id
stringlengths 10
13
| image
dict | conversations
listlengths 2
2
|
|---|---|---|
mind2web_1500 | {
"bytes": "",
"path": "./images/973bf55c-d1a0-41c7-9ec8-9f59b3dbfb58_ddec100d-f916-4321-ba6a-dceb8f48e51c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Repost on my feed a rock playlist.\nPrevious actions:\n[searchbox] Search -> TYPE: rock"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.541, 0.007, 0.553, 0.014] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1501 | {
"bytes": "",
"path": "./images/9e9d7935-0c16-46e6-9e5c-3ea9124a6bf7_c6b0f017-31fc-4a65-880b-30d19b72e561.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\n[link] Hip-hop & Rap -> CLICK\n[div] Play -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.655, 0.252, 0.675, 0.262] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1502 | {
"bytes": "",
"path": "./images/5d69e640-7765-4381-979c-9881afc048dd_ff85d6b0-e760-47c9-9cbe-0b2c40ea369f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the monthly payment of a 15k car with a down payment of 5k in Michigan for a fair-rated person for a term length of 48 months, then shop with this budget for the cheapest car and add it to the favorites.\nPrevious actions:\n[textbox] Vehicle Price -> TYPE: 15000\n[textbox] Down Payment -> TYPE: 5000\n[combobox] State -> SELECT: Michigan\n[combobox] Credit Score -> SELECT: Fair (580-669 FICO® Score)\n[combobox] Term Length -> SELECT: 48 months"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.548, 0.214, 0.835, 0.235] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1503 | {
"bytes": "",
"path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_74dc5d68-9acc-4106-936e-cba53c2782cf.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.316, 0.004, 0.371, 0.027] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1504 | {
"bytes": "",
"path": "./images/c7058499-3dc9-4175-9142-d22416d25a1f_0aeafd95-fef4-4d22-aaea-cd873ef8fd5c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the best VIP seat to the Red Hot Chili Peppers 2023 Tour\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.514, 0.515, 0.535, 0.526] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1505 | {
"bytes": "",
"path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_3260885d-20b9-4daf-9f4b-1a95e0a6a4d5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[combobox] List -> SELECT: New\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] Explore All -> CLICK\n[link] 3,682,991 Pop -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.188, 0.362, 0.305, 0.43] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1506 | {
"bytes": "",
"path": "./images/2f660153-d470-4744-8b75-f8dc64c7f94e_2da87719-cf27-463c-859e-44538f0428bb.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Games & Puzzles in the Toys category that are suitable for ages 14+\nPrevious actions:\n[link] Categories -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.066, 0.15, 0.316, 0.167] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1507 | {
"bytes": "",
"path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_8031c316-8f33-49ca-85a3-4f274aac7fb9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] Where to? -> TYPE: TOKYO\n[span] -> CLICK\n[div] Multi-city -> CLICK\n[span] Sat 13 May -> CLICK\n[checkbox] 1 June 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.073, 0.148, 0.354, 0.17] in the image\nAnd my action is Action: TYPE\nValue: TOKYO"
}
]
|
mind2web_1508 | {
"bytes": "",
"path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_949e1e48-94d8-4d69-aa74-24e5582011bd.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.578, 0.056, 0.664, 0.069] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1509 | {
"bytes": "",
"path": "./images/b30b9f84-0541-4826-a3af-98220b851f7c_c31b9357-ee70-4f66-974d-647feb53a5da.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's sports wear, size S.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.839, 0.012, 0.858, 0.027] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1510 | {
"bytes": "",
"path": "./images/91f56f3b-e3de-4d57-95df-f976a11c64f7_dbb99d1d-77d3-4826-a887-2bee8e5bf43c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 veterinarian emergency service for dogs in Hawaii with a BBB rating of A+\nPrevious actions:\n[link] Veterinarians -> CLICK\n[input] -> TYPE: hawaii\n[link] Hawaii, HI -> CLICK\n[button] Find -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.07, 0.084, 0.123, 0.098] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1511 | {
"bytes": "",
"path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_3851cdfd-1081-4f86-b05d-6062a054e094.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Samsung-made and larger than 11-inch screen Android tablet, in the price range of 200 to 300 dollars and add it to the cart.\nPrevious actions:\n[span] 8.7\" -> CLICK\n[button] APPLY -> CLICK\n[span] $200 - $300 -> CLICK\n[button] APPLY -> CLICK\n[combobox] Featured Items -> SELECT: Lowest Price"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.248, 0.437, 0.33, 0.45] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1512 | {
"bytes": "",
"path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_ef69e26b-3544-4e04-95cb-b382313130d4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.313, 0.118, 0.321, 0.123] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1513 | {
