id
stringlengths 10
13
| image
dict | conversations
listlengths 2
2
|
|---|---|---|
mind2web_2200 | {
"bytes": "",
"path": "./images/2b562465-e325-4743-8e68-6e7852594f93_e71abc2c-4ffb-460e-ba94-f76587391fc8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 terms and conditions of Amtrak RideReserve for Multi-Ride Passes\nPrevious actions:\n[button] DEALS -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.734, 0.102, 0.969, 0.217] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2201 | {
"bytes": "",
"path": "./images/3be7acd4-c8c4-4e0d-b2b6-f82a4e17de8c_62ad40a1-3e77-4bb7-bced-d863ee082eb0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the Resident evil 4 game guide.\nPrevious actions:\n[path] -> CLICK\n[link] Guides -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.191, 0.539, 0.276, 0.563] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2202 | {
"bytes": "",
"path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_0bcc192a-b80b-485c-a8f5-66deacb89805.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] , United States -> CLICK\n[link] click here -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: Ohare, Chicago\n[span] , United States -> CLICK\n[span] , Chicago -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.748, 0.389, 0.905, 0.419] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2203 | {
"bytes": "",
"path": "./images/4b431888-9909-40b5-8351-be52905e4d5a_1a497e83-83d0-4ccb-ae4d-22ec497edc64.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Real Madrid team schedule of the UEFA Champions League championship.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.931, 0.035, 0.966, 0.059] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2204 | {
"bytes": "",
"path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_c45ca820-5c91-49f7-8eae-05462119775d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy tv shows on netflix sorted by audience score.\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[img] netflix -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.391, 0.402, 0.514, 0.422] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2205 | {
"bytes": "",
"path": "./images/b1eb6602-3aa7-40ee-8968-69d83e7ef21c_fda96947-caa3-40a5-8f47-4413cf7cc0cc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[menuitem] Buy -> HOVER\n[menuitem] New Cars -> CLICK\n[p] SUV / Crossover -> CLICK\n[textbox] ZIP -> TYPE: 10017"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.025, 0.272, 0.233, 0.305] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2206 | {
"bytes": "",
"path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_e34a10ea-d14a-452f-a318-785adaca157d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: resident evil\n[span] resident evil -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.013, 0.262, 0.094, 0.298] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2207 | {
"bytes": "",
"path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_5ca5d0ff-3a34-437d-bee2-1fac238301f0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the most popular Women's Athletic Shoes.\nPrevious actions:\n[span] Shop by Category -> CLICK\n[link] Women -> HOVER\n[link] Shoes & Sandals -> CLICK\n[link] Athletic Shoes & Sneakers Athletic Shoes & Sneaker... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.796, 0.163, 0.986, 0.186] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2208 | {
"bytes": "",
"path": "./images/7ad37a91-c4c2-42d6-9b87-1f3e6a81647e_417ecefd-898d-409e-b06a-fedebbcfd761.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation availability for an Indian restaurant with price below $30 in East village\nPrevious actions:\n[link] restaurants. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.395, 0.164, 0.644, 0.198] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2209 | {
"bytes": "",
"path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_f72fce46-9cea-405a-bda3-7fa5b65f08b0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[link] Tickets & Passes -> CLICK\n[link] Birthdays -> CLICK\n[button] Buy Now -> CLICK\n[button] Next -> CLICK\n[input] -> TYPE: Neo"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.213, 0.107, 0.487, 0.134] in the image\nAnd my action is Action: TYPE\nValue: Thomas"
}
]
|
mind2web_2210 | {
"bytes": "",
"path": "./images/dd057bda-33ea-40b8-9865-771242e22f40_36ac0711-a68d-408f-b2eb-1451647e0fe0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fiction audio books sorted by lowest price.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Audio Books -> CLICK\n[link] Fiction -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.684, 0.122, 0.834, 0.134] in the image\nAnd my action is Action: SELECT\nValue: Price, low to high"
}
]
|
mind2web_2211 | {
"bytes": "",
"path": "./images/4b99412b-6be2-4274-8843-4fc97f0c8247_449b0be6-d463-4adf-bc5a-5a7c1173d402.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.443, 0.011, 0.559, 0.053] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2212 | {
"bytes": "",
"path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_24838af0-91ab-40e0-808b-4f59a031f1dc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[svg] -> CLICK\n[link] Luxury Car Rental -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.108, 0.18, 0.438, 0.197] in the image\nAnd my action is Action: TYPE\nValue: north las vegas"
