Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/d4f9c67f-00c5-41ed-bde1-c704b92647f7_45ac5967-b39a-4abb-abe9-314ab611fcc0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare Pro Plans with other plans available.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.623, 0.0, 0.702, 0.023] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_d7aae626-e02f-4f67-a2ed-100574db0121.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] + -> CLICK\n[textbox] About Your Trip: -> TYPE: Wedding Anniversary\n[button] Continue -> CLICK\n[textbox] *First Name -> TYPE: John\n[textbox] *Last Name -> TYPE: Mark" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.314, 0.711, 0.34] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/dc2aa3f8-eda0-455b-98dc-adc56089259a_6b02e5e0-bda2-415d-9468-9796ce2ad2b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 route information for flights from Ohio and New York airports that have already arrived.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.419, 0.469, 0.449] in the image\nAnd my action is Action: TYPE\nValue: Ohio" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_8f3e61f6-be1e-4fbc-b01c-904f68a74086.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[gridcell] Choose Tuesday, April 25th 2023. It's available. -> CLICK\n[button] 1 Room, 2 Guests Click to edit rooms and guests -> CLICK\n[path] -> CLICK\n[button] sub 1 -> CLICK\n[div] open -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.327, 0.389, 0.497, 0.405] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_ae0e503c-2e94-4e89-92e5-a385c1434d50.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.1, 0.777, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc174cb2-520d-49c3-93da-f93a1c485c03_77d2fade-b9c9-46c2-b41b-81e8bc671d15.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fare options to go from the south station to the north station\nPrevious actions:\n[button] Fares  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.057, 0.303, 0.074] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/17fffbee-e41b-46e4-ab75-675b263ca7b7_d0ed97a5-260e-43f7-b268-72fa521ff5a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 power supply unit with at least 600W power output.\nPrevious actions:\n[searchbox] Search Site -> TYPE: 600w power supply\n[button]  -> CLICK\n[generic] 600 W -> CLICK\n[combobox] Featured Items  -> SELECT: Lowest Price" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.233, 0.451, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c0eeead1-f8ea-4819-a6da-ef0108b40c89_3f6e79c5-fb1f-41c7-be6c-53bedd7bd544.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sign Allan Smith for email offers with the email [email protected] and zip code 10001\nPrevious actions:\n[a] -> CLICK\n[textbox] First Name (required) -> TYPE: Allan" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.196, 0.754, 0.221] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/851ed4e6-51ee-47ad-a861-a28bdc61a102_d47cbb1c-7d70-445f-a145-f4af8c2e35f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the page to schedule a Model X test drive.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Demo Drive -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.452, 0.667, 0.474] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a440d5f-1cc8-43de-86f5-ea181b0d12f8_c53a794a-53ea-4564-b4f3-5ef7c0279bab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Who were the NBA season leaders from the 2020-21 regular season?\nPrevious actions:\n[link] NBA -> CLICK\n[link] Stats  -> CLICK\n[button] Stats -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.133, 0.517, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf8da12a-e1fd-48b5-8c53-b88f301ca1e0_bac428a8-a55a-4c2d-a416-51ae11d42509.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 video game consoles and filter the results to show only those that have Wi-Fi Capability.\nPrevious actions:\n[button] Video Games & Consoles -> CLICK\n[link] Video Game Consoles -> CLICK\n[button] All Filters -> CLICK\n[tab] Features -> CLICK\n[checkbox] Wi-Fi Capability -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.203, 0.757, 0.222] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/05e1f2bd-3498-4fcb-8d43-37c903397ded_a695dfc5-ea9d-4bb7-8efb-45d3aa1f8928.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 balance for a gift card with the number 1000000000000000 and pin 1222\nPrevious actions:\n[link] Visit the Gift Cards page -> CLICK\n[link] Check Balance -> CLICK\n[spinbutton] Gift Card Number -> TYPE: 1000000000000000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.276, 0.5, 0.304] in the image\nAnd my action is Action: TYPE\nValue: 1222" } ]

