Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/0b16b42c-dea7-4079-a2a8-79eb23447193_a2427697-98ac-41ad-9fbf-861751daa293.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[button] New York/Newark (EWR) Miami (MIA) Roundtrip|Econom... -> CLICK\n[textbox] Departure -> CLICK\n[gridcell] Saturday, May 13, 2023 -> CLICK\n[gridcell] Thursday, May 18, 2023 -> CLICK\n[button] Search flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.12, 0.573, 0.132] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_a1c39cfa-dd66-4ab5-ad95-670f09f04659.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[path] -> CLICK\n[button] Make -> CLICK\n[listitem] Chevrolet (101) Chevrolet (101) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.015, 0.161, 0.121, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2eaf60d5-d2af-4f50-a3ad-5cc9132a770a_4fefd40e-5a97-42d1-968e-b429e4b4c5c7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[label] 5 (10) -> CLICK\n[combobox] Sort By: -> SELECT: Price: Low - High\n[img] -> CLICK\n[radio] 5 -> CLICK\n[radio] GRADE_A -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.41, 0.812, 0.436] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_70fd7564-5163-44de-b8cf-c90ccb96379d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking space in Houston. Name: James Smith, Email: [email protected], phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[textbox] Last Name * -> TYPE: Smith\n[textbox] Email * -> TYPE: [email protected]\n[textbox] Phone * -> TYPE: 8888888888\n[combobox] Market: * -> SELECT: Chicago\n[textbox] Spot Address: * -> TYPE: 123rd st" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.503, 0.264, 0.529] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4aaf59c0-889a-406c-b0c2-454d7670e04f_871a1cc6-f377-40b7-bb1e-aba28ec0787e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 TSA Guidelines to travel with Children\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.047, 0.664, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_5fd3f332-ce1d-4724-b698-be9c1146adac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[button] Depart at 8:40 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 14, 2023 -> CLICK\n[combobox] Hour -> TYPE: 12\n[combobox] Minute -> TYPE: 00" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.348, 0.305, 0.374] in the image\nAnd my action is Action: SELECT\nValue: PM" } ]

{ "bytes": "", "path": "./images/fc21339a-5dc0-489c-b348-2fac79483f76_0e11dda9-eff8-4ab3-a636-a4a0237becdd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Metformin 1000mg tablet price and details.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.029, 0.054, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a83c14aa-1a0b-4aaf-a801-ac828d2e81ca_9be4c700-75be-4c66-9202-8f31718ddabe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 4 star rated Hotel in New York Timesquare for 2 adults.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: Timesqure New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.391, 0.409, 0.436] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3edc9c7-397d-478b-a0b9-0ffa0897acca_c3255b9c-7b61-4e73-a586-b21159ed70fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 person named John Smith in New York.\nPrevious actions:\n[link] Find People -> CLICK\n[input] -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.35, 0.291, 0.546, 0.315] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/21f5aaaa-d54e-42a6-91c0-d1a427533963_6be71501-c895-4f3c-934f-16a21938dec0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new arrivals on Easter home decor\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: easter home decor\n[span] easter home decor -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.297, 0.974, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_f5829ff5-6294-41b7-b00b-3433d86971d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[textbox] From -> TYPE: New York\n[option] New York City area (NYC) -> CLICK\n[textbox] To -> TYPE: Aruba\n[option] Aruba (AUA) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.471, 0.258, 0.505, 0.282] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/91843d71-05c3-4b17-9b8c-856f2390fe02_57a8bfec-2f70-49b8-b132-25569b94616a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 year that Tom Brady had the most touchdowns in a single seasson.\nPrevious actions:\n[link] Players -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.46, 0.071, 0.472] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/957878ba-cb47-40d1-bf37-23039b2dff27_708acb3e-66cf-4976-83fe-0fc5a575f150.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 CarMax in Michigan, 49107 and book an appointment for a car repair on April 7th..\nPrevious actions:\n[button] Open helpful links menu -> CLICK\n[link] Service & Repairs -> CLICK\n[link] FIND A SHOP NEAR YOU -> CLICK\n[link] Find a Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.036, 0.148, 0.087, 0.163] in the image\nAnd my action is Action: TYPE\nValue: 49107" } ]