}
]
|
mind2web_2213 | {
"bytes": "",
"path": "./images/5f2c3149-1820-4632-bfdb-3cf4615de2cc_b33f3bf0-ed3d-4894-92b0-3f5a17a350c4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dog food for puppies that is rated at least 4 stars and sort the results by price from low to high.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: dog food"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.276, 0.137, 0.673, 0.171] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2214 | {
"bytes": "",
"path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_9ae9ccd0-147e-4ce8-881a-79d4b3d8f717.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[h1] My New Playlist -> TYPE: Dirty\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.563, 0.524, 0.645, 0.552] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2215 | {
"bytes": "",
"path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_18f61a73-f84b-4cb1-a2f3-7b6865a53d80.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Add Less than 1 -> CLICK\n[button] Add 1 -> CLICK\n[button] Add 2 -> CLICK\n[button] Find Hotels -> CLICK\n[checkbox] Show rates with taxes and all fees -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.798, 0.24, 0.808, 0.248] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2216 | {
"bytes": "",
"path": "./images/8e721b00-f406-449b-9885-0267b47ecfdb_6d12a2b4-31a8-4534-97a2-6c84c75d3fad.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Jaguar XFs with no black exterior color and save the search as Jaguar to get a notification daily.\nPrevious actions:\n[searchbox] Search make, model, or keyword -> TYPE: jaguar xf"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.033, 0.149, 0.967, 0.183] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2217 | {
"bytes": "",
"path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_ec287a0e-e011-48ba-b37d-0ed8176625e6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Los Angeles (LAX - Los Angeles Intl.) California, ... -> CLICK\n[button] Going to -> TYPE: Miami, FL\n[textbox] Going to -> TYPE: Miami, FL\n[button] Miami (MIA - Miami Intl.) Florida, United States -> CLICK\n[button] 1 traveler -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.809, 0.172, 0.828, 0.18] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2218 | {
"bytes": "",
"path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_258c60a2-eebd-485f-86e6-890e57a66ec3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[span] Vacation packages -> CLICK\n[textbox] From -> TYPE: san francisco\n[a] SFO - San Francisco International, CA -> CLICK\n[textbox] To -> TYPE: new york\n[a] NYC - New York, NY -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.636, 0.372, 0.875, 0.41] in the image\nAnd my action is Action: SELECT\nValue: 2"
}
]
|
mind2web_2219 | {
"bytes": "",
"path": "./images/87989b8e-0b6a-4dbe-a8bf-6adc2bdf3c29_78412c79-dfb9-4973-9e9c-c241d9af03fe.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book an hourly parking at Atlanta International Airport.\nPrevious actions:\n[tab] Hourly -> CLICK\n[textbox] Search for parking -> TYPE: Atlanta International Airport\n[li] Atlanta International Airport, Spine Road, College... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.259, 0.44, 0.372, 0.484] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2220 | {
"bytes": "",
"path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_9d37eb8e-33e6-4a01-b91d-82a919ed0da2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[button] 1 Adult -> CLICK\n[button] Substract one Adult -> CLICK\n[button] Substract one Child -> CLICK\n[generic] Economy -> CLICK\n[option] Premium economy -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.284, 0.426, 0.478, 0.459] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2221 | {
"bytes": "",
"path": "./images/fb9c0e7f-02dd-453f-8c73-da19282abf84_1cdaba22-bf16-40a4-a417-9191b610019d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Ford Mustang with lowest price and save it.\nPrevious actions:\n[link] Cars for Sale -> CLICK\n[textbox] Search by Make, Model, Body Style or Keyword -> TYPE: Mustang\n[div] Ford -> CLICK\n[combobox] Sort By: -> SELECT: Price - Lowest\n[heading] Used 2000 Ford Mustang GT -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.835, 0.084, 0.854, 0.095] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2222 | {
"bytes": "",
"path": "./images/afa1f70c-c0ff-4e4d-a5c2-0c0d292ee066_1429b238-de97-4a6a-a14d-c14ac1c47e7b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cruise deals to Europe this summer that includes airfare and are all-inclusive.\nPrevious actions:\n[textbox] Where? -> CLICK\n[div] Europe -> CLICK\n[textbox] When? -> CLICK\n[li] Summer -> CLICK\n[button] SEARCH DEALS -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.203, 0.134, 0.266, 0.151] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2223 | {
"bytes": "",
"path": "./images/ad0369b6-cfd5-4555-bb4f-d84a942be555_d7c369dd-f0a0-4296-b42a-21e848626295.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order the cheapest climbing shoes in today's deals.\nPrevious actions:\n[button] Deals -> HOVER\n[link] Explore Deals -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.789, 0.214, 0.956, 0.228] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2224 | {