"bytes": "",
"path": "./images/4777d638-204d-4e44-b81c-2fb43c471fb2_8baa6a27-c421-47ea-9ad4-efeeba6e1815.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most reviewed cocktail bar with outdoor seating for reservation in San Francisco.\nPrevious actions:\n[span] Reservations -> CLICK\n[textbox] Near -> TYPE: SAN FRANCISCO\n[span] San Francisco -> CLICK\n[checkbox] Cocktail Bars -> CLICK\n[checkbox] Outdoor Seating -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.539, 0.119, 0.635, 0.131] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1514 | {
"bytes": "",
"path": "./images/f3bf7fe9-6987-4153-81b4-4b51fe25bbbc_bc2c2145-162c-46a9-8bfd-32e070aa3cb4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental cars in Seattle, WA and filter the results by the Best score.\nPrevious actions:\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Seattle\n[span] Seattle, Washington, United States -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.545, 0.163, 0.702, 0.181] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1515 | {
"bytes": "",
"path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_4b2dcd3a-0b40-469e-845d-e7b4f050d030.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[svg] -> CLICK\n[tab] One-way -> CLICK\n[svg] -> CLICK\n[button] Increment -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.225, 0.133, 0.244, 0.147] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1516 | {
"bytes": "",
"path": "./images/34e13beb-0235-41d4-b108-137cc7480904_38d7f841-8b1f-4c5b-8131-310960d438fe.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[span] Find your state -> CLICK\n[link] New York -> CLICK\n[link] New York -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: 66 perry st\n[span] 66 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.567, 0.096, 0.628, 0.112] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1517 | {
"bytes": "",
"path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_e835b0d2-5db9-498a-81f5-598bb3d144c4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[button] Search -> CLICK\n[span] -> CLICK\n[button] Show all 14 -> CLICK\n[span] -> CLICK\n[button] Show all 25 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.081, 0.339, 0.263, 0.348] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1518 | {
"bytes": "",
"path": "./images/ebae9339-93bf-4f5a-9396-ce30bcec7b49_d834a522-37a2-4ae0-88eb-0d4490a2d956.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 price of Boys' INFANT UA SURGE 3 RUNNING SHOES. black color and 9K size\nPrevious actions:\n[menuitem] Kids -> CLICK\n[div] Product Category -> CLICK\n[link] Shoes -> CLICK\n[div] Color -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.047, 0.31, 0.07, 0.334] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1519 | {
"bytes": "",
"path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_23a4d8ba-846f-4a6b-9d5e-8e9059bbd4be.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.441, 0.431, 0.518, 0.442] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1520 | {
"bytes": "",
"path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_118b28dd-087b-45f4-8490-baa847a291ab.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find premium car in Brooklyn for a day.\nPrevious actions:\n[button] Pick-up -> TYPE: Brooklyn\n[button] Brooklyn New York, United States -> CLICK\n[button] Search -> CLICK\n[input] -> CLICK\n[input] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.888, 0.18, 0.959, 0.209] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1521 | {
"bytes": "",
"path": "./images/240952bd-853b-4653-a358-49c2784cf568_39a3a8d8-dbe1-4949-8d5f-a9097d58c4fc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.328, 0.021, 0.409, 0.045] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1522 | {
"bytes": "",
"path": "./images/e437082b-8383-4322-aa58-a6a683113970_f9b97955-f20c-41ea-83d4-8b3c274cb9f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[searchbox] Type your destination -> TYPE: Las Vegas\n[option] Las Vegas Nevada, United States -> CLICK\n[checkbox] 10 April 2023 -> CLICK\n[gridcell] 16 April 2023 -> CLICK\n[button] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.294, 0.197, 0.44, 0.226] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1523 | {
"bytes": "",
"path": "./images/0790c8be-6e6d-4e2a-9c13-43ac9367da4c_8bcadcd3-882c-4c95-a59f-121cd8e75eba.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the most recent full time Accounting & Finance Job available in Richmond, Virginia.\nPrevious actions:\n[button] Open helpful links menu -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.237, 0.139, 0.384, 0.156] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1524 | {
"bytes": "",
"path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_ffaf6b03-f8a7-4d88-b8b3-e95d8ac0b97a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Matthews winery"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.66, 0.077, 0.987, 0.101] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1525 | {
"bytes": "",
"path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_6c235a86-4748-4b46-bb48-86f39329f0e1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Easter Eggs -> CLICK\n[button] Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Price -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.72, 0.123, 0.838, 0.147] in the image\nAnd my action is Action: TYPE\nValue: 5"
