Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_abe9b06e-30c5-4200-a4da-afbd766799c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[li] May -> CLICK\n[combobox] How many guests? -> SELECT: 1 Guest\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Pet-Friendly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.435, 0.296, 0.502, 0.311] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_cde21781-bb33-4185-a6ab-f03a12216547.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[img] james9091 -> CLICK\n[link] Playlists -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.49, 0.373, 0.588, 0.402] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_994e0184-cc07-44d1-b721-977f549fd4a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.357, 0.125, 0.418, 0.163] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_608512bb-519f-407a-a619-1eeffcb9d896.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[label] Lowest price -> CLICK\n[button] Back to all categories -> CLICK\n[button] Fuel Type -> CLICK\n[listitem] Gas (45) Gas (45) -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.268, 0.253, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_602e1f0b-b86e-4f60-8c92-40b3aece1274.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: Smithsonian\n[li] Smithsonian National Air and Space Museum, Indepen... -> CLICK\n[button] Filter -> CLICK\n[checkbox] EV Charging (1) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.697, 0.452, 0.734] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_572f791d-97d7-4e35-adf9-34762045fb72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[svg] -> CLICK\n[link] Luxury Car Rental -> CLICK\n[label] Pick-up location -> TYPE: north las vegas\n[div] North Las Vegas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.444, 0.116, 0.548, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_5be16eae-be60-40bd-ab2c-acfab3a0cd36.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[svg] -> CLICK\n[checkbox] 15 June 2023 -> CLICK\n[checkbox] 20 June 2023 -> CLICK\n[span] 2 adults -> CLICK\n[button] - -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.827, 0.213, 0.927, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8634bbc0-7bcd-4c88-ad0f-5c73c3f69e53_78bfd4cf-87db-44f9-9bc0-a390988df75b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Join the waitlist for a ticket for the Hackney Clothes Swap - Earth Day event being held on April 22nd. Name: Joe Bloggs. Email: joe@bloggs.com\nPrevious actions:\n[combobox] autocomplete -> TYPE: Hackney\n[div] London, UK -> CLICK\n[textbox] Search events -> TYPE: Hackney Clothes Swap - Earth Day\n[div] Hackney Clothes Swap - Earth Day -> CLICK\n[button] Get tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.268, 0.573, 0.297] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6678924a-0a3d-4c8b-ac35-3ba0aceea4d5_40298f0b-61e7-46f8-bb2e-5c1acb88b464.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Golden State Warriors Player List.\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Golden State Warriors" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.065, 0.931, 0.086] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b2c18588-b115-4937-b69f-8feeab22c387_1d9aa0c2-db0a-47b1-9e38-267bea54a66c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the list of movies \"at home\", sorted by most recent.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.176, 0.587, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_db6d2722-20ac-437d-ba01-65b4408ee420.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest return tickets from Leeds to Sheffield leaving at 8:30 am on Mar 25, 2023 and returning at 23:00 pm on same day for 1 adult and 2 child.\nPrevious actions:\n[link] 25 -> CLICK\n[listbox] hour -> SELECT: 23\n[svg] -> CLICK\n[listbox] select children -> SELECT: 2\n[listbox] select child age -> SELECT: 5-15" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.494, 0.391, 0.523] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_3565c84e-3f3a-4a37-9d8c-1bfcae9e432f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[combobox] Departure station, none selected. Select a station... -> TYPE: london" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.065, 0.326, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddee9314-5a29-4258-b11b-b6432ec719f1_05ffdddd-205e-48b4-9f8a-65ff0ac005ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all free virtual business start-up events happening tomorrow in Las Vegas and follow the organizer with most followers.\nPrevious actions:\n[combobox] autocomplete -> TYPE: LAS VEGAS\n[div] Las Vegas -> CLICK\n[svg] -> CLICK\n[div] Tomorrow -> CLICK\n[p] Startups & Small Business -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.127, 0.476, 0.26, 0.551] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b02e47ac-c1a6-4f5c-886f-f32af745e7f3_9f90d836-c2d6-473c-9f78-705033f9ec52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a reservation made under the last name Walker in Australia for a car using the reservation confirmation number A987654.\nPrevious actions:\n[link] close dialog -> CLICK\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK\n[combobox] Select Residency -> SELECT: AUSTRALIA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.305, 0.347, 0.557, 0.387] in the image\nAnd my action is Action: TYPE\nValue: Walker" } ]