"bytes": "",
"path": "./images/f8027aa8-c193-47c8-a97b-432836093939_1fdaf4a6-f9af-477b-a6ad-d549a923e148.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Las Vegas, NV that offer free airport shuttle service.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.241, 0.079, 0.478, 0.099] in the image\nAnd my action is Action: TYPE\nValue: Las Vegas"
}
]
|
mind2web_2225 | {
"bytes": "",
"path": "./images/5c91b907-39db-49c3-af73-5eb5c2390a93_ed78af31-521a-4b45-b4f7-9b09e5b15a09.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 store in Modesto California and set is as my store.\nPrevious actions:\n[link] Find a store -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.032, 0.099, 0.32, 0.116] in the image\nAnd my action is Action: TYPE\nValue: california"
}
]
|
mind2web_2226 | {
"bytes": "",
"path": "./images/7eff6c15-bab6-4ce4-abb8-72619f593ea1_4ff772da-2257-42ff-8770-abeb5ee76e71.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my bus with service number SE4.\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: SE4"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.094, 0.279, 0.264, 0.295] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2227 | {
"bytes": "",
"path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_057168d0-10f5-478b-88de-40fc2f2a1544.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Search by product -> TYPE: mirror\n[button] Search -> CLICK\n[span] Columbus -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.664, 0.076, 0.961, 0.103] in the image\nAnd my action is Action: TYPE\nValue: atlanta georgia"
}
]
|
mind2web_2228 | {
"bytes": "",
"path": "./images/cdb6b70d-6083-49b5-908c-a6c0f711c175_ffe46fa1-15a2-44a5-8017-0b39e33fa3b2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces near Warner Theatre in Washington DC.\nPrevious actions:\n[link] CITIES -> CLICK\n[heading] WASHINGTON DC -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.526, 0.389, 0.588, 0.443] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2229 | {
"bytes": "",
"path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_2a4fda62-04d0-4158-8033-5c8be0ba3f71.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the most popular Women's Athletic Shoes.\nPrevious actions:\n[span] Shop by Category -> CLICK\n[link] Women -> HOVER\n[link] Shoes & Sandals -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.185, 0.288, 0.344, 0.336] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2230 | {
"bytes": "",
"path": "./images/22e33a38-902c-4f62-9e9a-822b2370b6d1_8ffa34a7-0378-4a31-9367-019e2fa0115e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Exotic Cars -> CLICK\n[link] Reserve Now -> CLICK\n[link] Beverly Hills -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.162, 0.347, 0.268, 0.376] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2231 | {
"bytes": "",
"path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_3bf9fc1a-cc1f-4276-a11a-485dc45a4eab.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[link] 2 -> CLICK\n[textbox] Date use format: -> CLICK\n[link] 2 -> CLICK\n[listbox] hour -> SELECT: 17\n[button] Get cheapest tickets -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.747, 0.145, 0.925, 0.172] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2232 | {
"bytes": "",
"path": "./images/102c50a4-23f8-44ae-8300-43822b271dbf_06c977cf-f2d5-40bc-ab31-453cdb6412b0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 3 places from OMG! below $500 to Wishlist and name it \"Togo\".\nPrevious actions:\n[button] Filters -> CLICK\n[textbox] max price $ -> TYPE: 500\n[link] Show 684 stays -> CLICK\n[path] -> CLICK\n[textbox] Name -> TYPE: Togo"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.297, 0.28, 0.703, 0.302] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2233 | {
"bytes": "",
"path": "./images/51fce1f7-566e-4ae4-89a4-dea4d0ec569e_6cab71d0-6ddd-4214-a367-31723a534fe1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an available wine at Kroger.\nPrevious actions:\n[path] -> CLICK\n[button] Departments -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.25, 0.26, 0.5, 0.281] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2234 | {
"bytes": "",
"path": "./images/3bb1c925-71ef-4713-a139-a3be65f8a7a5_211ae34b-54e9-4b42-acbb-df977fb6dba6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reviews for Fallout 4 and mark the first one as helpful.\nPrevious actions:\n[textbox] search -> TYPE: Fallout 4\n[link] Fallout 4 $19.99 -> CLICK\n[select] 1900 -> SELECT: 1995"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.427, 0.513, 0.508, 0.541] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2235 | {
"bytes": "",
"path": "./images/b28e6a37-6e9c-46bb-8012-18ca742a521f_24cd8cb6-fad4-4840-a423-b2bf2ce4de58.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.217, 0.022, 0.277, 0.055] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2236 | {
"bytes": "",
"path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_5cf65818-7dae-4713-b976-169a11e7b498.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[link] Tickets, Passes, VIP Tours -> CLICK\n[link] Tickets & Passes -> CLICK\n[span] Buy Now > -> CLICK\n[button] Buy Now -> 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 [0.367, 0.405, 0.418, 0.419] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2237 | {