}
]
|
mind2web_1526 | {
"bytes": "",
"path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_3b99d7fa-1730-4fcd-86c1-d5244bc75520.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[button] Sort selector. Best Match selected. -> CLICK\n[button] Listing options selector. List View selected. -> CLICK\n[link] Gallery View -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK\n[link] Price + Shipping: lowest first -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.192, 0.339, 0.4, 0.374] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1527 | {
"bytes": "",
"path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_227dfbfe-6b1f-473c-b87d-101c9dfd7306.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[link] Make a Reservation -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] Next -> CLICK\n[link] 1 -> CLICK\n[link] 2 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.695, 0.145, 0.891, 0.173] in the image\nAnd my action is Action: SELECT\nValue: 11 00 AM"
}
]
|
mind2web_1528 | {
"bytes": "",
"path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_7d5af9ff-4e09-4a12-a7aa-870797c20fcb.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.369, 0.069, 0.582, 0.128] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1529 | {
"bytes": "",
"path": "./images/cd8f1f63-f6c3-4b1b-9ec9-3b13b9f0386c_961171c8-d057-442d-9bd2-68aa64900442.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Read the 1 star reviews of DayQuil Severe Cough Liquicaps.\nPrevious actions:\n[combobox] Search products and services -> TYPE: dayquil\n[button] Submit search -> CLICK\n[div] Vicks DayQuil SEVERE Cough, Cold & Flu Relief, 24 ... -> CLICK\n[img] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.206, 0.567, 0.362, 0.58] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1530 | {
"bytes": "",
"path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_fd4aace9-856c-4933-a18f-8817c81c926b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Franchise -> CLICK\n[checkbox] Resident Evil Resident Evil -> CLICK\n[button] Done -> CLICK\n[heading] Resident Evil 4 - Xbox Series X -> CLICK\n[span] Digital -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.77, 0.159, 0.825, 0.184] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1531 | {
"bytes": "",
"path": "./images/f9723022-04b9-4778-ad33-cf54eac3d393_c8f29a0e-e477-43e2-a3c5-2895cac22164.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events starting from April 1, 2023 within 100 miles of New York and see who are going in the top listed event and follow all of them who are going.\nPrevious actions:\n[link] Events -> CLICK\n[button] Near you -> CLICK\n[textbox] Location search -> TYPE: new york\n[span] New York -> CLICK\n[combobox] SEARCH RADIUS -> SELECT: 100 km"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.396, 0.5, 0.459, 0.528] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1532 | {
"bytes": "",
"path": "./images/930803d7-4032-4144-89a2-e44f3c5c9ccf_29445a41-8ff2-4bff-b2fa-3f892a59bbf3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for a group at Hurricane harbor Phoenix on April 22\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Hurricane Harbor Phoenix -> CLICK\n[button] Go! -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.657, 0.004, 0.761, 0.03] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1533 | {
"bytes": "",
"path": "./images/2e133e56-ac17-41dc-987a-257078d770c3_ac2708fd-5705-4b77-8cf4-684e0e121f2a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on the water activities in Dubai from 5pm to 12am with a maximum duration of four hours\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.271, 0.292, 0.463, 0.302] in the image\nAnd my action is Action: TYPE\nValue: Dubai"
}
]
|
mind2web_1534 | {
"bytes": "",
"path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_0360e768-e23e-4a3f-8e45-956e24c36c5c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[button] Done -> CLICK\n[button] Preferred flight class Economy -> CLICK\n[menuitem] First class -> CLICK\n[button] Departing April 5, 2023 -> CLICK\n[button] May 27, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.929, 0.351, 0.985, 0.369] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1535 | {
"bytes": "",
"path": "./images/e93fe82b-c3ed-4661-92f6-ea0abb1b2b63_5f4a93f4-ae47-4f5c-b7ba-c9ccc2463d53.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 page to find classic rock concert tickets.\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.314, 0.152, 0.517, 0.173] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1536 | {
"bytes": "",
"path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_e672e49c-5049-4b40-b486-40028a26aa99.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: kashi vishwanath temple\n[span] Kashi Vishwanath Temple, Varanasi, Uttar Pradesh, ... -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.538, 0.177, 0.571, 0.195] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1537 | {
"bytes": "",
"path": "./images/da679cfe-9180-49f7-b8a2-a2b1bd6d8803_2ec82da8-e3d5-4d54-a618-84c72889c172.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the artists with smith in their name\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: smith"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.837, 0.029, 0.897, 0.045] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1538 | {