{ "bytes": "", "path": "./images/b307117b-e10c-470f-a85d-968b2e442b19_cc41d893-f1d0-4303-b3a7-b19fc73f05a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coffee shop with wi-fi.\nPrevious actions:\n[textbox] Find -> TYPE: coffee shop\n[span] Coffee Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.259, 0.162, 0.363, 0.178] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e15efa0-f646-4dc4-9ce0-2e3d155c788b_8e68485f-08ab-473e-9845-e5fb8af0833b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mover in Honolulu to shift a vehicle and large appliances out of state and who has virtual discussion options available.\nPrevious actions:\n[link] Home Services -> HOVER\n[span] Movers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.018, 0.564, 0.029] in the image\nAnd my action is Action: TYPE\nValue: HONOLULU" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_56e1e554-8541-4c1a-a4bb-d8ad1f7b95cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SUV in Brooklyn for 1 day.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.167, 0.573, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13a676be-2f4f-4abf-83fb-4ab641793801_a7e54311-1339-4fde-a1b9-2571f6f85d29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of Administrative and Clerical jobs MTA is currently recruiting for in Brooklyn\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.912, 0.353, 0.921] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_99c101a0-07d4-433d-86f7-9d16d464c14b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[button] 11:30 -> CLICK\n[button] 11:00 -> CLICK\n[button] Let's go -> CLICK\n[link] Large cars 5 Seats 3 Large bags -> CLICK\n[ins] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.16, 0.771, 0.34, 0.802] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/701bc7ed-4b55-4fd2-b333-128e55c0a4c2_637682df-5b80-4530-a3eb-e242bef29336.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[button] Discover -> CLICK\n[link] Upcoming Games -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.412, 0.13, 0.565, 0.152] in the image\nAnd my action is Action: SELECT\nValue: PS5" } ]

{ "bytes": "", "path": "./images/a3edc9c7-397d-478b-a0b9-0ffa0897acca_2dfa3c40-55c0-42ec-b141-50b68a77b02a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 person named John Smith in New York.\nPrevious actions:\n[link] Find People -> CLICK\n[input] -> TYPE: John\n[input] -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.56, 0.223, 0.688, 0.241] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_290eda81-bc60-42d8-95be-e11a2a5de824.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find trade in value for PS4 console\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Consoles -> CLICK\n[searchbox] Find values for games and more -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.141, 0.932, 0.165] in the image\nAnd my action is Action: TYPE\nValue: PS4" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_011c68d2-620f-46fc-a2cd-48650f992b99.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[link] Trade in by mail -> CLICK\n[combobox] search input -> TYPE: Nemo Front Porch 2P Tent\n[img] search icon -> CLICK\n[button] Trade in -> CLICK\n[link] Complete trade-in -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.751, 0.514, 0.977, 0.556] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_8066875c-cbad-453f-8371-11f45293f19b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Chennai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.116, 0.573, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_b2e83bac-a21a-425c-a069-086f2dca47e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Select My Car -> CLICK\n[generic] Close -> CLICK\n[button] Reservations -> CLICK\n[link] Make a Reservation -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.46, 0.245, 0.477] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_91d99a7d-e270-4d8e-ac84-4df6ee2ab313.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[span] Exterior Color -> CLICK\n[div] -> CLICK\n[checkbox] Online Paperwork (4) -> CLICK\n[span] Vehicle History -> CLICK\n[checkbox] No Accidents (4) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.775, 0.257, 0.888, 0.294] in the image\nAnd my action is Action: SELECT\nValue: Price - Lowest" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_7de0d4fb-357b-420e-997e-df792f9099ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[svg] -> CLICK\n[label] 32\" -> CLICK\n[svg] -> CLICK\n[label] Less than $100 -> CLICK\n[span] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.507, 0.981, 0.534] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81b6bba7-3d05-40a4-a475-48eaeacbda0d_aa99e548-cd12-4d60-876a-1b739f2c9009.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.655, 0.114, 0.866, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1df0723c-f732-4ecb-b202-8e1854b7c079_819a213b-c14d-4a2b-92d9-438c0755d8da.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of rental vehicles for Brooklyn, OH, US for 18 year old renter.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.187, 0.84, 0.21] in the image\nAnd my action is Action: TYPE\nValue: Brooklyn" } ]