{ "bytes": "", "path": "./images/04b8b406-a031-48a3-a002-b1791d872e16_83a425dd-09e4-4a42-b6c7-440c00333fd8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $100 Google Play Gift Card to cart and recipient email address as [email protected]\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Google Play\n[button] google play gift card -> CLICK\n[img] Sponsored Ad - Google Play gift code - give the gi... -> CLICK\n[button] $100 -> CLICK\n[textbox] To -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.819, 0.1, 0.968, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/94bd2a0f-fe08-4420-a0e8-d48248630b6e_062da2e4-9c43-48c4-898f-1ef4b05a7542.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Leaderboard for the top 10 fantasy Basketball players for the Rotisserie challenge.\nPrevious actions:\n[link] Fantasy . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.623, 0.08, 0.725, 0.089] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4777d638-204d-4e44-b81c-2fb43c471fb2_06935ea2-746d-401d-8d7f-39e882db3cd9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most reviewed cocktail bar with outdoor seating for reservation in San Francisco.\nPrevious actions:\n[link] Restaurants -> HOVER\n[span] Reservations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.022, 0.564, 0.035] in the image\nAnd my action is Action: TYPE\nValue: SAN FRANCISCO" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_3d430b08-3b31-40be-966d-0ebc25c0e439.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[button] close -> CLICK\n[button] Color -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Material -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.134, 0.824, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04b8b406-a031-48a3-a002-b1791d872e16_ba9f1b5e-9f7d-4890-b949-fab2446b19cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $100 Google Play Gift Card to cart and recipient email address as [email protected]\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Google Play\n[button] google play gift card -> CLICK\n[img] Sponsored Ad - Google Play gift code - give the gi... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.567, 0.26, 0.606, 0.273] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f567f79-e197-4d7e-9a49-877daae6dde5_fa456b75-d802-4cb8-a122-24ba577812f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\n[combobox] Search for anything -> TYPE: iPhone 12 Pro\n[button] Search -> CLICK\n[link] 128 GB - apply Storage Capacity filter -> CLICK\n[heading] Apple iPhone 12 Pro - 128GB - All Colors - Unlocke... -> CLICK\n[combobox] Please select a Color -> SELECT: Blue" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.205, 0.737, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_30031b64-c4c3-4741-a338-9de86a7bd529.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.596, 0.244, 0.746, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_f7c781d4-9856-4f3e-b227-20e1cfe0a4d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 closest parking spot to the Orlando Magic at Brooklyn Nets event, happening in Barclays Center, to enter after 3 pm and exit after 5 pm\nPrevious actions:\n[p] Orlando Magic at Brooklyn Nets -> CLICK\n[select] Sort by Distance -> SELECT: Sort by Distance\n[combobox] Start Time -> SELECT: 3:00 PM\n[combobox] End Time -> SELECT: 5:00 PM\n[button] Update Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.259, 0.496, 0.372, 0.533] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4947d606-626e-4da3-a595-bfedacbed3ec_68c477a3-d1b6-4c90-95e1-e78aa128bf1e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request ticket receipt for ticket no. 1234567890123 and last name Davis\nPrevious actions:\n[link] Receipts and refunds -> CLICK\n[link] Receipts for tickets and fees -> CLICK\n[textbox] Ticket number -> CLICK\n[textbox] Ticket number -> TYPE: 1234567890123\n[textbox] Last name -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.343, 0.656, 0.388] in the image\nAnd my action is Action: TYPE\nValue: Davis" } ]

