Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_5330614e-ce1a-4da4-906a-6fc408c6c3f3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.051, 0.553, 0.091] in the image\nAnd my action is Action: TYPE\nValue: mens black hoodie" } ]

{ "bytes": "", "path": "./images/44dcda68-082c-455a-a409-7091470cc006_c7bcbc4d-fcc6-40ae-8c77-900307f08664.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Edinburgh Waverly to Glagsgow Central on May 18, leaving nearest 3PM for 1 adult with a Veterans Railcard\nPrevious actions:\n[combobox] Arrival station, none selected. Select a station. -> TYPE: Glasgow\n[span] Glasgow Central -> CLICK\n[textbox] Date use format: 17-Mar-23 -> CLICK\n[path] -> CLICK\n[link] 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.198, 0.133, 0.215] in the image\nAnd my action is Action: SELECT\nValue: 15" } ]

{ "bytes": "", "path": "./images/d9c160e7-b179-4d42-8570-e6f3f85aa412_503a5c81-6a8a-4ece-9c8a-c80d7198f388.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated adults-only romantic beach vacation deals and book the cheapest one.\nPrevious actions:\n[link] Vacations -> CLICK\n[link] Beach Vacation Deals 95 DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.295, 0.079, 0.312] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_4e296369-5864-4c0d-b372-f4deb8454461.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[link] WOMEN -> HOVER\n[tab] Innerwear & Underwear -> CLICK\n[link] Bras -> CLICK\n[heading] Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.321, 0.471, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b30b9f84-0541-4826-a3af-98220b851f7c_d0666e22-cb4c-4bab-b17b-7dabac0d02b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's sports wear, size S.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: sports wear" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.88, 0.01, 0.898, 0.02] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_425a5e71-db07-473d-9e9a-43da9606841a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[label] Available in Store -> CLICK\n[label] KEEN -> CLICK\n[svg] -> CLICK\n[label] .Stars::before { -> CLICK\n[span] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.786, 0.309, 0.988, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dc0190c-57cc-4c0f-b939-c0617102166e_0096821b-49aa-4a8d-b059-a9cea6e724f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to favorites a cruise from San Francisco to the Panama Canal departing Oct 2024\nPrevious actions:\n[span] Sail To -> CLICK\n[button] Panama Canal -> CLICK\n[span] Sail From -> CLICK\n[button] San Francisco, CA -> CLICK\n[span] Dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.444, 0.149, 0.495, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_0b0bd6c0-a4c4-4a82-8757-549fe7ac92a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Enter your destination city, airport name, or airp... -> TYPE: AUSTIN\n[button] Austin, TX, US (AUS) -> CLICK\n[span] -> CLICK\n[button] Find flights -> CLICK\n[textbox] Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.178, 0.406, 0.187] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f94386a-d032-43cf-9dbe-2b64430c9c28_48bbbdea-1b37-4a5f-bd55-a9cb309e5507.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: locate the store in IL\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.608, 0.2, 0.63] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_2dd318f7-faa9-4bec-891d-2d35b588268d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[button] Done -> CLICK\n[button] Lowest Regular Rate -> CLICK\n[label] Senior Discount -> CLICK\n[button] Find Hotels -> CLICK\n[combobox] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.195, 0.258, 0.312, 0.274] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/851998b2-fda2-4bd4-a822-f1871a9fde12_ac062748-57fb-429f-a6a1-c6eeee2dee00.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of action figure items available for pre order.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK\n[link] Store -> CLICK\n[link] Pre-Orders -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.178, 0.219, 0.19] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9dfba9af-d79e-4a75-83b4-0f85ab04c2e6_0ceb3fb8-d1c7-4b00-a0f5-15d88fee4234.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a price quote for new Kia Carnival for 11101.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Free Dealer Price Quote -> CLICK\n[select] Make -> SELECT: Kia" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.491, 0.088, 0.947, 0.115] in the image\nAnd my action is Action: SELECT\nValue: Carnival" } ]

