Datasets:

neulab

/

Mind2Web_train_llava

like 2

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_4b926a9c-fd06-48cd-b8dd-62a5b7d509a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK\n[button] Continue -> CLICK\n[textbox] Credit card number -> TYPE: 123456789\n[combobox] Expiration month  * -> TYPE: 01" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.66, 0.492, 0.677] in the image\nAnd my action is Action: SELECT\nValue: 2024" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_1bbbf339-0ff9-4326-b590-da7e3b92be27.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] Military & Veterans -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: nevada city\n[span] Nevada City -> CLICK\n[span] 4831 Granite Dr -> CLICK\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.589, 0.41, 0.691, 0.427] in the image\nAnd my action is Action: SELECT\nValue: June 2023" } ]

{ "bytes": "", "path": "./images/4f069a59-c53b-4efe-bcfb-fc9fd864ea2e_2e04274f-f7b0-447f-a96d-7094c9e50f25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rare books and sort the results by auction end time.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: rare books\n[button] Search -> CLICK\n[link] Auction -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.628, 0.088, 0.792, 0.102] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b18e5e4-4873-49bf-b422-c3f5bc5d1f33_66efeee7-26da-4ccc-a8eb-1cb6b87f7b7b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 WWE ticket for price range between $50 to $100.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.599, 0.141, 0.612] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b6316ee-4cfb-490e-bf52-9ee6cdded08b_b77ac57b-8075-4c8d-8104-6551fac80aa0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ideas and recommendation for things to do in Cancun.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.311, 0.463, 0.321] in the image\nAnd my action is Action: TYPE\nValue: cancun" } ]

{ "bytes": "", "path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_91398ccf-62f2-4b00-99e8-538f8dc83ff1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[link] Collectibles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.309, 0.173, 0.319] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_79195bd7-6e14-43c7-818b-83aa994a0f60.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[button] Browse Vehicles -> CLICK\n[checkbox] SUVs -> CLICK\n[checkbox] 2+ -> CLICK\n[button] Select Nissan Kicks Vehicle -> CLICK\n[button] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.799, 0.31, 0.951, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_671005f8-0412-404e-b398-ad5476ea00cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[link] Gifting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.77, 0.052, 0.913, 0.07] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cac423-4be9-4f74-9031-7cef1fe60ef9_1553af30-7f22-4c4d-8037-4ac6c3a3b72b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fuel economy for a 2005 Toyota Corolla\nPrevious actions:\n[link] Price New/Used -> CLICK\n[combobox] Year -> SELECT: 2005\n[combobox] Make -> SELECT: Toyota" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.278, 0.355, 0.508, 0.392] in the image\nAnd my action is Action: SELECT\nValue: Corolla" } ]