{ "bytes": "", "path": "./images/92cfe78f-0385-4ef6-b829-ae34291e766f_28459c7a-e656-4f30-946d-53f528631e26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.226, 0.395, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_bf489b94-792e-475d-aa34-32cdcda0f2b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Fan & Heatsink CPU Cooler -> 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 [0.809, 0.262, 0.868, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f754d919-2191-464e-a407-0f3da9409081_3b050be4-1d7e-43f1-a584-1bf2ce238aa0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See today's deals on video games and find the best deal on the lowest-priced mouse.\nPrevious actions:\n[link] Today's Deals -> CLICK\n[link] PC -> CLICK\n[link] Accessories -> CLICK\n[link] Gaming Mice -> CLICK\n[span] Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.847, 0.081, 0.979, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_e9c074e0-eb15-4d22-92b6-f703bb5da185.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[link] All Toddler (6M-5Y) -> CLICK\n[heading] Category -> CLICK\n[input] -> CLICK\n[option] Socks -> CLICK\n[generic] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.761, 0.212, 0.943, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_78a55844-7ec2-4b4d-9a58-e35d37ef18e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is [email protected], and phone number is 6157075521.\nPrevious actions:\n[textbox] Other Ways We Can Help -> TYPE: ac recharge\n[button] See Pricing -> CLICK\n[button] Get Service Estimates -> CLICK\n[textbox] Your Name * -> TYPE: James Smith\n[textbox] Email Address * -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.541, 0.557, 0.561] in the image\nAnd my action is Action: TYPE\nValue: 6157075521" } ]

{ "bytes": "", "path": "./images/4775a0e3-3dad-46f2-b719-b1c0dae9e147_2bd4c20d-4f07-4507-a6c5-9cf1b634a4d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[button] COLUMBUS, OH -> CLICK\n[textbox] Zip Code -> TYPE: 59901\n[button] Search By Zip Code -> CLICK\n[button] MAKE MY STORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.048, 0.106, 0.056] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51e85ea8-7a75-40f3-8f35-ed255f87171f_98776082-1913-404c-8a5b-ff56c03291c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to cart 2 bottles of vitamin D that are buy 1 get 1 free and new arrival.\nPrevious actions:\n[button] Shop -> CLICK\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK\n[link] Vitamin D -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.421, 0.163, 0.441] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_f2aa38c8-10e2-4a9a-8305-480422409dd9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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, 0.54, 0.512, 0.563] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f804150b-c2e9-40ca-b71f-d0d0d95e0c46_ff4a9a5f-bb9a-4fe4-ac0d-1b6e7ef9a46d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in New York City for 2 adults from Apr7 to Apr 8.\nPrevious actions:\n[link] Hotel , Opens another site in a new window that ma... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.125, 0.4, 0.157] in the image\nAnd my action is Action: TYPE\nValue: New York City" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_e58c6cf0-b67e-459b-bdad-9bfe55c453ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.112, 0.041, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b39c9ac-a965-4902-a7d9-ec7fb36ca096_b9ee8eb8-3b77-4ec0-9278-a65267b9cc50.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of a flight between San Antonio, Texas, and Bellingham, Washington on April 8.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.658, 0.324, 0.894, 0.363] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/240952bd-853b-4653-a358-49c2784cf568_0d3bb8c1-0174-43bb-ba64-b4f5d4392c7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\n[button] Find Schedules -> CLICK\n[img] -> CLICK\n[span] -> CLICK\n[button] Close -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.182, 0.393, 0.296, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_875a9aaa-9e35-4575-868b-6dd03d6ca8dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[button] Go! -> CLICK\n[link] Tickets & Passes  -> CLICK\n[link] Birthdays -> CLICK\n[button] Buy Now -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.087, 0.487, 0.117] in the image\nAnd my action is Action: TYPE\nValue: Neo" } ]

