Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_8fd55a42-471e-4418-b2f5-bca74ede84ab.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: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.332, 0.07, 0.374, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_68c2b8e3-b806-4602-ac7d-027a7865a754.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 the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] May -> CLICK\n[combobox] How many guests? -> SELECT: 1 Guest" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.918, 0.066, 0.964, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9a5ab90-517c-4323-a343-6e10e6b9632f_9cbdc533-8352-4da3-b64c-bdc59d0517a0.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 gift registry of Carla Cahill, when asked for password use Michael Cahill as name and [email protected] as email.\nPrevious actions:\n[link] Gift Registry -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.328, 0.279, 0.492, 0.31] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_b6170a50-fd4d-4d7c-930f-66231442bda0.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 motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: seattle\n[option] Seattle (WA), United States (City) -> CLICK\n[button] Next Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.576, 0.757, 0.583, 0.764] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3016f6f-b0fe-46df-a5ae-d0ad80a6996c_16c54e19-5ee4-4204-9d47-a622771a3506.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 schedule for the Dallas Mavericks.\nPrevious actions:\n[link] NBA -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.638, 0.17, 0.794, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_62b92129-4035-4743-aef3-0b72cc301caa.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 one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[svg] -> CLICK\n[tab] One-way -> CLICK\n[generic] Thursday May 18th -> CLICK\n[div] 24 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.238, 0.077, 0.381, 0.099] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc27fdda-c68f-4d43-bbcb-6c7954bf00ec_016e7d79-50f7-4e96-b822-70b91f99a2e3.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 Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[textbox] City -> TYPE: Cincinnati\n[combobox] State -> SELECT: OH\n[button] find store -> CLICK\n[button] filter by services -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.522, 0.108, 0.62, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_0f034570-81d0-41ed-9f4e-e3ad4241112b.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 lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 8 -> CLICK\n[listbox] hour -> SELECT: 14\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.747, 0.227, 0.925, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/102c50a4-23f8-44ae-8300-43822b271dbf_ca152b05-af0c-47e0-8958-bce808d51e93.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 places from OMG! below $500 to Wishlist and name it \"Togo\".\nPrevious actions:\n[img] -> CLICK\n[button] Filters -> CLICK\n[textbox] max price $ -> TYPE: 500" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.404, 0.786, 0.424] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_81b1149d-7ff0-4e12-a33c-f093e82f71de.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 premium car in Brooklyn for a day.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.017, 0.509, 0.045] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0ff1648e-28bb-4014-9b8a-3c050c25e334_84042e46-ecd1-428d-b72c-53232329ed7a.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 women's hiking boots section and filter the results to show only those that are waterproof and have a rating of at least 4 stars and size 6.\nPrevious actions:\n[button] Camp & Hike -> HOVER\n[link] Women's -> CLICK\n[link] add filter: 6(220) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.296, 0.142, 0.304] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_be6f3ede-4d0a-4a03-8f49-78f91329c5e5.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 available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] hotels -> CLICK\n[div] Destination or property -> TYPE: jakarta\n[hp-input-button] Destination or property -> TYPE: jakarta" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.128, 0.274, 0.137] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc98662-4405-4a30-9854-9301c98fdb37_538f32f7-02af-4098-b8e7-d1861bd5819f.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: What are the parking options in Florida to book to enter on may 6 at 5 pm and leave the same day at 6pm?\nPrevious actions:\n[textbox] Search for parking -> TYPE: florida" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.121, 0.83, 0.13] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_a8ec1dff-5f2e-4bf7-be21-9a534e37ac41.