{ "bytes": "", "path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_8acc4e87-a3c3-4f37-a65d-ced00e37a017.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[link] BABY -> HOVER\n[tab] Toddler (6M-5Y) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.117, 0.388, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/604c4377-e24c-4900-a72f-346d8999d443_81d06b54-9858-498c-adf3-e40fd5b4ae17.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a deal which is highly rated in Fiji location.\nPrevious actions:\n[textbox] Where? -> TYPE: Fiji\n[div] Fiji -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.472, 0.772, 0.51] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb31a9f4-3465-4a91-aae6-bf70aa6b729f_10cb2e61-9f95-4cac-8db9-03791ea89776.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play a podcast about F1\nPrevious actions:\n[link]  -> CLICK\n[link] F1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.24, 0.195, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_3d80d70b-e911-4b66-832a-9e4e48884689.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[img] Travel Reinvented. -> CLICK\n[textbox] *Amount -> TYPE: 150\n[span] Marriott Deluxe Box -> CLICK\n[textbox] To -> TYPE: Clara\n[textbox] From -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.506, 0.873, 0.522] in the image\nAnd my action is Action: TYPE\nValue: Happy Christmas" } ]

{ "bytes": "", "path": "./images/0dd0b532-7bac-4b3e-b5a4-2ca6b0897af6_3ffa4643-b065-489e-824a-9c30771b411c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy TV shows streaming on HBO Max that was released in 2010.\nPrevious actions:\n[link] What to Watch on HBO Max -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.465, 0.286, 0.485] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_ac89e5b0-f806-42bb-81f7-e0e072172796.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: book a reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.833, 0.036, 0.938, 0.067] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/19847108-680f-4021-83a9-2548fab75fac_ded882d1-0f01-46b0-b67a-11ad3e9b513d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Mark a review in the best rated activity to do in Paris in May 12, 2023 as he\nlpful\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, 0.2, 0.729, 0.229] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_50cf3b67-127e-4d22-b584-4708cb56b602.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[textbox] From -> TYPE: TEL AVIV\n[span] Tel Aviv -> CLICK\n[textbox] To -> TYPE: VENICE\n[span] Venice Treviso -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.175, 0.185, 0.226, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e9d7935-0c16-46e6-9e5c-3ea9124a6bf7_d55123cf-0a80-4b19-9b22-6719bbab3231.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\n[link] Hip-hop & Rap -> CLICK\n[div] Play -> CLICK\n[button] More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.195, 0.761, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_cb0df657-8141-4273-979b-5d66494faae9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[menuitem] $99 or less -> CLICK\n[path] -> CLICK\n[button] Make -> CLICK\n[listitem] Chevrolet (101) Chevrolet (101) -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.248, 0.249, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/75db63ac-4fcf-400e-833f-d31f00cf6ab6_2bb2c81e-02b9-46b3-a3a0-89d174bd1e53.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.337, 0.8, 0.437, 0.813] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cfaa49bd-7943-4da8-ae5f-bb3a15dfaa05_2c3f007d-c4df-4247-8a58-bf4b58db1530.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find showtimes for John Wick 4 at a theater in Wichita, Kansas 67226\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.018, 0.443, 0.041] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_b03e5747-77f1-4f8a-9590-ca38c6b62ed3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[button] Find Hotels -> CLICK\n[combobox] Sort by: -> CLICK\n[option] Guest Rating -> CLICK\n[link] Pets welcome (118) -> CLICK\n[link] Free breakfast (57) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.482, 0.145, 0.556, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_c1c57834-374a-41c8-ac41-13163aad1f2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[link] Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.094, 0.861, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_992413a4-5f43-4f99-866a-cf43fa75678c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: addis ababa" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.286, 0.5, 0.314] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd8d723a-7a9f-4bd6-a8b9-75babb60835c_45868167-8aa0-44cb-972a-cf3113815043.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on how to get a ticket refund.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.684, 0.0, 0.756, 0.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_dac23220-8015-4eca-83ef-a520c024eb6a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] Postcode/ZIP code -> TYPE: 10001\n[combobox] State -> TYPE: new york\n[textbox] Card number -> TYPE: 1234\n[combobox] Card type -> SELECT: MasterCard\n[combobox] Month -> SELECT: 01" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.634, 0.308, 0.95, 0.347] in the image\nAnd my action is Action: SELECT\nValue: 2023" } ]