{ "bytes": "", "path": "./images/2c19d467-4e44-4c0d-b050-a13823ca545d_6468eb70-ab1c-4fce-9744-5fe7bfea7cde.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hard side Carry-on Luggage used for business in black color.\nPrevious actions:\n[span] Luggage -> CLICK\n[span] Carry-on Luggage -> CLICK\n[img] -> CLICK\n[svg] -> CLICK\n[button] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.099, 0.777, 0.112] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/34e13beb-0235-41d4-b108-137cc7480904_a991029f-599d-41f2-ad44-8fdc236dbc68.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[span] 01:30PM -> CLICK\n[link] 05:30PM -> CLICK\n[span] Apr 20 -> CLICK\n[gridcell] 21 -> CLICK\n[span] 07:30PM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.813, 0.435, 0.937, 0.462] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_c49c8db3-a45d-4c32-97bc-8a71c035485e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[svg] -> CLICK\n[heading] Supima® Cotton V-Neck Short-Sleeve T-Shirt (2022 E... -> CLICK\n[checkbox] L -> CLICK\n[button] ADD TO CART -> CLICK\n[button] VIEW CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.446, 0.959, 0.469] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f2258a-07c3-46ed-a974-01543606b31b_3dc9bc1a-201e-4f46-beb8-69950bc0d565.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 deals for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\n[textbox] Input departure airport -> TYPE: New York\n[textbox] Input arrival airport -> TYPE: Honolulu\n[option] Honolulu, HI, US (HNL) -> CLICK\n[textbox] Budget. Please enter a numerical value -> TYPE: 1300\n[div] Economy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.491, 0.94, 0.509] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_4ebb9e93-734c-4664-9f53-e5562feb80e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Cannes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.682, 0.493, 0.705, 0.507] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_adf9d11d-07e4-4751-8d2e-3cd3ce8f311d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] - -> CLICK\n[div] Mr -> CLICK\n[textbox] First name -> TYPE: Joe\n[textbox] Last name -> TYPE: Bloggs\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.846, 0.26, 0.934, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b431888-9909-40b5-8351-be52905e4d5a_bb8869c7-6b6f-4878-852b-40a52c258f7f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Real Madrid team schedule of the UEFA Champions League championship.\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Real Madrid\n[link] Real Madrid LaLiga -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.11, 0.093, 0.135] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/883fc533-d267-4eeb-8ccd-fe77bc28cd9b_be1bb8af-ec73-4160-82af-3279a45e05de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Discover Katy Perry and add bookmark to it and view all tracks.\nPrevious actions:\n[textbox] Search -> TYPE: Katy Perry\n[button] Search -> CLICK\n[a] -> CLICK\n[button] BOOKMARK -> CLICK\n[button] OKAY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.564, 0.67, 0.645, 0.679] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_4ea0b732-6a9c-4d03-8da2-9045ecc460b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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, james.john@gmail.com. It is a family trip organized by Johnson.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.317, 0.093, 0.493, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90557510-32dc-415f-8507-41b050594962_0f456a6f-04d4-4bc3-beb1-b377715f08b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coming soon AMC Artisan Films\nPrevious actions:\n[link] Visit the See A Movie page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.209, 0.912, 0.223] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_3e01a8bb-5799-45c2-b0c9-83891b43492b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.328, 0.333, 0.354, 0.351] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1e46885-62b3-42ae-837a-474b1541348a_5d2eec92-a8c9-436b-a89a-ed85f6174d4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking passes for New York Yankees game on April 14\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> CLICK\n[textbox] Search for artists, teams or venues... -> TYPE: New york yankees\n[option] New York Yankees -> CLICK\n[link] TICKETS -> CLICK\n[div] More Options -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.751, 0.188, 0.761, 0.199] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_7e7b3cd5-ee9e-4a9c-aee6-96220607e196.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[span] 22 -> CLICK\n[button] 03/25/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM\n[button] Browse Vehicles -> CLICK\n[combobox] SORT BY -> SELECT: Price: Low to High" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.209, 0.914, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d76a0fc-7ba9-4a74-ac52-db0cea359553_dc038372-b9b4-4b34-9eb0-10f048962d43.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced round trip flight with hotel on May 2 from Kathmandu, Nepal KTM to Shanghai, China PVG and return on May 5. Book a double room and check out with the default flights.