{ "bytes": "", "path": "./images/18a581b9-5021-40aa-835d-3c8110402df3_73c4da1e-dfc7-42c1-9b8b-493fc0048f3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adventure movies coming to theaters.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Coming soon to theaters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.238, 0.226, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2879afa9-05f9-4d97-bbfe-f95f5d665174_879c0f11-6c7b-4133-b30d-ecbee152194d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play the Wakanda Forever trailer\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.086, 0.259, 0.115] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_6ac8ac5c-31df-4c8f-8093-13f539417457.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[textbox] What city would you like to depart from? -> TYPE: Chicago\n[checkbox] I'm interested in the reverse trip of the selected... -> CLICK\n[checkbox] Deluxe Bedroom -> CLICK\n[button] Continue -> CLICK\n[link] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.448, 0.566, 0.486] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_9fd1755f-24be-469a-8f05-55c07c1b34a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[button] Next -> CLICK\n[input] -> TYPE: Crew\n[input] -> TYPE: James\n[input] -> TYPE: Johnson\n[input] -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.196, 0.525, 0.221] in the image\nAnd my action is Action: SELECT\nValue: Family Trip" } ]

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_26ba29a5-6c06-4176-a682-02c044459b30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.505, 0.28, 0.561] in the image\nAnd my action is Action: TYPE\nValue: addis ababa" } ]

{ "bytes": "", "path": "./images/fcb50c4e-a89e-4f18-b7c0-423295e7c298_35d8a6c9-4e1c-4b18-82fd-c4ee2821678f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 certified pre-owned front-wheel drive Jeep, Compass model car with single owner and the lowest mileage within 500 miles of zip 59316.\nPrevious actions:\n[combobox] models -> SELECT: Compass\n[textbox] Zip* -> TYPE: 59316\n[combobox] distance -> SELECT: 500 mi\n[button] Search Certified Pre-Owned -> CLICK\n[p] Four-Wheel Drive -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.223, 0.226, 0.231] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2f8b054-59b5-4fd8-bd58-9f95b29f979d_708f72c4-9e63-4fc5-84d7-d89623a406d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[link] Cars for Sale -> CLICK\n[textbox] ZIP Code -> TYPE: 07055\n[combobox] Distance -> SELECT: 100 Miles\n[combobox] Minimum Year -> SELECT: 2018\n[combobox] Maximum Year -> SELECT: 2018" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.174, 0.296, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_344872cd-6715-4851-a8f6-01eaff065563.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[textbox] Going to -> TYPE: national university of singapore\n[button] National University of Singapore Singapore, Singap... -> CLICK\n[button] Check-in April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.929, 0.355, 0.984, 0.374] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6643cfb-567e-4e11-8cab-f85483573539_49c73a41-8cf0-4ec0-b12e-b588fa3a2320.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] ESPN NHL Home Page -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.182, 0.175, 0.338, 0.197] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_5155bd89-c99d-4e8e-8cbe-185618e319e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[button] Add to bag, TÄRNÖ, Table+2 chairs, outdoor -> CLICK\n[link] Shopping bag, 1 items -> CLICK\n[span] Continue to checkout -> CLICK\n[span] Guest checkout -> CLICK\n[span] Select a store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.206, 0.969, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9c9e89c1-fdb9-424c-b544-b9fd2f1ef46e_d522a186-135f-4d08-a07a-852004c505fa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Limited Time Offers available in the Kids section and filter by size, 11-12Y(150).\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.007, 0.31, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/41ff100f-582a-422e-b387-3abd9008cee4_ea2e6ff2-b264-4578-aa3d-cd33be74b9a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open red line subway schedule.\nPrevious actions:\n[button] Transit  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.067, 0.367, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8cb94647-b0a8-4b8c-b00a-4788ef522b79_a6f1e015-8967-4d33-b56c-4daf513b7396.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[textbox] From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.228, 0.278, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab989f1e-bacb-4c37-ab81-c8f24ee3284b_73c5cb1c-f750-41f0-8bd2-ab89bf3b403c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the special timetable for Far Rockaway Branch of the Long Island Railroad.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.0, 0.445, 0.043] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_4d0ed0cc-72ac-4a64-8ff7-3d5962f067fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[input] -> TYPE: beauty salons\n[link] Beauty Salons -> CLICK\n[input] -> TYPE: Seattle, WA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.067, 0.788, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff82e848-f29e-477b-a286-c807cbd0d8fa_8a1e5242-bcce-46ec-8ba5-e1aa2b723b33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[link] Careers This link will take you away from the Qata... -> CLICK\n[span] 64 -> CLICK\n[textbox] Location -> TYPE: india\n[link] Mumbai - BOM, India - IN 2 jobs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.608, 0.179, 0.704, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb7c3e38-dd9c-4472-9774-0012586a1dcd_d5320812-311a-480e-934c-e35760ef5bff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 weekly deals of Columbus, Oh 43215 store.\nPrevious actions:\n[link] Locations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.175, 0.287, 0.2] in the image\nAnd my action is Action: TYPE\nValue: 43215" } ]

