id
stringlengths 10
13
| image
dict | conversations
listlengths 2
2
|
|---|---|---|
mind2web_5200 | {
"bytes": "",
"path": "./images/8308d10f-3904-473a-a186-c6b8f939f018_5c130bc2-2d39-4454-9e2b-13392f1fbe4b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest private sightseeing trip of India in the month of June\nPrevious actions:\n[gridcell] Fri Jun 30 2023 -> CLICK\n[button] Apply -> CLICK\n[circle] -> CLICK\n[button] -> CLICK\n[div] Sightseeing Tours -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.026, 0.471, 0.105, 0.482] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5201 | {
"bytes": "",
"path": "./images/4c4ab02e-a617-490d-96c6-333d7fa82fe9_b9cf6d20-8607-44e1-841c-7a2fac6505e9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my upcoming trip with booking number 123456789 and last name Smith.\nPrevious actions:\n[tab] My Trips -> CLICK\n[textbox] booking reference -> TYPE: 123456789"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.353, 0.419, 0.647, 0.466] in the image\nAnd my action is Action: TYPE\nValue: Smith"
}
]
|
mind2web_5202 | {
"bytes": "",
"path": "./images/7c2ab1ed-54b7-4316-8b2f-d7467e01b540_b7b26215-0fc1-4125-824d-34fab74c6e32.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.006, 0.037, 0.181, 0.056] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5203 | {
"bytes": "",
"path": "./images/13d78369-994a-4202-a9ed-8361e1fdea9d_119a3ffb-4740-4938-8d4e-ebe3d288562a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bluetooth headphones with active noise-cancellation.\nPrevious actions:\n[searchbox] Search Site -> TYPE: headphones"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.542, 0.011, 0.592, 0.034] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5204 | {
"bytes": "",
"path": "./images/3d76a0fc-7ba9-4a74-ac52-db0cea359553_2faa9698-198d-4c20-a35f-8e569196c53e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced round trip flight with hotel on May 2 from Kathmandu, Nepal KTM to Shanghai, China PVG and return on May 5. Book a double room and check out with the default flights.\nPrevious actions:\n[div] Pudong Intl Airport (PVG), China -> CLICK\n[span] Sat 8 Apr - Sat 15 Apr -> CLICK\n[checkbox] 2 May 2023 -> CLICK\n[checkbox] 5 May 2023 -> CLICK\n[button] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.019, 0.136, 0.253, 0.156] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5205 | {
"bytes": "",
"path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_60718d13-f9e1-432f-9901-b1bdea2cc50d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[combobox] Pick up time -> SELECT: 9:30 AM\n[combobox] Drop off time -> SELECT: 9:00 AM\n[div] Search -> CLICK\n[div] SUVs -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.58, 0.092, 0.753, 0.103] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5206 | {
"bytes": "",
"path": "./images/cc643c1f-e73e-4e9f-abe9-5ee2d3b0a0dd_09199a3b-66e4-43b0-9207-2b16c63f458d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.539, 0.133, 0.668, 0.158] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5207 | {
"bytes": "",
"path": "./images/cd4df5fa-2c90-4a76-b4b0-0ca7bcdac2ee_8b05e2c4-bf97-4b1b-a37f-8c1cf88209f9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[link] 31 -> CLICK\n[listbox] hour -> SELECT: 08\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK\n[div] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.743, 0.218, 0.926, 0.262] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5208 | {
"bytes": "",
"path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_05fdd74b-f274-4e42-8108-8a4d93a95506.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[checkbox] Beachfront -> CLICK\n[checkbox] Hot tub -> CLICK\n[checkbox] Pool -> CLICK\n[checkbox] Towels -> CLICK\n[button] Property style -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.078, 0.223, 0.089, 0.234] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5209 | {
"bytes": "",
"path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_496a9af2-4f3f-48b8-aaa4-2c0e5f30309a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get email alerts for a flight from BHZ to EWN leaving on april 30 on the email lin.lon@gmail.com\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.658, 0.245, 0.894, 0.274] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5210 | {
"bytes": "",
"path": "./images/6678924a-0a3d-4c8b-ac35-3ba0aceea4d5_18773f07-6800-4427-8cc0-f846379f6f4c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Golden State Warriors Player List.\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Golden State Warriors\n[link] Golden State Warriors NBA -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.137, 0.122, 0.182, 0.15] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5211 | {
"bytes": "",
"path": "./images/6b4aa5a9-79c5-49a3-9cc6-ead02159a3dd_4d976fd8-c4fb-49c4-bc13-c59b2122b543.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Queen size memory foam mattress with lowest price.\nPrevious actions:\n[button] Menu -> CLICK\n[button] Products -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.117, 0.226, 0.32, 0.246] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5212 | {
"bytes": "",
"path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_8031f639-c35b-4b15-b569-2d863a8cd52f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.075, 0.202, 0.259, 0.229] in the image\nAnd my action is Action: TYPE\nValue: MUMBAI"