\nPrevious actions:\n[link] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: KATHMANDU" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.13, 0.448, 0.157] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1538e37b-9c33-48b0-b10e-662e192ad53a_455a4731-6e47-4746-9c56-df4a0cc128eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bus stops in Alanson, MI\nPrevious actions:\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.062, 0.436, 0.108] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_62c7af18-1fb9-4022-a9ec-a69d457cf223.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[combobox] From -> TYPE: brain\n[link] T red line bus commuter rail Zone 2 Braintree -> CLICK\n[combobox] To  -> TYPE: boston\n[span] Boston -> CLICK\n[button] Get trip suggestions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.25, 0.352, 0.29] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_91b03325-cd3b-4a7f-b0dd-7a308e18b42b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find comedy tv shows on netflix sorted by audience score.\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[img] netflix -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.165, 0.317, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c91b907-39db-49c3-af73-5eb5c2390a93_643210af-4c59-4a5f-af43-ebfed3c9b5e5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Modesto California and set is as my store.\nPrevious actions:\n[link] Find a store -> CLICK\n[searchbox] Search carmax locations. -> TYPE: california\n[button] Search. -> CLICK\n[div] Modesto -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.109, 0.465, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0db002f6-db7d-4382-9c0d-8f5cef2afa17_22107c45-e852-4ec8-9e35-2609a62c2bbd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 detailed uses of Anuall Pass for 2023 on the USGS Online\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Passes -> CLICK\n[link] Annual Pass -> CLICK\n[button] Overview of the Annual Pass -> CLICK\n[button] Annual Pass Internet Order Questions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.463, 0.95, 0.486] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_f320b86a-6600-4949-8b57-4df2b3f9b664.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] -> CLICK\n[tab] Fastest -> CLICK\n[button] See flight -> CLICK\n[button] Select -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.668, 0.617, 0.712] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_960ebc24-1a13-4086-afd4-fd6e30b783fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[checkbox] PINK -> CLICK\n[checkbox] XXL -> CLICK\n[input] -> CLICK\n[option] 2 -> CLICK\n[button] ADD TO CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.38, 0.491, 0.401] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b079ace-b202-4d78-a9b0-4cde39e58934_f2b7effa-1ee4-4c0d-a8c6-c086818a5542.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vehicle at New York JFK International Airport May 2-May 5 for an owner above 25 years.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: New York JFK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.362, 0.526, 0.397] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a7eaba3-f6ec-4eba-9e04-ff974b228ef4_580a4333-fdc6-4c07-aa20-748b8b6c9ffb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select an event from the 2019 UFC schedule and show me the full profile from one of the athletes\nPrevious actions:\n[link] MMA -> HOVER\n[link] Schedule/Results -> CLICK\n[select] 2023 -> SELECT: 2019\n[select] All -> SELECT: UFC" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.409, 0.299, 0.419] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_068af6bd-86ad-4e0b-8449-467e35cd186b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request a refund for the traveler Ian Lo and, his document number is 12345678912345 and email ian.lo@gmail.com\nPrevious actions:\n[button] Add trip -> CLICK\n[textbox] Last Name* -> TYPE: Lo\n[textbox] Confirmation or ticket number* -> TYPE: 12345678912345\n[button] Add flight -> CLICK\n[textbox] Email address * -> TYPE: ian.lo@gmail.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.492, 0.189, 0.519] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/998e55fb-66d7-443f-bb73-9cb6a2bc26a8_60fa0498-f3bd-4aec-b81c-d4bc4ee53e24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BMW i3 for 10001 zip code with lowest price.\nPrevious actions:\n[menuitem] Buy -> CLICK\n[combobox] Select Make -> SELECT: BMW" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.012, 0.256, 0.324, 0.277] in the image\nAnd my action is Action: SELECT\nValue: i3" } ]

{ "bytes": "", "path": "./images/408cc1bd-0a76-4bad-b5f4-11db4405047f_ad4e03b0-1b4d-4943-b2d9-94ab2b408563.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Boston Logan Airport to North Station.\nPrevious actions:\n[tab] Trip Planner -> CLICK\n[combobox] From -> TYPE: Boston Logan Airport" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.188, 0.252, 0.464, 0.29] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_b69043a4-7684-42c4-b359-62bb1badccce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[checkbox] Show rates with taxes and all fees -> CLICK\n[checkbox] Show available hotels only -> CLICK\n[link] Free breakfast (18) -> CLICK\n[link] Pool (18) -> CLICK\n[generic] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.499, 0.325, 0.611, 0.337] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_b4e1ca8e-3b28-4edf-ad6a-992c4ed20441.