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 spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Customer Service -> CLICK\n[div] Need an extra part? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.451, 0.887, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_fb6edc44-52b6-4f64-8245-8ce967249d84.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 low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Xbox One -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK\n[checkbox] Microsoft Microsoft -> CLICK\n[button] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.296, 0.087, 0.32] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6df317e6-3414-4f2e-b5fc-b70914def4eb_3a79506e-4983-4f73-800e-97010e8017a6.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 Jazz music genre albums and tracks.\nPrevious actions:\n[link] Music -> CLICK\n[link] jazz -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.576, 0.219, 0.645, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e437082b-8383-4322-aa58-a6a683113970_1fad7c31-f747-4e0f-b2c7-99e5a4febcfe.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 Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[button] Book -> CLICK\n[link] Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.402, 0.414, 0.441] in the image\nAnd my action is Action: TYPE\nValue: Las Vegas" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_3359fd6e-131e-481b-8a7f-dad00e69757b.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[link] Search for packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.742, 0.455, 0.83, 0.466] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4f8a347-b288-4a00-9e6b-89cbccda42d2_d3c88cc2-8226-4464-b356-e448c7a3e5dc.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 near any airport in california starting april 20 and ending april 23\nPrevious actions:\n[link] View All Airports -> CLICK\n[link] Reserve Now -> CLICK\n[textbox] Select Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.173, 0.325, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_9a556b99-9709-438d-8d96-73c977afe480.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[label] Pick-up location -> TYPE: Heathrow\n[div] London Heathrow Airport (LHR) -> CLICK\n[div] Wed, Apr 19 -> CLICK\n[checkbox] 26 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 2:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.196, 0.282, 0.22] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_4885ec31-8249-4992-8ce2-c661f339be98.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 information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: [email protected]\nPrevious actions:\n[link] Careers -> CLICK\n[link] Sign up for job posting alerts -> CLICK\n[span] -> CLICK\n[button] Subscribe -> CLICK\n[textbox] First Name -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.711, 0.193, 0.977, 0.232] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/f4dcbd09-45f3-47b5-a49d-36658d5b50ca_6a0e5751-e659-44d8-b355-64280b94b4a4.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 tickets for Pizza making class in New York next month.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[combobox] Reservation type -> SELECT: Events" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.595, 0.489, 0.855, 0.551] in the image\nAnd my action is Action: SELECT\nValue: Next month" } ]

{ "bytes": "", "path": "./images/e4cf5835-4726-4a84-bc8f-5023e95ddec9_254d076a-6aec-4696-b23f-a83c21573d62.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 SkyMiles domestic Award Deals from Philadelphia to Atlanta.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.543, 0.012, 0.584, 0.032] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f0d7056-07f8-48b3-8093-e48abb301018_d28d30a1-9e44-4374-aa29-49d616e71df2.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: What is the cheapest luxury car to pickup on the second closest nearby location to New York, United States, 100\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.215, 0.804, 0.333, 0.822] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67f9fb2d-443a-4e5b-9530-e24372faedd2_79dd5af5-6248-4261-916d-6a5be124e417.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: What are the exotic vehicles they have available to rent?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.04, 0.333, 0.086] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bdc1f69a-da73-4e51-9dd8-83494d4983c2_23a34dd1-6a2d-4b3b-b0ae-bd4472286e89.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 check-in flight for John Smith having ticket no. 123456780\nPrevious actions:\n[link] Check In -> CLICK\n[textbox] first name maxlimit is 30 -> TYPE: John\n[textbox] last name maxlimit is 30 -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.177, 0.369, 0.354, 0.4] in the image\nAnd my action is Action: SELECT\nValue: Ticket Number" } ]