}
]
|
mind2web_5213 | {
"bytes": "",
"path": "./images/d7631fa2-ce46-4e20-a043-71ce70627c46_8177f07d-7a0e-40d0-8cd1-7185952cceb2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hip hop concerts that are happening this weekend.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.112, 0.038, 0.205, 0.069] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5214 | {
"bytes": "",
"path": "./images/10de6ac5-a69e-4d09-87fd-5737ca6f4b99_51296200-a767-42ec-86ee-fe3bc80412f4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket listing on floor B row 17 seat listing to Beyoncé music concert on Mon Aug 14 at 7:00pm.\nPrevious actions:\n[link] Music -> HOVER\n[a] Trending -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.314, 0.066, 0.517, 0.08] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5215 | {
"bytes": "",
"path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_7305cebb-6397-41a8-a67f-cec246c6c821.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[textbox] First name -> TYPE: Joe\n[textbox] Last name -> TYPE: Bloggs\n[button] Continue -> CLICK\n[button] Continue -> CLICK\n[button] Okay, got it. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.545, 0.203, 0.582, 0.251] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5216 | {
"bytes": "",
"path": "./images/42f64db7-c573-4ba8-9cab-a390e2f5e535_6c045a29-7c8f-408d-bf6d-e75aafa65bac.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] To Destination Airport or City Your Destination -> CLICK\n[textbox] Destination City or Airport -> TYPE: New York City\n[link] NYC New York City Area Airports, NY -> CLICK\n[combobox] Trip Type:, changes will reload the page -> CLICK\n[option] One Way -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.474, 0.07, 0.652, 0.095] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5217 | {
"bytes": "",
"path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_7d0cf261-5cc6-41cf-8142-21fbdd4ffda8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue with this address -> CLICK\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.119, 0.276, 0.2, 0.321] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5218 | {
"bytes": "",
"path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_b959a299-bca3-4ce1-a18c-1605c44fc90a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[textbox] Leaving from -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: changi\n[button] Singapore (SIN - Changi) Singapore -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.65, 0.198, 0.931, 0.232] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5219 | {
"bytes": "",
"path": "./images/4b2030ff-b83c-445f-bf87-9c8fbc68498b_8a5b0737-d36f-4476-bfdc-64c4c76d5551.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for wall art with a price range of $25 to $50.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: wall art\n[input] -> CLICK\n[link] Wall Art -> CLICK\n[div] Price -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.016, 0.39, 0.127, 0.401] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5220 | {
"bytes": "",
"path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_0564ac9b-e9d9-4084-a3f6-7688481a04d5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[select] 00 -> SELECT: 45\n[select] AM -> SELECT: AM\n[button] 3/25/2023 -> CLICK\n[link] 25, Saturday March 2023 -> CLICK\n[button] Open Travel Preferences modal. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.397, 0.204, 0.609, 0.231] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5221 | {
"bytes": "",
"path": "./images/521aa0aa-e099-4fc9-bb4e-f8a593a29f81_ea4f8853-82be-4579-8d16-ba3a72401d3c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 user reviews for the game \"Cyberpunk 2077\"\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.028, 0.06, 0.047, 0.069] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5222 | {
"bytes": "",
"path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_b0fe0bea-76e5-4c18-9b01-925d5f4d247e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: mens black hoodie\n[span] mens black hoodie -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.008, 0.206, 0.168, 0.22] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5223 | {
"bytes": "",
"path": "./images/0991035b-6acb-4dca-aaef-5384a0739781_b57c2e90-05e1-41db-9d48-e8af6eb99120.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 careers at the company on the Product Management team\nPrevious actions:\n[link] Company -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.074, 0.342, 0.161, 0.352] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5224 | {
"bytes": "",
"path": "./images/d9c160e7-b179-4d42-8570-e6f3f85aa412_c72364e6-89d8-4b78-8d47-2636bcd591d2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated adults-only romantic beach vacation deals and book the cheapest one.\nPrevious actions:\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK\n[button] Adults-Only -> CLICK\n[button] Romantic -> CLICK\n[button] DONE -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.016, 0.331, 0.491, 0.566] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5225 | {
"bytes": "",
"path": "./images/706d0ccd-c0ec-423d-88c0-a5716700a855_ca69e7b5-562b-4bf2-9457-9254ea31cee2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for used BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\n[listitem] X5 (87) X5 (87) -> CLICK\n[path] -> CLICK\n[switch] COMPARE -> CLICK\n[button] Add to Compare -> CLICK\n[button] Add to Compare -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.816, 0.196, 0.899, 0.243] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5226 | {