{ "bytes": "", "path": "./images/44dcda68-082c-455a-a409-7091470cc006_d99edb30-3e73-492f-ab89-8e248147726d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[listbox] hour -> SELECT: 15\n[svg] -> CLICK\n[button] Add railcard -> CLICK\n[listbox] Select railcard 01 -> SELECT: Veterans Railcard\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.277, 0.327, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6080a77-ec5d-44d6-a51e-0b4ca0d50879_9e41be5e-d1a9-4ae3-82bb-2d9cf7e3fd22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of critic reviews for the movie Creed III.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: creed III\n[div] Creed III -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.803, 0.166, 0.896, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6fd2a5e9-12e7-4f3c-bf1b-42702d56105e_db9f5f4a-cfd7-4ca7-9dd7-e73dd9314048.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 park in the National Park System that is related to the topics of Industry and also Laborer and Worker.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[link] Search by Activity or Topic -> CLICK\n[button] Topic -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.139, 0.679, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_59857729-5631-4bd5-be03-ae871b6c7549.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[img] james9091 -> CLICK\n[link] Playlists -> CLICK\n[link] NEW PLAYLIST -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.043, 0.091, 0.173, 0.117] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f0988e0-e3a4-4dd7-a89f-482175a474a8_a684c98a-c238-4bef-b2ad-f476f07d73f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Wheelchair accessible parking for April 09 event in Barclays Center that allows entry after 10am\nPrevious actions:\n[textbox] Select Event Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK\n[p] Philadelphia 76ers at Brooklyn Nets -> CLICK\n[button] Filter -> CLICK\n[checkbox] Wheelchair Accessible (18) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.677, 0.458, 0.714] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14a4e19d-d82d-45dd-b4f0-6b60ed87d085_9d995e9a-9209-44b2-995e-c789e80640fe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\n[img] -> CLICK\n[link] Deals -> CLICK\n[div] Add -> CLICK\n[span] Add -> CLICK\n[link] View More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.22, 0.367, 0.241] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2ef470ab-b06a-4479-883f-78b4e3b94a04_a73e46ae-d077-4494-bbb6-3e900105e7b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[span] Cultural Tours -> CLICK\n[span] Any -> CLICK\n[li] -> CLICK\n[spinbutton] Max Price -> TYPE: 75\n[span] mm/dd/yyyy-mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.218, 0.312, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_5e1367e4-40be-4bd7-a0e7-0f4cea0043e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] TYO -> CLICK\n[span] Where to? -> TYPE: NEW DELHI\n[b] DEL -> CLICK\n[button] Choose departure date -> CLICK\n[checkbox] 5 June 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.844, 0.273, 0.93, 0.307] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2f8b054-59b5-4fd8-bd58-9f95b29f979d_98fac87d-a77e-45a6-be35-d7582402efd9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[link] Cars for Sale -> CLICK\n[textbox] ZIP Code -> TYPE: 07055" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.183, 0.211, 0.204] in the image\nAnd my action is Action: SELECT\nValue: 100 Miles" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_05ee4572-3449-45bc-81de-0ca98ab19c32.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[link] Shop Pre-Orders -> CLICK\n[button] Franchise -> CLICK\n[checkbox] Resident Evil Resident Evil -> CLICK\n[button] Done -> CLICK\n[heading] Resident Evil 4 - Xbox Series X -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.358, 0.751, 0.39] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_09094d31-83aa-4538-842f-a3d990b2c0f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[button] Find & Reserve -> CLICK\n[link] Book Meetings & Events -> CLICK\n[heading] Weddings -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Wedding -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.403, 0.336, 0.432] in the image\nAnd my action is Action: TYPE\nValue: Venice Beach" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_1bc3cce0-b1be-4e81-8248-4525ffd46b09.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my parking space in Houston. Name: James Smith, Email: [email protected], phone: 8888888888. Address: 123rd st.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.217, 0.69, 0.329, 0.701] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a35becb-e07b-4235-8cd3-fc2a29f8dd6f_e4a9cbd4-088d-4619-bea8-f2012f168a59.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the most most popular of all time tab to a playlist\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.064, 0.176, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_a0d343ae-e59d-44b8-abfb-e1ed3c0df2d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Like A Virgin -> CLICK\n[button] Add to List -> CLICK\n[combobox] List -> SELECT: New\n[button] Save -> CLICK\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.051, 0.188, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aae9804-0765-4e14-ab71-4dc13ada32f7_585b6e77-b0da-452f-b0c9-97e223fc786a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 camping tents that can fit 6 people and sort the results by price from low to high.\nPrevious actions:\n[button] Camp & Hike -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.199, 0.377, 0.21] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_60a55e3d-54ea-4570-8fe0-92972c015964.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.08, 0.421, 0.105] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_28857cab-172b-4651-b610-831598ecf7e4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.029, 0.05, 0.06, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd4df5fa-2c90-4a76-b4b0-0ca7bcdac2ee_d25fbaa1-54f2-4aaa-9446-6f113794dfc7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a train ticket with seat from Berlin to Zurich on March 31 after 8 am in aisle quite zone in side by side seat formation.\nPrevious actions:\n[div] -> CLICK\n[heading] to next step -> CLICK\n[div] -> CLICK\n[div] -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.693, 0.341, 0.926, 0.387] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e0ff7945-56b0-487a-920b-cbf954e6fb72_bbe959f7-08e3-4dfd-b80b-b837caab3e9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[button] Today -> CLICK\n[button] April 12, 2023. -> CLICK\n[button] View more availability for BayLeaf Modern Indian C... -> CLICK\n[button] 8:15 PM Table -> CLICK\n[button] Reserve Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.325, 0.523, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9215395-70cd-4da5-af99-9ba36cde858a_e9787ce7-b544-442f-bfc9-3c56c68ad182.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trailer for a new winter show from HBO.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.751, 0.141, 0.851, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_b07896e7-2e85-4045-9080-9134edeafe41.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.004, 0.204, 0.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_47c0995c-7238-4f67-8bfd-dcb9ebad4a86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: calculate a car loan payment for a $25000 car with a $5000 down payment and 12 percent interest rate for 48 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK\n[input] -> TYPE: 25000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.198, 0.473, 0.217] in the image\nAnd my action is Action: TYPE\nValue: 5000" } ]

