Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/862faed7-449c-4624-902b-6b512a977d0c_a2f2bb0d-a51e-4c53-9468-5b4fa030a112.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 new surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: surge protector\n[button] surge protector -> CLICK\n[link] Surge Protectors -> CLICK\n[link] 6 to 8 Outlets -> CLICK\n[link] Under $25 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.394, 0.219, 0.414] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_dc3c5e75-a90a-4e6f-877f-dd1b5c40e9c3.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 wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[textbox] Event space -> TYPE: 100\n[textbox] Start Date -> CLICK\n[button]  -> CLICK\n[button]  -> CLICK\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.28, 0.394, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b310ebc-d9f4-4eb9-b348-30b329207a36_223fed6c-ab5a-40ca-8fd7-4ca5fdc52d9b.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 dry cleaning shop with the highest rating and virtual consultation option for Ironing and stain treatment for a pair of suits and a few delicates in New York City.\nPrevious actions:\n[link] More -> HOVER\n[span] Dry Cleaning -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.015, 0.564, 0.025] in the image\nAnd my action is Action: TYPE\nValue: new york city" } ]

{ "bytes": "", "path": "./images/61563837-99af-45e2-a13f-9d6bd9f74a81_38ec759c-f290-4d3f-8336-d7f5d20f5580.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 all the external solid state drives available with lowest price first.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] See All -> CLICK\n[link] Computers -> CLICK\n[link] Drives & Storage -> CLICK\n[link] External Solid State Drives -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.899, 0.092, 0.929, 0.099] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_c859da83-a276-460b-ba2b-d37555a94449.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 single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK\n[link] Tickets, Passes, VIP Tours  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.073, 0.523, 0.082] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a440d5f-1cc8-43de-86f5-ea181b0d12f8_991f70b5-0160-4220-bfc2-f69b70d2b1f7.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: Who were the NBA season leaders from the 2020-21 regular season?\nPrevious actions:\n[link] NBA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.068, 0.411, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/46a3683f-fbe0-40d0-8729-6c7964d994e6_6bb0ea02-190d-46c8-98fb-ebfe04f58ecd.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\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.35, 0.194, 0.358] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_13288e86-8e09-4608-93f3-ed250f087a42.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: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[div] Search -> CLICK\n[div] Premium -> CLICK\n[label] Distance -> CLICK\n[svg] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.791, 0.272, 0.916, 0.287] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_21c94120-79c7-4305-af25-b347848f9b6c.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 the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[link] Baggage info -> CLICK\n[link] Baggage fee calculator -> CLICK\n[combobox] From -> TYPE: columbus\n[button] Columbus, OH, US (CMH) -> CLICK\n[combobox] To -> TYPE: new orleans" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.251, 0.561, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03103341-f9d3-40a8-8435-f7946dd707b3_81263190-8c66-422d-ba92-ece80af4d80b.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 budget price for the vehicle with most seats availible at Roanoke Regional Airport from April 5-6.\nPrevious actions:\n[span] Roanoke Regional Airport -> CLICK\n[button] Select My Car -> CLICK\n[link] Price (Low to High) -> CLICK\n[div] Sort by: -> CLICK\n[link] Number of Seats (High to Low) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.793, 0.307, 0.918, 0.329] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c577209-47dc-4645-8d10-0b659663a969_88cb6de4-642d-4878-916b-7ab443d2af7b.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 score of the latest nba game played by the phoenix suns.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.219, 0.037, 0.728, 0.069] in the image\nAnd my action is Action: TYPE\nValue: phoenix suns" } ]