{ "bytes": "", "path": "./images/8865ca64-0df2-4e3f-905d-a9e07e1eeb68_d684a2b4-143e-4851-b9e2-6b1bdef467fc.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 bike service charges for store at Lafayette St, 10013.\nPrevious actions:\n[button] Cycle -> CLICK\n[link] Shop Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.405, 0.295, 0.595, 0.321] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_6ecf4fe7-562e-42cd-8cb4-871246f9d45a.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[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[span] Mar 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.394, 0.351, 0.438] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/277a776a-b335-4761-a543-bed1c6eca1d6_d147dd83-a0b3-4263-9db4-30b58e266a21.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 kayaks and filter the results to show only those that are suitable for whitewater rapids.\nPrevious actions:\n[searchbox] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.035, 0.668, 0.064] in the image\nAnd my action is Action: TYPE\nValue: Kayaks" } ]

{ "bytes": "", "path": "./images/fb9c0e7f-02dd-453f-8c73-da19282abf84_7a6574e9-178c-4a06-8a4f-3854f3d5279c.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 Ford Mustang with lowest price and save it.\nPrevious actions:\n[link] Cars for Sale -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.032, 0.673, 0.032] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e62d1f6c-d98c-4ea2-b699-527eeedf3e9b_495d586d-b1a2-41e0-a289-1abc2365840e.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: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[link] Beverage Packages -> CLICK\n[img] -> CLICK\n[link] Beverage Packages -> CLICK\n[button] add Bottomless Bubbles to the cart with price $9.5... -> CLICK\n[div] I want to give a gift to a booked cruiser -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.322, 0.352, 0.341] in the image\nAnd my action is Action: TYPE\nValue: Joe" } ]

{ "bytes": "", "path": "./images/0dd0b532-7bac-4b3e-b5a4-2ca6b0897af6_644f0928-6069-4c8e-9ed7-51ec7e259184.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 comedy TV shows streaming on HBO Max that was released in 2010.\nPrevious actions:\n[link] What to Watch on HBO Max -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.288, 0.077, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc27fdda-c68f-4d43-bbcb-6c7954bf00ec_0495b180-3090-4b4a-901c-07cd307f9e82.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 Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[link] Find Stores -> CLICK\n[button] enter zip or city, state -> CLICK\n[textbox] City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.481, 0.283, 0.639, 0.303] in the image\nAnd my action is Action: TYPE\nValue: Cincinnati" } ]

{ "bytes": "", "path": "./images/2ef470ab-b06a-4479-883f-78b4e3b94a04_9a0d4689-c0ba-46ce-acd9-03b108d9dd8c.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 five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[button] Select Activities -> CLICK\n[span] Cultural Tours -> CLICK\n[span] Any -> CLICK\n[li] -> CLICK\n[spinbutton] Max Price -> TYPE: 75" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.224, 0.217, 0.242] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/998e55fb-66d7-443f-bb73-9cb6a2bc26a8_2212f16a-7a5d-446c-a124-7afa61604d92.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 used BMW i3 for 10001 zip code with lowest price.\nPrevious actions:\n[menuitem] Buy -> CLICK\n[combobox] Select Make -> SELECT: BMW\n[combobox] Select Model -> SELECT: i3\n[textbox] Zip Code -> TYPE: 10001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.012, 0.526, 0.324, 0.563] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f408cdf3-06c8-459c-ba08-71bd471341a0_c854a73c-ba42-4f57-b19b-514c037bdf3e.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 places that serve burgers in 44012 zip code and sort the results by highest rated\nPrevious actions:\n[textbox] Find -> CLICK\n[textbox] Find -> TYPE: Burgers\n[span] Burgers -> CLICK\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: 44012" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.011, 0.62, 0.032] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_ba18ee7c-dbe9-4345-b2c9-b4f7b2fa559a.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 offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[label] VIN -> CLICK\n[textbox] Enter VIN (17 digits) Where can I find the VIN -> TYPE: 1HGCM66543A064159" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.596, 0.25, 0.746, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1f84888a-bebf-45aa-b8e3-2d9383ff01d3_ada350af-59cc-4e4c-aedb-8b128a8ee14e.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 chords for the song La Bomba\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.03, 0.838, 0.045] in the image\nAnd my action is Action: TYPE\nValue: La Bomba" } ]