{ "bytes": "", "path": "./images/f8089c50-e80c-4532-82a1-96009f485c57_931c5aca-4b73-4e84-9797-1c93a3bd176b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Women's t-shirt for $40-$60 and add it to Wishlist, stop at the Login screen.\nPrevious actions:\n[link] WOMEN -> CLICK\n[tab] Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.119, 0.332, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/351568c6-452d-4f32-9375-2b6301f0cb36_7c298bc0-fed0-40a1-b15b-c6cad7071b60.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[searchbox] From -> TYPE: Queensboro plaza" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.238, 0.359, 0.274] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/932c0ec6-d500-495a-a7a7-0f632acbf6a5_70e49603-f22f-465e-b9b9-1344b4a905ad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 camping stoves that have an auto ignition feature.\nPrevious actions:\n[button] Camp & Hike -> HOVER\n[link] Stoves, Grills & Fuel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.543, 0.149, 0.553] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fcb50c4e-a89e-4f18-b7c0-423295e7c298_1f8f403a-057f-40c8-8f98-5ac2d1a46e9e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 certified pre-owned front-wheel drive Jeep, Compass model car with single owner and the lowest mileage within 500 miles of zip 59316.\nPrevious actions:\n[combobox] distance -> SELECT: 500 mi\n[button] Search Certified Pre-Owned -> CLICK\n[p] Four-Wheel Drive -> CLICK\n[p] Single Owner -> CLICK\n[combobox] Select Sort Order -> SELECT: Lowest mileage first" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.396, 0.605, 0.417] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c64dcaa1-555d-43f3-adb4-3452c4e5d09b_15c7fb1a-57d3-453f-b3de-6cf368e782f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 barbershops that have private lot parking.\nPrevious actions:\n[textbox] Find -> TYPE: barbershop\n[span] Barbershop -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.513, 0.203, 0.529, 0.213] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_d7ac76c3-c31d-4daf-ba91-f07a2250eb2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[button] Sort: Best Match -> CLICK\n[link] Time: newly listed -> CLICK\n[button] Price -> CLICK\n[link] Under $75.00 -> CLICK\n[button] Delivery Options -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.299, 0.218, 0.44, 0.24] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_60dc39b7-782e-4aa3-836d-62fc57fe8819.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[listbox] hour -> SELECT: 12\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK\n[heading] Continue -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.587, 0.642, 0.624] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_395e5287-15fc-412e-8c91-356376438cd4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[link] Complete trade-in -> CLICK\n[button] Verify membership to continue -> CLICK\n[input] -> TYPE: Joe\n[input] -> TYPE: Bloggs\n[input] -> TYPE: 123456789" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.561, 0.224, 0.604] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c4538b84-ca81-413a-8f3d-7ce87e42b4f6_96892596-2a86-4978-8c2c-701040a4f9f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Saturday park hours for Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.057, 0.281, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6643cfb-567e-4e11-8cab-f85483573539_adbd43a1-3981-48e5-97e4-1f12fb54e667.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] ESPN NHL Home Page -> HOVER\n[link] Teams -> CLICK\n[heading] Boston Bruins -> CLICK\n[link] Full Team Statistics -> CLICK\n[heading] David Pastrnak RW -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.104, 0.249, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8634bbc0-7bcd-4c88-ad0f-5c73c3f69e53_9b9bea77-138e-40d6-bebe-86d163d835a2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Join the waitlist for a ticket for the Hackney Clothes Swap - Earth Day event being held on April 22nd. Name: Joe Bloggs. Email: [email protected]\nPrevious actions:\n[div] Search for events -> CLICK\n[combobox] autocomplete -> TYPE: Hackney\n[div] Hackney -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.182, 0.418, 0.218] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_7e1d3bb9-5950-4300-ad90-dd0be92707da.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[button] Sort by:Our top picks -> CLICK\n[div] Price (lowest first) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.803, 0.348, 0.913, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_0c03bd04-974b-4904-9ccd-9ec0e2152f29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[LabelText] Sell My Car -> CLICK\n[textbox] Enter license plate -> TYPE: YAW639\n[combobox] state -> SELECT: LA\n[button] Get your offer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.196, 0.124, 0.217] in the image\nAnd my action is Action: TYPE\nValue: 70726" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_b9964889-17f7-4897-92d3-a2221740f0bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[rect] -> CLICK\n[link] 26 -> CLICK\n[polyline] -> CLICK\n[span] Youth -> CLICK\n[combobox] Select passenger age -> SELECT: 16" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.085, 0.17, 0.319, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d6dd19a2-c57e-4e4d-b7e1-8919a86f1157_87e9c2d8-c6f0-42c3-8bfb-f1456f4699d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest likely to sell out activity in Los Angeles on April 2\nPrevious actions:\n[textbox] Where to? -> TYPE: Los Angeles\n[b] Los Angeles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.286, 0.777, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0692908b-4bf4-48ac-b41a-37c59ea5ba1d_12063f39-2856-480c-aa96-7e4eb94ffcc2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the score of the latest nfl game played by the las vegas raiders.\nPrevious actions:\n[combobox] Search query -> TYPE: las vegas raiders\n[img] Las Vegas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.5, 0.976, 0.559] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_095d6d7a-0df6-4731-83ef-14e17d810b5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.679, 0.222, 0.937, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_59d223e5-8ce1-47cc-a614-ad75954151b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Need an extra part? -> CLICK\n[link] Read more -> CLICK\n[span] Order spare parts -> CLICK\n[input] -> TYPE: 105307\n[button] 105307 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.431, 0.617, 0.508] in the image\nAnd my action is Action: SELECT\nValue: 2" } ]