{ "bytes": "", "path": "./images/8e3c7ad0-f138-490e-918e-42bcce9f55a9_ecec671d-d6ef-4da5-ac94-b680f5e904dc.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 harry potter book to my wishlist.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: Harry Potter\n[button] Search -> CLICK\n[link] Harry Potter and the Cursed Child - Parts I & II -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.745, 0.285, 0.973, 0.303] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d9c6a43-eeb3-40ec-8617-d09a68fb0fb3_9cce8c69-8195-4b45-822d-283e082837b6.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 routes from NYP to WAS on May 15th.\nPrevious actions:\n[textbox] From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.152, 0.278, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/980d35af-6c00-4d6c-94cd-0c41e0fabb76_feb0706b-a5b2-4b57-b2f4-a4574d9af828.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 mens Timberland boots in size 9 and under $100 and filter by lowest price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.029, 0.652, 0.052] in the image\nAnd my action is Action: TYPE\nValue: mens timberland boots" } ]

{ "bytes": "", "path": "./images/0fc202d2-4c12-48ca-b04b-b667aac49156_b12e1589-6f9a-4f0c-9123-81a42039d8c0.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 benadryl items for Allergy Treatments in Liquid form.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.022, 0.804, 0.054] in the image\nAnd my action is Action: TYPE\nValue: benadryl" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_6d1f7b66-139a-4ec9-ad57-c5a574f6988f.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 Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[searchbox] To -> TYPE: stoney brook\n[span] Stony Brook -> CLICK\n[select] 1 -> SELECT: 10\n[select] 00 -> SELECT: 00\n[link] Find Schedules -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.843, 0.346, 0.866, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_8a76a674-3387-477b-95a5-02919a9dd32d.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 pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[svg] -> CLICK\n[span] Pickup -> CLICK\n[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: CHICAGO" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.174, 0.734, 0.232] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd4df5fa-2c90-4a76-b4b0-0ca7bcdac2ee_4038a1d1-b391-48f7-9093-45bec729f442.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: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[combobox] Arrival station, none selected. Select a station. -> TYPE: ZURICH\n[span] Zürich -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 31 -> CLICK\n[listbox] hour -> SELECT: 08" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.177, 0.194, 0.193] in the image\nAnd my action is Action: SELECT\nValue: 00" } ]

{ "bytes": "", "path": "./images/44ad28c9-c0d6-4d41-a49d-afeaa6ecaabe_82978229-c1f9-4bb2-a23f-900adb290f39.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 bus ticket between Albany, NY and Bloomington, NY April 10th and add the second one to cart.\nPrevious actions:\n[textbox] To (type text or use the arrow keys) -> TYPE: Bloomington, NY\n[span] Bloomington, NY -> CLICK\n[textbox] Pick a date -> CLICK\n[button] Next month -> CLICK\n[gridcell] April 10, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.256, 0.831, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_348c21cb-4bc5-454a-b3b3-3955c93b08ea.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: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless printer\n[button]  -> CLICK\n[dt] Customer Ratings -> CLICK\n[i] -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.643, 0.309, 0.659] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7c28f4e3-3dcf-477b-98c3-087c4fc16655_5200e3d5-946c-41fe-b34d-015858be3dec.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: Locate a store which is nearest to 10017 zip code.\nPrevious actions:\n[link] Store Locator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.176, 0.701, 0.211] in the image\nAnd my action is Action: TYPE\nValue: 10017" } ]