{ "bytes": "", "path": "./images/87989b8e-0b6a-4dbe-a8bf-6adc2bdf3c29_3407d7f3-e070-45e0-8ee6-cb9b2512b40c.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 an hourly parking at Atlanta International Airport.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.378, 0.15, 0.43, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3a85b415-9e68-4cf0-91be-386d4d8f0710_785d0f3e-72f0-4f03-80cd-dc73dcf41af2.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: download pdf for list of accessible station in NYC.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.062, 0.058] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d637c171-dc6e-4a4e-a162-9c230e822932_3cdab44c-9799-48ba-a720-3dc25eb00579.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 popular news which is at number one in comics.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.094, 0.047, 0.104] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fb1c90e-a494-4de9-86ac-d4e5366869c4_6ef520ac-7d19-4d52-852c-5a128b13cc40.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: Schedule a virtual consultation for Solar Roof. The name is James Smith. The address is 123 st rd. The emial address is [email protected]\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.054, 0.532, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3236b068-8eaf-4a39-913f-b71884a35c39_dea7fb0b-b89c-4513-b5f3-9156a5463b72.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 most played games sorted by daily player count.\nPrevious actions:\n[link] New & Noteworthy -> CLICK\n[link] Most Played -> CLICK\n[generic] By Current Players -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.213, 0.543, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/64779409-c396-4779-a574-b219c3b22282_bb6ec3fd-7f24-4864-a4cc-1f7df779b2b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest skiing activity in August 10\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.306, 0.463, 0.317] in the image\nAnd my action is Action: TYPE\nValue: skiing" } ]

{ "bytes": "", "path": "./images/d6a0ab7c-f0d7-4ff7-9d42-55b44b5e7f74_99759d39-96b3-4093-881d-b50db542dd56.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the artist profile of M S Subbulakshmi and play all from the top tracks.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.005, 0.675, 0.026] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_2fe0fae8-1e67-4bfa-92d5-61c9c7eb65ef.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 me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[button] Wednesday, August 2, 2023 -> CLICK\n[button] Monday, August 7, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.172, 0.481, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2b159c8-86d0-4b76-9244-f19cc41d5ad8_2188f829-c7c5-4e97-b301-26caa57486ed.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 Medical book related to Diseases & Disorders to basket.\nPrevious actions:\n[link] Shop by category∨ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.048, 0.129, 0.064] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_3f033257-fd1c-4875-8b86-4f0b4cd589c7.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 women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\n[menuitem] Women -> HOVER\n[menuitem] Golf -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.228, 0.233, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5a15ea92-571d-4a45-ad18-5b4eddbc70a6_f8928c84-d27a-42db-a6d1-dcd1f656d6ab.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 the lowest priced plus size one piece active swimsuit in color black.\nPrevious actions:\n[link] Shop by Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.219, 0.159, 0.232] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_f444dc13-937a-4b04-8052-da002702db08.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: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[link] Gifting -> CLICK\n[link] Gift Cards -> CLICK\n[div] Send a physical card through the mail. -> CLICK\n[textbox] * Amount: -> TYPE: 50\n[button] VIEW ALL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.421, 0.448, 0.48, 0.484] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87989b8e-0b6a-4dbe-a8bf-6adc2bdf3c29_3de2c511-3989-41b9-8f34-d4cb2d3853b1.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 an hourly parking at Atlanta International Airport.\nPrevious actions:\n[tab] Hourly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.138, 0.202, 0.73, 0.229] in the image\nAnd my action is Action: TYPE\nValue: Atlanta International Airport" } ]