"bytes": "",
"path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_346e50e8-6e74-4963-907f-f63753b97234.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.363, 0.062, 0.421, 0.081] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5227 | {
"bytes": "",
"path": "./images/62c5067e-daff-4af6-bd79-83f6a969f4d6_43243a2c-3d76-40fc-8e5e-7fc1f48328e0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get details of the fastest trip between 52nd Street,Brooklyn and 74th Street, Brooklyn, leaving now, that is accessible for a disabled person.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.141, 0.279, 0.359, 0.309] in the image\nAnd my action is Action: TYPE\nValue: 52nd street, brooklyn"
}
]
|
mind2web_5228 | {
"bytes": "",
"path": "./images/4a9a05f8-6c23-46c5-bb38-eec63a477475_d3fae0d1-475d-4570-b0bf-7288bf69fc36.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK\n[textbox] Where? -> TYPE: mexico\n[div] Mexico -> CLICK\n[textbox] When? -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.218, 0.078, 0.81, 0.098] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5229 | {
"bytes": "",
"path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_7c2b9362-222c-4103-b794-de349596c06d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: CDG\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: JFK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.302, 0.159, 0.595, 0.177] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5230 | {
"bytes": "",
"path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_5b95df26-ff7a-49e4-b1ea-3abec2316d97.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[heading] Color -> CLICK\n[label] BLACK -> CLICK\n[svg] -> CLICK\n[heading] Supima® Cotton V-Neck Short-Sleeve T-Shirt (2022 E... -> CLICK\n[checkbox] L -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.666, 0.496, 0.906, 0.531] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5231 | {
"bytes": "",
"path": "./images/63e3020c-bf52-4950-9e26-50f98a59b5e3_d5348938-9876-40b0-81d5-01436fa10e76.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fast responding highest-rated electrician, who is currently open for replacement of some light fixtures in Westminster, and request a quote.\nPrevious actions:\n[link] Home Services -> HOVER\n[span] Electricians -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.36, 0.018, 0.564, 0.029] in the image\nAnd my action is Action: TYPE\nValue: WESTMINSTER"
}
]
|
mind2web_5232 | {
"bytes": "",
"path": "./images/bf159a0f-e6d7-46fa-beea-c231934fa7a9_5dc7ac8f-f789-4d98-9805-733815243c37.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel agents in Grand Junction, Colorado\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.729, 0.08, 0.787, 0.103] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5233 | {
"bytes": "",
"path": "./images/dc1f0824-5483-4d3b-87d2-3f760a42a25e_afa03dc3-151d-4448-8936-79d4ce60b351.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the events at any six flags park in Texas\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Fiesta Texas -> CLICK\n[button] Go! -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.654, 0.046, 0.714, 0.054] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5234 | {
"bytes": "",
"path": "./images/33064851-00d9-46c8-b0b7-6b5048005c51_7ca8088d-aaf6-4a6a-a81f-854a7fddcd12.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[button] Find a registry -> CLICK\n[textbox] First name -> CLICK\n[textbox] First name -> TYPE: SHELDON\n[textbox] Last name -> CLICK\n[textbox] Last name -> TYPE: COOPER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.722, 0.139, 0.839, 0.159] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5235 | {
"bytes": "",
"path": "./images/73960473-941b-4e09-8eb1-f059b85c2dba_a3a0d384-cfcc-439e-a071-d50217cb46b6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: Chicago\n[menuitem] Chicago United States of America ORD OHare Interna... -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: Paris\n[menuitem] Paris France CDG Charles De Gaulle Airport -> CLICK\n[option] One way -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.101, 0.197, 0.16, 0.225] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5236 | {
"bytes": "",
"path": "./images/112459f9-10ea-44b5-affa-79008c2977e7_fe0d8eda-4222-4b4f-989d-c947c8219867.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 check in with confirmation number 123456 for John.\nPrevious actions:\n[heading] Check-in -> CLICK\n[textbox] Confirmation or ticket number* -> TYPE: 123456"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.075, 0.218, 0.481, 0.243] in the image\nAnd my action is Action: TYPE\nValue: John"
}
]
|
mind2web_5237 | {
"bytes": "",
"path": "./images/3d83f3de-58f2-4aba-9b02-4a230d35a4ef_57dfa0ac-76e8-4753-948d-3d86bac41a80.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated adventure game available for early access.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Early Access -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.164, 0.51, 0.225, 0.524] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5238 | {
"bytes": "",