{ "bytes": "", "path": "./images/14b5885e-5454-465f-92bf-d8f7315c4a46_a8277574-07e0-411e-8787-81cb20501c1c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[textbox] Pick an origin Pick a destination -> TYPE: Abbotsford\n[span] Abbotsford, WI -> CLICK\n[textbox] Enter a town, city or zipcode -> TYPE: Sheboygan\n[span] Sheboygan, WI -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.216, 0.721, 0.248] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/15a0ffe5-8462-4a8e-8938-91b05a40756f_96779cdb-a229-44fd-848a-8522a105e38d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new address to the account. The address is 2983 Marietta Street, APT 2. Business name is Buck.\nPrevious actions:\n[span] 171 2nd street -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.185, 0.702, 0.22] in the image\nAnd my action is Action: TYPE\nValue: 2983 Marietta Street" } ]

{ "bytes": "", "path": "./images/ccee2694-0d3e-4d81-8d52-5cdf82a9b81f_eac1ae66-8d5a-48b1-b2b1-a0fd06cb5690.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 nearest apple store to zip code 60540 and check its opening time tomorrow.\nPrevious actions:\n[link] Store -> CLICK\n[link] Find one near you (opens in a new window)  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.031, 0.669, 0.054] in the image\nAnd my action is Action: TYPE\nValue: 60540" } ]