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[div] Availability -> CLICK\n[checkbox] In Stock In Stock -> CLICK\n[button] Done -> CLICK\n[button] Best Matches -> CLICK\n[link] Price Low To High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.449, 0.177, 0.479] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db53ba89-9cff-441a-a703-053e89e32961_da1da5de-72e9-43ca-93c7-7638f6b66736.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\n[path] -> CLICK\n[span] Browse Movies by Genre -> CLICK\n[link] Superhero -> CLICK\n[checkbox] Superhero Sci Fi (745) -> CLICK\n[checkbox] Based On Comic Book (226) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.237, 0.313, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cc81f50-465c-4d77-8fd7-d81fe1ffde84_f04f3bd9-068a-491b-a24c-c356de9dfcc5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.608, 0.217, 0.652, 0.232] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/73960473-941b-4e09-8eb1-f059b85c2dba_b88c0362-1340-41c4-be55-38cf7e7c180d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.348, 0.28, 0.387] in the image\nAnd my action is Action: TYPE\nValue: Chicago" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_e65a5c29-d512-478a-99f5-ff82dcc22246.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Rock -> CLICK\n[img] David Bowie -> CLICK\n[link] David Bowie -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.122, 0.77, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/77be98ff-e4db-4745-9b87-6ce69754c4c2_5b2e46d2-a778-4bd0-9ba5-fbd526c7c17e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest wheelchair accessible parking for the Pittsburgh Pirates at St. Louis Cardinals event in Busch Stadium on Apr 13.\nPrevious actions:\n[li] Busch Stadium, Clark Avenue, St. Louis, MO, USA -> CLICK\n[p] Pittsburgh Pirates at St. Louis Cardinals -> CLICK\n[button] Filter -> CLICK\n[checkbox] Wheelchair Accessible (10) -> CLICK\n[button] Show 10 Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.404, 0.397, 0.417] in the image\nAnd my action is Action: SELECT\nValue: Sort by Price" } ]

{ "bytes": "", "path": "./images/bd4b77db-00a5-405f-bf0a-a4d168967d64_c649a304-2019-4ff6-9bab-817b700a4e2d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Panini Diamond Kings Baseball cards set below $25.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.098, 0.646, 0.133] in the image\nAnd my action is Action: TYPE\nValue: Panini Diamonds Kings Baseball cards" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_e07fd3ab-03a2-4115-baef-7334d62c7687.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[div] -> CLICK\n[button] 1, Saturday, April 2023. Available. Select as chec... -> CLICK\n[button] 8, Saturday, April 2023. Available. Select as chec... -> CLICK\n[span] -> CLICK\n[span] Castles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.898, 0.046, 0.97, 0.069] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_405b8bdc-3279-4507-8ed8-b6102b66252e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[span] Pick a date... -> CLICK\n[button] 15 -> CLICK\n[button] 16 -> CLICK\n[div] Petaluma Music Festival -> CLICK\n[button] Get tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.51, 0.149, 0.573, 0.169] in the image\nAnd my action is Action: SELECT\nValue: 2" } ]

{ "bytes": "", "path": "./images/b7082615-e6e1-4981-b51b-9259671d1adf_74dcfb10-d052-4f30-b65c-a2a06d3bb983.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Change your store to the one nearest to 07055\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.74, 0.015, 0.891, 0.046] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3a231c03-d038-4b61-b5a2-685b77d9920e_ef0e466a-4175-4c3c-80fb-9471d37a9103.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the bag charges for the passenger James Son for the flight with the confirmation number 10000002\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Baggage info -> CLICK\n[link] Baggage fee calculator -> CLICK\n[tab] My flights -> CLICK\n[textbox] Confirmation number (required) -> TYPE: 10000002" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.27, 0.471, 0.446, 0.498] in the image\nAnd my action is Action: TYPE\nValue: Son" } ]

{ "bytes": "", "path": "./images/701bc7ed-4b55-4fd2-b333-128e55c0a4c2_a36b8ff4-cf58-4fa8-9f5c-e3246e288c83.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[button] Discover -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.087, 0.216, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/604c4377-e24c-4900-a72f-346d8999d443_341e6e6d-828b-40a6-acfd-90e47191518d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a deal which is highly rated in Fiji location.\nPrevious actions:\n[textbox] Where? -> TYPE: Fiji" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.164, 0.89, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112459f9-10ea-44b5-affa-79008c2977e7_fc7ce1dd-bf86-4110-95b6-073aa3e5b082.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse check in with confirmation number 123456 for John.