Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/e8ce2bcd-894d-4b2f-99e4-ae695a6b9dd9_a5d935f5-61f6-4797-9dc6-33eb9a260ece.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest cars available at San Francisco Airport for a day.\nPrevious actions:\n[link] San Francisco Airport -> CLICK\n[div] Fri, Mar 31 -> CLICK\n[checkbox] 29 March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.097, 0.923, 0.125] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_f3f39cfc-eb80-4f5e-ab84-0bce4f894d21.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at jacksparrow@gmail.com.\nPrevious actions:\n[button] State / Province -> CLICK\n[span] -> CLICK\n[button] City -> CLICK\n[span] -> CLICK\n[button] Hiring Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.323, 0.218, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c64dcaa1-555d-43f3-adb4-3452c4e5d09b_5630e994-101d-43c2-8c69-da80024e3159.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 barbershops that have private lot parking.\nPrevious actions:\n[textbox] Find -> TYPE: barbershop\n[span] Barbershop -> CLICK\n[button] All -> CLICK\n[button] See all -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.262, 0.688, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eee72e78-71bd-434b-ba74-33888ea5522d_238e3167-126e-4c08-8de2-c51cb969c94b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in Le maraise neighborhood in paris with 2 room for 3 adult on March 27th to April 2nd.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Le maraise\n[span] Le Marais, Paris, France -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.375, 0.246, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4008118a-68a1-4a9f-968c-8b92a979dff7_62b5851a-66ac-4f7b-ab41-5c8ca47f87b0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 breakfast options on the Carnival Breeze ship.\nPrevious actions:\n[button] Explore -> HOVER\n[link] Dining -> CLICK\n[span] EXPLORE DINING -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.035, 0.27, 0.055, 0.28] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_bf3a4668-958b-4149-a5b0-3870bf764b06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[button] Add to cart -> CLICK\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue with this address -> CLICK\n[button] Continue without membership -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.789, 0.2, 0.817] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61563837-99af-45e2-a13f-9d6bd9f74a81_90dd2ba7-06e3-4e8d-b4a7-cd9f16ee5fd2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all the external solid state drives available with lowest price first.\nPrevious actions:\n[link] See All -> CLICK\n[link] Computers -> CLICK\n[link] Drives & Storage -> CLICK\n[link] External Solid State Drives -> CLICK\n[span] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.847, 0.118, 0.979, 0.134] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e0d115f-9da7-4211-9d99-122912890b40_865d6d65-322d-4261-8173-2a3f843e747d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Delete the history of what i heard recently.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.232, 0.0, 0.313, 0.021] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_53510142-0f5f-4f73-86f1-61dc206fb9a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] Run Search -> CLICK\n[label] -> CLICK\n[label] -> CLICK\n[label] -> CLICK\n[combobox] autocomplete -> TYPE: portland" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.077, 0.338, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_92de7066-88c4-424e-97df-4a48ba0b59b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.18, 0.259, 0.204] in the image\nAnd my action is Action: TYPE\nValue: SPRINGFIELD" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_e977dfbb-fe57-43f2-979f-b9249b2747b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[link] Fares & Tolls -> CLICK\n[link] See railroad fare details. -> CLICK\n[link] Plan a trip to see fares. -> CLICK\n[searchbox] From -> TYPE: grand central\n[span] Grand Central -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.215, 0.474, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9c7496f-bdea-4651-aeae-0f4d12d59d12_85fb9ffc-48b1-4e4b-b07f-f81e89cebb4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter car accident lawyers in Stanford, CA, sort them by distane and find the phone number of the nearest one.\nPrevious actions:\n[input] -> TYPE: Stanford, CA\n[input] -> TYPE: car accident lawyers\n[link] car accident lawyers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.59, 0.112, 0.683, 0.124] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_e1297f39-b8fc-447a-a101-078ec44c68f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York\n[li] New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.325, 0.195, 0.336] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdc94e3a-caa3-42b0-aa1b-b99f728f6292_807e15c8-e808-4db8-abf7-e3e606df063c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a demo drive for Model Y for Roy Adams with phone number 123-999-0000, email address RA@gmail.com and zip code 90001 in the United States.\nPrevious actions:\n[link] Demo Drive -> CLICK\n[button] Model Y -> CLICK\n[textbox] Last Name -> TYPE: Adams\n[textbox] First Name -> TYPE: Roy" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.481, 0.416, 0.659, 0.436] in the image\nAnd my action is Action: TYPE\nValue: 123-999-0000" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_db0dd015-f9d9-4fd6-9c1b-90ee29a84a8e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is buckeye.foobar@gmail.com. Employer's name is Gua AB.\nPrevious actions:\n[link] BOOK MONTHLY PARKING -> CLICK\n[textbox] First Name -> CLICK\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: SMith\n[textbox] Address1 -> TYPE: 133 st avenue" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.345, 0.24, 0.38] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_226e8bc5-1ca6-42ef-867a-370029f7942b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[div] Recommended -> CLICK\n[option] Price (Low to High) -> CLICK\n[heading] La Quinta Inn & Suites by Wyndham Houston Hobby Ai... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.715, 0.26, 0.953, 0.292] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/08f78082-3408-4714-99ea-5a699840317d_5660db7c-d327-43d3-ba70-3c9541460e84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Magnolia Texas.\nPrevious actions:\n[link] Find Stores -> CLICK\n[link] View store directory -> CLICK\n[link] Texas -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.168, 0.559, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_46fee503-6ddf-4dcb-914b-7b66ac2afbaa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.497, 0.333, 0.742, 0.355] in the image\nAnd my action is Action: TYPE\nValue: Lo" } ]