"bytes": "",
"path": "./images/4272e233-3440-4572-bd86-b3a2b22a4061_678dddb3-2699-4a17-9a70-578517f9260f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular tours and attractions in Kyoto, Japan from May 25 with free cancellation option, check availability for 2 adults and 1 infant, and book.\nPrevious actions:\n[div] Kyoto -> CLICK\n[div] Select your dates -> CLICK\n[svg] -> CLICK\n[checkbox] 25 May 2023 -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.093, 0.641, 0.165, 0.655] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1539 | {
"bytes": "",
"path": "./images/7eff6c15-bab6-4ce4-abb8-72619f593ea1_941c96f6-80a7-4f83-bcdd-a4c57106ddc9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.133, 0.17, 0.25, 0.198] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1540 | {
"bytes": "",
"path": "./images/26fff471-7083-46e4-945e-d1b167157a0d_427fc741-820d-4659-b46e-ba46fa397047.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 refund status for John Davis for ticket no. 1234567890123\nPrevious actions:\n[link] Receipts and refunds -> CLICK\n[link] Check the status of a refund -> CLICK\n[textbox] Ticket number -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.105, 0.255, 0.285, 0.301] in the image\nAnd my action is Action: TYPE\nValue: 1234567890123"
}
]
|
mind2web_1541 | {
"bytes": "",
"path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_3e7c0282-8e70-4f28-af2d-3f6c13c55221.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[option] Aruba (AUA) -> CLICK\n[span] 1 -> CLICK\n[button] return Friday, May 5, 2023 -> CLICK\n[span] -> CLICK\n[span] Search flights -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.156, 0.264, 0.223, 0.276] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1542 | {
"bytes": "",
"path": "./images/0ff1648e-28bb-4014-9b8a-3c050c25e334_685cf19d-39cf-483b-9d1d-0b664f121910.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the women's hiking boots section and filter the results to show only those that are waterproof and have a rating of at least 4 stars and size 6.\nPrevious actions:\n[button] Camp & Hike -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.056, 0.331, 0.21, 0.342] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1543 | {
"bytes": "",
"path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_697b485d-dfb7-4825-8e41-6d0fffe55a76.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[li] Smithsonian National Air and Space Museum, Indepen... -> CLICK\n[button] Filter -> CLICK\n[checkbox] EV Charging (1) -> CLICK\n[button] Show 1 Results -> CLICK\n[textbox] Start Date -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.02, 0.446, 0.05, 0.481] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1544 | {
"bytes": "",
"path": "./images/6803cd71-78a9-4bff-a1a3-1153dcc28c11_09dcc085-8dd6-4a59-89f8-c14cb6266555.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 organic dog food and add it to the cart.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.506, 0.037, 0.821, 0.06] in the image\nAnd my action is Action: TYPE\nValue: organic dog food"
}
]
|
mind2web_1545 | {
"bytes": "",
"path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_61d45c64-e415-47a6-b881-54e29f1cdc68.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[span] Vehicle History -> CLICK\n[checkbox] No Accidents (4) -> CLICK\n[combobox] Sort By: -> SELECT: Price - Lowest\n[link] Confirm Availability for Used 2019 Buick Encore Pr... -> CLICK\n[textbox] First Name -> TYPE: James"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.506, 0.085, 0.643, 0.101] in the image\nAnd my action is Action: TYPE\nValue: Smith"
}
]
|
mind2web_1546 | {
"bytes": "",
"path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_4d38e663-23c7-43da-9cf4-3667c1872ff3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking with EV charging for month with lowest price in Chicago.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: Chicago\n[li] Chicago, IL, USA -> CLICK\n[button] Filter -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.323, 0.548, 0.339, 0.567] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1547 | {
"bytes": "",
"path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_ba02b1c4-6cdb-4c43-8f62-e7fbe49c6a90.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[button] Search by location -> CLICK\n[button] Add to cart -> CLICK\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue with this address -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.156, 0.527, 0.455, 0.552] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1548 | {
"bytes": "",
"path": "./images/9e44c63b-2c7a-445c-b9c4-6580f4271268_078ff56d-4223-448a-a76d-bd8b5b747c95.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of a rebate for Monty Lue, house number 4847, zip code 10019\nPrevious actions:\n[link] Track your rebates -> CLICK\n[textbox] * Required Fields First Initial * Required Fields... -> TYPE: Monty\n[textbox] * Required Fields Last Name * Required Fields Las... -> TYPE: Lue\n[textbox] * Required Fields House Number -> TYPE: 4847\n[textbox] * Required Fields ZIP Code * Required Fields Zip -> TYPE: 10019"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.024, 0.424, 0.476, 0.456] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1549 | {
"bytes": "",