"bytes": "",
"path": "./images/0f9dd411-f3ab-494e-8a3a-5dc9a908f4ee_aa137e85-cbce-4920-89d7-24cb550fbf81.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cvs pharmacy nearest to zip code 45201 that provides hair loss evaluation and treatment.\nPrevious actions:\n[link] Schedule a women's health exam -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.019, 0.32, 0.256, 0.331] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2238 | {
"bytes": "",
"path": "./images/da386775-280b-4a84-9801-4ae3098044b0_1f1cfcc3-ec16-49ed-83bd-4b388b1948a9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in California city for Limos which also offers military discounts and free wi-fi.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.243, 0.028, 0.324, 0.051] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2239 | {
"bytes": "",
"path": "./images/747429fa-7dac-4ab0-b604-13cb9bf787fe_7a476beb-eca9-48bf-abb4-286b0d996196.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 unused wireless Logitech Keyboard under $70.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless keyboard\n[button] -> CLICK\n[span] New -> CLICK\n[button] APPLY -> CLICK\n[span] Logitech -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.148, 0.552, 0.192, 0.565] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2240 | {
"bytes": "",
"path": "./images/ccee2694-0d3e-4d81-8d52-5cdf82a9b81f_aefbb363-74ca-43d6-9af5-1ed82db20b26.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the nearest apple store to zip code 60540 and check its opening time tomorrow.\nPrevious actions:\n[link] Store -> CLICK\n[link] Find one near you (opens in a new window) -> CLICK\n[combobox] Find a store -> TYPE: 60540\n[option] 60540 Naperville, IL, United States -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.117, 0.133, 0.352, 0.265] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2241 | {
"bytes": "",
"path": "./images/6a9a2e52-24b4-46c3-9e52-0f79c15ae3d0_b1e774ca-1b61-47d4-bcaa-5e233a773cdb.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[button] Country -> CLICK\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK\n[button] Team -> CLICK\n[searchbox] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.075, 0.326, 0.29, 0.357] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2242 | {
"bytes": "",
"path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_4074b1d5-90b6-4f54-a8bf-80233191ff1b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.037, 0.638, 0.114, 0.66] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2243 | {
"bytes": "",
"path": "./images/1d0dcb84-da65-4830-ba60-cc2b09a52a13_f5ffe0d3-f3c5-4f81-800e-d00052a64734.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\n[button] Submit -> CLICK\n[span] Select store -> CLICK\n[textbox] Enter zip code to save preferred delivery location... -> TYPE: 60173\n[span] Update ZIP code -> CLICK\n[span] See all bathroom boxes & baskets -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.462, 0.142, 0.546, 0.162] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2244 | {
"bytes": "",
"path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_b63cef7a-d7c0-4fd6-a051-17bf4be350e5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[button] Confirm -> CLICK\n[button] Show flights -> CLICK\n[heading] LKR 1,120,521 -> CLICK\n[button] Select fare -> CLICK\n[heading] LKR 3,125,932 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.057, 0.521, 0.48, 0.56] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2245 | {
"bytes": "",
"path": "./images/d7631fa2-ce46-4e20-a043-71ce70627c46_8bd2ba25-f3c9-464c-8943-020e48f3c1c8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] CONCERTS -> CLICK\n[link] Rap / Hip Hop -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.632, 0.224, 0.655, 0.237] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2246 | {
"bytes": "",
"path": "./images/41b8202c-9092-4307-ac58-2283c76df3b7_a7f466e8-470a-4460-b10b-38a6ab84458c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hot Dogs in Oakland, CA that Offers Delivery.\nPrevious actions:\n[textbox] Near -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.288, 0.012, 0.45, 0.019] in the image\nAnd my action is Action: TYPE\nValue: Oakland, CA"
}
]
|
mind2web_2247 | {
"bytes": "",
"path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_7c5a9c22-a130-4225-84ab-c661784863e6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[button] $ Price: Low to High -> CLICK\n[button] DONE -> CLICK\n[heading] $139 Vermont: Cozy Kimpton in the heart of Manches... -> CLICK\n[button] CHECK DATES -> CLICK\n[link] $189 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.861, 0.077, 0.9, 0.103] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2248 | {
"bytes": "",
"path": "./images/15a0ffe5-8462-4a8e-8938-91b05a40756f_2f2426db-0cca-4e67-a6b0-333de7a4b037.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a new address to the account. The address is 2983 Marietta Street, APT 2. Business name is Buck.\nPrevious actions:\n[span] 171 2nd street -> CLICK\n[textbox] Add a new address -> TYPE: 2983 Marietta Street\n[span] 2983 Marietta Street -> CLICK\n[textbox] Apt, floor, suite, etc (optional) -> TYPE: 2"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.298, 0.325, 0.702, 0.389] in the image\nAnd my action is Action: TYPE\nValue: Buck"