{ "bytes": "", "path": "./images/84d8a4df-0bba-45f9-b4c8-f5d455de451c_d8706414-226d-4656-b7d5-818d440c9c6d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one baby one piece to cart.\nPrevious actions:\n[link] BABY -> CLICK\n[link] One-Pieces -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.388, 0.256, 0.584] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b99412b-6be2-4274-8843-4fc97f0c8247_fe2329c4-61b1-43e9-9ef6-52d2ee4bdd48.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track the bus with service number 10000001\nPrevious actions:\n[button] Check my bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.434, 0.075, 0.559, 0.105] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_a2ff1967-a42c-486a-9a4b-356fc3d1f590.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[textbox] Guest rooms -> TYPE: 1\n[textbox] Event space -> TYPE: 7\n[button] Find -> CLICK\n[link]  All Filters -> CLICK\n[heading] Amenities  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.354, 0.181, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d4f7da1f-2ed8-4110-8dea-35f07b7a1756_d2dc023e-7146-43f3-88e4-dd00ce65a2f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Begin booking a 14 day cruise from Los Angeles to Hawaii\nPrevious actions:\n[span] Sail To -> CLICK\n[button] Hawaii -> CLICK\n[button] SAIL FROM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.272, 0.568, 0.293] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_67c0685a-9f53-46c3-9842-d416f890ea25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[tab] Travel Info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.792, 0.177, 0.846, 0.192] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_2ca80415-2ee3-421c-b26e-662116f8f61c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Departure station, London selected. -> TYPE: edinburg\n[span] Edinburgh (Waverley) -> CLICK\n[combobox] Arrival station, Sheffield selected. -> TYPE: manchester\n[span] Manchester -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.196, 0.14, 0.206, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/957878ba-cb47-40d1-bf37-23039b2dff27_ad1a48fb-4b8a-4ea8-8945-04d8b57dd201.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Find a Shop -> CLICK\n[li] 43065 -> TYPE: 49107\n[textbox] Zip Code -> TYPE: 49107\n[div] 49107 - Buchanan, MI -> CLICK\n[button] Request Appointment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.4, 0.333, 0.438, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/96e95a76-4a1d-491c-82ff-fac663d89ddb_2fe0da29-0224-4d57-8ca7-f203f4ee7f69.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adventure games under 30 dollars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.097, 0.387, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87b23bf1-3c23-45a6-82bf-5a535c7cdc2f_e8302760-d313-4bd7-9f3b-c38819b7d97d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[link] Price (Low to High) -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $16.99/Day$6.55/Day -> CLICK\n[checkbox] $5.99/Day$1.38/Day -> CLICK\n[checkbox] MARKET -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.812, 0.351, 0.93, 0.392] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/83ada6a6-e264-4d98-9d48-7f97f87bab5d_4f8da365-0e3a-49aa-a1d5-32e0ed17259d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Open Menu -> CLICK\n[link] Photos & Multimedia -> CLICK\n[link] NPGallery -> CLICK\n[span] Search all Parks -> CLICK\n[li] Acadia National Park -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.123, 0.727, 0.14] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_8c85d1f6-5d5f-4b7f-8ad8-8fcdb58ca94b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Children's Books -> CLICK\n[link] Non-Fiction -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.191, 0.196, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e783cb30-26d8-45b8-b3d3-04570566bd32_60f12b9c-9c86-4d52-986c-d66d26ff9ea0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check Flight status on 21 April for flight number DL145.\nPrevious actions:\n[tab] FLIGHT STATUS -> CLICK\n[span] Mon, Apr 10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.309, 0.269, 0.329] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/998d121b-c858-485d-9dd3-4609575d144b_6bed6fe2-2ce7-47ef-9b12-9a8f308a3102.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most popular song this week by the no. 1 weekly charts ranked artist\nPrevious actions:\n[link] Charts -> CLICK\n[link] Weekly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.149, 0.407, 0.206, 0.418] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b74d9cc-ba1b-441d-a1a2-a05cea62a800_0fffa0bb-9a4e-48b1-9023-298c7a5829c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the trending daily deals.\nPrevious actions:\n[link] Today's Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.549, 0.567, 0.562] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/978760ca-7ec3-4b78-86c6-98b173c1a00e_512c2744-f31b-4206-98c6-f69312994a72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an artist from the chill category.\nPrevious actions:\n[searchbox] Search -> TYPE: Chill" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.541, 0.014, 0.553, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_728b67b3-d076-4667-afca-854c4864e209.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.097, 0.777, 0.122] in the image\nAnd my action is Action: TYPE\nValue: Crew" } ]