{ "bytes": "", "path": "./images/74226fab-6285-45da-8582-d25a876aa7b0_7fffde10-7954-4767-b39f-f913cadf8a51.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for the next pop concert.\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.314, 0.148, 0.517, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff173880-e7f5-4b4e-b941-79e9c3504add_ccf0ae9a-6d2e-48e5-be97-d91c9528fc61.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wall mirrors for under $20.\nPrevious actions:\n[button] Home décor -> CLICK\n[link] Mirrors -> CLICK\n[link] Wall mirrors -> CLICK\n[button] Show more filters modal -> CLICK\n[span] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.169, 0.966, 0.21] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fcb50c4e-a89e-4f18-b7c0-423295e7c298_ea3c2af5-fb9c-4145-ab53-a35548df1e2d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 certified pre-owned front-wheel drive Jeep, Compass model car with single owner and the lowest mileage within 500 miles of zip 59316.\nPrevious actions:\n[menuitem] Buy -> HOVER\n[menuitem] Certified Cars -> CLICK\n[combobox] makes -> SELECT: Jeep\n[combobox] models -> SELECT: Compass" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.048, 0.19, 0.157, 0.207] in the image\nAnd my action is Action: TYPE\nValue: 59316" } ]

{ "bytes": "", "path": "./images/dc1f0824-5483-4d3b-87d2-3f760a42a25e_3d12ecd5-f8ec-4e3a-b0c0-7d16c6e27f06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the events at any six flags park in Texas\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.767, 0.846, 0.798] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_647547bf-d59a-4a3b-b32a-9ea1fb94a530.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.609, 0.276, 0.618] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_d02d7a6c-c5d6-4b61-bd22-20a8e2309ea5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[checkbox] Mediterranean -> CLICK\n[button] Submit -> CLICK\n[button] Open additional search filters -> CLICK\n[checkbox] Outdoors -> CLICK\n[checkbox] Wine tasting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.91, 0.713, 0.954] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ea8737b0-0ff4-4476-b97d-5677d4f526dc_82c86cfb-3786-4a17-95c7-5cb6562ae363.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated locksmith in San Francisco for a key extraction from a vehicle.\nPrevious actions:\n[button] All -> CLICK\n[radio] Key extraction -> CLICK\n[radio] Vehicle -> CLICK\n[generic] 2 filters Key extraction • Vehicle Clear all Cance... -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.179, 0.642, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/df3b7cd4-526e-453b-9114-c0db1b3ed5ea_d25c7cda-0f2b-477a-8971-de77649a5939.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Dining Room Sets under furniture and filter the results to show only items availble under the Buy It Now format.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.342, 0.059, 0.414, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_d5672242-c470-499b-bc08-b42bbd8fb450.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Add to List -> CLICK\n[combobox] List -> SELECT: New\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] Explore All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.074, 0.163, 0.085] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_388f7180-285e-4867-8f40-f223749016f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[checkbox] Pool -> CLICK\n[checkbox] Towels -> CLICK\n[button] Property style -> CLICK\n[checkbox] Beach -> CLICK\n[div] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.627, 0.337, 0.861, 0.365] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16e81dcf-9762-4b83-be3e-60a65a15efec_8f7c6002-5777-46f1-80f9-13e66c053b06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.148, 0.282, 0.158] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_458554fd-debe-4dbe-a011-b64a5301fbd0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\n[combobox] Search by city or activity -> TYPE: Miami\n[generic] United States -> CLICK\n[button] SEARCH -> CLICK\n[span] Sort and filter -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.165, 0.237, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b332a3c6-c4f5-423c-a207-b1bcb28db6c3_b22bf5a8-0dc7-4cb4-adb4-1ae86643fe10.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated Drop D guitar tab from the 1990s.\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Drop D 39,730 -> CLICK\n[link] 1990s 3,183 -> CLICK\n[div] Today's most popular -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.825, 0.45, 0.97, 0.473] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_afd0591d-15ef-4dec-ac72-b2cea47ba8dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: colombo\n[strong] Colombo -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.218, 0.5, 0.263] in the image\nAnd my action is Action: TYPE\nValue: new york" } ]