{ "bytes": "", "path": "./images/2177b546-5718-478b-8535-bc37975b0d0c_d5c1426a-876f-4bb5-945e-be4c53a4afc4.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 2 hot seat VIP tickets through email id [email protected] for Adele's concert in Las Vegas on the last weekend of June.\nPrevious actions:\n[option] Adele -> CLICK\n[link] TICKETS -> CLICK\n[div] Quantity -> CLICK\n[label] 2 -> CLICK\n[button] $3,535/ea -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.182, 0.213, 0.479, 0.244] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/1b310ebc-d9f4-4eb9-b348-30b329207a36_1048aad4-2ed3-4bb9-8c0d-234cdb6b90ee.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 dry cleaning shop with the highest rating and virtual consultation option for Ironing and stain treatment for a pair of suits and a few delicates in New York City.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.324, 0.029, 0.376, 0.052] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d83f3de-58f2-4aba-9b02-4a230d35a4ef_2ec3122c-4656-4a11-b38a-ace3f4ecb082.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 adventure game available for early access.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Early Access -> CLICK\n[div] Narrow By -> CLICK\n[link] Adventure -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.365, 0.371, 0.432, 0.385] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_9c998cb2-c740-4cc3-8c99-58824e200687.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: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[ins] -> CLICK\n[ins] -> CLICK\n[ins] -> CLICK\n[link] Show all 10 cars -> CLICK\n[link] Opel Insignia or Similar , View deal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.283, 0.599, 0.298, 0.611] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_a0335e1b-4305-40b9-9379-c6ecb06799ff.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 the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[generic] Previous Month -> CLICK\n[gridcell] 1 -> CLICK\n[span] -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.178, 0.3, 0.325] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/930803d7-4032-4144-89a2-e44f3c5c9ccf_25c59d1d-3e28-490b-a832-aa15ee2497d3.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[button] Browse the Parks Below -> CLICK\n[span] Hurricane Harbor Phoenix -> CLICK\n[button] Go! -> CLICK\n[link] Groups  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.2, 0.821, 0.312, 0.851] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_b88c28d6-7d12-42fc-95b3-f4267b4fd200.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 Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Alaska -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Seattle, WA -> CLICK\n[span] Dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.163, 0.194, 0.214, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf469f30-6628-4017-b963-672645d7feab_ff268edf-5481-45b7-87dd-16072ddacf02.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 dog collar under 10 dollar.\nPrevious actions:\n[span] Pet Type -> CLICK\n[link] Dog (1,338) -> CLICK\n[span] Category -> CLICK\n[link] Collars & Leashes (485) -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.252, 0.974, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a9a2e52-24b4-46c3-9e52-0f79c15ae3d0_6fe96e04-6f9b-4de6-960e-14f70df89eb1.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 full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> CLICK\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.495, 0.32, 0.517] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5d69e640-7765-4381-979c-9881afc048dd_85a2842f-8d86-4d33-b7ae-a9a5af111f9f.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 the monthly payment of a 15k car with a down payment of 5k in Michigan for a fair-rated person for a term length of 48 months, then shop with this budget for the cheapest car and add it to the favorites.\nPrevious actions:\n[textbox] Down Payment -> TYPE: 5000\n[combobox] State -> SELECT: Michigan\n[combobox] Credit Score -> SELECT: Fair (580-669 FICO® Score)\n[combobox] Term Length -> SELECT: 48 months\n[link] SHOP WITH BUDGET -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.27, 0.137, 0.288, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e44e7b6-3d2a-4ca2-870a-edc9e9751d5d_dc7e4e12-7d61-48a8-a1ec-2c52646d5975.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 last minute cruise deal\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.148, 0.629, 0.178] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_aa22d0e0-82c3-4792-afb9-94cc4366b61b.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 a car loan payment for a $25000 car with a $5000 down payment and 12 percent interest rate for 48 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK\n[input] -> TYPE: 25000\n[input] -> TYPE: 5000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.109, 0.473, 0.132] in the image\nAnd my action is Action: TYPE\nValue: 12" } ]

{ "bytes": "", "path": "./images/78915162-53c9-4cb1-86e1-6be6047528e0_5a1b9d08-5eb0-4ae0-8fa1-7183a2c8a7c5.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 if Coldplay is playing any events in Columbus, OH on May 17.\nPrevious actions:\n[textbox] Search by team, artist, event or venue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.134, 0.719, 0.161] in the image\nAnd my action is Action: TYPE\nValue: Coldplay" } ]