"path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_d143425a-b021-4736-b687-76deed6509ee.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 sellmycar@mail.com.\nPrevious actions:\n[textbox] Mileage -> TYPE: 222900\n[button] Next -> CLICK\n[span] -> CLICK\n[div] Leather -> CLICK\n[button] Next -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.193, 0.445, 0.284, 0.472] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5239 | {
"bytes": "",
"path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_fa48db1f-c5f0-48de-863a-93d7dbd7f15a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[link] YXL -> CLICK\n[div] Size -> CLICK\n[div] Sports -> CLICK\n[div] Fit -> CLICK\n[link] Fitted -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.044, 0.483, 0.233, 0.52] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5240 | {
"bytes": "",
"path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_7db38950-78ce-4a65-a62e-a5df13e62ff5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Easter -> CLICK\n[span] Easter Eggs -> CLICK\n[button] Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.391, 0.282, 0.443, 0.315] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5241 | {
"bytes": "",
"path": "./images/693ae151-6a70-41b1-b016-87279c4c532e_80c51282-2c04-482f-a0f3-1dbbc5d4574b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find the cheapest xbox 360 game available for purchase\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: xbox 360 games\n[searchbox] Search games, consoles & more -> ENTER\n[i] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.084, 0.32, 0.261, 0.353] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5242 | {
"bytes": "",
"path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_f60eedf6-96f7-429a-bb55-803977b8efe9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[heading] Category -> CLICK\n[input] -> CLICK\n[option] Relaxed Wireless -> CLICK\n[heading] Size -> CLICK\n[label] XXS -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.445, 0.306, 0.463, 0.325] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5243 | {
"bytes": "",
"path": "./images/b5c98548-4a3f-4e7c-8287-c36963930348_b74a4253-bfcd-4616-9d96-4219baf3cce4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental car to pick up at Paris Charles de Gaulle Airport CDG on april 13 at 10 am and drop off on april 18 at the same time\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.154, 0.039, 0.263, 0.063] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5244 | {
"bytes": "",
"path": "./images/bdc1f69a-da73-4e51-9dd8-83494d4983c2_0add092e-4553-40ee-8190-317048d85eb0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find check-in flight for John Smith having ticket no. 123456780\nPrevious actions:\n[link] Check In -> CLICK\n[textbox] first name maxlimit is 30 -> TYPE: John"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.388, 0.26, 0.562, 0.294] in the image\nAnd my action is Action: TYPE\nValue: Smith"
}
]
|
mind2web_5245 | {
"bytes": "",
"path": "./images/1267fbd8-54c8-4f2e-8471-b13c4de332c7_a1e3d261-9e4d-4aa2-b851-4df6032e1794.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a tiny home anywhere for an adult and 2 pets to stay in from april 10 to april 12\nPrevious actions:\n[path] -> CLICK\n[span] Tiny homes -> CLICK\n[button] Check in / Check out Any week -> CLICK\n[button] 10, Monday, April 2023. Available. Select as check... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.322, 0.092, 0.359, 0.111] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5246 | {
"bytes": "",
"path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_032dd419-18b5-4870-988f-085b2fa6d74a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[link] SHOP HOTELS -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: Ohio\n[button] Ohio United States -> CLICK\n[button] Check-in March 18, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.959, 0.124, 0.984, 0.137] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5247 | {
"bytes": "",
"path": "./images/978376c1-8545-4160-81d5-722bdea60434_025ff1b1-db7d-4df4-ad4b-77f3a2b2ee2f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Start the process to sign up for CVS ExtraCare\nPrevious actions:\n[button] Prescriptions -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.091, 0.387, 0.397, 0.424] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5248 | {
"bytes": "",
"path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_9d29ae83-8236-4a48-96a6-61cc6b26aab2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find The Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[div] Purpose of your event -> CLICK\n[li] Social -> CLICK\n[textbox] Guest rooms -> TYPE: 7\n[textbox] Event space -> TYPE: 50\n[button] Find -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.76, 0.228, 0.807, 0.242] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5249 | {
"bytes": "",
"path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_760ccf46-fb45-43e6-adde-f9f3799c52bd.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[button] All Location Details -> CLICK\n[button] Selected Pick-Up Date 03/23/2023 -> CLICK\n[button] 03/27/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.312, 0.554, 0.351, 0.582] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5250 | {
"bytes": "",