{ "bytes": "", "path": "./images/8634bbc0-7bcd-4c88-ad0f-5c73c3f69e53_78e4da0e-d2e1-458b-a8ec-ee5acaa8d971.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Hackney -> CLICK\n[combobox] autocomplete -> CLICK\n[combobox] autocomplete -> TYPE: Hackney\n[div] London, UK -> CLICK\n[textbox] Search events -> TYPE: Hackney Clothes Swap - Earth Day" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.537, 0.766, 0.607] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3358dffd-3673-435b-bfcb-cb242a2c622c_67f3e885-cc8d-4607-bde7-b6dd64775a4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse round-trip bus tickets from Houston to Dallas leaving on May 7th and returning a week later.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Houston\n[span] Houston, TX -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Dallas\n[div] Dallas, TX -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.196, 0.77, 0.227, 0.794] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_b946c050-003b-4cd1-a7cc-f23d7e291ba1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 -> CLICK\n[link] Trade in by mail -> CLICK\n[combobox] search input -> TYPE: Nemo Front Porch 2P Tent" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.744, 0.246, 0.767, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_bc272ed7-686b-48e6-be10-19d50e5ff9d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[textbox] Start Date -> CLICK\n[gridcell] Sat, Apr 29, 2023 -> CLICK\n[div] 30 -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.635, 0.455, 0.648, 0.467] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f2f531ff-94d5-4320-8594-7ae5d3a52af5_34e7f545-430f-4557-84b4-ec4cfea0876d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.079, 1.0, 0.1] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/862faed7-449c-4624-902b-6b512a977d0c_2be16347-d879-4bba-abe1-8c4028244c19.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.008, 0.651, 0.037] in the image\nAnd my action is Action: TYPE\nValue: surge protector" } ]

{ "bytes": "", "path": "./images/f738b393-9234-4c07-8baf-20f05627d5ed_8c2bdab0-6b93-4326-83f2-c3bd35cff1de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[span] Landscaping -> CLICK\n[textbox] Near -> TYPE: WEST HOLLYWOOD\n[span] West Hollywood -> CLICK\n[radio] Lawns or greenscapes -> CLICK\n[button] Fast-responding -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.553, 0.092, 0.65, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_eb82b9a7-62d4-4ad0-93aa-7ddc9c93cb65.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Children's Books -> CLICK\n[link] Non-Fiction -> CLICK\n[link] History -> CLICK\n[select] All -> SELECT: Ages 9-11 (13,217)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.407, 0.196, 0.426] in the image\nAnd my action is Action: SELECT\nValue: Hindi (59)" } ]