{ "bytes": "", "path": "./images/a52774d2-550d-475a-922c-25c37d44557c_1ad12bdc-c43e-4bd9-acfe-a5fdd5d8e2ca.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 mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] Check in / Check out Any week -> CLICK\n[tab] Flexible dates -> CLICK\n[label] Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.621, 0.076, 0.737, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_3eb249cb-72cb-4fdb-be0b-adee49627c52.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 Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[combobox] Return Time Selector -> SELECT: 1:00 PM\n[button] Browse Vehicles -> CLICK\n[checkbox] SUVs -> CLICK\n[checkbox] 2+ -> CLICK\n[button] Select Nissan Kicks Vehicle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.871, 0.437, 0.93, 0.458] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_0e088632-253f-4d11-af58-c48d7b276f16.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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.361, 0.281, 0.369] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a51b649f-15b4-4ce4-936e-0b76efa0dd2d_34ecbbb5-7d8b-4f1a-b63c-b940c801e7e2.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 travel credits for the passenger Leon Sin with the record locator jcqnhd ans ticket number 1234567\nPrevious actions:\n[searchbox] Search AA.com® -> TYPE: travel credit\n[searchbox] Search AA.com® -> ENTER\n[heading] Find your trip - Find a reservation - American Air... -> CLICK\n[textbox] Last name -> TYPE: sin" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.377, 0.196, 0.618, 0.24] in the image\nAnd my action is Action: TYPE\nValue: 1234567" } ]

{ "bytes": "", "path": "./images/0dc0190c-57cc-4c0f-b939-c0617102166e_080b7f6e-4cf4-4bcd-b8b7-5de3e9fb5337.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 to favorites a cruise from San Francisco to the Panama Canal departing Oct 2024\nPrevious actions:\n[span] Sail To -> CLICK\n[button] Panama Canal -> CLICK\n[span] Sail From -> CLICK\n[button] San Francisco, CA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.452, 0.314, 0.591, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/39b037ac-0a11-4b05-8919-b4f9863fd0cd_885432a5-3a1f-40a1-9c83-3e2222987162.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 review of Prometheus movie.\nPrevious actions:\n[path] -> CLICK\n[tab] MOVIES -> CLICK\n[searchbox] Search -> TYPE: Prometheus" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.156, 0.677, 0.199] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_ff237f12-b8da-44a6-a94b-44c986bde324.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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.232, 0.5, 0.264] in the image\nAnd my action is Action: TYPE\nValue: nevada city" } ]