"path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_a2193e39-2058-4b6c-bfaa-6395e17662a8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cruises to Hawaii departing from Los Angeles in January 2024 with a duration of 12 days.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Hawaii -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Los Angeles, CA -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.452, 0.201, 0.591, 0.25] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1550 | {
"bytes": "",
"path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_de372882-c37b-4261-a0b7-a234e29456c7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Gift Cards -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.397, 0.314, 0.616, 0.355] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1551 | {
"bytes": "",
"path": "./images/56cfe20a-f008-48d3-b683-002ce7790616_c6dad653-0f55-4f00-83a7-7ac9cffc7316.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.421, 0.124, 0.469, 0.162] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1552 | {
"bytes": "",
"path": "./images/1337eca1-4ca6-4102-964e-e7f6ecebcd0b_c6e1208e-d16a-437b-aa5e-4bce43b335f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\n[tab] Things to do -> CLICK\n[textbox] Things to do in -> TYPE: singapore\n[button] Singapore Singapore -> CLICK\n[button] From April 5, 2023 -> CLICK\n[button] Apr 2, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.393, 0.216, 0.427, 0.238] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1553 | {
"bytes": "",
"path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_bda37da7-1fef-4ff8-9174-51730582abd0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[textbox] From -> TYPE: New York"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.148, 0.271, 0.434, 0.295] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1554 | {
"bytes": "",
"path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_c8ff6366-a117-4e3d-8a22-0c74ccf24360.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK\n[button] Listing options selector. List View selected. -> CLICK\n[link] Gallery View -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.599, 0.182, 0.774, 0.201] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1555 | {
"bytes": "",
"path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_55888df7-c6b9-4ab0-8f38-d6970f7a3025.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] APPLY -> CLICK\n[link] GIGABYTE B450M DS3H WIFI AM4 AMD B450 SATA 6Gb/s M... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.307, 0.359, 0.441, 0.381] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1556 | {
"bytes": "",
"path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_a5cac325-2527-4236-9fb6-6ecbfbd52c58.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.494, 0.302, 0.514, 0.313] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1557 | {
"bytes": "",
"path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_191f5324-8b5a-4b2d-aecd-47c7c053d9e5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: washington\n[span] Washington County Regional Apo -> CLICK\n[link] Make a Reservation -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] Next -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.804, 0.267, 0.831, 0.284] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1558 | {
"bytes": "",
"path": "./images/2ef75333-ca40-454f-a65c-88b6b60e2497_103a605a-1392-4f31-bc96-5a2f561540da.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: book a tour to the statue of liberty for 3 adult on march 27th\nPrevious actions:\n[link] tours. -> CLICK\n[li] Boat Tours -> CLICK\n[div] Show Info -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.719, 0.077, 0.894, 0.098] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1559 | {
"bytes": "",
"path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_1741ce47-1b26-41c1-9827-b8393e3dfab3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harrt Reid Intl Airport, LAS\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[generic] Close -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.504, 0.198, 0.691, 0.228] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1560 | {
"bytes": "",
"path": "./images/bb02400d-e9da-416a-839a-0068f511a630_48468ad4-f291-419b-9089-9ca9d1ffd9da.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get WWE tickets for April 10 event happening in seattle, and book 4 cheapest lower level tickets.\nPrevious actions:\n[link] TICKETS -> CLICK\n[p] Any Quantity -> CLICK\n[label] 4 -> CLICK\n[span] -> CLICK\n[div] Lower -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.922, 0.232, 0.982, 0.255] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1561 | {
"bytes": "",
"path": "./images/33964bc4-fc1d-417c-ba5a-2c1c45ed8d8b_33c00f88-b578-4fac-9e0c-a9a0520fc6f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the most expensive things to do anywhere in December in a map\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.098, 0.06, 0.492, 0.086] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1562 | {
"bytes": "",
"path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_ffc28c0e-9243-45a9-9470-4669e5a310e0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[button] Locations -> CLICK\n[link] United States Car Rental Locations -> CLICK\n[searchbox] Location (required) * Required Field -> TYPE: 02199\n[span] 02199 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.682, 0.167, 0.788, 0.188] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1563 | {