{ "bytes": "", "path": "./images/d1e46885-62b3-42ae-837a-474b1541348a_a03e1463-bb7f-481c-9579-9caa826a8644.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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... -> TYPE: New york yankees\n[option] New York Yankees -> CLICK\n[link] TICKETS -> CLICK\n[div] More Options -> CLICK\n[span] Parking Passes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.467, 0.978, 0.504] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1c1af35c-a0d7-4fe8-bcd3-baf30862235b_084b94a2-6e3c-4b64-baa1-ba2dc61777a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most expensive cruise deals in Europe and Mediterranean.\nPrevious actions:\n[link] Cruises -> CLICK\n[link] Europe & Mediterranean Cruises 16 DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.285, 0.079, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccb7c231-8655-4613-a28f-beb8074c523e_f9bbc023-4e46-4803-a374-743e972eb8df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\n[menuitem] Men -> CLICK\n[link] Shirts & Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.265, 0.155, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_e6345ea9-a5a4-4b88-95b5-4efececed261.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[button] close -> CLICK\n[button] Material -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[heading] Pickup -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.264, 0.152, 0.319, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c497534c-76a5-4ffb-af9a-10ee7afcc784_44cd97dd-6f7f-4709-b641-f662ff17208b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[div] Caldwell -> CLICK\n[textbox] Pickup -> CLICK\n[button] Saturday, April 8, 2023 -> CLICK\n[button] Thursday, April 13, 2023 -> CLICK\n[combobox] Pickup time Selected 10:00 a.m. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.371, 0.266, 0.392] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e91126e0-023d-4f96-9378-74efb5d6ecc3_c47062d6-0d58-4383-9d62-efc14a92807c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.279, 0.0, 0.354, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03ac581c-ef95-4435-9d35-435e198b82de_524b1cc6-240f-41df-a42b-9de89456c807.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the Emergency Sickness Plan policy certificates for Connecticut.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Protections & Coverages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.49, 0.341, 0.682] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_438fdc63-2ab2-4f1f-9731-321dc68fda6d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Add Adults -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Children -> CLICK\n[button] Add Age -> CLICK\n[button] Add Less than 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.235, 0.341, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_7b98db39-1751-42ca-b632-f40400c443bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[menuitem] Kids -> HOVER\n[menuitem] Pants & Leggings -> CLICK\n[div] Sports -> CLICK\n[link] Training -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.342, 0.122, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50bd08bd-989f-44ba-8a99-71e75ba602f1_c3f1eed3-fedd-4937-8837-44bcace14f3e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show cheapest monthly price for parking near Shubert Theatre.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Shubert Theatre\n[option] Shubert Theatre  225 West 44th Street, New York De... -> CLICK\n[link] MONTHLY -> CLICK\n[span] Distance -> CLICK\n[link] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.298, 0.328, 0.343] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/17fffbee-e41b-46e4-ab75-675b263ca7b7_0802ef06-4167-4e70-b52f-4f106bf1ce19.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 power supply unit with at least 600W power output.\nPrevious actions:\n[searchbox] Search Site -> TYPE: 600w power supply\n[button]  -> CLICK\n[generic] 600 W -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.276, 0.4, 0.295] in the image\nAnd my action is Action: SELECT\nValue: Lowest Price" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_3163cce7-c289-4004-94b8-15e312dac0dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: CDG\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] Depart , required. -> TYPE: 04/21/2023\n[button] Add another flight -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.522, 0.29, 0.542] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7cbd1771-ca62-47ed-97db-5577644d285c_6838510b-e62e-416f-b389-46cd59c40012.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my favorites a cruise for 4 people going to Caribbean.\nPrevious actions:\n[button] Caribbean -> CLICK\n[button] SEARCH CRUISES -> CLICK\n[button] Number of Guests -> CLICK\n[path] -> CLICK\n[button] Increase to 4 guest button -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.065, 0.233, 0.079] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00cef5a2-4d07-4dd9-837d-5b85ac3a63d8_e851afe1-7aac-43ac-ab6d-e36cb60ccbd5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chicago Bulls team schedule for the month of April.\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> TYPE: Chicago Bulls" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.132, 0.116, 0.406, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a39f20a6-4d31-4f5f-b0ac-be8d548d7fa5_aeeb7ac6-c8f3-4c56-bdb6-e9269dafab16.