Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/61d28a34-cc8e-46a9-b41d-c95933de2214_21f4dc7e-c394-4957-8985-4f8889128c41.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all time popular drop c rock tab of beginner difficulty\nPrevious actions:\n[link] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.214, 0.153, 0.227] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_f5d1ec4a-c8d9-4910-9f1e-577da891b353.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my parking space in Houston. Name: James Smith, Email: [email protected], phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[link] Rent My Parking Space -> CLICK\n[textbox] First Name * -> TYPE: James\n[textbox] Last Name * -> TYPE: Smith\n[textbox] Email * -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.539, 0.787, 0.581] in the image\nAnd my action is Action: TYPE\nValue: 8888888888" } ]

{ "bytes": "", "path": "./images/3e50b35f-7af9-4835-a741-158c2d941722_62891d67-0dd1-4e76-86cf-cb8ae1c0e520.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\n[div] hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.082, 0.713, 0.093] in the image\nAnd my action is Action: TYPE\nValue: Athens, Attica, Greeece" } ]

{ "bytes": "", "path": "./images/ca049641-9721-4593-95c5-a47e22365b5b_8c84c4cf-69a8-4598-aae3-828c35e95aa6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 electric car with highest ev mile range per charge, see the details of the top result.\nPrevious actions:\n[link] Cars for Sale -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.027, 0.673, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fb04bb83-9ad5-4186-a0da-17af9ba2a63d_e8f30da3-c814-4d47-8040-6e285a960ae4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers for VIFP Club loyalty number 9016467685 and show the ones that are for members only.\nPrevious actions:\n[button] Manage -> HOVER\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.611, 0.755, 0.625] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ae969e05-d10e-4255-99f7-c27e071fad69_3e7af91f-3368-46f6-9c85-0c5de6736fa6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 standings for the English Premier League.\nPrevious actions:\n[div] … -> CLICK\n[link] Soccer . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.103, 0.391, 0.113] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2f8b054-59b5-4fd8-bd58-9f95b29f979d_7e4e90e4-e0f9-4262-878b-221a78155dee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[textbox] ZIP Code -> TYPE: 07055\n[combobox] Distance -> SELECT: 100 Miles\n[combobox] Minimum Year -> SELECT: 2018\n[combobox] Maximum Year -> SELECT: 2018\n[button] Make  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.872, 0.277, 0.883] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a831fb6-3110-4ffb-8687-1d2acab09873_677f0c0a-d900-4ca9-8c5e-73fd4036a379.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a park that has a campground and is located in the state of Colorado.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[link] Search by Activity or Topic -> CLICK\n[combobox] By State -> SELECT: Colorado" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.164, 0.641, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_c35de92f-4b70-42f2-827e-95ba59506320.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[textbox] Enter ZIP or State -> TYPE: 07470\n[button] set store -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Nationwide -> CLICK\n[menuitem] 100 miles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.202, 0.317, 0.255, 0.338] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c497534c-76a5-4ffb-af9a-10ee7afcc784_9ae02909-fe47-4383-8a72-7194c0f533cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[heading] CAR -> CLICK\n[label] Book with miles -> CLICK\n[LabelText] Enter pick up city, airport name, or airport code. -> TYPE: caldwell\n[div] Caldwell -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.654, 0.158, 0.679] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fd460cc-679c-4d04-8816-c6460bdf895a_6ad45996-e569-422b-8e82-f5d261f319d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Confirm my vip tour at the six flags Discovery Kingdom\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.369, 0.783, 0.402] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_fbca318e-9c4e-417a-9f36-e39c77345c0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[searchbox] Find a location -> TYPE: NAPA VALLEY\n[span] Napa Valley -> CLICK\n[combobox] Reservation type -> SELECT: Wineries\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.528, 0.354, 0.573, 0.373] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/21e5c264-df85-4055-a566-ecb65cdd8c63_8acab6b2-6b28-45c9-84b2-0c56d4964684.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Alfred\n[span] Alfred, NY -> CLICK\n[textbox] Pick a date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.163, 0.781, 0.194, 0.848] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e5c228ff-7834-46d2-b906-dcea21a0c477_62479223-7350-45b8-a272-43a71a83db44.