}
]
|
mind2web_2249 | {
"bytes": "",
"path": "./images/f738b393-9234-4c07-8baf-20f05627d5ed_f29b8470-f482-4097-a3c0-014d0ea77cb8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[textbox] Near -> TYPE: WEST HOLLYWOOD\n[span] West Hollywood -> CLICK\n[radio] Lawns or greenscapes -> CLICK\n[button] Fast-responding -> CLICK\n[button] Recommended -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.538, 0.124, 0.632, 0.141] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2250 | {
"bytes": "",
"path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_a5bc6789-f1f0-4aeb-9457-993e852ff0fa.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Drop off time -> SELECT: 9:00 AM\n[div] Search -> CLICK\n[div] SUVs -> CLICK\n[span] -> CLICK\n[label] Price (lowest first) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.791, 0.305, 0.916, 0.324] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2251 | {
"bytes": "",
"path": "./images/0b2c1886-0345-4ca7-a555-8b1cd1b1c40a_31825227-163b-4f9a-8253-81e49cd90371.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 certified fresh sci-fi films streaming at home.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.548, 0.233, 0.587, 0.244] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2252 | {
"bytes": "",
"path": "./images/61fa0552-66ac-4572-95f2-800537cfee7b_72041631-5eab-482b-9413-7c3553541926.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant with delivery service available 6pm on Mar 25th in Detroit, MI.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.086, 0.5, 0.292, 0.573] in the image\nAnd my action is Action: SELECT\nValue: Delivery"
}
]
|
mind2web_2253 | {
"bytes": "",
"path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_c207e1a1-c5a2-4a3c-aba7-4bf4e98d6829.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.45, 0.019, 0.491, 0.048] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2254 | {
"bytes": "",
"path": "./images/4e3cc9e2-baf7-449f-bf61-919eb773f29c_d95c30f0-a89a-4c2b-ac95-293e0904cf22.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Pack for hiking.\nPrevious actions:\n[button] Travel -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.223, 0.128, 0.377, 0.135] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2255 | {
"bytes": "",
"path": "./images/11344944-81ef-4fde-82b7-7e9724fc96f1_20dccc2d-feeb-4527-b6c6-8873b4b1f8f0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of discussion forums for games I own.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.405, 0.0, 0.482, 0.035] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2256 | {
"bytes": "",
"path": "./images/c987dd1d-9ade-4701-8cdb-a31f8f3bf673_398e93e6-b97d-4290-846d-dc5d8ec462a7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[link] Restaurants -> HOVER\n[span] Thai -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.36, 0.016, 0.564, 0.025] in the image\nAnd my action is Action: TYPE\nValue: WESTMINSTER"
}
]
|
mind2web_2257 | {
"bytes": "",
"path": "./images/eeeee9d8-5387-46bc-a741-5bcb66b46f31_8c6d633b-d81f-42ce-98c8-0704f88dd95e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a job opening in sales in San Fransisco, and if found, apply for the job.\nPrevious actions:\n[link] Our Team -> CLICK\n[menuitem] olink -> CLICK\n[link] See Open Roles -> CLICK\n[textbox] Select Department -> CLICK\n[option] Sales & Ad Ops -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.031, 0.316, 0.256, 0.341] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2258 | {
"bytes": "",
"path": "./images/ccd8d9f9-65f1-42ac-a699-5db7e380c760_e8482e40-59db-4fc3-aa34-8f93399de23b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Washington airports to New York airports and only show those with scheduled status.\nPrevious actions:\n[link] Flight Tracking -> HOVER\n[link] Flight Finder -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.059, 0.208, 0.463, 0.235] in the image\nAnd my action is Action: TYPE\nValue: Washington"
}
]
|
mind2web_2259 | {
"bytes": "",
"path": "./images/60e7ffd3-dda8-4ec6-9c10-115a5ab1bf90_0dc5da7a-7c42-43ad-8c6d-1270e1186f5f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 latest news from rotten tomatoes.\nPrevious actions:\n[link] NEWS -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.871, 0.089, 0.91, 0.095] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2260 | {
"bytes": "",
"path": "./images/2fc63250-ac9a-4cd4-a29d-6460f0652fa3_222cd8db-5718-4f2a-9fe2-93b144ba93cc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 keyboard and mouse combo under $100.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless keyboard mouse\n[button] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.125, 0.385, 0.192, 0.411] in the image\nAnd my action is Action: TYPE\nValue: 100"
}
]
|
mind2web_2261 | {
"bytes": "",
"path": "./images/1bf4f465-99cb-483b-aac1-a7512b150755_e209fc5a-4d34-43aa-88dc-898fc2cb3c9d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hydropack and make the results to show only items that have a capacity of 21 to 35L.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[li] Hydration Packs -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.051, 0.147, 0.119, 0.158] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2262 | {
"bytes": "",