{ "bytes": "", "path": "./images/bba6dd60-babd-4d8d-9e8b-242b0ffc08d7_10bba13a-2813-4375-9199-70db338f88c2.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 guide for paying with commuter benefits.\nPrevious actions:\n[p] About -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.04, 0.627, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_eaa6d53f-db1e-4d44-a4bf-95031cb2e235.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 motherboard under $200 and a compatible processor at any price to the shopping cart.\nPrevious actions:\n[button]  -> CLICK\n[textbox] price to -> TYPE: 200\n[button] APPLY -> CLICK\n[link] GIGABYTE B450M DS3H WIFI AM4 AMD B450 SATA 6Gb/s M... -> CLICK\n[a] Processors - Desktops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.719, 0.376, 0.745] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_a2787ae6-4fa3-444f-a098-41c7fe2c1de0.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 Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[gridcell] June 21 -> CLICK\n[button] Search packages -> CLICK\n[button] Amenities -> CLICK\n[checkbox] Beachfront -> CLICK\n[checkbox] Hot tub -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.335, 0.089, 0.344] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_95063aac-bdf3-44d0-9ac9-ff9893c88672.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 top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] Events & Activities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.154, 0.561, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_943d00d4-11cc-4ffc-8bad-584d783ae37a.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[link] Search for cars -> CLICK\n[textbox] Pick-up location -> TYPE: new orleans" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.233, 0.573, 0.286] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51b75f3d-b293-495d-a5a0-8ed5cc8270a2_2c773e90-ebe7-4e70-ad41-8b5e3ea66c7e.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: Make a reservation for 2 guests on april 21 at noon in a restaurant in Austin that is new on resy\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.138, 0.223, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b39c9ac-a965-4902-a7d9-ec7fb36ca096_596faa46-ddf1-4243-8f12-aae808036582.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 the status of a flight between San Antonio, Texas, and Bellingham, Washington on April 8.\nPrevious actions:\n[link] Flight status -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.177, 0.365, 0.192] in the image\nAnd my action is Action: TYPE\nValue: san antonio" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_d4a307c1-04e4-46fa-8d17-2bd949c405ce.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 group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[button] Buy Now -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.07, 0.777, 0.094] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/373dec75-7278-4d12-bcc3-0e802e337c4a_9a6d2ff8-b4aa-4bfe-8962-01e45d156bf3.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 Tree stands with at least 3 stars, and sort the results by price from low to high.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Climbing Stands -> CLICK\n[svg] -> CLICK\n[label] .Stars::before { -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.962, 0.273, 0.974, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9e9c178-e945-49fe-9d06-a01cf02ab2db_bbe4a682-8575-43f2-919e-1e66ee9af9ef.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 the highest rated spas that are $$ dollar signs and under.\nPrevious actions:\n[span] Spa -> CLICK\n[button] Price: -> CLICK\n[input] -> CLICK\n[input] -> CLICK\n[span] Save -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.162, 0.63, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_a0ae2016-64e5-4317-b950-1a708db07062.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 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK\n[button] 2010 -> CLICK\n[menuitem] 2017 -> CLICK\n[button] 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.364, 0.238, 0.381] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b28e6a37-6e9c-46bb-8012-18ca742a521f_f4f9eaa4-d365-4194-ac5c-02412f49c7e1.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: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[textbox] Passengers / Class -> CLICK\n[button] Increase number of infant passengers -> CLICK\n[button] Confirm -> CLICK\n[button] Show flights -> CLICK\n[heading] QAR 4,980 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.358, 0.712, 0.382] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/69661946-6c3e-4e26-95ed-1f7641a31f22_1faa68ab-b59e-4b69-85ad-8f3f1c42d617.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 listings for a used Toyota Corolla near 10019 and sort by cheapest.\nPrevious actions:\n[LabelText] Buy Used -> CLICK\n[combobox] Select Make -> SELECT: Toyota" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.196, 0.473, 0.222] in the image\nAnd my action is Action: SELECT\nValue: Corolla" } ]