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 subway station nearest to 07055\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.383, 0.61, 0.867, 0.751] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_de99fc69-4313-49d0-9740-e0fabd61bc14.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.214, 0.843, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e50b35f-7af9-4835-a741-158c2d941722_a09ec185-740a-4090-85e2-0bb866a277d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\n[div] , Greece -> CLICK\n[div] Choose date -> CLICK\n[generic] 1 -> CLICK\n[div] Choose date -> CLICK\n[generic] 3 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.191, 0.953, 0.24] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7eff6c15-bab6-4ce4-abb8-72619f593ea1_c8297402-4dc8-4983-9ec1-6ee82f468ab6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track my bus with service number SE4.\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK\n[tab] Service Number -> CLICK\n[combobox] Search by Service Number -> TYPE: SE4\n[span] Columbia, SC -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.212, 0.98, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1a1f767-8611-4539-9c08-475011d38e12_3703e141-87f5-412d-9675-2eaf6c10dbea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest news about Mikal Bridges\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.931, 0.06, 0.966, 0.1] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f738b393-9234-4c07-8baf-20f05627d5ed_c45c6c0c-d446-41da-99c0-cc44abed21eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[radio] Lawns or greenscapes -> CLICK\n[button] Fast-responding -> CLICK\n[button] Recommended -> CLICK\n[span] Most Reviewed -> CLICK\n[button] Verified License -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.287, 0.626, 0.302] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/66a5b212-cf94-4917-8015-58970dc54187_1a954a07-0ffd-4322-a31d-b66f330025eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 amtrak national route map\nPrevious actions:\n[button] DESTINATIONS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.554, 0.122, 0.922, 0.134] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_d4bf4941-facb-40a5-844f-31f00302fd71.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[textbox] From -> CLICK\n[button] Ireland -> CLICK\n[span] Dublin -> CLICK\n[button] France -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.164, 0.715, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/85706225-aa42-43c1-8cfa-8696118698a2_a5c25f8f-2e98-4c30-bbdc-a56abaee49bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of flights from Los Angeles area to Boston area tomorrow\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.491, 0.026, 0.578, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_afe07d47-565f-4f9c-be14-366c5a45b1c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[heading] Color -> CLICK\n[span] BLACK -> CLICK\n[svg] -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.463, 0.51, 0.482, 0.522] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/33964bc4-fc1d-417c-ba5a-2c1c45ed8d8b_96597d17-6899-4300-8c45-7ae8387e89dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[tab] Select a Month -> CLICK\n[li] December -> CLICK\n[button] Filter -> CLICK\n[button] $ Price: High to Low -> CLICK\n[button] DONE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.114, 0.195, 0.128] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00e83fae-f2f0-48ab-912c-32c03982642b_dfbd7cb5-d7b8-4500-b831-e7be9b8494eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 computer game reviews sorted by score.\nPrevious actions:\n[button] Reviews -> CLICK\n[link] Game Reviews -> CLICK\n[combobox] Platform -> SELECT: PC" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.178, 0.291, 0.202] in the image\nAnd my action is Action: SELECT\nValue: Sort by Score" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_5b8da6f5-c53c-4b69-bfad-7bdfd2e6ce20.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: laguardia airport\n[span] LaGuardia Airport -> CLICK\n[button] Find a Location -> CLICK\n[link] 1 Laguardia Airport (LGA)  -> CLICK\n[combobox] Pick Up Time -> SELECT: midnight" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.136, 0.5, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56d210ec-22eb-4b3f-ba76-ee531403701a_f52cc040-3159-499d-8b13-ea4613b23b63.