{ "bytes": "", "path": "./images/cdd9ef05-4d5b-4469-b001-8d73b6dc8120_aee3baf0-fbec-4ac0-8ff2-60d01149dd39.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 documents required to sell a car in New Jersey for which payments are being paid and it has single person on the title who can come to the store\nPrevious actions:\n[link] Sell/Trade -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.567, 0.22, 0.823, 0.265] in the image\nAnd my action is Action: SELECT\nValue: New Jersey" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_8efdb3e2-d599-4e4c-91de-518fbcfe3e4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Categories -> CLICK\n[link] Grocery -> CLICK\n[span] Frozen Foods -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.285, 0.316, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_1643a5ef-db8a-42fb-a052-37a0e9122ac1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[img] A person holding a tomato and a grocery bag with a... -> CLICK\n[button] Next -> CLICK\n[link] Personal Care -> CLICK\n[svg] -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.751, 0.285, 0.83, 0.302] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4970cd99-ce6b-42e3-bc78-695c9d510f6c_517a437f-10b1-4713-b44e-9d72da782cb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[textbox] Enter your Origin -> TYPE: Cheyenne\n[textbox] Enter your Destination -> TYPE: Helena\n[button] Get Directions -> CLICK\n[li] Cheyenne, WY, USA -> CLICK\n[li] Helena, Montana -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.498, 0.549, 0.573, 0.572] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_98caa132-9fac-4589-8b0d-4fcc6e8e0f75.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[label] -> CLICK\n[label] -> CLICK\n[label] -> CLICK\n[combobox] autocomplete -> TYPE: portland\n[div] Portland -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.286, 0.216, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_75f3bf7b-84da-4fb6-9810-13ca7ce311fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Different drop-off -> CLICK\n[tab] Same drop-off -> CLICK\n[button] End date -> CLICK\n[button] May 22, 2023 -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.404, 0.049, 0.442, 0.061] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_b106cb92-845b-4cc4-b750-58e03d6ac5f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 romantic summer vacations in Spain\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Spain\n[div] Spain -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.586, 0.017, 0.781, 0.052] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4777d638-204d-4e44-b81c-2fb43c471fb2_1a28a0b0-4e06-4b68-9287-28d439b713ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most reviewed cocktail bar with outdoor seating for reservation in San Francisco.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.104, 0.036, 0.201, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_a35dc0e8-fa41-4eb8-a854-1f952e660828.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[textbox] From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.17, 0.195, 0.286, 0.212] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c1a354a1-7990-4ca8-9fc5-2fdb1b5df337_2763fe68-209b-4181-b309-e9e75ebaf703.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 book in Hindi with ISBN 1648926800.\nPrevious actions:\n[link] Advanced Search -> CLICK\n[input] -> CLICK\n[input] -> TYPE: 1648926800\n[select] All -> SELECT: Hindi" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.859, 0.383, 0.969, 0.424] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_8b26cb30-f938-42d7-ad51-858d186a5422.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[link] SSD Storage -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.425, 0.512, 0.44] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35cf31d3-c88d-45fe-9959-4cf1de72bc7d_f0e05a7d-56d2-4f09-b264-8e29f664c2ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for trending women sports bras and add 3 trending black bras to Wishlist.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK\n[div] Color -> CLICK\n[link] Refine by color: Black -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.464, 0.157, 0.485, 0.17] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_5c48bea6-ba29-458e-8ccb-ab038bfe9f9c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is thomas.neo@gmail.com and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[link] Birthdays -> CLICK\n[button] Buy Now -> CLICK\n[button] Next -> CLICK\n[input] -> TYPE: Neo\n[input] -> TYPE: Thomas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.14, 0.487, 0.167] in the image\nAnd my action is Action: TYPE\nValue: 05/05/1995" } ]

{ "bytes": "", "path": "./images/969f36c3-52e7-42da-80bd-11a2d04d53ae_a48a19f1-6b38-44bf-9f1c-923274418b08.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Biography of the NFL player named Michael Jordan\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.931, 0.046, 0.966, 0.078] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/942e315d-b494-469c-93df-cd69c88ea2d2_6c20de6d-fcb6-460e-a454-34f681cbb142.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 information regarding Fastbreak program.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.743, 0.018, 0.837, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_ed1bafa7-9add-4b87-989b-90aa882fac86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Age of Child 1(Child's age (years)) -> SELECT: 3\n[img] Add -> CLICK\n[combobox] Age of Child 2(Child's age (years)) -> SELECT: 5\n[img] Add -> CLICK\n[combobox] Age of Child 3(Child's age (years)) -> SELECT: 8" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.259, 0.393, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ad0369b6-cfd5-4555-bb4f-d84a942be555_d4d09cdb-86cd-4870-9e02-5cc4fc3a08d2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order the cheapest climbing shoes in today's deals.\nPrevious actions:\n[button] Deals -> HOVER\n[link] Explore Deals -> CLICK\n[link] Climbing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.247, 0.448, 0.428, 0.483] in the image\nAnd my action is Action: SELECT\nValue: Price Low - High" } ]