{ "bytes": "", "path": "./images/8082086a-10a7-4631-9792-b57337426f9a_0938ce44-198a-4d1f-a88a-c26cd07e7a2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a SUV with automatic transmission in New York drop off at March 30.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: New York\n[div] New York, NY -> CLICK\n[div] Sat, Apr 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.459, 0.575, 0.493] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_f235354f-5877-4b33-82b4-dd854cf552a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade in value for PS4 console\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Consoles -> CLICK\n[searchbox] Find values for games and more -> CLICK\n[searchbox] Find values for games and more -> TYPE: PS4\n[button] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.387, 0.085, 0.419] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb02400d-e9da-416a-839a-0068f511a630_4f7e3555-112c-40b1-b45e-a729bb210f51.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 WWE tickets for April 10 event happening in seattle, and book 4 cheapest lower level tickets.\nPrevious actions:\n[link] WWE Tickets -> CLICK\n[link] TICKETS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.177, 0.755, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a52774d2-550d-475a-922c-25c37d44557c_0b65497e-6dbe-4d02-b48d-0662c365c294.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[span] Mansions -> CLICK\n[button] Location Anywhere -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.583, 0.262, 0.68, 0.367] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e72f9c32-4633-4fcf-abd7-b7cc4a9aaba3_42319d5e-a274-4be1-a41e-e97ed6615952.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 similar artists to the Weekend.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.004, 0.675, 0.02] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc643c1f-e73e-4e9f-abe9-5ee2d3b0a0dd_cea8fdc0-7489-497d-b118-515681b710bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[combobox] Select Make -> SELECT: Lexus\n[combobox] Select Model -> SELECT: RX\n[textbox] Zip -> TYPE: 90012\n[button] Search -> CLICK\n[combobox] Select Minimum Year -> SELECT: 2017" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.476, 0.235, 0.506] in the image\nAnd my action is Action: SELECT\nValue: 2017" } ]

{ "bytes": "", "path": "./images/2ef75333-ca40-454f-a65c-88b6b60e2497_11949dd6-6d1a-42e9-a965-3bad963bac16.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tour to the statue of liberty for 3 adult on march 27th\nPrevious actions:\n[link] View Tickets Now -> CLICK\n[button] Check Availability -> CLICK\n[div] 27 -> CLICK\n[button] increase number -> CLICK\n[button] Apply -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.393, 0.355, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/701bc7ed-4b55-4fd2-b333-128e55c0a4c2_9bb8527b-4f0f-4adb-a232-baaaf881902d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[button] Discover -> CLICK\n[link] Upcoming Games -> CLICK\n[combobox] Platform -> SELECT: PS5\n[tab] AUG '23 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.284, 0.523, 0.405] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccee2694-0d3e-4d81-8d52-5cdf82a9b81f_8ae64ebc-8538-42aa-bd7e-f0675af9c375.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[combobox] Find a store -> TYPE: 60540" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.332, 0.092, 0.668, 0.129] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b310ebc-d9f4-4eb9-b348-30b329207a36_4231bc71-9555-49ec-8edf-0e46843f0832.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a dry cleaning shop with the highest rating and virtual consultation option for Ironing and stain treatment for a pair of suits and a few delicates in New York City.\nPrevious actions:\n[link] More -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.054, 0.388, 0.077] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_ef7e1558-a90e-4187-81be-290734f69625.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[path] -> CLICK\n[div] 4 -> CLICK\n[svg] -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.944, 0.109, 0.963, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdbd410d-170a-426d-b6d2-60dafaffe853_1c12e058-d63b-4514-bba9-ca7c1cec49d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best seller accessories for the Model X\nPrevious actions:\n[link] Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.389, 0.861, 0.611, 0.879] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fcb50c4e-a89e-4f18-b7c0-423295e7c298_f11eadf6-b789-4a4a-94d3-46613bffdc98.