{ "bytes": "", "path": "./images/6da08512-9375-4b47-8cd1-addec58f385c_08af7cdf-e95d-4875-a679-c15c9c08e85b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 musical instruments and filter the results to show only those that are available for free local pickup.\nPrevious actions:\n[combobox] Search for anything -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.02, 0.652, 0.035] in the image\nAnd my action is Action: TYPE\nValue: musical instruments" } ]

{ "bytes": "", "path": "./images/1ba150cb-3b4a-4f0a-bff0-b448c78608ae_dd0d509f-3050-4610-baa3-cd8f57e8ab83.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel deals in Las Vegas for four adults starting on May 17 and ending on May 20, and if deal is not available, set an alert for the same.\nPrevious actions:\n[textbox] When? -> CLICK\n[link] 17 -> CLICK\n[link] 20 -> CLICK\n[combobox] How many guests? -> SELECT: 4 Guests\n[button] SEARCH DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.404, 0.381, 0.596, 0.418] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_d1c3e4dc-571d-4ee7-84e2-6751f69713c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[link] Shop by category∨ -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.209, 0.176, 0.225] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edb8e817-e9d7-45eb-9706-01967e3a0fe8_507573e9-3eef-41c7-833f-a9992b520d5e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offer to sell car with AZ XA1234 number plate from Arizona state.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.435, 0.185, 0.536, 0.218] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d338fef-6d40-4f08-a045-861ddbc3d9f4_88a2761a-0c07-43a1-b931-1b8f81bb2cea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 glamping locations in Northern California.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.019, 0.68, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4f8a347-b288-4a00-9e6b-89cbccda42d2_fb0bb348-ec09-4106-a0c6-5072cb5a070c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking near any airport in california starting april 20 and ending april 23\nPrevious actions:\n[link] View All Airports -> CLICK\n[link] Reserve Now -> CLICK\n[textbox] Select Start Date -> CLICK\n[gridcell] Thu Apr 20 2023 -> CLICK\n[textbox] Select End Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.187, 0.173, 0.201, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b02e47ac-c1a6-4f5c-886f-f32af745e7f3_8ed5187f-287c-40c5-9ca9-9a142fb87136.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View a reservation made under the last name Walker in Australia for a car using the reservation confirmation number A987654.\nPrevious actions:\n[link] close dialog -> CLICK\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK\n[combobox] Select Residency -> SELECT: AUSTRALIA\n[input] -> TYPE: Walker" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.581, 0.347, 0.902, 0.387] in the image\nAnd my action is Action: TYPE\nValue: A987654" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_98de417c-491c-4137-a8d7-1071dc6e1f4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Finance -> CLICK\n[button] Time Type -> CLICK\n[searchbox] Search -> CLICK\n[option] Full time -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.443, 0.32, 0.485] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdd9ef05-4d5b-4469-b001-8d73b6dc8120_5f599e93-da0c-4046-a99f-5ee9b6b91c4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the documents required to sell a car in New Jersey for which payments are being paid and it has single person on the title who can come to the store\nPrevious actions:\n[link] Sell/Trade -> CLICK\n[combobox] In what state are you selling the car? -> SELECT: New Jersey\n[radio] Yes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.563, 0.667, 0.6] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/63e3020c-bf52-4950-9e26-50f98a59b5e3_80ec2d6b-ccfc-4134-88b5-e9ae4967039e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fast responding highest-rated electrician, who is currently open for replacement of some light fixtures in Westminster, and request a quote.\nPrevious actions:\n[link] Home Services -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.238, 0.138, 0.36, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_0a22a18c-983e-446f-871f-d2fd71f2c9ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: mumbai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.198, 0.795, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ea9ac0d-8c31-49bc-aa3d-e85b80580409_cfaf73bf-07fa-433e-a651-8c1c4a4a633c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight schedule between London and New York for April 7 and check the upgrade details of the noon flight.