{ "bytes": "", "path": "./images/4baa4918-3312-4b9b-9506-333057d6856b_0d2a5b19-2a2b-4397-b66e-ddb186bdebde.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 coupons and deals in New York.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.168, 0.961, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e2cb6d9-560c-4258-baed-82e0ed5b5dbc_00248976-2b6a-47d6-a025-29c82ff112f7.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 bus stop information at Abbotsford, WI.\nPrevious actions:\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.041, 0.377, 0.071] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/563ec938-b259-45b7-b0d3-6360b74e601d_b209f671-5caa-487b-a43c-666ba609b584.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 2 of WrestleMania single day Parking Passes on April 1st in California near LA.\nPrevious actions:\n[div] Sports -> HOVER\n[link] WWE -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.061, 0.259, 0.128, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_542b1db1-6a74-4c6c-bd1c-ff43a1309b99.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:\n[link] David Bowie -> CLICK\n[button] Add to List -> CLICK\n[radio] New List -> CLICK\n[textbox] Title -> TYPE: New\n[button] Save -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.46, 0.01, 0.469, 0.015] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_c1fa9374-0367-4285-a5f2-3f7cfa4f5379.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 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[label] -> CLICK\n[combobox] autocomplete -> TYPE: portland\n[div] Portland -> CLICK\n[span] Pick a date... -> CLICK\n[button] 15 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.007, 0.307, 0.036, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5f9182dc-d35d-4c0e-9abe-cd913c136528_8450e2c6-f8aa-40bc-876e-21cf29a8cb77.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 career openings in the marketing department\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.6, 0.35, 0.706, 0.398] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_777270ff-78c9-4c91-81f2-776107cbcd41.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 hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[button] Apr 26, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Price: low to high\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.157, 0.422, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6803cd71-78a9-4bff-a1a3-1153dcc28c11_9f57308e-e4bb-4c1c-8514-5c0d179fa5db.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 organic dog food and add it to the cart.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: organic dog food\n[link] organic dog food -> CLICK\n[link] Tender & True Organic Small Breed Chicken and Live... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.748, 0.225, 0.988, 0.256] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_86b669c9-2974-40ed-8fc8-6c3f5b709c7e.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 a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: bali" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.244, 0.795, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aedabbf-a7b4-4da7-8eaf-9e159a3ec99b_2146a4a1-d5b8-42c5-94b9-547d31930e44.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: review the dinner menu of La Bergamote restaurant in Hell's Kitchen.\nPrevious actions:\n[link] restaurants. -> CLICK\n[i] -> CLICK\n[textbox] Search by restaurant name, cuisine, or anything be... -> TYPE: La Bergamote\n[button] Search -> CLICK\n[heading] La Bergamote — Midtown -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.551, 0.347, 0.609, 0.375] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/37c09901-63d4-4194-8a96-1d87ca8c37ae_dbe89b77-d51e-4e13-8e3f-970b5ce60eca.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 washing machines available for free local pickup within 25 miles of zip code 90026.\nPrevious actions:\n[combobox] Search for anything -> TYPE: washing machine\n[button] Search -> CLICK\n[textbox] Zip code -> TYPE: 90026" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.694, 0.108, 0.702] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16886ec7-3301-4103-b175-9fa817335984_96b11da3-438a-468c-a35a-da87b5a3b3ba.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 NBA team with the highest average points scored in the current season\nPrevious actions:\n[button] NBA -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.155, 0.116, 0.312, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1c8b3d98-ffcf-42b9-ae0b-73d22d87bad7_00d49134-71de-43ed-9c37-19452b46685e.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 pair of diamond stud earrings to the cart.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: diamond stud earrings" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.074, 0.342, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/839ad551-da04-4c8e-96c3-093e762ea167_83ce3ed0-9d5e-4e13-885c-6cd6b0291439.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 and book the cheapest daytime only monthly parking option in Seattle near Stripe, 5th Avenue\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.069, 0.785, 0.086] in the image\nAnd my action is Action: TYPE\nValue: stripe, 5th avenue" } ]