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[button] Meetings & Events -> CLICK\n[link] Book An Event Book a Meeting or Event -> CLICK\n[textbox] Destination -> TYPE: Boston" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.245, 0.335, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e5c228ff-7834-46d2-b906-dcea21a0c477_52e1bc08-aa96-46ba-aa6d-d0191b7a51a2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 subway station nearest to 07055\nPrevious actions:\n[span] Nearby Stations & Stops -> CLICK\n[searchbox] Address, station, landmark -> CLICK\n[searchbox] Address, station, landmark -> TYPE: 07055" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.134, 0.235, 0.366, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_b060d99c-865a-4016-b147-d497c82a20db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.077, 0.203, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5e5f14-c875-4cfd-a517-175619491b90_bea83466-1716-4e8b-81aa-7df1c9d2586d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[link] NFL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.09, 0.206, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_8676f7b9-73e2-4bf3-b8e6-d38576f3f87f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.065, 0.441, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_02680f4d-0ad2-4cac-b260-f95bda93cf34.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: addis ababa\n[strong] Addis Ababa -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: accra\n[strong] Accra -> CLICK\n[option] One way -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.745, 0.252, 0.795, 0.282] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3358dffd-3673-435b-bfcb-cb242a2c622c_1b86bf52-d450-49a1-b6e9-54aac49ff1cd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round-trip bus tickets from Houston to Dallas leaving on May 7th and returning a week later.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.151, 0.312, 0.165] in the image\nAnd my action is Action: TYPE\nValue: Houston" } ]

{ "bytes": "", "path": "./images/160fc162-7f03-4f59-83e1-5502d00806f2_edb1d676-2d90-478f-a19b-c083f267b082.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See what is playing on Showtime sorted by newest.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.614, 0.126, 0.668, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/373dec75-7278-4d12-bcc3-0e802e337c4a_096ee7c8-8209-4457-9239-6737dd54c324.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Tree stands with at least 3 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 [0.062, 0.135, 0.104, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_043449b3-6d42-43f7-844d-b5855db096f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[checkbox] 25 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.333, 0.263, 0.342] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_5e5cfcd1-5a2e-4b97-9a6c-60e242291757.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[searchbox] From -> TYPE: brooklyn\n[listitem] Brooklyn, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.313, 0.359, 0.343] in the image\nAnd my action is Action: TYPE\nValue: staten island" } ]

{ "bytes": "", "path": "./images/26fff471-7083-46e4-945e-d1b167157a0d_411cc346-144b-4861-ba9e-c9395f8f0598.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Ticket number -> TYPE: 1234567890123\n[textbox] First name -> CLICK\n[textbox] First name -> TYPE: John\n[textbox] Last name -> CLICK\n[textbox] Last name -> TYPE: Davis" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.715, 0.417, 0.895, 0.467] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_1ce7ca32-49ee-4274-abe9-5294b2487601.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.005, 0.561, 0.023] in the image\nAnd my action is Action: TYPE\nValue: Selena Gomez" } ]

{ "bytes": "", "path": "./images/6a326478-2a1b-4e47-b298-53f3ac12ed51_e46c7544-0dea-4eee-8a35-8253034883a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the page with information about luggage and what to bring.\nPrevious actions:\n[button] Plan -> HOVER\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.202, 0.262, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78915162-53c9-4cb1-86e1-6be6047528e0_e1f6fdb8-4efe-45dc-90d8-624bdd5a4e2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 out if Coldplay is playing any events in Columbus, OH on May 17.\nPrevious actions:\n[textbox] Search by team, artist, event or venue -> TYPE: Coldplay\n[paragraph] Coldplay -> CLICK\n[button] Filter by Date -> CLICK\n[button] Next month -> CLICK\n[div] 17 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.357, 0.645, 0.377] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_41227868-8f44-46fc-9ee1-31604f7f4dbb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[textbox] Last name -> TYPE: Bloggs\n[button] Continue -> CLICK\n[button] Continue -> CLICK\n[button] Okay, got it. -> CLICK\n[img] undefined -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.784, 0.423, 0.953, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_c523456c-2910-4d24-a99f-3ca35aa410c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[div] Premium -> CLICK\n[svg] -> CLICK\n[span] -> CLICK\n[path] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.254, 0.331, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b70e49b-2759-4276-ad4f-471e405544b9_c2d31bb2-2ab9-4d3f-b785-17fddb4b85f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all conductor trainee job openings in Amtrak New York and apply to the latest job.