{ "bytes": "", "path": "./images/e104a4ef-521f-4ca0-8e1a-098656207de2_587b5c69-60df-46d7-a9bb-da2624630a64.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK\n[textbox] Vehicle Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.176, 0.459, 0.197] in the image\nAnd my action is Action: TYPE\nValue: 10000" } ]

{ "bytes": "", "path": "./images/0cb50efe-4568-4c8d-bf0e-ed106cf99d1d_5633f55b-e5ea-434b-9aae-06fec4fbe863.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all time most popular solo track by ArianaGrande\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: Ariana Grande\n[button] Search -> CLICK\n[a] -> CLICK\n[button] Sorted by: Last 7 days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.568, 0.546, 0.656, 0.569] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1e46885-62b3-42ae-837a-474b1541348a_6a689c11-d9a8-4139-b828-7312938f530d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.158, 0.782, 0.188] in the image\nAnd my action is Action: TYPE\nValue: New york yankees" } ]

{ "bytes": "", "path": "./images/71638c81-42f0-4218-a1b0-d3a137ad1cff_0ea5b7ba-2e88-4415-ac7e-eb3b6a7f71e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the price of Tesla Model Y Performance for the 10001 zip code.\nPrevious actions:\n[link] Model Y -> CLICK\n[link] Order Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.713, 0.454, 0.963, 0.484] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_cff604f9-1605-4b09-b220-446853102b4c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[heading] Amenities  -> CLICK\n[label] Business center (11) -> CLICK\n[label] High-speed Internet (11) -> CLICK\n[button] APPLY -> CLICK\n[generic] Distance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.506, 0.37, 0.525] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/28f6ac29-940a-4ec6-a8bd-16ae2ce69a1c_e24f4566-ec7e-49e8-b98f-bfab996bad35.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Find a receipt -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.182, 0.082, 0.192] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_0f7759b9-f43a-4d97-ace7-6405722611eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Chennai\n[option] Chennai, Tamil Nadu, India -> CLICK\n[button] Monday March 20, 2023 -> CLICK\n[button] Search -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.552, 0.22, 0.765, 0.246] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_4fc9c4f6-0be4-45fe-b57b-1950681d0415.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[link] Gift Cards  -> CLICK\n[link] Browse Gift Cards -> CLICK\n[button] Our Brands -> CLICK\n[img] Travel Reinvented. -> CLICK\n[textbox] *Amount -> TYPE: 150" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.687, 0.247, 0.783, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_8abf4ce0-758b-4ae6-8a7d-5a906da17d25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.142, 0.148, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9653dc0d-96d9-414f-a711-3af94bd7cf5b_5302abb9-8cce-45a3-8c07-a1b13fc6f6a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: sell playstation controller for cash credit on GameStop in 43240.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[img] -> CLICK\n[link] Sony DUALSHOCK 4 Wireless Controller for PlayStati... -> CLICK\n[div] Find a Store -> CLICK\n[link] FIND A STORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.168, 0.657, 0.194] in the image\nAnd my action is Action: TYPE\nValue: 43240" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_50fd7aaa-959c-4d4c-b224-5dd9a2bd05fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[textbox] Flight origin input -> TYPE: Mumbai\n[span] Chhatrapati Shivaji Intl -> CLICK\n[textbox] Flight destination input -> TYPE: Dubai\n[span] Dubai, United Arab Emirates -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.106, 0.292, 0.13] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_d28a21e8-c00e-4910-b822-cc0f714abbc5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Explore All -> CLICK\n[link] 3,682,991 Pop -> CLICK\n[img] Phil Collins - No Jacket Required -> CLICK\n[button] Add to List -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.325, 0.346, 0.375, 0.359] in the image\nAnd my action is Action: SELECT\nValue: New" } ]