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.0, 0.169, 0.035] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_9db12986-1e76-4bff-80d8-6fd5ec3fb7b9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[span] Pickup -> CLICK\n[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: CHICAGO\n[span] Chicago -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.234, 0.095, 0.448, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cc81f50-465c-4d77-8fd7-d81fe1ffde84_d80603c1-f854-4923-ae8c-dae6003a5cd4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\n[link] Live TV -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.323, 0.27, 0.333] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_2bb14193-cad0-433f-aa68-3def5ba090a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[span] Get pre-qualified -> CLICK\n[button] Get started -> CLICK\n[textbox] First name -> TYPE: john\n[textbox] Last name -> TYPE: doew\n[textbox] Email address -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.173, 0.495, 0.2] in the image\nAnd my action is Action: TYPE\nValue: 4533234565" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_926471db-6655-45d2-9182-4af24f614ad2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[link] Students & Grads -> CLICK\n[link] INTERNSHIP PROGRAMS -> CLICK\n[link] HOTEL INTERNSHIPS INTERNATIONAL -> CLICK\n[button] Locations -> CLICK\n[button] Germany -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.615, 0.209, 0.728, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ac35e5a5-f52f-4886-9a23-65f0a6492c5e_a634663a-b496-4ead-94e0-e2c1a1f4b86a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 FC Barcelona's next fixture in the Spanish Copa de Rey\nPrevious actions:\n[li] Soccer -> HOVER\n[link] Barcelona -> CLICK\n[link] Fixtures -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.508, 0.138, 0.534] in the image\nAnd my action is Action: SELECT\nValue: Spanish Copa del Rey" } ]

{ "bytes": "", "path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_0dfd6898-ef1c-4b83-9abb-6fb4630af976.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.099, 0.181, 0.119] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e592a68f-567f-4d6a-a1d6-4166cd129638_55015e6d-ec84-41ae-99cc-1c8298eba5a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Reservations -> CLICK\n[link] Budget Truck -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.126, 0.352, 0.15] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_ac979c95-d410-4b40-83b9-32caefbe0fcf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] Flights -> CLICK\n[b] Columbus -> TYPE: NEW YORK\n[span] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.228, 0.617, 0.269] in the image\nAnd my action is Action: TYPE\nValue: TOKYO" } ]

{ "bytes": "", "path": "./images/fc8342f9-3e2e-4f59-b54e-b35cd7285fdb_e47414c2-b553-4232-82d6-5172de9eb75c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.334, 0.064, 0.387, 0.071] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27a8bf82-2e7e-48c3-8fb1-66909c13d585_53a3e30c-6fe2-4f5a-b132-8390e74be073.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Buick for sale within 250 miles from 26807.\nPrevious actions:\n[textbox] Zip Code: 43085 -> TYPE: 26807\n[combobox] 25 miles -> CLICK\n[generic] 250 miles -> CLICK\n[button] View 95 Vehicles -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.709, 0.048, 0.717] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ca80bb42-2617-4f29-bbcd-bcc426b3e407_83815d26-fe3f-46de-8fdf-b8d347a78e50.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.253, 0.038, 0.36, 0.051] in the image\nAnd my action is Action: SELECT\nValue: Airport" } ]