"path": "./images/644b7bed-b5fb-4090-b04f-a669d41ac93a_5fe867ec-cc98-4ef2-85ce-691bb9dadb48.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule of the East Boston ferry, check connections, and fares and download the pdf schedule.\nPrevious actions:\n[link] Ferry -> CLICK\n[span] East Boston Ferry -> CLICK\n[link] Schedule & Maps -> CLICK\n[button] Connections -> CLICK\n[button] Fares -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.648, 0.416, 0.868, 0.427] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5251 | {
"bytes": "",
"path": "./images/479bdc82-ec52-447b-a577-fa2bcdc3886f_ffb9e96b-9a62-4d47-b786-609d07e1a214.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers on home essentials under $20 and add the first 3 items to favorites.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Home Essentials Under $20 -> CLICK\n[button] Save to favorites, KUDDARNA, Chair pad, outdoor -> CLICK\n[button] Save to favorites, GULLBERGSÖ, Cushion cover, in/o... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.578, 0.76, 0.609, 0.784] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5252 | {
"bytes": "",
"path": "./images/36f2e415-356b-4e44-9ab1-6c3054d4de1f_466cf611-17b2-457e-97cc-7dc9d643ef86.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if cars are available for tomorrow at Elevated Escape in North Carolina.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.108, 0.123, 0.441, 0.136] in the image\nAnd my action is Action: TYPE\nValue: Elevated Escape"
}
]
|
mind2web_5253 | {
"bytes": "",
"path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_acc19e2a-1a0f-4208-a5a2-8c63425767d1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[radio] Price: low to high -> CLICK\n[button] Sort -> CLICK\n[button] Shape -> CLICK\n[span] -> CLICK\n[button] Shape -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.656, 0.492, 0.966, 0.532] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5254 | {
"bytes": "",
"path": "./images/71638c81-42f0-4218-a1b0-d3a137ad1cff_6bf9852e-ea2c-456d-8c70-2fc0f68b13dd.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 price of Tesla Model Y Performance for the 10001 zip code.\nPrevious actions:\n[link] Model Y -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.639, 0.363, 0.845, 0.38] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5255 | {
"bytes": "",
"path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_fa213183-95d3-41e5-a2ed-9593cb0934c4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[input] -> TYPE: Seattle, WA\n[link] Seattle, WA -> CLICK\n[link] Seattle, WA -> CLICK\n[button] Find -> CLICK\n[span] Coupons -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.13, 0.116, 0.23, 0.125] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5256 | {
"bytes": "",
"path": "./images/ccee2694-0d3e-4d81-8d52-5cdf82a9b81f_33c5ade5-919c-4875-be8a-5061b1ed3947.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.771, 0.112, 0.867, 0.119] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5257 | {
"bytes": "",
"path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_c744062d-fb8a-4354-b660-adb22d70dc2b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[button] Condition -> CLICK\n[link] Used -> CLICK\n[button] Style -> CLICK\n[link] French -> CLICK\n[button] Material -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.53, 0.328, 0.671, 0.344] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5258 | {
"bytes": "",
"path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_4b083d95-5ecd-4c5e-b53c-f9940aa9134d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Baggage info -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.073, 0.243, 0.205, 0.257] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5259 | {
"bytes": "",
"path": "./images/cfb351f8-804b-4074-9826-0b3525f68727_57afa34e-90f7-4742-b214-dbeae90b3f08.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2022 highest goal scorer in the MLS league\nPrevious actions:\n[button] Soccer -> HOVER\n[link] Leagues & Cups -> CLICK\n[link] Stats -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.034, 0.198, 0.091, 0.213] in the image\nAnd my action is Action: SELECT\nValue: 2022"
}
]
|
mind2web_5260 | {
"bytes": "",
"path": "./images/e6643cfb-567e-4e11-8cab-f85483573539_82ac4858-e319-4d30-b3e5-f4a4c395f697.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow one of the team leaders of one of the NHL teams from the Atlantic Division\nPrevious actions:\n[link] ESPN NHL Home Page -> HOVER\n[link] Teams -> CLICK\n[heading] Boston Bruins -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.816, 0.716, 0.903, 0.723] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5261 | {
"bytes": "",
"path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_af658e24-111b-4b86-bc49-099bb5c8baec.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[link] 1,342 2016 -> CLICK\n[link] 98 £15 - £20 -> CLICK\n[link] Condition -> CLICK\n[link] Phil Collins - Both Sides (CD, Album, RE + CD + Dl... -> CLICK\n[link] Add to Cart -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.475, 0.39, 0.485, 0.4] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5262 | {
"bytes": "",
"path": "./images/1267fbd8-54c8-4f2e-8471-b13c4de332c7_091dfb3c-d0d9-49c2-a922-18e6468bc29a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a tiny home anywhere for an adult and 2 pets to stay in from april 10 to april 12\nPrevious actions:\n[path] -> CLICK\n[span] Tiny homes -> CLICK\n[button] Check in / Check out Any week -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.247, 0.353, 0.284, 0.385] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5263 | {