{ "bytes": "", "path": "./images/40cd58cd-6c9a-47b9-a927-92243970d87a_abeec9fe-726d-4040-9765-cc8bb0a8b920.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly daytime only parking nearest to Madison Square Garden starting from April 22\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: madison square garden" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.229, 0.914, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4596152e-6589-4bf2-9c9f-dd3ed9e8c0dc_83a8bc23-465e-4b2f-a976-ae902a22fc9a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out details about cancellation fees.\nPrevious actions:\n[link] FAQs -> CLICK\n[link] Cancellation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.866, 0.157, 0.879, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_d0ce30cd-701a-4a18-88a0-296d0f6c054c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.84, 0.022, 0.93, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_5a47ed74-98e7-45da-a78e-7084c186f24c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[button] Done -> CLICK\n[button] Back -> CLICK\n[path] -> CLICK\n[link] Shower Essentials -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.751, 0.372, 0.83, 0.397] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_c42f6c09-f6c3-462b-959f-2973c7f727bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Next -> CLICK\n[div] Select Your Options -> CLICK\n[generic] Black image Black -> CLICK\n[button] Next -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.38, 0.634, 0.409] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/02142919-1e63-4059-9471-419158e159a7_32e7b754-8ce2-4176-a691-0dce0ebe24af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 prices for luxury sedan car in Houston with insurance.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Houston\n[button] Place Houston, TX -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.113, 0.923, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d5c4d19-c2cc-4e68-9f51-71ba6cd6e38a_dc9fbc47-c21f-4f1d-bd12-6bd2c9d95272.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 with 4 star and above rating in Los Angeles for 3 days next week and save it.\nPrevious actions:\n[link] Search for hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.087, 0.478, 0.109] in the image\nAnd my action is Action: TYPE\nValue: Los Angeles" } ]

{ "bytes": "", "path": "./images/7c2ab1ed-54b7-4316-8b2f-d7467e01b540_73330912-2776-4a17-99b0-8b5976828695.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\n[link] Search for flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.317, 0.139, 0.376, 0.173] in the image\nAnd my action is Action: TYPE\nValue: madurai" } ]

{ "bytes": "", "path": "./images/5ad0f114-6cea-4f61-af3d-f9f4d4096d6c_26c209a2-46d8-42f1-bac1-7f3ed1d525bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Uncharted: Legacy of Thieves Collection to my guide and find the Queen's bracelet information.\nPrevious actions:\n[link] Guides -> CLICK\n[svg] -> CLICK\n[searchbox] Search -> TYPE: Uncharted Legacy of Thieves Collection\n[div] Uncharted: Legacy of Thieves Collection -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.43, 0.301, 0.449] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_571bfafa-ad8c-454a-bcd7-5d507abb8478.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[div] Choose date -> CLICK\n[div] Jun -> CLICK\n[generic] 1 -> CLICK\n[generic] 4 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.509, 0.383, 0.702, 0.413] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6803cd71-78a9-4bff-a1a3-1153dcc28c11_6c95fe7c-6317-48bf-a43b-7f3032763ef7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find organic dog food and add it to the cart.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: organic dog food" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.091, 0.757, 0.124] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7cd5a347-0e44-4ea2-8fcf-45fec1844279_ff9510d8-86fe-40ad-b787-0a90b1d78a19.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 music event organizers and follow the second one.\nPrevious actions:\n[link] Music -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.231, 0.235, 0.316, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_1222eefa-0175-4eef-a66f-e6bd0d109c4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Trade in -> CLICK\n[link] Complete trade-in -> CLICK\n[button] Verify membership to continue -> CLICK\n[input] -> TYPE: Joe\n[input] -> TYPE: Bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.318, 0.347, 0.372] in the image\nAnd my action is Action: TYPE\nValue: 123456789" } ]