{ "bytes": "", "path": "./images/e9300d50-11fa-4f98-8c39-424630668ab9_6b487bd0-fda3-43e7-8adb-45fd77815a64.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the popular online Health events for tomorr\now?\nPrevious actions:\n[link] Health -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.409, 0.189, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_25595676-125c-4c39-8a05-9d86e9f3b5a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[button] Continue -> CLICK\n[div] + -> CLICK\n[textbox] About Your Trip: -> TYPE: Wedding Anniversary\n[button] Continue -> CLICK\n[textbox] *First Name -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.194, 0.711, 0.24] in the image\nAnd my action is Action: TYPE\nValue: Mark" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_82d93f55-8572-4c68-8aa7-982b1774b04c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Hotels -> CLICK\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.373, 0.122, 0.966, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_39ab3869-5aa7-4ee7-b1f2-d2e182997e3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Search -> CLICK\n[link] Selena Gomez -> CLICK\n[link] Popular tracks -> CLICK\n[button] More -> CLICK\n[button] Add to playlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.449, 0.042, 0.589, 0.061] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_36632f49-e9c1-4dbc-866d-eb03522d0614.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[svg] -> CLICK\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight origin input -> TYPE: NEW YORK\n[span] All airports -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.103, 0.702, 0.127] in the image\nAnd my action is Action: TYPE\nValue: PARIS" } ]

{ "bytes": "", "path": "./images/690eedad-706c-4c48-a803-45b4f1c069bb_f32216ff-a9d3-426b-ad6b-0081850a3db0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bestsellers under $20 and available in hardback.\nPrevious actions:\n[link] Bestsellers -> CLICK\n[select] All -> SELECT: Under US$20" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.276, 0.196, 0.307] in the image\nAnd my action is Action: SELECT\nValue: Hardback" } ]

{ "bytes": "", "path": "./images/14f0e837-af77-44b9-9cad-a8911aab30c6_89ea3db5-1984-4912-a93a-8cdb9b2402af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the status of flight from Columbus, number 1234 on April 5th, 2023.\nPrevious actions:\n[heading] Flight status -> CLICK\n[textbox] Flight number -> TYPE: 1234" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.275, 0.478, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50bd08bd-989f-44ba-8a99-71e75ba602f1_2a7a1bbf-df80-4b6f-a57f-fd754cc16db3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest monthly price for parking near Shubert Theatre.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.183, 0.592, 0.201] in the image\nAnd my action is Action: TYPE\nValue: Shubert Theatre" } ]

{ "bytes": "", "path": "./images/6d338fef-6d40-4f08-a045-861ddbc3d9f4_7f571a32-da4f-48e1-b26c-5c5b412dca5e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 glamping locations in Northern California.\nPrevious actions:\n[link] WAYS TO STAY  -> CLICK\n[link] GLAMPING  -> CLICK\n[link] glamping near you -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.314, 0.141, 0.336] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_becee9e3-be6c-4d01-b62e-3b2e23d3413a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: mumbai\n[span] Mumbai -> CLICK\n[span] 12 -> CLICK\n[i] -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.351, 0.686, 0.394] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_84502966-8969-4b4f-bbef-370c2f4e62bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.313, 0.486, 0.337] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a9708ad7-bec8-4435-b055-8ef6da520b8c_6baa7eb5-d650-4920-80c4-bfea64397c55.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top track for the top indie artist in the last 30 days\nPrevious actions:\n[link] Music -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.824, 0.182, 0.957, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_285f5467-2cad-4f8d-8b01-8f90a80e3cce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[searchbox] Search Site -> CLICK\n[searchbox] Search Site -> TYPE: Western Digital internal SSD 1 TB\n[button]  -> CLICK\n[link] Western Digital WD_BLACK SN770 M.2 2280 1TB PCIe G... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.807, 0.412, 0.963, 0.437] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc643c1f-e73e-4e9f-abe9-5ee2d3b0a0dd_ec2b8835-2edf-4769-a89a-5c36d204ee52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[combobox] Select Model -> SELECT: RX\n[textbox] Zip -> TYPE: 90012\n[button] Search -> CLICK\n[combobox] Select Minimum Year -> SELECT: 2017\n[combobox] Select Maximum Year -> SELECT: 2017" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.212, 0.226, 0.231] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_9ce95ce5-01c8-4a7a-87a4-aae8193cd6d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is [email protected], and phone number is 6157075521.