{ "bytes": "", "path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_1e255fc2-932c-41e6-b97e-1d1c15da28bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car rentals in San Francisco for a weekend trip and filter the results by the rental company Avis and car type Economy.\nPrevious actions:\n[textbox] Pick-up -> TYPE: San Francisco\n[button] San Francisco California, United States -> CLICK\n[button] Pick-up date April 2, 2023 -> CLICK\n[button] Apr 8, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.338, 0.568, 0.37] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_36028024-168b-4da8-a0fc-6452fcb120f1.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] Model -> CLICK\n[listitem] Civic (35) Civic (35) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.214, 0.234, 0.232] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_e95cc523-03ff-48de-a9d7-0f07b4906ccd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[span] 0 -> TYPE: 7\n[tab] 7 -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.169, 0.219, 0.193, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/62806bef-eeeb-4892-b4d5-6a8d2005c58d_4f0c10f1-48d0-4d3a-af3b-f9d37f97fc96.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 trending searches in Columbus.\nPrevious actions:\n[link] CITY PAGES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.107, 0.43, 0.119] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e91126e0-023d-4f96-9378-74efb5d6ecc3_c5e5e76f-39da-440f-a771-be5ef5b7e0c6.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 reviews and research information about Audi A6 2020.\nPrevious actions:\n[menuitem] Research -> CLICK\n[combobox] Select Make -> SELECT: Audi\n[combobox] Select Model -> SELECT: A6\n[combobox] Select Year -> SELECT: 2020" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.555, 0.151, 0.624, 0.173] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/839ad551-da04-4c8e-96c3-093e762ea167_9efe842d-9955-4569-9692-f96a5edd3d49.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:\n[textbox] Search for parking -> TYPE: stripe, 5th avenue\n[li] Stripe, 5th Avenue, Seattle, WA, USA -> CLICK\n[tab] Monthly -> CLICK\n[select] All Parking Options -> SELECT: Daytime Only Parking" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.37, 0.397, 0.383] in the image\nAnd my action is Action: SELECT\nValue: Sort by Price" } ]

{ "bytes": "", "path": "./images/a4397261-95a5-4d57-a531-6082b2af8ac3_5dea1dea-02c6-4442-845b-c06ff9529037.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 black sleeping pad that is under $40.\nPrevious actions:\n[textbox] Search -> TYPE: black sleeping bag\n[button] Search -> CLICK\n[textbox] Upper Bound -> TYPE: 40\n[textbox] Lower Bound -> TYPE: 0" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.692, 0.073, 0.701] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c0eeead1-f8ea-4819-a6da-ef0108b40c89_093733bb-a6a3-48b0-9aa5-bbe2a4b258aa.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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.219, 0.484, 0.247] in the image\nAnd my action is Action: TYPE\nValue: Allan" } ]

{ "bytes": "", "path": "./images/19847108-680f-4021-83a9-2548fab75fac_158b6c1d-31c1-4888-ae71-7f8cb5bebcd0.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: Mark a review in the best rated activity to do in Paris in May 12, 2023 as he\nlpful\nPrevious actions:\n[textbox] Where to? -> TYPE: Paris\n[b] Paris -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.266, 0.777, 0.274] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31c12c59-d9b8-4d9a-8456-9f1107d0e5f8_88c22cbc-3eaa-4221-8790-92ab48659205.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the reservation made by James Smith in the United States with Confirmation Number 123456\nPrevious actions:\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK\n[combobox] Select Residency -> SELECT: UNITED STATES\n[input] -> TYPE: smith\n[input] -> TYPE: 123456" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.415, 0.416, 0.585, 0.455] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/984f5bdb-d6d0-4b9d-ae23-bee8283a4f40_05faad15-74f4-4e7d-b3ec-1fecd007f9d6.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 2-5 day cruises to the Caribbean from Miami during August 2023.\nPrevious actions:\n[link] 2-5 DAY CRUISES Get big savings! Check out 2-5 day... -> CLICK\n[button] Sail To -> CLICK\n[button] Caribbean -> CLICK\n[div] Sail From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.689, 0.09, 0.82, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f863168b-1d7e-4f51-9681-79891abc4b45_cb1c3f11-8fe0-41ee-bb51-2e8061bdfc57.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 park in the National Park System that has a Junior Ranger Program for kids.