\nPrevious actions:\n[textbox] Search by Keyword -> TYPE: Conductor\n[textbox] Search by Location -> TYPE: New Yok\n[button] To make this website accessible to screen reader, ... -> CLICK\n[button] To make this website accessible to screen reader, ... -> CLICK\n[link] To make this website accessible to screen reader, ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.777, 0.241, 0.879, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_e2bca4e2-c8ba-4505-bb4a-2c11560be18b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[textbox] Depart (date format mm/dd/yyyy) -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 9 -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 19 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.43, 0.875, 0.468] in the image\nAnd my action is Action: SELECT\nValue: First" } ]

{ "bytes": "", "path": "./images/66d12284-5525-42d2-a66f-fe5c460b7764_184d3ce5-9bab-402e-bf38-9d7a0072c5ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order popcorn at AMC Grove City 14\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.421, 0.026, 0.524, 0.06] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42f64db7-c573-4ba8-9cab-a390e2f5e535_951b37fc-526a-4203-93fe-e65dfab59126.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight from Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] From Departure Airport or City Your Origin -> TYPE: Mumbai\n[link] BOM Mumbai, India -> CLICK\n[link] To Destination Airport or City Your Destination -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.255, 0.103, 0.515, 0.125] in the image\nAnd my action is Action: TYPE\nValue: New York City" } ]

{ "bytes": "", "path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_8aabcd7c-a3ec-4ba4-83c7-c61f37de5cea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[button] Antiques -> CLICK\n[link] Furniture -> CLICK\n[link] Chairs -> CLICK\n[button] Sort: Best Match -> CLICK\n[link] Time: newly listed -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.63, 0.17, 0.713, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5098c679-dacc-4abd-9331-18b898f936dd_ec93c9c4-0c2e-4576-84b5-0f558804edc3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the St louis park policies regarding security?\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags St. Louis -> CLICK\n[button] Go! -> CLICK\n[link] Plan Your Visit  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.749, 0.245, 0.894, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_507874fe-1115-4387-ae3a-678440621c58.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.071, 0.327, 0.095] in the image\nAnd my action is Action: TYPE\nValue: london" } ]

{ "bytes": "", "path": "./images/581da9fe-4d75-42a7-b138-9b287a153575_5382b192-80ec-4d29-8cfe-cea3aa9af99b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pair of mens running shoes in black, size 7 extra wide, 4+ stars and under $50 and add them to my cart\nPrevious actions:\n[textbox] Search Amazon -> TYPE: mens black running shoes\n[button] Go -> CLICK\n[region] 4 Stars & Up -> CLICK\n[link] Under Armour Men's Charged Assert 9 Running Shoe -> CLICK\n[button] 7 X-Wide -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.729, 0.483, 0.869, 0.502] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efe9051b-d626-443c-b8c8-e7844a0acd29_4c53006a-8253-499c-9e1f-0abe87119311.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular tracks from the rock band Nirvana.\nPrevious actions:\n[searchbox] Search -> TYPE: Nirvana" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.308, 0.02, 0.567, 0.037] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_91b89cbd-5da5-4edf-a302-06a3338116a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: colombo\n[strong] Colombo -> CLICK\n[textbox] To 2180 results are available, use up and down arr... -> TYPE: new york\n[strong] New York -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.803, 0.445, 0.851, 0.469] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_e4ab6d47-920a-4d58-98a1-6ae5bf1c6cab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[link] Hostels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.274, 0.41, 0.304] in the image\nAnd my action is Action: TYPE\nValue: udupi" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_850cc85e-d691-4b91-ac4c-1212d64d2b5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[span] -> CLICK\n[button] Country -> CLICK\n[span] -> CLICK\n[button] State / Province -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.268, 0.245, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_516114e2-6390-41c7-b809-44aea3dfef43.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Nike -> CLICK\n[button] US Shoe Size -> CLICK\n[link] 9 -> CLICK\n[button] Condition -> CLICK\n[link] Pre-owned -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.212, 0.923, 0.235] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_67a25df3-31cd-4a0c-88ca-4468b63ad958.