{ "bytes": "", "path": "./images/8e133f6c-155d-4ba4-89f5-16f569d6e918_b8094fea-6545-48cd-b82a-d9420fd540c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest food tour in Paris which offers free cancellation\nPrevious actions:\n[textbox] Where to? -> TYPE: Paris" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.185, 0.729, 0.221] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c95ac388-3fea-457d-bb5d-fede3785c6f6_90c6af14-70ab-4b7d-962e-c01741f97a29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in New York city to stay in during spring\nPrevious actions:\n[textbox] Where? -> TYPE: New York City" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.152, 0.89, 0.171] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_6c7ee22f-e6b6-4cdb-a287-5162da143ba5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[link] hotels. -> CLICK\n[textbox] Check In  -> CLICK\n[link] 24 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.171, 0.389, 0.2] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b2dd00ff-3f09-46bf-a043-7b996f3815da_c06ba573-4b50-4b1e-9a87-70d18fa8474a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 holiday campground in Alaska.\nPrevious actions:\n[link] CAMPING AT KOA  -> CLICK\n[link] KOA HOLIDAY CAMPGROUNDS  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.234, 0.508, 0.282, 0.522] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/360eeaa8-0077-42f4-8200-1e3cf6414cda_a7be10f1-c85f-444d-93a6-48f078088d83.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a message to Joe Bloggs who has the username 'boredcelt'.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.007, 0.475, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_8c0f2845-0345-4194-a6bd-c1143e3da795.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[option] 6 -> CLICK\n[button] Update -> CLICK\n[button] Search -> CLICK\n[button] Search without signing in -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.764, 0.278, 0.779] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_6a78e4e9-77a2-4025-8623-e0d7eda8379b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[button] Austin, TX, US (AUS) -> CLICK\n[span] -> CLICK\n[button] Find flights -> CLICK\n[textbox] Date -> CLICK\n[button] Move backward to switch to the previous month. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.597, 0.227, 0.627, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d86d5cc1-50f7-4bfd-8e5b-60db84e87956_fca33043-62dc-44e2-b64d-f14bb211f687.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the trade-in value for Call of Duty: Black Ops III for Xbox One.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: trade in\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.441, 0.258, 0.618, 0.373] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/408cc1bd-0a76-4bad-b5f4-11db4405047f_e1f976e1-1ac3-447e-921f-672cd8545c6c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.199, 0.152, 0.46, 0.17] in the image\nAnd my action is Action: TYPE\nValue: Boston Logan Airport" } ]

{ "bytes": "", "path": "./images/e104a4ef-521f-4ca0-8e1a-098656207de2_62309d1f-10e6-4601-9cbb-6b407fe0a0a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[link] Finance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.383, 0.07, 0.617, 0.094] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_b3cf21f4-85bf-4461-8154-b500af3a6b9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a first class vacation travel for 2 adults from San Francisco to New york leavind on april 9 and returning on april 19\nPrevious actions:\n[combobox] Number of passengers -> SELECT: 2\n[textbox] Depart (date format mm/dd/yyyy) -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 9 -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.465, 0.407, 0.492, 0.43] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a1d1f6c0-1ae9-47f0-b054-8f3f9935b7da_2a83533c-7eff-4390-817b-d6032b626a7a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule for the San Francisco 49ers.\nPrevious actions:\n[link] Schedule -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.058, 0.387, 0.1] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_857ae6d3-3942-4710-a68b-2ecaf84fda28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[svg] -> CLICK\n[listbox] select children -> SELECT: 2\n[listbox] select child age -> SELECT: 5-15\n[button] Done -> CLICK\n[button] Get cheapest tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.583, 0.709, 0.621] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c2a17420-ceb4-4324-ae8f-60cf845a144b_6f4fd24e-96c4-4cba-9914-2abd10715701.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Canyon de Chelly schedule calendar.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[combobox] Park Name -> TYPE: Canyon de Chelly" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.147, 0.784, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e91126e0-023d-4f96-9378-74efb5d6ecc3_57555471-f75f-42f1-a810-cf336ce2258b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reviews and research information about Audi A6 2020.\nPrevious actions:\n[menuitem] Research -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.151, 0.183, 0.173] in the image\nAnd my action is Action: SELECT\nValue: Audi" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_4ab4e823-aad2-4316-90bd-3e6b9c41cf08.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[link] Filter -> CLICK\n[generic] Refine by Category: Video Games -> CLICK\n[generic] Refine by Category: Xbox Series X|S -> CLICK\n[link] Shop Pre-Orders -> CLICK\n[button] Franchise -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.453, 0.366, 0.467] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bd729e8-abb2-4649-bb81-8c790c04f8ad_3fb0efb0-a518-4c6b-b5e6-709f2274140e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Paint -> CLICK\n[link] Painting Tools -> CLICK\n[button] 43229 -> TYPE: 44240" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.31, 0.053, 0.417, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_20a29fa4-5700-4dae-a6c7-46b5d878e615.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email sellmycar@mail.com.\nPrevious actions:\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[radio] Owned -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.326, 0.284, 0.359] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_549866d9-de41-45c4-934c-6f26d3529dd7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Okay, got it. -> CLICK\n[img] undefined -> CLICK\n[button] Continue without a seat -> CLICK\n[div] 1 Small Bag only -> CLICK\n[label] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.866, 0.79, 0.953, 0.825] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55518089-52b9-4504-8e4f-885a9b2943a8_f1ee27e8-e8cb-43fd-882f-97d3c7dbdfb8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of comedy movies, sorted by user ratings.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.111, 0.364, 0.125] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/46a3683f-fbe0-40d0-8729-6c7964d994e6_02471179-19b4-45e2-9121-a5e8a2a39f26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Short Sleeves -> CLICK\n[div] Size -> CLICK\n[link] XL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.189, 0.495, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a8474730-82eb-4f12-b947-db64ac08660b_fdf8015b-4c08-45d5-a48a-750a95229995.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most recently posted job opening in customer service in Ireland with a remote working option.\nPrevious actions:\n[ppc-content] Ireland -> CLICK\n[button] Flexible Workstyles -> CLICK\n[span] -> CLICK\n[button] Category -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.886, 0.408, 0.977, 0.423] in the image\nAnd my action is Action: SELECT\nValue: Most recent" } ]