{ "bytes": "", "path": "./images/2bc47bba-32d7-406b-bb39-c6f2b2f2039a_41b08949-112b-453b-83cf-1426058407d7.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 the top rock track\nPrevious actions:\n[link] Music -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.111, 0.645, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_230a1bfe-cf97-4bde-8268-f70287809032.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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[combobox] Pick Up Time -> SELECT: 11:00 AM\n[combobox] Return Time -> SELECT: 11:00 AM\n[textbox] Return to same location -> TYPE: washington\n[div] Washington Dulles Intl Airport -> CLICK\n[generic] Vehicle Type * -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.285, 0.782, 0.302] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c0eeead1-f8ea-4819-a6da-ef0108b40c89_0be743dd-2860-4ed8-81aa-211cb3c67518.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: Sign Allan Smith for email offers with the email [email protected] and zip code 10001\nPrevious actions:\n[a] -> CLICK\n[textbox] First Name (required) -> TYPE: Allan\n[textbox] Last Name (required) -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.231, 0.754, 0.255] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_a3d23bf6-5aa6-4245-8bb3-0c4d05470750.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 Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[button] Close -> CLICK\n[searchbox] Search Site -> TYPE: 8GB Ram\n[button]  -> CLICK\n[img] 8GB (1x8GB) DDR3L 1600 (PC3L-12800) Desktop Memory... -> CLICK\n[button] ADD TO CART  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.769, 0.235, 0.852, 0.248] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1f28fed3-bed9-444a-bf2b-3700b516b97f_d5d286c4-6f8e-4b7a-8fff-e50d13cf9ada.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 parking garage near Thalia Hall in Chicago that offers pre purchasing.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: Thalia Hall\n[span] South Allport Street, Chicago, IL, USA -> CLICK\n[strong] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.257, 0.379, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_2ca10cfe-4ab1-488f-b16d-305182e3c99f.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 two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[gridcell] Category -> CLICK\n[input] -> CLICK\n[option] Sweatpants -> CLICK\n[heading] Sweatpants -> CLICK\n[checkbox] PINK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.89, 0.246, 0.918, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d6dd19a2-c57e-4e4d-b7e1-8919a86f1157_f4a04bcc-0ce6-4a2c-a076-b96a65d0a7e6.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 likely to sell out activity in Los Angeles on April 2\nPrevious actions:\n[gridcell] Sun Apr 02 2023 -> CLICK\n[circle] -> CLICK\n[link] Likely To Sell Out -> CLICK\n[svg] -> CLICK\n[span] Price (Low to High) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.249, 0.785, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_75341aa4-49d6-43ad-86f6-b82d2b6c95fe.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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[path] -> CLICK\n[span] Delivery -> CLICK\n[button] Change location -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.119, 0.719, 0.163] in the image\nAnd my action is Action: TYPE\nValue: NEW YORK" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_f26ebe1e-3767-41cc-9263-447a47ea8ce3.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 birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[span] Hurricane Harbor Phoenix -> CLICK\n[button] Go! -> CLICK\n[link] Tickets & Passes  -> CLICK\n[link] Birthdays -> CLICK\n[button] Buy Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.435, 0.04, 0.443] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_4ac20b82-db8a-4e3f-94c8-d76357986448.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 service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is [email protected], and phone number is 6157075521.\nPrevious actions:\n[link] Car Repair -> HOVER\n[link] Auto Repair Prices -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.331, 0.151, 0.365] in the image\nAnd my action is Action: SELECT\nValue: 2022" } ]

{ "bytes": "", "path": "./images/e2adf8f1-547d-4671-96c1-4a21a56e135d_33dc45c6-f292-4b68-8df3-95a76a20a619.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 upcoming schedule from Otis St@Summer St to City Point of the transit near South Station for today.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.175, 0.05, 0.369, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_cbf7f977-c76b-4ae7-bfec-2ff4b8c4f362.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 an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Exterior Color -> CLICK\n[listitem] Gray (5) Gray (5) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Transmission -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.317, 0.249, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_c3c60d0c-7d49-46c8-ba77-3b9a28a14d52.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 highest rated romantic summer vacations in Spain\nPrevious actions:\n[div] Vacations -> CLICK\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Spain\n[div] Spain -> CLICK\n[textbox] When? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.07, 0.58, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a39f20a6-4d31-4f5f-b0ac-be8d548d7fa5_7a9bc022-4dfa-4b45-bcf3-35db5c5902c3.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 the hot deals within 500 miles from 10001\nPrevious actions:\n[link] DEALS  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.06, 0.266, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/240952bd-853b-4653-a358-49c2784cf568_7577fa72-6d3d-468b-9c75-a4dd8f2d35bd.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 scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\n[textbox] Type a date, or use enter to open, escape to close... -> CLICK\n[gridcell] Saturday, March 25, 2023 -> CLICK\n[button] Find Schedules -> CLICK\n[img] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.689, 0.397, 0.727] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_8fbb902f-04fa-4bd7-a4e9-d0ba0f793c6a.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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.326, 0.271, 0.339] in the image\nAnd my action is Action: TYPE\nValue: WASHINGTON" } ]

