, 0.19] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_d02f058f-0877-48fe-bec7-bb51b808656a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Fashion -> HOVER\n[link] Men's Shoes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.377, 0.173, 0.385] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bd729e8-abb2-4649-bb81-8c790c04f8ad_521ea3e1-7da1-4fd9-94f0-6d5eafd32fe4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.037, 0.106, 0.043] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccb7c231-8655-4613-a28f-beb8074c523e_a8a56cd5-cf3c-46a5-a241-47d55e04c119.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\n[menuitem] Men -> CLICK\n[link] Shirts & Tops -> CLICK\n[link] Graphic T-shirts -> CLICK\n[div] Sports -> CLICK\n[link] Football -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.567, 0.495, 0.593] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a7eaba3-f6ec-4eba-9e04-ff974b228ef4_37743c80-cdfa-45ca-8318-679da8952f30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select an event from the 2019 UFC schedule and show me the full profile from one of the athletes\nPrevious actions:\n[link] MMA -> HOVER\n[link] Schedule/Results -> CLICK\n[select] 2023 -> SELECT: 2019" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.228, 0.145, 0.242] in the image\nAnd my action is Action: SELECT\nValue: UFC" } ]

{ "bytes": "", "path": "./images/c577375b-ecca-42f8-920c-b06809eef2b4_851fc5a4-d856-4f18-9634-c1e1a0669314.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the retired players named James Smith\nPrevious actions:\n[link] Players -> CLICK\n[link] RETIRED -> CLICK\n[textbox] Search by player name -> TYPE: James Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.509, 0.377, 0.666, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_4349ee88-0a9c-44d8-b554-f4952ee742fa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get email alerts for a flight from BHZ to EWN leaving on april 30 on the email [email protected]\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.196, 0.29, 0.227] in the image\nAnd my action is Action: TYPE\nValue: bhz" } ]

{ "bytes": "", "path": "./images/46a3683f-fbe0-40d0-8729-6c7964d994e6_67cfe42d-b9db-4b88-a753-af5ee18af657.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Mens -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.284, 0.233, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/607cea69-abb5-4055-aa09-117650cb7cc9_8bb3b4e6-7581-4aca-ac35-060f04786c75.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request information for tickets for a group of 100 people at a park in california\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.419, 0.844, 0.456] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_7e8bf2cf-620f-4e0f-9a98-cb0a178f6cfd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] Leaving from -> TYPE: Los Angeles, CA\n[button] Los Angeles (LAX - Los Angeles Intl.) California, ... -> CLICK\n[button] Going to -> TYPE: Miami, FL\n[textbox] Going to -> TYPE: Miami, FL\n[button] Miami (MIA - Miami Intl.) Florida, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.787, 0.088, 0.85, 0.102] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a7f7732-ec9b-4d78-91ad-f0fe10bf7daf_6fad4f05-f655-4e45-b926-c773034e90c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a gaming pc which can run Call of Duty Warzone at 4k.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK\n[button] 4K -> CLICK\n[div] Remove -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.377, 0.703, 0.39] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc8342f9-3e2e-4f59-b54e-b35cd7285fdb_b605b086-ec49-460a-ba68-c3117d5a3499.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Purchase the classic bundle for the simulation game Cities Skylines.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Simulation -> CLICK\n[link] CITIES: SKYLINES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.267, 0.231, 0.355, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8a6f2641-9896-4657-b447-56927420e8c4_5e79823e-7c1a-455c-afb4-c9a536f0c4ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[button] Genre -> CLICK\n[checkbox] Educational Educational -> CLICK\n[button] Done -> CLICK\n[button] Best Matches -> CLICK\n[link] Price Low To High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.614, 0.184, 0.649] in the image\nAnd my action is Action: CLICK" } ]