"bytes": "",
"path": "./images/d4298ee7-ac1d-4cac-bfa6-62bf7cd67004_3e652678-e0e8-49b3-9954-f5076aa0631e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 camping hammocks with lowest price first.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[button] Camp & Hike -> CLICK\n[link] Hammocks -> CLICK\n[link] Camping Hammocks (21) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.247, 0.248, 0.428, 0.27] in the image\nAnd my action is Action: SELECT\nValue: Price Low - High"
}
]
|
mind2web_1564 | {
"bytes": "",
"path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_29373ca9-75bb-449f-9f36-2cd26f44674b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[button] 03/29/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 1:00 PM\n[button] Browse Vehicles -> CLICK\n[checkbox] SUVs -> CLICK\n[checkbox] 2+ -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.834, 0.369, 0.914, 0.406] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1565 | {
"bytes": "",
"path": "./images/277a776a-b335-4761-a543-bed1c6eca1d6_b29cd238-ad53-4b4d-b6cc-8a139d724bf3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for kayaks and filter the results to show only those that are suitable for whitewater rapids.\nPrevious actions:\n[searchbox] Search -> CLICK\n[searchbox] Search -> TYPE: Kayaks"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.294, 0.099, 0.668, 0.132] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1566 | {
"bytes": "",
"path": "./images/d7ab9bf0-99e2-4f32-92c9-c1a10bc68f82_c0e76686-4c8a-44e1-8982-6cb008ef9a29.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Manchester City Performance Stats of 2022/2023 season in the champions league\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.36, 0.034, 0.407, 0.057] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1567 | {
"bytes": "",
"path": "./images/c82bd6d6-6f08-4f1d-aeef-351c86694bbc_19e8ffd0-e981-4b9e-8eac-a752dabc1b72.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest movies for rent in the Redbox kiosk at any Winn Dixie in Daytona Beach.\nPrevious actions:\n[button] Navigate to Find a kiosk nearby -> CLICK\n[textbox] City or ZIP Code -> TYPE: Daytona\n[button] select to search for a kiosk using city or zipcode -> CLICK\n[button] select to browse a kiosk -> CLICK\n[button] Show Filters -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.047, 0.226, 0.105, 0.247] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1568 | {
"bytes": "",
"path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_18adac7f-bb79-4f9d-85b4-e4ec43f9775c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: BWI\n[button] Baltimore, MD, US (BWI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: NYC\n[button] New York, NY, US (NYC - All Airports) -> CLICK\n[textbox] Depart -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.548, 0.552, 0.571, 0.579] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1569 | {
"bytes": "",
"path": "./images/14b5885e-5454-465f-92bf-d8f7315c4a46_7ad31fb5-8326-41d3-b6d1-d7de45193fc1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[span] Abbotsford, WI -> CLICK\n[textbox] Enter a town, city or zipcode -> TYPE: Sheboygan\n[span] Sheboygan, WI -> CLICK\n[button] Search -> CLICK\n[input] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.006, 0.524, 0.037, 0.574] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1570 | {
"bytes": "",
"path": "./images/55518089-52b9-4504-8e4f-885a9b2943a8_07860790-53f1-4130-90cc-6a68c134f319.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a list of comedy movies, sorted by user ratings.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.069, 0.009, 0.144, 0.033] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1571 | {
"bytes": "",
"path": "./images/18a581b9-5021-40aa-835d-3c8110402df3_2c3caf3a-dd47-45ad-9bb0-4b63ea700dfe.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find adventure movies coming to theaters.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.548, 0.193, 0.587, 0.203] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1572 | {
"bytes": "",
"path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_dd2c3bba-7534-49fa-9567-2db678f5486e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: trash can automatic lid\n[option] automatic trash can lid -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.09, 0.479, 0.147, 0.501] in the image\nAnd my action is Action: TYPE\nValue: 60"
}
]
|
mind2web_1573 | {
"bytes": "",
"path": "./images/31df4f0d-8852-4694-b6cf-5f337bd26d39_ebc2b67a-b88f-4ff5-8a9a-3b93c778a404.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking 1234567890 booked by Jason Smith\nPrevious actions:\n[tab] My Trips -> CLICK\n[textbox] booking reference -> TYPE: 1234567890"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.353, 0.244, 0.647, 0.271] in the image\nAnd my action is Action: TYPE\nValue: Smith"
}
]
|
mind2web_1574 | {
"bytes": "",
"path": "./images/eeeee9d8-5387-46bc-a741-5bcb66b46f31_f66238f2-ef35-41ed-bd5a-61140b435c0b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[menuitem] olink -> CLICK\n[link] See Open Roles -> CLICK\n[textbox] Select Department -> CLICK\n[option] Sales & Ad Ops -> CLICK\n[textbox] Locations -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.026, 0.279, 0.25, 0.303] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1575 | {