"bytes": "",
"path": "./images/63e3020c-bf52-4950-9e26-50f98a59b5e3_408335c6-cd6f-4e47-a018-845ce17a180d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fast responding highest-rated electrician, who is currently open for replacement of some light fixtures in Westminster, and request a quote.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.158, 0.032, 0.243, 0.058] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5264 | {
"bytes": "",
"path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_8af6839d-a6e9-4945-ba6a-3cacefda382a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 johnmark@gmail.com and phone number of 234567890.\nPrevious actions:\n[button] DEALS -> CLICK\n[link] VACATIONS & RAIL TOURS Train vacation packages thr... -> CLICK\n[img] -> CLICK\n[link] Close -> CLICK\n[button] Instant Quote -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.289, 0.197, 0.711, 0.227] in the image\nAnd my action is Action: TYPE\nValue: Chicago"
}
]
|
mind2web_5265 | {
"bytes": "",
"path": "./images/4b99412b-6be2-4274-8843-4fc97f0c8247_c33f9822-9241-43c5-99b9-d2f95f871ed9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Track my bus -> CLICK\n[tab] Service Number -> CLICK\n[combobox] Search by Service Number -> TYPE: 10000001"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.02, 0.212, 0.715, 0.255] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5266 | {
"bytes": "",
"path": "./images/8eae88ef-9641-43c6-be6d-f8abc96d99fa_23bd27eb-bad8-45f9-88df-ba23d36bc19d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.027, 0.203, 0.215, 0.225] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5267 | {
"bytes": "",
"path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_c75eb377-9d6e-4a59-866a-86b6912f4e6c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Features -> CLICK\n[listitem] Sunroof(s) (2) Sunroof(s) (2) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Exterior Color -> CLICK\n[listitem] Black (1) Black (1) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.0, 0.175, 0.249, 0.195] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5268 | {
"bytes": "",
"path": "./images/1a2befd0-5e90-4bed-81b5-8ee0a93873df_f93c512a-0e48-4c6d-9271-edbd7a0af295.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 RPG video games.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Video Games chevron_right -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.225, 0.052, 0.287, 0.06] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5269 | {
"bytes": "",
"path": "./images/7b7079f0-8891-426a-8e53-0818a02a0159_39c6a073-6af9-4a14-9be0-2a6d782ae73d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 things to do nearby in Mar 30, 202\n3\nPrevious actions:\n[textbox] Where to? -> CLICK\n[button] Nearby -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.668, 0.123, 0.705, 0.139] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5270 | {
"bytes": "",
"path": "./images/26d3a803-b0aa-4a2c-bd31-3fe97a63388c_2ff008e7-d6e6-46bb-893d-375d5dd41af9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vacation packages to Hawaii.\nPrevious actions:\n[link] Search for packages -> CLICK\n[link] Hawaii Vacations -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.141, 0.171, 0.509, 0.197] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5271 | {
"bytes": "",
"path": "./images/0c7a69f9-989d-4899-a3fe-94c952859007_3208832e-8eae-44a6-afde-a00344187ea6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Chicago to London on 20 April and return on 23 April.\nPrevious actions:\n[textbox] From -> TYPE: Chicago"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.093, 0.268, 0.385, 0.292] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5272 | {
"bytes": "",
"path": "./images/2eaf60d5-d2af-4f50-a3ad-5cc9132a770a_bfb2a8b3-ca1e-4ce4-8be1-65c9a7ddad63.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[combobox] Sort By: -> SELECT: Price: Low - High\n[img] -> CLICK\n[radio] 5 -> CLICK\n[radio] GRADE_A -> CLICK\n[button] Add To Cart -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.554, 0.086, 0.793, 0.12] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5273 | {
"bytes": "",
"path": "./images/277bdab6-e924-45dd-ba26-d659d864d671_86fafa00-08fd-4d15-9ca1-88658c080ec1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\n[span] dog treats -> CLICK\n[span] View all 20+ items -> CLICK\n[span] Best match -> CLICK\n[option] Price: lowest first -> CLICK\n[span] Add -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.405, 0.227, 0.466, 0.243] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5274 | {
"bytes": "",
"path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_98f238b5-18bb-4181-816a-6d9b5a5d3b55.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Stays -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.684, 0.208, 0.841, 0.243] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5275 | {
"bytes": "",
"path": "./images/712d9d7f-d7ee-4554-affa-133449231ae4_492f1698-0267-4a06-b636-cc4f0480d04c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest medical audiobook on complementary medicine for under 20 dollars and add the top book to the cart.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Medical -> CLICK\n[link] Complementary Medicine -> CLICK\n[select] All -> SELECT: Audio (376)"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.027, 0.35, 0.196, 0.373] in the image\nAnd my action is Action: SELECT\nValue: Under US$20"