"path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_f3d13de0-6b97-4f7e-acb5-77fc953b68f7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[li] Social -> CLICK\n[textbox] Guest rooms -> TYPE: 7\n[textbox] Event space -> TYPE: 50\n[button] Find -> CLICK\n[generic] Brand -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.202, 0.337, 0.34, 0.392] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2263 | {
"bytes": "",
"path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_2211b437-d9e0-41b7-a052-7d3867619be7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[checkbox] Walgreens New -> CLICK\n[button] Done -> CLICK\n[path] -> CLICK\n[link] View More -> CLICK\n[img] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.751, 0.819, 0.83, 0.847] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2264 | {
"bytes": "",
"path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_7d152147-a44e-4294-bc01-98b93f05e570.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: add a motherboard under $200 and a compatible processor at any price to the shopping cart.\nPrevious actions:\n[searchbox] Search Site -> TYPE: motherboard\n[button] -> CLICK\n[textbox] price to -> TYPE: 200"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.148, 0.804, 0.192, 0.816] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2265 | {
"bytes": "",
"path": "./images/c51cc2c0-5750-4bae-b665-ad1b7fafa63e_1f2e7cce-dfb0-4d72-82ce-64467ec3600d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\n[span] Attractions -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.175, 0.119, 0.453, 0.14] in the image\nAnd my action is Action: TYPE\nValue: Aquarium of Paris"
}
]
|
mind2web_2266 | {
"bytes": "",
"path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_bc0cace1-a724-4637-933a-587043f890c6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: mumbai\n[span] Mumbai -> CLICK\n[span] 12 -> CLICK\n[i] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.184, 0.208, 0.808, 0.235] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2267 | {
"bytes": "",
"path": "./images/92cfe78f-0385-4ef6-b829-ae34291e766f_391b3a9a-8396-4709-86c0-7d88ba2b43e7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an LED TV below $1000.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.016, 0.014, 0.05, 0.046] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2268 | {
"bytes": "",
"path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_c507a159-e69a-4a8a-9f3a-64cb387e850e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[select] 1 -> SELECT: 10\n[select] 00 -> SELECT: 00\n[link] Find Schedules -> CLICK\n[link] Edit -> CLICK\n[button] 04/11/2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.604, 0.415, 0.626, 0.431] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2269 | {
"bytes": "",
"path": "./images/af6655c8-0047-4c93-8da2-aeb04ff06b17_232b3998-bdde-46ec-839f-e1ddcd632443.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 climbing courses within 50 miles of 90028.\nPrevious actions:\n[link] Classes & Events -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.221, 0.246, 0.378, 0.272] in the image\nAnd my action is Action: SELECT\nValue: Climbing"
}
]
|
mind2web_2270 | {
"bytes": "",
"path": "./images/969f36c3-52e7-42da-80bd-11a2d04d53ae_d4851253-54fd-4a8e-bfee-8b3e7448733f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Biography of the NFL player named Michael Jordan\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Michael Jordan\n[textbox] Search -> ENTER\n[span] Michael Jordan -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.098, 0.172, 0.126, 0.201] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2271 | {
"bytes": "",
"path": "./images/50bd08bd-989f-44ba-8a99-71e75ba602f1_2add8689-72ac-4b04-b149-3ae7d54b630b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show cheapest monthly price for parking near Shubert Theatre.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Shubert Theatre"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.252, 0.5, 0.748, 0.529] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2272 | {
"bytes": "",
"path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_96b8805f-69fa-420b-823e-29ff28e471f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[button] DEALS -> CLICK\n[link] VACATIONS & RAIL TOURS Train vacation packages thr... -> CLICK\n[img] -> CLICK\n[link] Close -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.62, 0.153, 0.773, 0.174] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2273 | {
"bytes": "",
"path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_5e01100b-9202-4e0d-84f9-a986283066f4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] ADD TO CART -> CLICK\n[button] VIEW CART -> CLICK\n[button] CHECKOUT -> CLICK\n[button] Pick up in store Shipping: Free -> CLICK\n[searchbox] City, State, or ZIP code -> TYPE: 10005"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.602, 0.423, 0.62, 0.445] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2274 | {
"bytes": "",
"path": "./images/db72bae1-ff16-495c-89c7-1cff7c0ae503_2b8a282b-a072-4637-8dc2-bbba1e04c12b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the most popular Spanish recipe book available in paperback that are in stock.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: recipe"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.212, 0.094, 0.745, 0.11] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2275 | {