{ "bytes": "", "path": "./images/a2959cdb-fbc4-435f-ba89-85d50d22298c_88a36484-1756-4a0d-8e91-cf10a9abaa0e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces in JFK airport between April 18-20 that have lowest shuttle times\nPrevious actions:\n[tab] Airport -> CLICK\n[searchbox] Airport Name, Code or City -> TYPE: jfk\n[li] John F. Kennedy International Airport (JFK) -> CLICK\n[textbox] Parking Start Date -> CLICK\n[gridcell] Tue Apr 18 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.173, 0.391, 0.187, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9215395-70cd-4da5-af99-9ba36cde858a_c9b80332-9b10-41ac-b0ae-09330173af4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trailer for a new winter show from HBO.\nPrevious actions:\n[link] Recommendations -> CLICK\n[link] Recommendations -> HOVER\n[menuitem] Winter Preview: New Shows Worth Watching -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.175, 0.555, 0.191] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3236b068-8eaf-4a39-913f-b71884a35c39_8c018b5c-efad-4b19-8fdf-607219a937e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.11, 0.369, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bd2b5866-dced-4ec1-8b3e-8a8a24e71a96_2dfb62c9-c929-4cef-a5b5-ee1b8b9d7faf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.118, 0.129, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_f3e095cc-b31b-4f6b-83ab-677044140ff8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.563, 0.545, 0.645, 0.581] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc194d4-2f71-496a-b378-e18ab698ab0f_641f627f-98e5-4b3e-a0b5-4bb370e16340.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reggae concerts this weekend.\nPrevious actions:\n[button] CONCERTS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.391, 0.121, 0.45, 0.135] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_7337a4ab-f0d2-4e5a-9498-4f133b64972f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[img] TAHE Beach SUP-Yak Tandem Inflatable Stand Up Padd... -> CLICK\n[button] Add to cart—$799.95 -> CLICK\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue without membership -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.366, 0.2, 0.405] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_cbcdb41a-a319-4771-a94b-6c5348430bd7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[input] -> TYPE: 6000\n[span] Good -> CLICK\n[span] 48 mo -> CLICK\n[span] Get pre-qualified -> CLICK\n[button] Get started -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.15, 0.495, 0.17] in the image\nAnd my action is Action: TYPE\nValue: john" } ]

{ "bytes": "", "path": "./images/9e9d7935-0c16-46e6-9e5c-3ea9124a6bf7_1aff894c-1861-4fe9-a936-bd4264f0c644.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\n[div] Play -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK\n[a] Create a playlist -> CLICK\n[textbox] Playlist title * -> TYPE: Top Hip Hop" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.108, 0.441, 0.114] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ca80bb42-2617-4f29-bbcd-bcc426b3e407_2fe12b3f-15f7-4cff-a0da-d485f189cb4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Airport information of Camarillo Airport, CA and check weather.\nPrevious actions:\n[combobox] Search Method -> SELECT: Airport\n[textbox] Airport City (e.g. New York) -> TYPE: Camarillo" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.444, 0.042, 0.483, 0.05] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_0180d34b-3ffd-44d5-ae82-c7e6b031c05e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[link] Explore All -> CLICK\n[link] 3,682,991 Pop -> CLICK\n[img] Phil Collins - No Jacket Required -> CLICK\n[button] Add to List -> CLICK\n[combobox] List -> SELECT: New" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.325, 0.306, 0.373, 0.32] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/75db63ac-4fcf-400e-833f-d31f00cf6ab6_442ce85b-f9ff-4a4b-8fc5-7c41fc303963.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[link] Nearby Restaurants -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.032, 0.169, 0.062] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/759d1c94-3314-481f-8763-5918b00567c4_97d43de2-df7c-4880-9368-ea38fa587621.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Mexican restaurants in Concord, CA and start an order at La Pinata Mexican Restaurant.\nPrevious actions:\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: Concord\n[span] Concord -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.02, 0.335, 0.031] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_fb8f3a51-6870-47b6-898a-25b1ebf691f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 49102\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 155000\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.205, 0.102, 0.26] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b467797c-5fab-4ee6-9b1f-ac6dc50c05cf_241522f0-f05c-49d3-89e1-e0db568af201.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.096, 0.215, 0.114] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9e88baa-a109-454b-839f-1ab0746a5f13_dd18b502-ec91-4183-9051-0866c49b0936.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all watch options of Avatar: The Way of Water and where it's available.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.108, 0.594, 0.121] in the image\nAnd my action is Action: TYPE\nValue: Avatar The Way of Water" } ]