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[link] hotels. -> CLICK\n[textbox] Check In  -> CLICK\n[link] 24 -> CLICK\n[textbox] Sun Mar 26  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.314, 0.259, 0.343, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/373dec75-7278-4d12-bcc3-0e802e337c4a_dc54e8cf-9e8b-4094-a90c-2230a4eedbff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Tree stands with at least 3 stars, and sort the results by price from low to high.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Climbing Stands -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.444, 0.087, 0.455] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0633c328-f1ad-42bd-8aec-7a1883b5898d_c9c98fc1-8b2b-42ba-a708-893695e385df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 luxury trip deal anywhere to go in spring\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Luxury Trips -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.104, 0.89, 0.12] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b30b9f84-0541-4826-a3af-98220b851f7c_712639b1-118b-4f73-b96f-cd5b48c06cb3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: sports wear\n[svg] -> CLICK\n[heading] Gender > Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.142, 0.471, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f208b8b-6d5c-4d3f-8df0-cab24d29edda_50018063-9417-46ac-a1ed-269e8302453d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Last of Us series and add it to my watch list.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: The Last of Us\n[link] The Last of Us The Last of Us 2023 Pedro Pascal, B... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.701, 0.228, 0.942, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_98a9cc6a-d5a0-4500-938f-546404bb57f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.01, 0.509, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_eb8c0d47-b9b8-4622-a93d-57b975949833.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[menuitem] Research -> HOVER\n[menuitem] Price Trends -> CLICK\n[span] -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.113, 0.16, 0.126] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2281faf9-ff02-42e3-b785-8bcc3a0e530a_cdff5762-b4b7-4a22-955e-f8148168d909.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 up information on the potential side effects of rogaine.\nPrevious actions:\n[combobox] Search products and services -> TYPE: rogaine" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.286, 0.33, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7003092-3e6e-4fac-9867-083cac064f89_075e3102-01a5-4d21-a14a-22ffb129f1b0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 JetBlue career openings in New York\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.134, 0.56, 0.183, 0.589] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c497534c-76a5-4ffb-af9a-10ee7afcc784_2ba8d331-eb38-47cf-a09d-60885c37a401.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.611, 0.294, 0.624] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e3cc9e2-baf7-449f-bf61-919eb773f29c_a43bbcfe-96dc-4222-ac22-4f2afc78bc28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Travel Pack for hiking.\nPrevious actions:\n[button] Travel -> CLICK\n[link] Travel Backpacks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.051, 0.45, 0.11, 0.459] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/21e5c264-df85-4055-a566-ecb65cdd8c63_f60f9f16-8348-47e1-b2ad-67b88dd5fac7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Alfred\n[span] Alfred, NY -> CLICK\n[textbox] Pick a date -> CLICK\n[gridcell] March 31, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.197, 0.312, 0.217] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42657330-bfc5-425d-ae21-396a9ba1fb12_4fdd3302-d141-439e-a0a2-9a01d9249890.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[link] WOMEN -> CLICK\n[RootWebArea] Women's, Men's & Kids' Clothing & Accessories | UN... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.094, 0.623, 0.114] in the image\nAnd my action is Action: TYPE\nValue: women t-shirts" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_45d41999-3dfb-4c9d-ba3b-cac736ee5256.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.255, 0.568, 0.291] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_0262cd12-5355-4602-be83-a0e4fc8e5196.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.662, 0.373, 0.688, 0.386] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d7a29cf-7e66-4660-9b26-4eeba7c3f158_34f7ec94-d726-48df-b6da-a798f9bc8325.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 children's program events in Illinois.