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[link] Search by Activity or Topic -> CLICK\n[button] Activity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.37, 0.524, 0.382, 0.534] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_f8725f0b-18d9-4b4c-845d-ad4fcd1a9d6c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[select] AM -> SELECT: AM\n[button] 3/25/2023 -> CLICK\n[link] 25, Saturday March 2023 -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Rail -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.144, 0.609, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d963cc0-90d3-4908-bee4-29a8530536af_09291760-75ab-4a52-b1a3-763fd1ac9e02.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all my offers for 2-5 day cruises\nPrevious actions:\n[button] Plan -> HOVER\n[use] -> CLICK\n[select] DURATION -> SELECT: 2 - 5 Days" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.781, 0.202, 0.969, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_0cef9097-2798-4c61-bc77-7ed372327135.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 and add four items from the personal care category at Walgreens.\nPrevious actions:\n[button] Back -> CLICK\n[path] -> CLICK\n[link] Shower Essentials -> CLICK\n[img] -> CLICK\n[span] Add to list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.48, 0.309, 0.492] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c82bd6d6-6f08-4f1d-aeef-351c86694bbc_c2addf44-300d-4f7e-9bec-b2b5471e0d2d.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 newest movies for rent in the Redbox kiosk at any Winn Dixie in Daytona Beach.\nPrevious actions:\n[button] Navigate to Find a kiosk nearby -> CLICK\n[textbox] City or ZIP Code -> TYPE: Daytona\n[button] select to search for a kiosk using city or zipcode -> CLICK\n[button] select to browse a kiosk -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.257, 0.17, 0.293] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1684f224-47d5-45ed-9a26-821b98b851cd_d55bc99d-7725-453e-b01d-c0cd6d36e985.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[img] Add -> CLICK\n[img] Add -> CLICK\n[i] -> CLICK\n[span] SEARCH -> CLICK\n[textbox] Minimum price filter -> TYPE: 150" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.217, 0.264, 0.229] in the image\nAnd my action is Action: TYPE\nValue: 200" } ]

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_0c9c1694-75c7-446b-b8a1-4585a8561f79.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 if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.833, 0.035, 0.938, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/783d5a91-5f7e-4184-8467-e7ea88e81c5b_1bb44b82-30be-4dc1-910e-458594103813.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: Set the 3rd top hip hop track as my current obsession\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.762, 0.004, 0.791, 0.021] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/62c5067e-daff-4af6-bd79-83f6a969f4d6_b847be3f-0e83-44b6-900e-cd2c4d162f97.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 details of the fastest trip between 52nd Street,Brooklyn and 74th Street, Brooklyn, leaving now, that is accessible for a disabled person.\nPrevious actions:\n[searchbox] To -> TYPE: 74th street, brooklyn\n[listitem] 74th Street, Brooklyn, NY, USA -> CLICK\n[label] Accessible Trip -> CLICK\n[link] Plan my Trip - Press enter key to submit the form ... -> CLICK\n[tab] Fastest -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.232, 0.324, 0.332, 0.359] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a35becb-e07b-4235-8cd3-fc2a29f8dd6f_f3309336-f65d-423d-943f-296c3d7a3b97.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 the most most popular of all time tab to a playlist\nPrevious actions:\n[link] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.147, 0.338, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b2c18588-b115-4937-b69f-8feeab22c387_ee795994-e62a-47c3-a705-bb02487f3c6f.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 the list of movies \"at home\", sorted by most recent.\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.404, 0.238, 0.672, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14d4edf5-e5ca-40e8-8e5d-77068a22c32c_2ea9701a-ab3d-4dbc-a9b4-bf8f615fe651.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 scores of the premiership on 19th of March.\nPrevious actions:\n[span] Scores -> CLICK\n[heading] SOCCER -> CLICK\n[a] FEATURED MATCHES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.188, 0.213, 0.41, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_9bb22c1b-f45d-478a-bf4f-1a018c576906.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] From -> TYPE: empire state building\n[listitem] Empire State Building, West 34th Street, New York,... -> CLICK\n[searchbox] To -> CLICK\n[searchbox] To -> TYPE: little caribbean\n[listitem] Little Caribbean, Brooklyn, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.335, 0.359, 0.362] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/693ae151-6a70-41b1-b016-87279c4c532e_68993e22-ae92-47b0-9712-e4e67c7c657e.