{ "bytes": "", "path": "./images/67f9fb2d-443a-4e5b-9530-e24372faedd2_62d943fd-4365-4704-9f70-94cb2619c702.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the exotic vehicles they have available to rent?\nPrevious actions:\n[button] Vehicles -> CLICK\n[link] Exotic Cars -> CLICK\n[link] Explore Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.541, 0.139, 0.577] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e12f51f6-c8c5-4a68-9586-d77927bca79c_8aaf0965-49ce-4370-9a67-300ef0a9123f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a Tesla Shop Gift Card for April May with the email april.may@gmail.com to my cart\nPrevious actions:\n[link] Shop -> CLICK\n[menuitem] Lifestyle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.478, 0.315, 0.836] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_5cf2cb2e-ee55-47fe-8fee-f18dbe96fb3c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[textbox] Depart , required. -> CLICK\n[textbox] Depart , required. -> TYPE: 04/22/2023\n[combobox] Number of passengers -> SELECT: 1\n[combobox] Passenger 1 -> SELECT: Adult (16-64)\n[combobox] Search by -> SELECT: Lowest fare" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.71, 0.688, 0.895, 0.71] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4596152e-6589-4bf2-9c9f-dd3ed9e8c0dc_86c7afdc-89d2-4a50-8f67-18f069d328f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out details about cancellation fees.\nPrevious actions:\n[link] FAQs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.292, 0.328, 0.342] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d73937b-3be7-4f5f-950f-b1905244a2ac_8f0334e0-1f8a-4958-9416-68b2d03744a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 MLB tickets for this weekend and select the next one.\nPrevious actions:\n[button] SPORTS -> HOVER\n[link] All MLB Tickets -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.227, 0.881, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/329d9ee8-de96-40c2-aa19-2dcf8e86b724_66a067aa-db40-45b7-bf6a-a4ba43889d2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 me info about planning a wedding cruise\nPrevious actions:\n[link] Weddings & Occasions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.721, 0.314, 0.923, 0.33] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87b23bf1-3c23-45a6-82bf-5a535c7cdc2f_79305d4e-54ba-42af-8bb6-7ae0e8aa483c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: orlando\n[span] Orlando Intl Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 29 -> CLICK\n[link] 28 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.701, 0.124, 0.902, 0.162] in the image\nAnd my action is Action: SELECT\nValue: 9 00 AM" } ]

{ "bytes": "", "path": "./images/40cd58cd-6c9a-47b9-a927-92243970d87a_29af2ad7-b801-42cd-93d0-f2c973573ee3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly daytime only parking nearest to Madison Square Garden starting from April 22\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: madison square garden\n[li] Madison Square Garden, Pennsylvania Plaza, New Yor... -> CLICK\n[select] All Parking Options -> SELECT: Daytime Only Parking" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.256, 0.384, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_62d7062f-27a8-4e87-b201-1aebf4117985.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[searchbox] Find values for games and more -> CLICK\n[searchbox] Find values for games and more -> TYPE: PS4\n[button] SEARCH -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles & Hardware -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.184, 0.375, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_7466e760-1596-4515-be42-00af9e90ecb1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Europe" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.173, 0.89, 0.193] in the image\nAnd my action is Action: CLICK" } ]