"bytes": "",
"path": "./images/cc643c1f-e73e-4e9f-abe9-5ee2d3b0a0dd_6e941c23-f01a-484c-bfdb-cbbac7ea4727.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[LabelText] Certified Pre-Owned -> CLICK\n[combobox] Select Make -> SELECT: Lexus"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.364, 0.203, 0.473, 0.235] in the image\nAnd my action is Action: SELECT\nValue: RX"
}
]
|
mind2web_2276 | {
"bytes": "",
"path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_58fa66a3-0966-4b45-bb59-6ae4cbac9f9f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[i] -> CLICK\n[i] -> CLICK\n[button] Go to next month -> CLICK\n[button] 2023-04-05 -> CLICK\n[combobox] Desired reservation time -> SELECT: 5:00 PM"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.703, 0.251, 0.909, 0.289] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2277 | {
"bytes": "",
"path": "./images/51d2bb04-8207-4c21-8bc3-c00d826a5d0c_4bbd596c-f120-4a5f-ad59-c4fa1887b64e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Remove the SSD on my cart\nPrevious actions:\n[link] Shopping Cart -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.631, 0.358, 0.695, 0.374] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2278 | {
"bytes": "",
"path": "./images/a747bed0-0f45-413a-8f48-2c45795e4e3d_a436dc7e-365b-4bc6-ad92-f1444c628f9c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Give a like to the #1 track of the Real Time Top Chart\nPrevious actions:\n[link] Charts -> CLICK\n[gridcell] Like Crazy -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.202, 0.127, 0.233, 0.147] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2279 | {
"bytes": "",
"path": "./images/96e95a76-4a1d-491c-82ff-fac663d89ddb_27521355-59c4-4bab-a47f-d1d98c5617c1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of adventure games under 30 dollars.\nPrevious actions:\n[link] Categories -> CLICK\n[link] Adventure -> CLICK\n[div] Narrow By -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.161, 0.79, 0.294, 0.806] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2280 | {
"bytes": "",
"path": "./images/c55b9949-b785-4d9e-8b20-b626cb595623_281334a6-f548-4381-9965-fdac05c9b599.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events in Phoenix for the next 3 days.\nPrevious actions:\n[button] CITY GUIDES -> HOVER\n[link] Phoenix -> CLICK\n[button] All dates -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.724, 0.345, 0.881, 0.362] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2281 | {
"bytes": "",
"path": "./images/360eeaa8-0077-42f4-8200-1e3cf6414cda_6db2cc83-aa0e-4f3e-91de-71acfed5bdb1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a message to Joe Bloggs who has the username 'boredcelt'.\nPrevious actions:\n[button] Community -> CLICK\n[link] Find Users -> CLICK\n[link] User Search -> CLICK\n[textbox] Enter First name, last name, and/or username: -> TYPE: Joe Bloggs\n[button] Go -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.723, 0.247, 0.736, 0.256] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2282 | {
"bytes": "",
"path": "./images/2fc63250-ac9a-4cd4-a29d-6460f0652fa3_a5e39e4d-8ef5-424e-9370-dc254fdbcb03.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 keyboard and mouse combo under $100.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.282, 0.019, 0.39, 0.06] in the image\nAnd my action is Action: TYPE\nValue: wireless keyboard mouse"
}
]
|
mind2web_2283 | {
"bytes": "",
"path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_ed51f63d-6cab-4ecb-831a-81833977302f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[searchbox] Search -> TYPE: Selena Gomez\n[button] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.372, 0.099, 0.454, 0.107] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2284 | {
"bytes": "",
"path": "./images/562d8516-e1fa-464b-9bb1-542fe818c721_d7379735-b499-442a-ab5b-b0b0d6e6d906.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[combobox] Search Board Games... -> TYPE: king of tokyo\n[link] King of Tokyo -> CLICK\n[button] Sort: Recently Added -> CLICK\n[link] Price (lowest first) -> CLICK\n[button] Add Filter -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.193, 0.198, 0.312, 0.212] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2285 | {
"bytes": "",
"path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_2edb875d-df64-4128-9e2e-c8d147290aff.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[link] Your lists -> CLICK\n[link] Create a list -> CLICK\n[svg] -> CLICK\n[span] Walgreens -> CLICK\n[textbox] Add a title (Required) -> TYPE: Walgreens"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.038, 0.698, 0.142, 0.787] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2286 | {
"bytes": "",
"path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_b564668c-3c8e-4538-9bee-e1e48c71fa99.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[option] Oct 2023 -> CLICK\n[button] Search flights + cruise -> CLICK\n[label] October 08, 2023 -> CLICK\n[span] Nights -> CLICK\n[label] Miami -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.836, 0.381, 0.952, 0.43] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2287 | {
"bytes": "",