\nPrevious actions:\n[span] London -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: new york\n[span] New York -> CLICK\n[generic] Apr 6, 2023 -> CLICK\n[option] Apr 7, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.257, 0.478, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_e390e8f2-c563-4082-b220-e8544fd3f37d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[menuitem] 100 miles -> CLICK\n[input] -> CLICK\n[button] Back to all categories -> CLICK\n[button] Make -> CLICK\n[listitem] Honda (116) Honda (116) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.171, 0.249, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/930803d7-4032-4144-89a2-e44f3c5c9ccf_9af5e2bf-542b-482b-b479-2cdead789a25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy tickets for a group at Hurricane harbor Phoenix on April 22\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Hurricane Harbor Phoenix -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.208, 0.843, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_853848fa-4225-4177-814e-f29de4ed4f5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[div] Recent Stations -> CLICK\n[searchbox] To -> TYPE: stoney brook\n[span] Stony Brook -> CLICK\n[select] 1 -> SELECT: 10\n[select] 00 -> SELECT: 00" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.405, 0.855, 0.44] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_289cdf09-4bfc-4ba0-affb-bf06c4b47593.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Hotels -> CLICK\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.605, 0.223, 0.643, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_a3853221-cf8e-4f1e-a89b-0d1e3fd620b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.959, 0.012, 0.984, 0.04] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_a94fc7a4-d560-4fa5-a4ab-7c97572032f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check flight status for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Flight status -> CLICK\n[generic] Apr 7, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.426, 0.349, 0.456] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_f3dc63f7-80a7-4979-99bd-7bda15aee89c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[button] Reservations -> CLICK\n[link] Make a Reservation -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[span] , United States -> CLICK\n[link] click here -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.154, 0.657, 0.182] in the image\nAnd my action is Action: TYPE\nValue: Ohare, Chicago" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_17ca5c93-6288-40dc-9018-691a97dc13d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[heading] Chicago O'Hare International Airport -> CLICK\n[textbox] Drop-off location -> TYPE: 123 Main St, West Chicago, IL\n[heading] 123 Main St -> CLICK\n[button] pickup date input field -> CLICK\n[button] 29, March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.644, 0.129, 0.73, 0.164] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff173880-e7f5-4b4e-b941-79e9c3504add_a229ef07-963b-4d03-aacc-695b5b923058.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Products -> CLICK\n[button] Home décor -> CLICK\n[link] Mirrors -> CLICK\n[link] Wall mirrors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.451, 0.333, 0.554, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_c7e2d653-d028-48ff-987d-7d48b3fc1bbd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[textbox] mm/dd/yyyy -> CLICK\n[select] April 2023 -> SELECT: June 2023\n[link] 6 -> CLICK\n[combobox] Pick Up Time -> SELECT: 11:00 AM\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.589, 0.62, 0.691, 0.64] in the image\nAnd my action is Action: SELECT\nValue: June 2023" } ]

{ "bytes": "", "path": "./images/b7003092-3e6e-4fac-9867-083cac064f89_f00afcea-c60d-4746-b705-8abad5a4a61c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find JetBlue career openings in New York\nPrevious actions:\n[link] CareersExternal Link should open in a new window o... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.406, 0.455, 0.688, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c7a69f9-989d-4899-a3fe-94c952859007_9732a0c7-bde5-479e-b4db-527fa1212bff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Chicago to London on 20 April and return on 23 April.\nPrevious actions:\n[textbox] From -> TYPE: Chicago\n[a] CHI - Chicago, IL -> CLICK\n[textbox] To -> TYPE: London" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.348, 0.525, 0.641, 0.55] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd057bda-33ea-40b8-9865-771242e22f40_e24783c6-df28-49de-a73f-cdf3cf4500a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fiction audio books sorted by lowest price.\nPrevious actions:\n[link] Shop by category∨ -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.177, 0.112, 0.331, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_c0bd78c0-c5b3-4607-9f24-fa07181701a2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] From -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.23, 0.359, 0.256] in the image\nAnd my action is Action: TYPE\nValue: empire state building" } ]