\nPrevious actions:\n[link] Car Repair -> HOVER\n[link] Auto Repair Prices -> CLICK\n[combobox] Year -> SELECT: 2022" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.35, 0.322, 0.387] in the image\nAnd my action is Action: SELECT\nValue: Toyota" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_2566660a-da4f-4da5-979a-0ffb4953d972.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[button] Remove -> CLICK\n[textbox] Flight origin input -> TYPE: Mumbai\n[span] Chhatrapati Shivaji Intl -> CLICK\n[textbox] Flight destination input -> TYPE: Dubai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.434, 0.175, 0.784, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/96fb7e5d-08b1-4def-a6f8-6ee81055d944_9bb86454-f3c6-453e-b06e-70f28ec3d09a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Gingerbread cakes recipe and add ingredients to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.225, 0.011, 0.776, 0.063] in the image\nAnd my action is Action: TYPE\nValue: Gingerbread cakes" } ]

{ "bytes": "", "path": "./images/7bda9645-0b5f-470a-8dd7-6af0bff4da68_a645bce8-e7b5-44ef-99b2-045410868809.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[searchbox] Find a location -> TYPE: Boston\n[span] Boston -> CLICK\n[svg] -> CLICK\n[button] 18 -> CLICK\n[combobox] Time -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.872, 0.13, 0.894, 0.145] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_c6cbec5e-1b4e-4c9b-bbc5-c0d55a1968e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[textbox] Zip Code -> TYPE: 10001\n[textbox] (###) ###-#### -> TYPE: 888888888\n[textbox] Email Address -> TYPE: [email protected]\n[textbox] Email Address -> TYPE: [email protected]\n[textbox] Employer Name -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.652, 0.685, 0.685] in the image\nAnd my action is Action: TYPE\nValue: Gua AB" } ]

{ "bytes": "", "path": "./images/44ad28c9-c0d6-4d41-a49d-afeaa6ecaabe_b178005b-95d0-4ad2-9d7a-fcf68844cf09.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way bus ticket between Albany, NY and Bloomington, NY April 10th and add the second one to cart.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Albany, NY" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.41, 0.135, 0.423] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_09862727-dffe-4e83-a678-d29962c98d92.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the mystery vehicle to pick up at Bradenton in Mahattan, Florida on april 20 at 3 pm and return at 6pm\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[link] 20 -> CLICK\n[link] 20 -> CLICK\n[combobox] Pick Up Time -> SELECT: 3:00 PM\n[combobox] Return Time -> SELECT: 6:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.237, 0.567, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/77be98ff-e4db-4745-9b87-6ce69754c4c2_e2dc345b-7f76-4518-9f6b-1e75f62a4fa5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wheelchair accessible parking for the Pittsburgh Pirates at St. Louis Cardinals event in Busch Stadium on Apr 13.\nPrevious actions:\n[textbox] Search for parking -> TYPE: busch stadium\n[li] Busch Stadium, Clark Avenue, St. Louis, MO, USA -> CLICK\n[p] Pittsburgh Pirates at St. Louis Cardinals -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.49, 0.339, 0.508] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_a40aa80f-344a-4d08-8333-4778e7549172.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.105, 0.181, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87b23bf1-3c23-45a6-82bf-5a535c7cdc2f_7adc528f-60dc-477b-8cb8-77ad576f840b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[link] Long-Term Car Rental -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: orlando\n[span] Orlando Intl Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 29 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.886, 0.126, 0.913, 0.143] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_6592370e-2797-4a62-9b33-9769fd75aa37.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Saturday April 1, 2023 -> CLICK\n[button] Noon -> CLICK\n[option] 2:00 pm -> CLICK\n[svg] -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.179, 0.105, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/351568c6-452d-4f32-9375-2b6301f0cb36_04339d0b-8754-454b-b068-ce03b1f45f86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[listitem] Queensboro Plaza Station, Long Island City, NY, US... -> CLICK\n[searchbox] To -> TYPE: Grand Central, NY\n[listitem] Grand Central Terminal, East 42nd Street, New York... -> CLICK\n[button] Open Travel Preferences modal. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.165, 0.609, 0.198] in the image\nAnd my action is Action: CLICK" } ]