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the hot deals within 500 miles from 10001\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.799, 0.013, 0.855, 0.035] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f804150b-c2e9-40ca-b71f-d0d0d95e0c46_c8b6e56e-4973-41fa-8ffb-0b3e044b052a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in New York City for 2 adults from Apr7 to Apr 8.\nPrevious actions:\n[link] Hotel , Opens another site in a new window that ma... -> CLICK\n[searchbox] Type your destination -> TYPE: New York City\n[option] New York (New York City) New York State, United St... -> CLICK\n[checkbox] 7 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.589, 0.388, 0.595, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c254dcec-bd9b-4cf0-9225-9d2bf1345f38_83752122-ca77-4eda-ba7c-c98b8fcfe3af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Real Madrid player Vinicius Junior bio\nPrevious actions:\n[button] MORE -> CLICK\n[div] Soccer -> CLICK\n[link] La Liga La Liga -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.664, 0.469, 0.715] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9f4b6bd4-69dc-4103-b1c4-eb621639e9dd_b30b2ef7-14ff-4170-b14a-4894124b0efc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List of publishers for board games\nPrevious actions:\n[button] Browse -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.085, 0.218, 0.098] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_481e6509-59bc-48c7-b6c0-1f065058835d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Continue without a seat -> CLICK\n[div] 1 Small Bag only -> CLICK\n[label] -> CLICK\n[button] Continue -> CLICK\n[button] No thanks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.841, 0.802, 0.953, 0.833] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_10d26c2c-7db7-44d7-b5cb-ae1e2a15f5dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Matthews winery\n[span] Matthews Winery -> CLICK\n[link] Book now Indoor Reservation, Two-hour indoor seati... -> CLICK\n[button] 2023-03-31 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.462, 0.202, 0.5, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db289bef-3d18-43c6-8ee3-a1ebc5d285b4_97a45713-c48e-4eef-8fe4-5711e87f4c5e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 news about the ps5.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.012, 0.337, 0.044, 0.358] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0633c328-f1ad-42bd-8aec-7a1883b5898d_7426506d-f253-4977-9475-faa2e4975689.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a luxury trip deal anywhere to go in spring\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Luxury Trips -> CLICK\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK\n[li] Spring -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.011, 0.82, 0.032] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a9b1b45-cb23-4073-897f-67410087df9d_b86bc343-260f-4335-980b-ea5e2fca2a71.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 COVID-19 test appointment at 90028.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.228, 0.41, 0.26] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_8f468438-c6e4-4af0-be8e-055e175d6de0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Continue with Value fare -> CLICK\n[button] Log in later -> CLICK\n[button] - -> CLICK\n[div] Mr -> CLICK\n[textbox] First name -> TYPE: Joe" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.372, 0.7, 0.541, 0.737] in the image\nAnd my action is Action: TYPE\nValue: Bloggs" } ]

{ "bytes": "", "path": "./images/c51cc2c0-5750-4bae-b665-ad1b7fafa63e_be1bab14-11b9-41e1-b4b2-b0a1f0a834c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show ticket price for Aquarium of Paris for 2 adults on May 5th.\nPrevious actions:\n[span] Attractions -> CLICK\n[searchbox] Where are you going? -> TYPE: Aquarium of Paris\n[div] Aquarium of Paris -> CLICK\n[div] Select your dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.737, 0.351, 0.763, 0.381] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/12324b80-88bd-4d48-962c-ae80203e5058_c01ad00e-d680-48e8-bfe6-bf73b8d30674.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $1 movie night film and rent blockers\nPrevious actions:\n[link] Navigate to deals -> CLICK\n[link] Navigate to 1-Night Kiosk Rentals See More -> CLICK\n[img] Blockers, MOVIE on , , Comedy, Romance, Special In... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.363, 0.338, 0.387] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_f16bc000-f7b9-4f57-b5e0-4fcf43b9bb40.