"bytes": "",
"path": "./images/d86d5cc1-50f7-4bfd-8e5b-60db84e87956_2471b465-ed09-45d5-9c2b-ecf0efc16f91.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade-in value for Call of Duty: Black Ops III for Xbox One.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: trade in\n[button] Search -> CLICK\n[p] Video Games -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.009, 0.255, 0.932, 0.298] in the image\nAnd my action is Action: TYPE\nValue: Black Ops"
}
]
|
mind2web_1576 | {
"bytes": "",
"path": "./images/27724810-0bc8-446a-a2f4-b53a87e190df_32f9fa3a-cc74-4d29-8347-ec82ea2f97f8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 location and operating hours of the nearest CVS pharmacy to zip code 90028\nPrevious actions:\n[button] change store -> CLICK\n[textbox] Search by Zip Code, City, State, or Landmark -> TYPE: 90028"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.598, 0.177, 0.637, 0.198] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1577 | {
"bytes": "",
"path": "./images/4f75897b-8df4-4f4c-88c3-72d440f6a4ee_cd059490-19cd-4a25-9017-ecd728b2b58c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[button] Plan -> CLICK\n[link] Try Somewhere New -> CLICK\n[link] Destinations -> CLICK\n[label] Armenia -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.076, 0.218, 0.086, 0.226] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1578 | {
"bytes": "",
"path": "./images/33964bc4-fc1d-417c-ba5a-2c1c45ed8d8b_cceccde0-e4da-420c-a4c0-3dc9ef3191a8.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the most expensive things to do anywhere in December in a map\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Things To Do -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.503, 0.203, 0.89, 0.22] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1579 | {
"bytes": "",
"path": "./images/5418beec-bc06-4e11-9664-4038fbdeefe9_587cf410-7484-4014-a232-ebe323189d47.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: BATMAN\n[span] BATMAN -> CLICK\n[link] Filter -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.042, 0.119, 0.139, 0.133] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1580 | {
"bytes": "",
"path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_b6b56f9c-77f1-40ed-bfef-d708917927c4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: calculate a car loan payment for a $25000 car with a $5000 down payment and 12 percent interest rate for 48 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.055, 0.225, 0.473, 0.256] in the image\nAnd my action is Action: TYPE\nValue: 25000"
}
]
|
mind2web_1581 | {
"bytes": "",
"path": "./images/4770e887-f523-4609-a989-ded8c8abad19_61dfd7e4-d733-4b03-a0bd-a80a9821c4a0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round trip economy flight from Pune to New York in June and select the fully refundable.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: Pune\n[button] Pune, IN (PNQ) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.298, 0.217, 0.481, 0.246] in the image\nAnd my action is Action: TYPE\nValue: New York"
}
]
|
mind2web_1582 | {
"bytes": "",
"path": "./images/1d738d01-507e-46ff-8d4d-d4a7dffed936_0bf9dab8-18e1-471d-a458-72708badf771.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 weekly chart-topper artist and play the number 1 track of that artist after liking the track.\nPrevious actions:\n[link] Charts -> CLICK\n[link] Weekly -> CLICK\n[link] The Weeknd -> CLICK\n[button] Love this track -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.079, 0.29, 0.104, 0.304] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1583 | {
"bytes": "",
"path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_30b98e40-d57a-4744-bfdb-660a9dfef288.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[div] Portland -> CLICK\n[span] Pick a date... -> CLICK\n[button] 15 -> CLICK\n[button] 16 -> CLICK\n[div] Petaluma Music Festival -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.706, 0.151, 0.95, 0.171] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1584 | {
"bytes": "",
"path": "./images/29f47ddb-3d25-4cfb-b1d6-d3987e998a13_8c16969c-e931-4482-9e62-dc9ac32fe338.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movie \"65\" that is digital at the AMC Grove City 14 showing at 7:30 pm on Tuesday, March 28, 2023 and buy four tickets for seats J10 through J7\nPrevious actions:\n[select] AMC Grove City 14 -> SELECT: AMC Grove City 14\n[select] All Movies -> SELECT: 65"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.295, 0.049, 0.455, 0.097] in the image\nAnd my action is Action: SELECT\nValue: Tue, Mar 28"
}
]
|
mind2web_1585 | {
"bytes": "",
"path": "./images/8a6f2641-9896-4657-b447-56927420e8c4_7581d740-729b-401a-9625-340b89af3dfc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[generic] Refine by Category: Nintendo Switch -> CLICK\n[checkbox] Everyone Everyone -> CLICK\n[button] Genre -> CLICK\n[checkbox] Educational Educational -> CLICK\n[button] Done -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.152, 0.366, 0.245, 0.381] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1586 | {
"bytes": "",
"path": "./images/14b5885e-5454-465f-92bf-d8f7315c4a46_197af70a-27ca-4bb0-bbfd-8374dcbca041.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Route map -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.078, 0.219, 0.389, 0.25] in the image\nAnd my action is Action: TYPE\nValue: Abbotsford"