}
]
|
mind2web_5276 | {
"bytes": "",
"path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_20ad31c2-db7f-461e-ae21-1fc7eb68b0bd.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: SPRINGFIELD\n[button] Springfield, IL, US (SPI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: AUSTIN\n[button] Austin, TX, US (AUS) -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.284, 0.306, 0.478, 0.33] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5277 | {
"bytes": "",
"path": "./images/61d28a34-cc8e-46a9-b41d-c95933de2214_d4189d13-7ce7-4aeb-80da-c3fe1b0ac5a1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all time popular drop c rock tab of beginner difficulty\nPrevious actions:\n[link] Beginner 554,088 -> CLICK\n[link] Drop C 3,930 -> CLICK\n[link] Rock 2,420 -> CLICK\n[link] Tab -> CLICK\n[div] Today's most popular -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.825, 0.19, 0.97, 0.206] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5278 | {
"bytes": "",
"path": "./images/33964bc4-fc1d-417c-ba5a-2c1c45ed8d8b_eb02273c-148b-4fdf-9b98-90ddaec0236a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the most expensive things to do anywhere in December in a map\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Things To Do -> CLICK\n[div] Anywhere -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.586, 0.008, 0.781, 0.025] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5279 | {
"bytes": "",
"path": "./images/f57e6c0a-8f8b-4756-9f1d-1bdea7a0af5c_8f862cf0-ac81-4f52-84aa-550ecc2e259c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a pack of toilet paper and a bottle of laundry detergent to your Amazon cart with the lowest total price.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: toilet paper"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.651, 0.004, 0.686, 0.021] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5280 | {
"bytes": "",
"path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_04457367-8505-4973-b9af-ecd5eb814182.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 johnmark@gmail.com and phone number of 234567890.\nPrevious actions:\n[link] Close -> CLICK\n[button] Instant Quote -> CLICK\n[textbox] What city would you like to depart from? -> TYPE: Chicago\n[checkbox] I'm interested in the reverse trip of the selected... -> CLICK\n[checkbox] Deluxe Bedroom -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.289, 0.192, 0.447, 0.23] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5281 | {
"bytes": "",
"path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_c30f4d49-9308-4bb4-95e9-925b39ffde9a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: Ohio\n[button] Ohio United States -> CLICK\n[button] Check-in March 18, 2023 -> CLICK\n[button] Next month -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.963, 0.169, 0.981, 0.182] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5282 | {
"bytes": "",
"path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_f6af5393-0ce0-46f0-8b74-4e24be4e2eb7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[menuitem] Price Trends -> CLICK\n[span] -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK\n[gridcell] 1 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.324, 0.357, 0.335, 0.366] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5283 | {
"bytes": "",
"path": "./images/66625c9d-5bf3-42d1-b463-ab2767307201_ef8fc370-3a59-4d06-bcc6-a8048ad914f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Learn more about the Partner Deal that gives 25% off for Veterans.\nPrevious actions:\n[button] Deals -> CLICK\n[link] Partner Deals -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.382, 0.74, 0.618, 0.759] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5284 | {
"bytes": "",
"path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_963d0e12-9794-4fa0-bf40-2c8b8d7a7885.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Search location -> TYPE: TEXAS CITY\n[div] Texas City, TX -> CLICK\n[textbox] Select a date range. -> CLICK\n[img] Right -> CLICK\n[gridcell] Choose Saturday, April 22nd 2023. It's available. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.438, 0.532, 0.464, 0.562] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5285 | {
"bytes": "",
"path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_0ebc6a29-19cc-47fc-bd87-454c1635c3a2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] 20 -> CLICK\n[combobox] Pick Up Time -> SELECT: 3:00 PM\n[combobox] Return Time -> SELECT: 6:00 PM\n[button] Select My Car -> CLICK\n[link] Close -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.757, 0.569, 0.882, 0.608] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5286 | {
"bytes": "",
"path": "./images/d64cbfc6-7ace-4cad-9f0a-6643cd83de6e_1abdf652-813a-4b30-8713-7c1777b532cf.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[link] $50 to $100 -> CLICK\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK\n[link] Amazon Basics 7-Piece Lightweight Microfiber Bed-i... -> CLICK\n[button] Red Buffalo Plaid $57.81 In Stock. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.811, 0.333, 0.97, 0.354] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5287 | {
"bytes": "",