{ "bytes": "", "path": "./images/f8428085-905f-4190-9404-3e28fb691252_2326f36e-ad6b-4850-a5cd-83eb7df45721.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 newest on-demand releases.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.521, 0.022, 0.614, 0.052] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2adf8f1-547d-4671-96c1-4a21a56e135d_d9f6a27e-20e4-4711-939c-c1d832462aa2.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 upcoming schedule from Otis St@Summer St to City Point of the transit near South Station for today.\nPrevious actions:\n[tab] Schedules -> CLICK\n[span] Transit Near Me -> CLICK\n[input] -> TYPE: South Station\n[option] South Station, 700 Atlantic Ave, Boston, MA 02110,... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.277, 0.344, 0.309] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_36517be2-c47a-4c23-8d97-fefc258aa5b9.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 travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights multiple cities -> 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, 0.288, 0.29, 0.305] in the image\nAnd my action is Action: TYPE\nValue: JFK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_2fbd874e-8a6d-4382-8e29-670c173354bc.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 the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[span] Frozen Foods -> CLICK\n[span] Frozen Pizza -> CLICK\n[button] Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.269, 0.634, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_30499164-5c21-4aa3-861e-81c8b848a22d.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 two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[button] EUR -> CLICK\n[div] GBP -> CLICK\n[button] -> CLICK\n[div] £ -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.695, 0.916, 0.77] in the image\nAnd my action is Action: TYPE\nValue: Happy Birthday Love" } ]

{ "bytes": "", "path": "./images/b20d38a9-8c0f-4ed5-becc-f0f54fb90798_91811be9-5687-41af-9800-b2ad1470e844.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 page with information about the NBA Finals schedule.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.059, 0.958, 0.075] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6f4e562e-91f9-401d-8730-af947985b821_30c13bcc-6f9d-4265-8c57-1073030ce44f.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\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK\n[button] View Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.27, 0.144, 0.286] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cfe20a-f008-48d3-b683-002ce7790616_f96e7319-7712-4074-9b25-48a0c4769033.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 luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[combobox] Pick-up time -> SELECT: 9:00 am\n[combobox] Drop-off time -> SELECT: 6:00 pm\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.644, 0.045, 0.656] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_f5195da6-57eb-4def-a279-ec2069340b01.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: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 70726\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 222900\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.269, 0.102, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a807a1c-d3b2-425e-9684-2a9e79846676_77ccb021-cc33-47a9-9637-3cf72d44d1af.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 restaurant that offers African Cuisine in east village under $30\nPrevious actions:\n[link] restaurants. -> CLICK\n[li] Cuisine -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.391, 0.164, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_070d9bc0-242b-4d83-ae47-c1a17c0040e9.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 hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Shop Hotels -> CLICK\n[button] Going to -> TYPE: New Delhi" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.254, 0.571, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_aa72534c-0de6-4c4c-8d2e-378dd9bb25ec.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 two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: red sox vs yankees" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.781, 0.149, 0.871, 0.177] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a10e6232-923d-4635-bdc8-c6d989380e45_5e338d2e-d804-4b2b-8f81-7311a89ccce4.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[span] for 12 -> CLICK\n[div] Every iPad can connect to Wi‑Fi, so you can stay c... -> CLICK\n[radio] Add engraving It won’t impact returns or trade-in ... -> CLICK\n[textbox] First line -> TYPE: Hello World\n[button] Save -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.707, 0.938, 0.76] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f395aad-6f10-4055-932a-d2af443e6bfa_214bef59-0758-44eb-886f-b6745b668e05.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 Star Wars The Mandalorian statue and add to cart.\nPrevious actions:\n[searchbox] Search... -> TYPE: Star Wars The Mandalorian statue\n[img] The Mandalorian ArtFX+ 1/10th Scale Statue - Manda... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.544, 0.269, 0.969, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_efdcb0e6-e118-4995-bf76-1dc64e6f6e0e.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 prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[span] Good -> CLICK\n[span] 48 mo -> CLICK\n[span] Get pre-qualified -> CLICK\n[button] Get started -> CLICK\n[textbox] First name -> TYPE: john" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.76, 0.698, 0.786] in the image\nAnd my action is Action: TYPE\nValue: doew" } ]

{ "bytes": "", "path": "./images/701bc7ed-4b55-4fd2-b333-128e55c0a4c2_d32919a6-4663-42fb-a081-9cbd842bc551.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 an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.262, 0.084, 0.281] in the image\nAnd my action is Action: CLICK" } ]