{ "bytes": "", "path": "./images/82f654ab-fbfe-43f2-a2fe-0001b2ac853f_f083d98e-f278-4e39-9c59-c02d95e8dd2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights from New York City to London and filter the results to show only non-stop flights.\nPrevious actions:\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 [0.313, 0.126, 0.321, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_ca2a9f0f-84e9-4e41-9462-32f12264b4ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Size -> CLICK\n[span] Now Trending -> CLICK\n[li] Newest -> CLICK\n[button] Add to Wish List -> CLICK\n[button] Add to Wish List -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.925, 0.136, 0.947, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_6506aee3-cdd1-4f39-b9ff-4968228cfcda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[button] Find -> CLICK\n[link]  All Filters -> CLICK\n[heading] Amenities  -> CLICK\n[label] Business center (11) -> CLICK\n[label] High-speed Internet (11) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.86, 0.789, 0.96, 0.823] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_1d37262b-2901-4468-bb2f-f5a9dd9e95b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] Select a trip start date -> CLICK\n[gridcell] Wednesday, April 5, 2023 -> CLICK\n[button] Done -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.774, 0.573, 0.957, 0.701] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2cb6558b-3dd7-4acd-a495-a4d3b96369ad_798b286b-adb3-4c20-b60c-f9d140ca52ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of convertible cars for sale under 20000.\nPrevious actions:\n[button] Car Sales -> CLICK\n[link] Shop Vehicles Under $20,000 Link opens in a new wi... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.382, 0.225, 0.399] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10de6ac5-a69e-4d09-87fd-5737ca6f4b99_f3a45444-8db6-4965-b692-96e995ab489b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket listing on floor B row 17 seat listing to Beyoncé music concert on Mon Aug 14 at 7:00pm.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.016, 0.211, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_66ecd249-ed96-47a9-9e83-29e6d273fb6b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[button] Transit  -> CLICK\n[link] Parking -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.434, 0.863, 0.464] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_88859090-cc5c-4b82-b5cc-3a7c2cce4f4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] SEARCH -> CLICK\n[span] Sort and filter -> CLICK\n[div] -> CLICK\n[checkbox] 4 stars rating -> CLICK\n[radio] Lowest price first -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.48, 0.791, 0.507] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_1bf42320-592b-4bfb-8141-a292892eb093.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[textbox] Search for parking -> TYPE: street taco\n[li] Street Taco, Broadway, New York, NY, USA -> CLICK\n[textbox] Monthly Start Date -> CLICK\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.223, 0.3, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/862faed7-449c-4624-902b-6b512a977d0c_60b25c01-6a9c-456e-a2de-296e7090b8c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: surge protector\n[button] surge protector -> CLICK\n[link] Surge Protectors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.557, 0.097, 0.572] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_9912f695-1f04-491d-bcb4-dcc99b5eb3ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[input] -> TYPE: 05/05/1995\n[input] -> TYPE: Texas city\n[input] -> TYPE: 252-654-5258\n[input] -> TYPE: [email protected]\n[input] -> TYPE: Anderson" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.495, 0.147, 0.769, 0.176] in the image\nAnd my action is Action: TYPE\nValue: po box 2846" } ]