"path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_1c9b36d1-16c5-4ca4-9e82-ce67012536be.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harrt Reid Intl Airport, LAS\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[generic] Close -> CLICK\n[textbox] mm/dd/yyyy -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.639, 0.528, 0.666, 0.551] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5288 | {
"bytes": "",
"path": "./images/48ca542f-5346-40b9-b586-9294a2f64519_3d969a7c-5bb4-45b6-9fd1-ba7943641510.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Like a game mix album.\nPrevious actions:\n[searchbox] Search -> TYPE: game mix"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.541, 0.008, 0.553, 0.016] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5289 | {
"bytes": "",
"path": "./images/2ef75333-ca40-454f-a65c-88b6b60e2497_d5cf93d2-7fa2-4971-8668-436c866e37c2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] tours. -> CLICK\n[li] Boat Tours -> CLICK\n[div] Show Info -> CLICK\n[link] View Tickets Now -> CLICK\n[button] Check Availability -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.742, 0.156, 0.754, 0.165] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5290 | {
"bytes": "",
"path": "./images/caafd610-202e-49d2-85d1-3f167f3ab443_d7bfb473-8c73-4808-96bc-187d00be5ad7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 map of a Six flags park in mexico\nPrevious actions:\n[button] Browse the Parks Below -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.527, 0.735, 0.846, 0.779] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5291 | {
"bytes": "",
"path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_bddaad73-e494-46f5-a14b-25dddc2c137b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] Search for packages -> CLICK\n[textbox] From -> TYPE: Birmingham\n[span] Birmingham, England, United Kingdom -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.431, 0.141, 0.587, 0.175] in the image\nAnd my action is Action: TYPE\nValue: Paris"
}
]
|
mind2web_5292 | {
"bytes": "",
"path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_db1a7212-3913-4f4a-97d9-dea87a43cf1a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[combobox] Return Time -> SELECT: 1:00 PM\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $14.45/Day$13.95/Day -> CLICK\n[checkbox] $12.99/Day -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.812, 0.508, 0.93, 0.553] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5293 | {
"bytes": "",
"path": "./images/7c28f4e3-3dcf-477b-98c3-087c4fc16655_6f6671ae-98f0-4b14-8c7c-870d0ed1d39d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store which is nearest to 10017 zip code.\nPrevious actions:\n[link] Store Locator -> CLICK\n[searchbox] Postal code, address, store name -> TYPE: 10017"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.708, 0.149, 0.727, 0.164] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5294 | {
"bytes": "",
"path": "./images/a88676d0-c252-408f-b796-93c95f6b71fc_5499a9c1-e7dc-4ed6-a400-bbb551015eba.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my trade offers.\nPrevious actions:\n[link] BUCKEYE.FOOBAR -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.496, 0.249, 0.552, 0.275] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5295 | {
"bytes": "",
"path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_85b15500-7ef7-44a8-bb3c-d956b2a1361b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] Continue -> CLICK\n[button] Continue -> CLICK\n[button] Okay, got it. -> CLICK\n[img] undefined -> CLICK\n[button] Continue without a seat -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.357, 0.361, 0.516, 0.384] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5296 | {
"bytes": "",
"path": "./images/4a4ecf18-e7a3-448a-b8cb-b337ee20048d_1004b2e9-f35b-41b0-8d61-f0b4bc059024.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 table for 3 in Los angeles for diner at 09 PM on Mar 10\nPrevious actions:\n[svg] -> CLICK\n[button] Los Angeles -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: diner"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.171, 0.06, 0.673, 0.095] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5297 | {
"bytes": "",
"path": "./images/164cf025-e767-4781-930d-5bd46ad2c4c1_9329b2b4-204c-456d-803b-fd5be3bb63a3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Resy Staff Favorites in Seattle?\nPrevious actions:\n[button] Location Atlanta -> CLICK\n[button] Seattle -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.15, 0.026, 0.423, 0.059] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5298 | {
"bytes": "",
"path": "./images/a63b891b-4703-46ab-8633-b151b26574d1_91fc5db3-bc62-423e-ac0f-c4b6fa8cb02f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 software requirements for iPhones that support live tv on demand streaming.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.166, 0.079, 0.259, 0.105] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_5299 | {
"bytes": "",
"path": "./images/4a9a05f8-6c23-46c5-bb38-eec63a477475_c0a0ef81-6f9f-44d3-9189-18f73175c4ea.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[textbox] Where? -> TYPE: mexico\n[div] Mexico -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] May -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.203, 0.146, 0.266, 0.173] in the image\nAnd my action is Action: CLICK"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.