{ "bytes": "", "path": "./images/7f0d7056-07f8-48b3-8093-e48abb301018_c6d1a72d-6a78-4b55-a5e1-a7360cf50158.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] Luxury Car Rental -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: New York, United States, 100\n[textbox] Enter your pick-up location or zip code -> ENTER\n[link] Close -> CLICK\n[div] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.298, 0.493, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e592a68f-567f-4d6a-a1d6-4166cd129638_c741a4b9-037f-4e8f-8a72-606fb1bcba61.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 truck for 10001 zip code on Sunday 11:30 am with flexible dates.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.018, 0.535, 0.026] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_26e80001-b32e-4aee-982e-5d3ff6fb21bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[link] Trade In -> CLICK\n[link] Trade in by mail -> CLICK\n[combobox] search input -> TYPE: Nemo Front Porch 2P Tent\n[img] search icon -> CLICK\n[button] Trade in -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.57, 0.206, 0.758, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_bf14f1d4-470f-4110-b3f4-019a9f7d0aed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.273, 0.512, 0.296] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_d35e0d76-e5a4-478c-ae41-af9e27ffd454.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[link] Careers -> CLICK\n[link] Open Jobs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.296, 0.218, 0.314] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_0edebd4f-be22-427c-84d1-2223ab345ef6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[span] 22 -> CLICK\n[button] 03/25/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM\n[button] Browse Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.773, 0.142, 0.965, 0.17] in the image\nAnd my action is Action: SELECT\nValue: Price Low to High" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_bdb13abb-d7a0-428b-94c5-64951f68f1db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: street taco\n[li] Street Taco, Broadway, New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.21, 0.386, 0.216, 0.4] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_178bad0d-047f-4dc2-84ec-7f2a39924cc2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[label] Brown -> CLICK\n[svg] -> CLICK\n[label] 9 -> CLICK\n[label] Available in Store -> CLICK\n[label] KEEN -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.658, 0.223, 0.668] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_7ee2e3b2-d056-429c-a1c7-301f38f08660.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[link] Search for cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.123, 0.38, 0.153] in the image\nAnd my action is Action: TYPE\nValue: new orleans" } ]

{ "bytes": "", "path": "./images/fc8342f9-3e2e-4f59-b54e-b35cd7285fdb_672b06cb-3141-4330-b5c0-dfa51a37ba3f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Purchase the classic bundle for the simulation game Cities Skylines.\nPrevious actions:\n[link] Categories -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.238, 0.488, 0.25] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_d1f6fe24-c802-40ec-9de5-9c81c57b69aa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: Smithsonian" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.094, 0.78, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_404af1a6-ec27-4b33-aa24-691486c2ec74.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] 2+ -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.68, 0.114, 0.699] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2cb6558b-3dd7-4acd-a495-a4d3b96369ad_b3189405-5a1b-427c-a196-d223b6799956.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a list of convertible cars for sale under 20000.\nPrevious actions:\n[button] Car Sales -> CLICK\n[link] Shop Vehicles Under $20,000 Link opens in a new wi... -> CLICK\n[button] Body Type  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.134, 0.22, 0.196, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a92a83ca-25ff-4751-8754-c65ef858699d_98fb426d-f6ca-4336-8792-05ee6ea8b7e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Lava Hot Springs East KOA photo gallery.\nPrevious actions:\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: Lave Hot Springs East KOA\n[list] KOA Logo Icon Lava Hot Springs West KOA Holiday La... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.66, 0.225, 0.771, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90557510-32dc-415f-8507-41b050594962_317a2951-ef4e-4a9f-bd40-18d345a63cd1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coming soon AMC Artisan Films\nPrevious actions:\n[link] Visit the See A Movie page -> CLICK\n[link] Coming Soon -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.125, 0.285, 0.149] in the image\nAnd my action is Action: SELECT\nValue: AMC Artisan Films" } ]

{ "bytes": "", "path": "./images/84f19aba-ad0a-46db-84bb-c279b5353b8a_353e5f4e-0dd3-4175-b341-462558576da0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cafes that have outdoor seating and is dog friendly.\nPrevious actions:\n[textbox] Find -> TYPE: cafe\n[span] Cafe -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.252, 0.332, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_83552bdf-be4a-412c-a088-0615ea08bbaa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.091, 0.343, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_b84d10b2-35ff-4c2f-9e47-89243f5d02b4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[link] Rent a Moving Truck Budget Truck -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.148, 0.352, 0.176] in the image\nAnd my action is Action: TYPE\nValue: 07718" } ]