\nPrevious actions:\n[link] Events -> CLICK\n[button] All -> CLICK\n[input] -> CLICK\n[button] All -> CLICK\n[label] Children’s Program -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.234, 0.161, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_a007f0aa-95eb-4604-96a1-fe8c2dfbd07c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] 7 -> CLICK\n[button] Select My Car -> CLICK\n[generic] Close -> CLICK\n[button] Select My Car -> CLICK\n[generic] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.023, 0.535, 0.034] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_c3bca17f-7481-4506-a7fd-bded60c14834.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: belo horizonte" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.175, 0.104, 0.438, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_c7f7cff6-1d18-48c2-8a61-dc14b5b44b96.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Fashion -> HOVER\n[link] Men's Shoes -> CLICK\n[link] Nike -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.392, 0.465, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29f639c1-20da-46a6-b9c5-bbec77ac3c03_93aa5675-083a-42ed-9c3f-a25176a028ec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open community discussions for Dota 2 game and open latest topic.\nPrevious actions:\n[link] COMMUNITY -> HOVER\n[link] DISCUSSIONS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.194, 0.325, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03e45ce0-4375-44aa-b57f-cf439ccbe363_08c9c18f-c5f0-460c-ba3d-a1e51201ddf5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest news article and send an email about it.\nPrevious actions:\n[link] Jets signing former Packers QB Boyle to 1-year dea... -> CLICK\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.743, 0.268, 0.768, 0.286] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/11344944-81ef-4fde-82b7-7e9724fc96f1_9078fd3a-f526-43ca-8756-187c5f59b43f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of discussion forums for games I own.\nPrevious actions:\n[link] COMMUNITY -> HOVER\n[link] DISCUSSIONS -> CLICK\n[link] Game Forums -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.231, 0.189, 0.443, 0.204] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/76514d5c-cc1c-40b0-8c08-427cedb106e4_4fc26c69-ac92-4f10-b4ac-36bdbe42d9af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 queen-size pillow protectors from the Marriot shop, and if found, add two pieces to the cart and checkout.\nPrevious actions:\n[button] Special Offers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.149, 0.487, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_f932237e-6a41-40a9-8df8-38ab876cc6b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Napa Valley -> CLICK\n[combobox] Reservation type -> SELECT: Wineries\n[svg] -> CLICK\n[svg] -> CLICK\n[button] 15 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.275, 0.724, 0.334] in the image\nAnd my action is Action: SELECT\nValue: 10 00 AM" } ]

{ "bytes": "", "path": "./images/b467797c-5fab-4ee6-9b1f-ac6dc50c05cf_fec13c43-55d5-4c4d-9059-7137018069eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[link]  Computer Peripherals  -> CLICK\n[link] Printer Ink & Toner  -> CLICK\n[link] Xerox Toner -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.428, 0.158, 0.442] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_c19e76a4-4664-435b-ba46-9aa4971e02db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.376, 0.044, 0.468, 0.067] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3bc6528-5fd5-45ac-81aa-7fafde757022_cd20ad0a-0250-46b7-93aa-2bcd1837d9f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.025, 0.652, 0.044] in the image\nAnd my action is Action: TYPE\nValue: laptop" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_bfc2aafb-1493-4af0-8bd9-8680ffbec320.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[tab] Flights -> CLICK\n[button] Leaving from -> TYPE: Los Angeles, CA\n[button] Los Angeles (LAX - Los Angeles Intl.) California, ... -> CLICK\n[button] Going to -> TYPE: Miami, FL\n[textbox] Going to -> TYPE: Miami, FL" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.261, 0.652, 0.304] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c175fe34-143b-4a87-a462-e8e9d69d0b95_b7ea921e-9106-4ffa-8427-c196f77649fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check flight status from London to New York City for next day.\nPrevious actions:\n[link] Flight status -> CLICK\n[textbox] From , required. -> TYPE: London" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.132, 0.385, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_9a38f090-86ba-4472-b089-7737200bcfaf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[div] Add -> CLICK\n[button] View Cart. Items in cart: 5 -> CLICK\n[button] View Cart. Items in cart: 5 -> CLICK\n[div] Go to checkout -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.23, 0.606, 0.273] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_4749e515-087a-47b2-a652-3a8342d174a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[label] Weekend -> CLICK\n[div] May -> CLICK\n[span] -> CLICK\n[span] Filters -> CLICK\n[textbox] max price $ -> TYPE: 100" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.139, 0.495, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29f47ddb-3d25-4cfb-b1d6-d3987e998a13_cdfc251d-d069-4874-9855-405b68bd27ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[select] Sun, Mar 26 -> SELECT: Tue, Mar 28\n[link] 7:30pm -> CLICK\n[text] J10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.82, 0.591, 0.889] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_4fdb839d-8ee9-406c-bd79-3ae4d764b752.