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 xbox 360 game available for purchase\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: xbox 360 games" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.228, 0.055, 0.645, 0.075] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_a9216e09-9cdf-4e76-961a-972569f94327.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[button] 30th March (Thursday) -> CLICK\n[combobox] Time -> SELECT: 8:15 PM\n[combobox] Size -> SELECT: 10 guests\n[button] Update search -> CLICK\n[button] Edit cuisine type filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.645, 0.345, 0.663, 0.368] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab1ae27a-029c-4f0c-9e01-82715e08d518_639a3c92-a608-447c-9f65-176900f37e9d.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 tables at Chianti - MG Road restaurant on March 30,1:30 PM for 4 Guests.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: CHIANTI\n[combobox] Guests -> SELECT: 4 Guests\n[button] March 30, 2023. Selected date. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.358, 0.275, 0.466, 0.297] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/63d1f820-37bf-4adb-aabb-65eb7925790c_73adafc4-ae3f-4cc6-89c4-64510b8e7910.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 current roster of the Miami Heat.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.066, 0.335, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_f8dc3296-ee92-4059-922e-f380c7f8a6ed.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[img] Add -> CLICK\n[combobox] Age of Child 4(Child's age (years)) -> SELECT: 12\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK\n[checkbox] list-filter-item-label-4 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.15, 0.089, 0.16] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff6ff6e5-e73c-4ba2-809e-59a1e269d68f_af68a13f-cead-4bad-9b91-ac1fbc14b005.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 Hair Loss Evaluation and Treatment in 10018 and show directions.\nPrevious actions:\n[button] Health -> CLICK\n[button] load Health Services Menu -> CLICK\n[link] Skin, Hair & Nails -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.015, 0.284, 0.363, 0.312] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd2e9403-3201-4bb7-a19d-f475960cf5be_90d3a2c2-9fdb-4edf-ad99-15fd086454e1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse Thai restaurants that offer delivery and have vegan options available.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.023, 0.232, 0.037] in the image\nAnd my action is Action: TYPE\nValue: thai restaurants" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_4a697de0-aa51-43f3-ad3e-d3312265bd48.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Charleston -> CLICK\n[textbox] zip or city, state -> TYPE: 25504\n[button] Look up -> CLICK\n[heading] Barboursville -> CLICK\n[link] More info about Barboursville store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.497, 0.24, 0.521] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc202d2-4c12-48ca-b04b-b667aac49156_ba1cf05e-362c-499a-bd3a-1fbc5d649325.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:\n[combobox] Search products and services -> TYPE: benadryl\n[button] Search for benadryl -> CLICK\n[img] -> CLICK\n[div] -> CLICK\n[button] Form -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.439, 0.143, 0.471] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_b0d8ab74-8854-487a-805c-2f920b08af49.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[label] Pick-up location -> TYPE: Heathrow\n[div] London Heathrow Airport (LHR) -> CLICK\n[div] Wed, Apr 19 -> CLICK\n[checkbox] 26 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.555, 0.131, 0.643, 0.17] in the image\nAnd my action is Action: SELECT\nValue: 2 00 PM" } ]

{ "bytes": "", "path": "./images/e9f5f0d0-7241-4a28-b387-c65a0ce52a61_60fe2dd5-eaff-4563-9cf3-dd946f846edc.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 rental car in Miami, FL for pick up at the airport and drop off at a different location within the same city.\nPrevious actions:\n[link] Search for cars -> CLICK\n[svg] -> CLICK\n[tab] Different drop-off -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Miami Airport" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.131, 0.573, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_56ec5ed4-9bd9-4caa-9fd3-21b38487f195.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[combobox] autocomplete -> TYPE: portland\n[div] Portland -> CLICK\n[span] Pick a date... -> CLICK\n[button] 15 -> CLICK\n[button] 16 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.255, 0.304, 0.452, 0.321] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_75b39e1c-d143-4ade-8ba1-6ebad9aacff8.