{ "bytes": "", "path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_0bfd0d38-184d-4d8a-9764-9b845095d0df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[button] Marketplace -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.098, 0.475, 0.125] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_92db244d-ca13-4885-8d45-87f3df9a87c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[searchbox] Search -> TYPE: gobites uno spork\n[button] Search -> CLICK\n[img] humangear GoBites Uno Spork 0 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.684, 0.269, 0.723, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_22ad9507-f8b7-4f15-bd7f-c0f99312acd7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[div] 4 -> CLICK\n[svg] -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.543, 0.181, 0.815, 0.219] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/330d5618-9db4-447b-9b56-0d2c33f414d5_769575d0-1e94-4299-9e76-4b79f5704861.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the full menu for AMC dine-in locations.\nPrevious actions:\n[link] Visit the Food & Drinks page -> CLICK\n[link] Explore Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.748, 0.172, 0.782] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/df73be67-e81a-444f-82cc-e69d54a72734_7322835c-5bca-4b29-a680-c8d122209a40.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the gift shops available at a park in New York\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Darien Lake -> CLICK\n[button] Go! -> CLICK\n[link] Rides & Experiences  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.473, 0.206, 0.654, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1860601a-faef-4dba-8cbb-807ea8434dca_31f0c71f-7a90-4fa6-beac-319af1442002.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[combobox] Origin -> CLICK\n[combobox] Origin -> TYPE: New York\n[p] New York City -> CLICK\n[combobox] Destination -> CLICK\n[combobox] Destination -> TYPE: Tokyo" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.236, 0.318, 0.403, 0.347] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5a0a291-ef9c-408d-9505-af7aeb6f5280_ed7b5274-aae9-47a3-8b14-63e67b3f171c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Railcard options for a 20 year old couple traveling within London and the South East\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK\n[menuitem] Railcards -> CLICK\n[combobox] How old are you? -> SELECT: 18-25\n[combobox] Who do you usually travel with? -> SELECT: Couple" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.689, 0.186, 0.941, 0.219] in the image\nAnd my action is Action: SELECT\nValue: Yes" } ]

{ "bytes": "", "path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_a17e5768-0ac8-450e-af82-4b7c2656c3ad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[label] Nearest distance -> CLICK\n[button] Back to all categories -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Change Location -> CLICK\n[textbox] Enter ZIP or State -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.265, 0.113, 0.703, 0.129] in the image\nAnd my action is Action: TYPE\nValue: 07055" } ]

{ "bytes": "", "path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_48650296-30f6-4c10-90bc-b65a4f8d92c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[link] Search for flights -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.089, 0.292, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/66d12284-5525-42d2-a66f-fe5c460b7764_bc74f169-259e-446a-a63b-77e3f990d729.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order popcorn at AMC Grove City 14\nPrevious actions:\n[link] Visit the Food & Drinks page -> HOVER\n[link] Order Food & Drinks -> CLICK\n[select] AMC Columbus 10 -> SELECT: AMC Grove City 14\n[button] Order Now -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.418, 0.182, 0.439] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_005bc9e7-3f90-4be3-9512-4e6c3fc9517d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] Depart , required. -> TYPE: 04/19/2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.439, 0.29, 0.461] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_b0a24212-9aae-4fbc-a62d-bc7129890aec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.145, 0.782, 0.172] in the image\nAnd my action is Action: TYPE\nValue: red sox vs yankees" } ]