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[span] Mumbai -> CLICK\n[span] 12 -> CLICK\n[i] -> CLICK\n[i] -> CLICK\n[span] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.456, 0.198, 0.574, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/76514d5c-cc1c-40b0-8c08-427cedb106e4_08747f7d-7119-4877-821b-f4fc61f180d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 queen-size pillow protectors from the Marriot shop, and if found, add two pieces to the cart and checkout.\nPrevious actions:\n[button] Special Offers -> CLICK\n[link] Shop Marriott Opens a new window -> CLICK\n[menuitem] category pillows -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.667, 0.251, 1.0, 0.442] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44ad28c9-c0d6-4d41-a49d-afeaa6ecaabe_ed7860e2-f5ac-45ce-9b5f-6eedf85b7cd1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way bus ticket between Albany, NY and Bloomington, NY April 10th and add the second one to cart.\nPrevious actions:\n[div] Albany, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Bloomington, NY\n[span] Bloomington, NY -> CLICK\n[textbox] Pick a date -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.716, 0.069, 0.769] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f122e4c9-7634-4193-94f9-8623cd75d1f1_78a07e5a-688d-4a24-9bde-901d62e64a5c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets from Manchester Piccadilly to any station in London on April 8, leaving nearest 10 AM for 1 adult\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.076, 0.327, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d7c3103a-c195-4503-ab20-ecae4d4ce419_bf283bf2-f76d-42be-b04d-3dcf4f25f1ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 motorcycle toll fee for the Queens midtown tunnel.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.0, 0.597, 0.035] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58badcfc-343a-47c1-8aec-f609925eb4ed_d2244643-d85f-47f6-a9c3-8db219104141.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ricky Kej track to listen and share which has been added in the last year and is between 2 to 10 minutes.\nPrevious actions:\n[searchbox] Search -> TYPE: Ricky Kej\n[link] Search for “Ricky Kej” -> CLICK\n[link] Tracks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.261, 0.212, 0.281] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8c5ccffa-b88e-4928-9394-6d46cfd36e59_2d6cc8ed-6f0c-4311-a5aa-860a52c8452e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are today's Limited Time Offers deals?\nPrevious actions:\n[link] Coupons & Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.465, 0.096, 0.476] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b56d5b8-1f41-43ca-9f21-369d849f1aa0_00aa52ec-0e86-450f-b72e-2dc795817cac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 season pass prices for Hurricane HarborLos Angeles.\nPrevious actions:\n[span] Hurricane Harbor Los Angeles -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.047, 0.434, 0.056] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5a181549-c79c-499c-b7d7-90860f0e0068_a2f3a3c8-b17a-48c3-9762-f1311a93667c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play Trailer of \"The Flash\" 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.173, 0.156, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ea8737b0-0ff4-4476-b97d-5677d4f526dc_ef71de36-8d22-4f74-a4db-9ef1d45fd9fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\n[link] Home Services -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.145, 0.474, 0.176] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fb04bb83-9ad5-4186-a0da-17af9ba2a63d_1bdbfb19-e149-4494-8c81-823066198ce4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers for VIFP Club loyalty number 9016467685 and show the ones that are for members only.\nPrevious actions:\n[button] Manage -> HOVER\n[use] -> CLICK\n[link] Visit our cruise deals page to view your offers -> CLICK\n[button] Show My Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.128, 0.445, 0.323, 0.455] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_0d5b7f9f-9236-43f6-a551-ef4633323303.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[i] -> CLICK\n[button] Buy Tickets -> CLICK\n[button] April 30, 2023 -> CLICK\n[button] Buy Now -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.047, 0.777, 0.063] in the image\nAnd my action is Action: CLICK" } ]