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.121, 0.237, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/126b4604-8b04-4eb1-9027-266631c96f01_773b414e-e1c4-4471-bbdf-f8143c8a606f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book an outdoor table for 3 people at a Los Angeles restaurant for 5:00 PM on April 7th\nPrevious actions:\n[button] Los Angeles -> CLICK\n[link] La Cha Cha Cha -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.225, 0.228, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_ab620f2c-ea4d-4465-b77b-aa3b064e0f47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[div] Best match -> CLICK\n[label] Nearest distance -> CLICK\n[button] Back to all categories -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Change Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.265, 0.243, 0.703, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e592a68f-567f-4d6a-a1d6-4166cd129638_98480951-572a-451f-8538-188191a9a0c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 truck for 10001 zip code on Sunday 11:30 am with flexible dates.\nPrevious actions:\n[button] Reservations -> CLICK\n[link] Budget Truck -> CLICK\n[textbox] US City,State or Zip Code -> TYPE: 10001\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.353, 0.116, 0.373] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27a8bf82-2e7e-48c3-8fb1-66909c13d585_2f4873c2-1964-4640-8275-11655aa7465f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Buick for sale within 250 miles from 26807.\nPrevious actions:\n[combobox] 25 miles -> CLICK\n[generic] 250 miles -> CLICK\n[button] View 95 Vehicles -> CLICK\n[i] -> CLICK\n[checkbox] Buick1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.248, 0.237, 0.588, 0.411] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7180c4d1-971b-418d-8a64-87ab0d29c20e_a8cfda8a-1fc7-4f7c-bec5-09e4f3b1c420.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[button] 03/27/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK\n[button] 03/30/2023 -> CLICK\n[button] Browse Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.537, 0.059, 0.554] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549452ab-637a-4997-bce1-5898541bb288_218bb404-5a73-4d8f-a72d-1b680a898e89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all NFL tickets\nPrevious actions:\n[button] SPORTS -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.206, 0.099, 0.319, 0.118] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccb7c231-8655-4613-a28f-beb8074c523e_38c21a93-8c5b-4d31-b72c-06acc63a2afc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\n[menuitem] Men -> CLICK\n[link] Shirts & Tops -> CLICK\n[link] Graphic T-shirts -> CLICK\n[div] Sports -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.468, 0.194, 0.476] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_e9a53ae9-3b3d-444a-9dcc-a92bec2b77de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Matthews winery\n[span] Matthews Winery -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.426, 0.654, 0.439] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7b5b2188-afd4-4279-b738-c37a1b5f2142_e1cdcfc1-fc66-4d3b-8858-876e11893c7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of available opportunities for a volunteer event for year 2023\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Volunteer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.269, 0.398, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_a03f2e58-8fe0-4622-998b-ddcd17a238ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: MUMBAI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.327, 0.359, 0.359] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_93807878-de8b-4b57-83bd-6964dd4decf2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK\n[button] Team -> CLICK\n[searchbox] Search -> CLICK\n[option] Finance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.632, 0.32, 0.646] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_e8fc2f56-54e4-48fc-8ec2-dd86b6042ceb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harrt Reid Intl Airport, LAS\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.689, 0.158, 0.705, 0.168] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/39fd14c2-3bdd-4ca6-8a3a-1a6e7374c8e6_25b74fe3-6b52-453a-9885-aaa17ab27940.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 woman t-shirt in xl size from merchandise section, add 2 pieces to the cart and check out.\nPrevious actions:\n[link] Merchandise -> CLICK\n[span] Women's Last.fm Spiral Hex Tee -> CLICK\n[select] S -> SELECT: XL\n[svg] -> CLICK\n[button] ADD TO CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.931, 0.016, 0.953, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d538537c-ff96-4918-8807-af09b26199d1_20f844f5-7336-4362-91e4-577a81d9d46d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights between SFO and EWR using the Boeing 787-9 aircraft\nPrevious actions:\n[textbox] Origin -> CLICK\n[textbox] Origin -> TYPE: SFO" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.496, 0.222, 0.514, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_31217e2a-0ae5-4c3a-9559-dbf6eba97bf0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button]  SELECT -> CLICK\n[link] Gaming Monitors Accessories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.527, 0.868, 0.545] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_dc71652f-34de-4786-b270-3b5b750c5905.