{ "bytes": "", "path": "./images/83ada6a6-e264-4d98-9d48-7f97f87bab5d_c944c80a-9545-44eb-a901-aad8b0834d7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 photo gallery of Acadia National Park.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.869, 0.0, 0.945, 0.035] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_68c8701d-311a-40ba-ad1a-482ee7d84c6a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[button] Any -> CLICK\n[menuitem] $99 or less -> CLICK\n[path] -> CLICK\n[button] Make -> CLICK\n[listitem] Chevrolet (101) Chevrolet (101) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.171, 0.249, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_7d0e900d-c57c-45f7-a2fc-a41e9ae471a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.23, 0.617, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/000c2828-e8ce-4b18-bfe0-89ed333add06_dc03dd08-a61b-430e-97ce-1c37fec505ff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $25 digital gift card for Tim Stebee, whose email address is [email protected]. Fill in sender name Jeerimiah Waton\nPrevious actions:\n[img] -> CLICK\n[img] GameStop Digital Gift Cards -> CLICK\n[textbox] Recipient Name -> TYPE: Tim Stebee\n[textbox] Recipient Email -> TYPE: [email protected]\n[textbox] Sender Name -> TYPE: Jeerimiah Waton" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.745, 0.975, 0.779] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/604c4377-e24c-4900-a72f-346d8999d443_338368ed-2c11-449d-ae56-e8726649f0ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a deal which is highly rated in Fiji location.\nPrevious actions:\n[textbox] Where? -> TYPE: Fiji\n[div] Fiji -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.251, 0.442, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29d6b448-a688-4c2f-8f6d-a13546d506d8_ffc9b6af-f030-473b-8333-db8f3f2cf31f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of jazz albums released in 1890.\nPrevious actions:\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.441, 0.241, 0.581, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a45ede7-6449-40b2-b032-149ddbe205a9_942f53c6-7c06-488e-af27-0fefddaa6b13.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\n[combobox] autocomplete -> TYPE: New Orleans" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.171, 0.318, 0.506, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b332a3c6-c4f5-423c-a207-b1bcb28db6c3_63febe49-b818-4412-96ee-0589ed46caba.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated Drop D guitar tab from the 1990s.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.055, 0.176, 0.068] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_26b869aa-497e-4de5-82f9-4f7fc39977d7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] Departure date input -> CLICK\n[button] Next month -> CLICK\n[gridcell] June 18 -> CLICK\n[gridcell] June 21 -> CLICK\n[button] Search packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.409, 0.249, 0.423] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_f34b6e67-a22e-4092-8304-c34b40b107e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[button] 1 adult -> CLICK\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight destination input -> CLICK\n[textbox] Flight origin input -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.097, 0.321, 0.102] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_f0138e48-b01c-4f47-81cf-41be44fa3298.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: MUMBAI\n[button] Mumbai, IN (BOM) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: LONDON" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.229, 0.582, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/102c50a4-23f8-44ae-8300-43822b271dbf_d0f7d055-29ae-4ebe-bd92-0c2e7ae2de4c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Show 684 stays -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.3, 0.276, 0.7, 0.287] in the image\nAnd my action is Action: TYPE\nValue: Togo" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_998b318b-b288-443e-9cd0-039f263ea2b3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: kashi vishwanath temple\n[span] Kashi Vishwanath Temple, Varanasi, Uttar Pradesh, ... -> CLICK\n[path] -> CLICK\n[div] 6 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.162, 0.721, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db72bae1-ff16-495c-89c7-1cff7c0ae503_1a75f8c0-4a9a-4c49-bac5-85a1ad22aecd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most popular Spanish recipe book available in paperback that are in stock.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: recipe\n[link] recipe book -> CLICK\n[select] All -> SELECT: In Stock (7,640)\n[select] All -> SELECT: Spanish (42)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.221, 0.196, 0.252] in the image\nAnd my action is Action: SELECT\nValue: Paperback (39,356)" } ]

{ "bytes": "", "path": "./images/92cfe78f-0385-4ef6-b829-ae34291e766f_81a0d494-3e16-47e6-ae12-96ca4d918431.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an LED TV below $1000.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] TV & Home Theater  -> CLICK\n[div] TV & Accessories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.195, 0.212, 0.23] in the image\nAnd my action is Action: CLICK" } ]