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 the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[span] -> CLICK\n[button] Find flights -> CLICK\n[textbox] Date -> CLICK\n[button] Move backward to switch to the previous month. -> CLICK\n[button] Saturday, April 29, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.719, 0.059, 0.807, 0.089] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36f2e415-356b-4e44-9ab1-6c3054d4de1f_362a4918-c9e4-43c7-b7c7-e6c5ab3b2f67.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 if cars are available for tomorrow at Elevated Escape in North Carolina.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Elevated Escape\n[div] Elevated Escape -> CLICK\n[div] Tue, Mar 28 -> CLICK\n[checkbox] 24 March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.649, 0.094, 0.753, 0.124] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_bb5a4639-d62c-4155-8099-1ebe298b6bbc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car rentals in San Francisco for a weekend trip and filter the results by the rental company Avis and car type Economy.\nPrevious actions:\n[button] Pick-up date April 2, 2023 -> CLICK\n[button] Apr 8, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.209, 0.045, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_50d10c0a-7be8-4680-97b3-b7047b61e733.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] None -> CLICK\n[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.814, 0.284, 0.837] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eab97f0c-38b3-4421-bff6-697b3267f23c_78cd3d9b-a495-4c39-9102-2dc14b522e61.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 carnival cruise options that include Alaska.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.117, 0.285, 0.156] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_b0412512-a7db-4bf6-9cf1-06586305037f.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 value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[link] Car Values -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.394, 0.042, 0.546, 0.042] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_88e0ed6a-8359-41a6-99d4-e55bd567816c.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 GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[searchbox] Search by location -> TYPE: Seattle, WA\n[button] Search by location -> CLICK\n[button] Add to cart -> CLICK\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.243, 0.462, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bd2b5866-dced-4ec1-8b3e-8a8a24e71a96_a9210afa-f255-4b10-9dc0-401b91e86fb4.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 all English Reading and Writing skills Educational Books for Ages 6-8 currently in stock that are available in hardback under 20$.\nPrevious actions:\n[link] Shop by category∨ -> CLICK\n[link] Shop by category∨ -> CLICK\n[link] Ages 6-8 -> CLICK\n[link] Education -> CLICK\n[span] English Language -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.153, 0.196, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42657330-bfc5-425d-ae21-396a9ba1fb12_a451cb2d-a5e8-4808-88cb-c026cbda67da.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 yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[div] WOMEN / Tops -> CLICK\n[gridcell] Size -> CLICK\n[label] S -> CLICK\n[gridcell] Color -> CLICK\n[label] YELLOW -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.497, 0.25, 0.516, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_3a7df161-0055-43f8-a7b3-0705eb5f73a4.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 Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[button] Meetings & Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.089, 0.487, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/229199b4-9988-485f-8175-b5efd8faf08b_a309368f-6646-468c-8039-1867c9223c7a.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: Ask a question regarding Health Insurance Top Up plans beneficial or not?\nPrevious actions:\n[link] QUESTIONS & ANSWERS -> CLICK\n[link] Insurance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.155, 0.602, 0.175] in the image\nAnd my action is Action: TYPE\nValue: Health Insurance Top Up plans beneficial or not?" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_8cd6279c-0398-4d6d-8efd-cc77ddc492c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.035, 0.051, 0.082, 0.073] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6643cfb-567e-4e11-8cab-f85483573539_caecd46f-1c1b-4494-bb4f-2d64fa469b04.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: Follow one of the team leaders of one of the NHL teams from the Atlantic Division\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.188, 0.053, 0.223, 0.089] in the image\nAnd my action is Action: CLICK" } ]