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[link] Baggage fee calculator -> CLICK\n[combobox] From -> TYPE: columbus\n[button] Columbus, OH, US (CMH) -> CLICK\n[combobox] To -> TYPE: new orleans\n[button] New Orleans, LA, US (MSY) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.319, 0.309, 0.35] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f17fa68b-27dd-4b9c-bc11-7a5dbe206741_9d136317-f8c9-430b-a4d1-ecb67729f4c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Premium Cars available to rent at LondonHeathrow Airport.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.108, 0.166, 0.429, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81b6bba7-3d05-40a4-a475-48eaeacbda0d_f46868bc-232a-4680-8b33-8e5198c0010c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.035, 0.272, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eb609e15-ff10-4b3d-82ce-348c439548ca_94563925-37bd-495c-9e75-5a2cfda4e37e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[menuitem] Outlet -> CLICK\n[link] Girls -> CLICK\n[link] Jackets -> CLICK\n[div] Product Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.264, 0.194, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e437082b-8383-4322-aa58-a6a683113970_d46fc387-0c97-4047-b400-07d10dd1c8d7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[button] Book -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.046, 0.073, 0.109, 0.084] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccf98191-100e-441a-93e8-8ff4076aeaa0_d4a3cabd-8df7-4d25-a8a7-2ed784bafd3f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\n[link] WOMEN -> HOVER\n[tab] Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.123, 0.332, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_808a3d44-fd0e-4a1e-aef7-55fead922731.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[select] All -> SELECT: Hindi (59)\n[button] Refine results -> CLICK\n[link] Notify me -> CLICK\n[link] Add to wishlist -> CLICK\n[textbox] Wishlist name -> TYPE: Must buy" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.607, 0.159, 0.716, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/08f78082-3408-4714-99ea-5a699840317d_88495664-04bf-43d1-93fd-d2afd216d7f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.753, 0.294, 0.785, 0.31] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/33064851-00d9-46c8-b0b7-6b5048005c51_5b1347ea-791a-4e8d-bc7b-db15fe3375e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[textbox] First name -> CLICK\n[textbox] First name -> TYPE: SHELDON\n[textbox] Last name -> CLICK\n[textbox] Last name -> TYPE: COOPER\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.499, 0.361, 0.589, 0.385] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_7c4bf048-7214-4ba9-aa74-822f50390427.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Transmission -> CLICK\n[span] Automatic -> CLICK\n[button] Back to all categories -> CLICK\n[heading] Distance & Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.322, 0.237, 0.344] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90a0f029-c1af-4dd7-8ccd-c4c2a74e8731_bd2e6fd5-bbac-40dc-8a8b-1f2ed8eb5c07.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[span] San Francisco, CA -> CLICK\n[textbox] Departure -> CLICK\n[button] Tuesday, April 11, 2023 -> CLICK\n[button] Friday, April 14, 2023 -> CLICK\n[button] 1 Traveler -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.501, 0.194, 0.532, 0.21] in the image\nAnd my action is Action: TYPE\nValue: 1" } ]

{ "bytes": "", "path": "./images/117c1176-b5bd-4b9a-9be2-80a7f390e207_1a347d26-3f20-44c8-8030-c09a8ae8ec9a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 US box office revenue for the highest tomatometer rated movie that the actress playing Sam Carpenter in the most recent Scream movie has been in.\nPrevious actions:\n[textbox] Search -> TYPE: scream\n[p] Neve Campbell, Courteney Cox, David Arquette -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.629, 0.195, 0.695, 0.229] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c577209-47dc-4645-8d10-0b659663a969_338aee04-6bae-4c3a-b3c3-1a8a12a61210.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 score of the latest nba game played by the phoenix suns.\nPrevious actions:\n[combobox] Search query -> TYPE: phoenix suns" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.22, 0.119, 0.727, 0.165] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/928ec908-ea23-42a4-8b13-3ca6f0721ead_9d934934-db77-4af8-89ca-56dfc9f9f1c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter search results for guitar tabs to only show songs with a difficulty rating of \"Beginner\"\nPrevious actions:\n[link] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.166, 0.153, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_73fac390-4a7e-41a3-814e-caa47a3ad866.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Chhatrapati Shivaji Intl -> CLICK\n[textbox] Flight destination input -> TYPE: Dubai\n[span] Dubai, United Arab Emirates -> CLICK\n[svg] -> CLICK\n[tab] One-way -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.706, 0.156, 0.928, 0.193] in the image\nAnd my action is Action: CLICK" } ]