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.278, 0.082, 0.389, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eb609e15-ff10-4b3d-82ce-348c439548ca_0dffc638-04bd-4d82-87de-2094b4767d4e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Girls -> CLICK\n[link] Jackets -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.267, 0.233, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_8deea034-568e-4813-992f-b74bdf900906.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Build Your Own Custom PC Build Your Own Cu... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.272, 0.406, 0.395] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_84bf94c3-3a36-4743-a629-a73720bfa17f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[button] Check-in March 18, 2023 -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Jul 2, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.952, 0.206, 0.994, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_585cb70c-a451-4298-add8-b19c4b26f1c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[textbox] Destination -> TYPE: Venice Beach\n[menuitem] Venice Beach, Los Angeles, CA, USA -> CLICK\n[textbox] Event space -> TYPE: 100\n[textbox] Start Date -> CLICK\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.61, 0.161, 0.648, 0.176] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e133e56-ac17-41dc-987a-257078d770c3_e0ca183e-3787-4b09-87f3-b7b9079d4b6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find on the water activities in Dubai from 5pm to 12am with a maximum duration of four hours\nPrevious actions:\n[textbox] Where to? -> TYPE: Dubai\n[button] Dubai United Arab Emirates -> CLICK\n[path] -> CLICK\n[button] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.12, 0.103, 0.129] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1a1f767-8611-4539-9c08-475011d38e12_f720be0a-2053-4046-94b6-7ce03c2d5f6d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Mikal Bridges" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.174, 0.931, 0.207] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f2f531ff-94d5-4320-8594-7ae5d3a52af5_2861d75f-d51e-42a9-bf74-e1e0fc01fda6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top 50 Movies and TV shows by Sci fi genre.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.003, 0.031, 0.02] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/708cbe51-b493-41da-afa8-648564133972_b1b1da1b-a169-4ae8-8540-090e1735abfc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.259, 0.264, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_1f0b8000-4fe1-4b1f-8034-8f8e4023440d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] 1 Laguardia Airport (LGA)  -> CLICK\n[combobox] Pick Up Time -> SELECT: midnight\n[textbox] Enter your pick-up location or zip code -> CLICK\n[combobox] Return Time -> SELECT: noon\n[textbox] Return to same location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.351, 0.567, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/759a1b1b-bb1f-4981-aef4-02a319f8dbaa_34e4693d-d86b-4536-ba7c-274c55c63850.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the profile page for author of latest shot\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.176, 0.061, 0.222, 0.077] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/581da9fe-4d75-42a7-b138-9b287a153575_b4e28822-72ba-426d-820b-e5984992fff9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.255, 0.219, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_d5a67096-558b-4e6c-be09-957a0e4ae20e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[textbox] Mileage -> TYPE: 40000\n[button] Go -> CLICK\n[div] XLE Sedan 4D -> CLICK\n[button] Next -> CLICK\n[div] Select Your Options -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.564, 0.208, 0.575] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_b756f03a-d366-4b47-a6f4-5acb671698b4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\n[button] Submit price range -> CLICK\n[input] -> CLICK\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK\n[link] Price + Shipping: lowest first -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.316, 0.027, 0.329] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04ec089f-2ae1-4fa9-bfdf-4dff9ab710ad_9f957e9c-cf83-4dc3-8223-a5da537ceafc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 highest rated white water rafting experience available in Montana from May 1 to May 7\nPrevious actions:\n[textbox] Where to? -> TYPE: Montana\n[button] Montana USA -> CLICK\n[button] Next -> CLICK\n[gridcell] Mon May 01 2023 -> CLICK\n[gridcell] Sun May 07 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.346, 0.78, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_57ecc027-a48c-4a61-9ffb-931ae1fab2a5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[div] -> CLICK\n[button] close -> CLICK\n[heading] Same Day Delivery -> CLICK\n[link] Self-Rising Crust Uncured Pepperoni Frozen Pizza -... -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.603, 0.144, 0.775, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/22e33a38-902c-4f62-9e9a-822b2370b6d1_8ff5337a-6643-4d26-88c1-f731c8d15f93.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Exotic Cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.197, 0.15, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/789b7d2d-fb01-453c-b933-383965e6123c_e7becd76-12f3-404f-a927-5c51aa736b85.