}
]
|
mind2web_1587 | {
"bytes": "",
"path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_2ac7ed26-b119-4a0a-bcdb-a83f63b211f2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NAPA VALLEY\n[span] Napa Valley -> CLICK\n[combobox] Reservation type -> SELECT: Wineries\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.547, 0.578, 0.566, 0.597] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1588 | {
"bytes": "",
"path": "./images/01dcf2f1-0b80-4819-a4d1-5063062d1aa5_ea5b4be4-62c9-4afd-8e22-69ce9b7b0102.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Romantic Audio fiction books with the 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 [0.038, 0.559, 0.196, 0.584] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1589 | {
"bytes": "",
"path": "./images/3bb1c925-71ef-4713-a139-a3be65f8a7a5_bfa33329-4c33-4284-bdd5-ffae4b862d8e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.533, 0.387, 0.577, 0.405] in the image\nAnd my action is Action: SELECT\nValue: 1995"
}
]
|
mind2web_1590 | {
"bytes": "",
"path": "./images/91e18ec8-5eae-4b14-a49e-9ed7ee1ebb10_a6f4f6b6-0ea3-435f-95bb-55fd74917bad.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of playstation 5 games available for pre-orders.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.009, 0.055, 0.036, 0.08] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1591 | {
"bytes": "",
"path": "./images/60e1de47-efdb-47e8-935f-2ac38af1ead3_4d44da5c-7602-419f-a8d1-e48ccbe0ccb7.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Prometheus movie to watchlist.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.189, 0.009, 0.613, 0.031] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1592 | {
"bytes": "",
"path": "./images/928ec908-ea23-42a4-8b13-3ca6f0721ead_1287a730-f1cc-4046-9b54-e1aa12b6d33f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter search results for guitar tabs to only show songs with a difficulty rating of \"Beginner\"\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.142, 0.062, 0.176, 0.078] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1593 | {
"bytes": "",
"path": "./images/5f2c3149-1820-4632-bfdb-3cf4615de2cc_f1699e8f-d02e-4667-92f0-13061818f3c6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.28, 0.005, 0.651, 0.024] in the image\nAnd my action is Action: TYPE\nValue: dog food"
}
]
|
mind2web_1594 | {
"bytes": "",
"path": "./images/2d4b44c7-d11a-41c1-8be7-af4ae80b7a8c_8a8aa71c-c8b4-4fb8-85d8-c47a3787306b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 near 11231 zip code.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.782, 0.069, 0.882, 0.083] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1595 | {
"bytes": "",
"path": "./images/c7b0d1bc-2a0c-4060-92dd-cd4b8721b625_7fd7c256-6857-49f5-bd5a-c761fb99587b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 KOA near Lansing, Michigan for June 7, 2023 to June 12, 2023.\nPrevious actions:\n[list] KOA Logo Icon Auburn Hills / Holly KOA Holly, MI K... -> CLICK\n[textbox] CHECK IN -> CLICK\n[link] Next -> CLICK\n[link] Next -> CLICK\n[link] 7 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.548, 0.126, 0.659, 0.145] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1596 | {
"bytes": "",
"path": "./images/03103341-f9d3-40a8-8435-f7946dd707b3_ed48cb9a-ee51-4e80-9a71-bdd03240fef1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 budget price for the vehicle with most seats availible at Roanoke Regional Airport from April 5-6.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Roanoke\n[span] Roanoke Regional Airport -> CLICK\n[button] Select My Car -> CLICK\n[link] Price (Low to High) -> CLICK\n[div] Sort by: -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.29, 0.206, 0.493, 0.221] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1597 | {
"bytes": "",
"path": "./images/725c38e7-7987-40b3-8f19-8450f8277f06_43f973b3-95d3-440f-8ecd-60b4b10a1d46.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 event to attend in Athens, Greece on April 2nd\nPrevious actions:\n[button] Athens -> CLICK\n[button] Go! -> CLICK\n[div] Sort by -> CLICK\n[div] Lowest price -> CLICK\n[div] All dates -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.584, 0.185, 0.616, 0.194] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1598 | {
"bytes": "",
"path": "./images/33964bc4-fc1d-417c-ba5a-2c1c45ed8d8b_b655d9a9-a403-46c8-8b35-5686ceb8c895.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the most expensive things to do anywhere in December in a map\nPrevious actions:\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] December -> CLICK\n[button] Filter -> CLICK\n[button] $ Price: High to Low -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.708, 0.343, 0.772, 0.361] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_1599 | {
"bytes": "",
"path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_9754a5ea-7a5e-4822-8c16-3049b3ec50ce.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a black blazer for men with L size and add to wishlist.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: blazer\n[span] blazer -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.23, 0.243, 0.328, 0.256] 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.