"path": "./images/f7b93dc1-2f19-419e-a6e0-a701008c17fa_b3d17b95-f512-463c-8359-a1ed302829ee.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 booking with ticket 123456 under the name James Buck.\nPrevious actions:\n[button] View / Modify / Cancel Reservation -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.166, 0.347, 0.833, 0.387] in the image\nAnd my action is Action: TYPE\nValue: 123456"
}
]
|
mind2web_2288 | {
"bytes": "",
"path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_35217f76-ff90-428e-a78f-72c14b82dc4f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[link] Search for packages -> CLICK\n[link] Hawaii Vacations -> CLICK\n[generic] Departure date input -> CLICK\n[button] Next month -> CLICK\n[gridcell] June 18 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.424, 0.302, 0.448, 0.319] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2289 | {
"bytes": "",
"path": "./images/cf8da12a-e1fd-48b5-8c53-b88f301ca1e0_0db62d4c-e735-47bf-bd3f-f5a51ee7f6fd.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for video game consoles and filter the results to show only those that have Wi-Fi Capability.\nPrevious actions:\n[link] Electronics -> CLICK\n[button] Video Games & Consoles -> CLICK\n[link] Video Game Consoles -> CLICK\n[button] All Filters -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.235, 0.29, 0.393, 0.309] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2290 | {
"bytes": "",
"path": "./images/7bda9645-0b5f-470a-8dd7-6af0bff4da68_961c3a5e-f8ce-4c71-a917-aa546dcea7fb.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.086, 0.302, 0.292, 0.341] in the image\nAnd my action is Action: SELECT\nValue: Pickup"
}
]
|
mind2web_2291 | {
"bytes": "",
"path": "./images/130b1cd5-3e2f-4676-aea4-24ba9706171b_90aba443-6a23-47d7-bd15-ccab225917fc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the on demand sales section and rent a film in HD format.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.521, 0.026, 0.614, 0.062] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2292 | {
"bytes": "",
"path": "./images/ecb649da-0ca7-4707-8ebb-8707296e28b7_40bef6c6-0468-4277-8a65-6b4fd6ef2c5d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights available from Calgary (CYYC) to New York (ZNY).\nPrevious actions:\n[textbox] Origin -> TYPE: Calgary\n[div] Calgary -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.494, 0.363, 0.619, 0.385] in the image\nAnd my action is Action: TYPE\nValue: New York"
}
]
|
mind2web_2293 | {
"bytes": "",
"path": "./images/a5c1095b-bba1-4029-8b8d-fa5848702827_fa625908-78ca-4882-a85e-528a818b3a77.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City from June 5th to 9th.\nPrevious actions:\n[option] New York City City -> CLICK\n[span] Mar 9 -> CLICK\n[i] -> CLICK\n[i] -> CLICK\n[i] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.578, 0.244, 0.607, 0.278] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2294 | {
"bytes": "",
"path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_13275433-ad18-45f4-8742-60e8c549e96f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[checkbox] Ship to Home Eligible (97) -> CLICK\n[checkbox] Stainless Steel (75) -> CLICK\n[checkbox] Equal Bowl (69) -> CLICK\n[checkbox] 19 inch (7) -> CLICK\n[button] Sort By: Best Match -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.795, 0.158, 0.991, 0.179] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2295 | {
"bytes": "",
"path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_d59408ec-1909-4c52-9d24-9d21802048b6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for car rentals in San Francisco for a weekend trip and filter the results by the rental company Avis and car type Economy.\nPrevious actions:\n[tab] Cars -> CLICK\n[textbox] Pick-up -> TYPE: San Francisco"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.069, 0.224, 0.495, 0.255] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2296 | {
"bytes": "",
"path": "./images/70b3ef5b-d900-44cf-9b62-9ecece97954c_91a0d4fe-3524-448a-995f-8c4d570884ec.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 climbing gear and sort the results by price high to low.\nPrevious actions:\n[button] Climb -> CLICK\n[button] Climb -> CLICK\n[link] Explore Climb -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.421, 0.577, 0.579, 0.605] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2297 | {
"bytes": "",
"path": "./images/fc81025d-f5a3-4b68-9551-e84175b87a63_3fac526d-a878-4292-a372-861c97b8d5e1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 video highlights of the most recent Super Bowl.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.506, 0.01, 0.519, 0.016] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2298 | {
"bytes": "",
"path": "./images/d29fd2a4-2305-4276-8a0e-2599291d0a17_0944f5d6-5126-4eeb-a660-bb87994aeb13.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the list of reviews I wrote about my games.\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, 0.074, 0.552, 0.088] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2299 | {
"bytes": "",
"path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_745736e0-20b8-4366-bfa1-c023ed7c78df.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[li] New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.185, 0.328, 0.195, 0.339] 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.