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cast and crew of Titanic and add to watchlist\nPrevious actions:\n[textbox] Search TV Shows and Movies... -> TYPE: Titanic" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.137, 0.594, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_cd9ce436-abb2-4fd7-aef5-356733c7e1a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BWM cars made in 2010 and compare the four cheapest listings\nPrevious actions:\n[button] Close dialog -> CLICK\n[select] 2024 -> SELECT: 2010\n[combobox] Sort By -> SELECT: Price: Low to High\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.42, 0.217, 0.435, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fb36232-0d2a-4115-9012-99dbaad25a5e_1ac506ac-dd62-4adb-8cc6-e42e39ea1e35.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flights from New York to Toronto.\nPrevious actions:\n[span] -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: New York\n[button] New York, NY, US (NYC - All Airports) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: Toronto" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.314, 0.582, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_08b7c08f-c6d0-44a6-95d8-59c4f97021f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[checkbox] Stainless Steel (75) -> CLICK\n[checkbox] Equal Bowl (69) -> CLICK\n[checkbox] 19 inch (7) -> CLICK\n[button] Sort By: Best Match -> CLICK\n[button] Price Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.236, 0.155, 0.278, 0.162] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cfaa49bd-7943-4da8-ae5f-bb3a15dfaa05_919527a3-b5dd-493f-ab2b-dc9cc35b2cbc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 showtimes for John Wick 4 at a theater in Wichita, Kansas 67226\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK\n[link] Find a Theatre -> CLICK\n[link] Wichita -> CLICK\n[link] Showtimes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.15, 0.559, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_f3c95979-f964-4912-8cf9-a627b0322a93.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[button] Show more filters modal -> CLICK\n[button] Sort Best match -> CLICK\n[radio] Price: low to high -> 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 [0.95, 0.298, 0.969, 0.315] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_034c4eb3-eecf-41d3-b403-54797be9544a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Locations -> CLICK\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: laguardia airport\n[span] LaGuardia Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.421, 0.272, 0.579, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_b08e91e1-2c15-4dda-a02d-558267a8292f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request a refund for the traveler Ian Lo and, his document number is 12345678912345 and email ian.lo@gmail.com\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Request a refund -> CLICK\n[button] Add trip -> CLICK\n[textbox] Last Name* -> TYPE: Lo\n[textbox] Confirmation or ticket number* -> TYPE: 12345678912345" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.226, 0.57, 0.482, 0.604] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86897828-35e8-4002-a98a-4e1dd26c6edb_c7a0d65f-bad9-4424-90af-42b14680cc05.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the lowest price ticket for All star stand up comedy event happen 6pm on the 25th March 2023.\nPrevious actions:\n[link] concerts. -> CLICK\n[textbox] Search by Name -> TYPE: all star stand up comedy\n[p] All Star Stand Up Comedy -> CLICK\n[link] View Tickets -> CLICK\n[span] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.425, 0.975, 0.466] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61d28a34-cc8e-46a9-b41d-c95933de2214_6e15b8bd-803c-4dd4-8e9e-0b102e3d9a69.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Beginner 554,088 -> CLICK\n[link] Drop C 3,930 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.226, 0.153, 0.247] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_8159f605-56cd-4c82-8451-7c0f4743d451.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[span] -> CLICK\n[button] Show all 14 -> CLICK\n[span] -> CLICK\n[button] Show all 25 -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.153, 0.263, 0.163] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc194d4-2f71-496a-b378-e18ab698ab0f_411a33e1-09da-4e0a-96a5-303cfa86ccae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reggae concerts this weekend.\nPrevious actions:\n[button] CONCERTS -> CLICK\n[link] Reggae -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.632, 0.245, 0.655, 0.259] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_3b3620c3-4b5c-44fa-a170-36828db8938a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[button] Departing April 5, 2023 -> CLICK\n[button] Apr 11, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[checkbox] Nonstop (1) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.302, 0.048, 0.318] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/229199b4-9988-485f-8175-b5efd8faf08b_2ab5735a-26cd-414e-b9ed-52d802f1408d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Ask a question regarding Health Insurance Top Up plans beneficial or not?\nPrevious actions:\n[link] QUESTIONS & ANSWERS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.149, 0.075, 0.262, 0.091] in the image\nAnd my action is Action: CLICK" } ]