{ "bytes": "", "path": "./images/d538537c-ff96-4918-8807-af09b26199d1_d8aed545-1860-46ac-a290-ce24e2ee12b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 -> TYPE: SFO\n[div] San Francisco Int'l (San Francisco) - -> CLICK\n[textbox] Destination -> CLICK\n[textbox] Destination -> TYPE: EWR\n[div] Newark Liberty Intl (Newark) - -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.283, 0.639, 0.291] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_bac24a0f-8c3f-47d7-8870-0facc3b7352b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[button] 03/25/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM\n[button] Browse Vehicles -> CLICK\n[combobox] SORT BY -> SELECT: Price: Low to High\n[button] Select Mitsubishi Mirage Vehicle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.799, 0.169, 0.951, 0.204] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bdc1f69a-da73-4e51-9dd8-83494d4983c2_b068a66c-b3fe-4991-a9c1-b534eac1c4ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 check-in flight for John Smith having ticket no. 123456780\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.021, 0.466, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_1d0ce156-c4ff-462f-9503-71e97ddc7bc5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[link] Large cars 5 Seats 3 Large bags -> CLICK\n[ins] -> CLICK\n[ins] -> CLICK\n[ins] -> CLICK\n[link] Show all 10 cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.839, 0.259, 0.974, 0.28] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff82e848-f29e-477b-a286-c807cbd0d8fa_85e67d52-dbf2-4548-bc57-7030b7d926c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[link] Careers This link will take you away from the Qata... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.316, 0.494, 0.511] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_ade4eacb-a963-445c-bb0d-c025a8ac3b47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[searchbox] From -> TYPE: brooklyn\n[listitem] Brooklyn, NY, USA -> CLICK\n[searchbox] To -> TYPE: staten island\n[listitem] Staten Island, NY, USA -> CLICK\n[button] Leave now Change Time -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.372, 0.359, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/370a037c-c397-4adb-ab7c-0c388f448f68_4c7b25a2-d944-488e-ab04-8558592e50ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vinyl records at the lowest price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.465, 0.0, 0.557, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/126b4604-8b04-4eb1-9027-266631c96f01_db04e65a-c4bc-47b4-90cb-2a233cee4a12.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.517, 0.153, 0.647, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/64779409-c396-4779-a574-b219c3b22282_7f72659d-d09a-4ec5-8d21-174f5ad2b87e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 longest skiing activity in August 10\nPrevious actions:\n[textbox] Where to? -> TYPE: skiing\n[button] When -> CLICK\n[button] Next -> CLICK\n[path] -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.318, 0.777, 0.331] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab989f1e-bacb-4c37-ab81-c8f24ee3284b_cf49630d-7148-4457-b45c-0bc7ccde4df7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 special timetable for Far Rockaway Branch of the Long Island Railroad.\nPrevious actions:\n[link] Schedules -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.142, 0.875, 0.156] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6407babe-fe48-492a-8211-1f22a81b9ac0_52d7c938-aadd-4349-b61b-4db12d69371b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 men's running shoes of size 9 with lowest price and add to bag.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.35, 0.039, 0.391, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1282a011-194c-40c4-8f76-875e502cdd53_17bb4834-cbfd-40cc-84dc-8a06cb5be3d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 laptops with at least 16gb of ram and under $700.\nPrevious actions:\n[button]  -> CLICK\n[textbox] price to -> TYPE: 700\n[button] APPLY -> CLICK\n[dt] Memory -> CLICK\n[span] Show -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.62, 0.158, 0.629] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/725c38e7-7987-40b3-8f19-8450f8277f06_f9eba4a9-dc63-44b8-9382-822cac46e582.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest event to attend in Athens, Greece on April 2nd\nPrevious actions:\n[button] Greece -> CLICK\n[button] Athens -> CLICK\n[button] Go! -> CLICK\n[div] Sort by -> CLICK\n[div] Lowest price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.31, 0.176, 0.359, 0.193] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_2193b3f2-8f8a-4bca-b688-831462294ca0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.053, 0.441, 0.085] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_6daab355-c31f-4f01-9790-b621f663409c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[svg] -> CLICK\n[link] Luxury Car Rental -> CLICK\n[label] Pick-up location -> TYPE: north las vegas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.243, 0.438, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/984f5bdb-d6d0-4b9d-ae23-bee8283a4f40_efb82e4d-b2c7-4b75-9125-34401b88bb10.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2-5 day cruises to the Caribbean from Miami during August 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.373, 0.746, 0.529] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fe6b5531-ce29-4ba1-8e98-43b5fecf57fa_ea2935b1-0eeb-4873-985f-fcf52085b341.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from London to New York on 9th May.\nPrevious actions:\n[option] Destination London -> CLICK\n[combobox] Flying to -> TYPE: New York\n[option] Destination New York (NY) -> CLICK\n[span] 9 -> CLICK\n[button] SEARCH FLIGHTS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.327, 0.816, 0.357] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_4fdc91b7-4ecb-4279-81f3-3e53e6e92071.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[span] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: SHANGHAI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.301, 0.448, 0.34] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_2edb2388-3a5b-444f-9824-2bd1e69cbf18.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[link] Fishing -> CLICK\n[menuitem] View All -> CLICK\n[label] Ice Fishing -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.401, 0.106, 0.411] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/706d0ccd-c0ec-423d-88c0-a5716700a855_5d3e3c95-6cc7-41d8-923c-a543635c2643.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\n[link] Crossover vehicle icon Crossovers -> CLICK\n[button] Make -> CLICK\n[listitem] BMW (389) BMW (389) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Model -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.289, 0.045, 0.309] in the image\nAnd my action is Action: CLICK" } ]