Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/5a181549-c79c-499c-b7d7-90860f0e0068_2682ad2f-8cd9-4b44-a3ac-40ed813b6192.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play Trailer of \"The Flash\" 2023.\nPrevious actions:\n[textbox] Search IMDb -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.28, 0.156, 0.298] in the image\nAnd my action is Action: TYPE\nValue: The Flash" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_5a39e836-5fa1-4b38-b70d-d1191480b770.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[span] Special events -> CLICK\n[DisclosureTriangle] All locations -> CLICK\n[li] NYC -> CLICK\n[DisclosureTriangle] All Categories -> CLICK\n[li] Outdoors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.215, 0.165, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_d01a0aa8-14a8-454c-8544-dcc082a22324.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Driscoll's Organic Strawberries -> CLICK\n[span] All stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.225, 0.011, 0.776, 0.063] in the image\nAnd my action is Action: TYPE\nValue: organic strawberries" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_38ec61e1-77aa-4f6f-9bfe-c062d0f80e62.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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: Neo\n[input] -> TYPE: Thomas\n[input] -> TYPE: 05/05/1995\n[input] -> TYPE: Texas city\n[input] -> TYPE: 252-654-5258" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.495, 0.076, 0.769, 0.103] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_149c287a-3fb6-4483-929b-aee42e6e4527.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[span] Add -> CLICK\n[span] Add -> CLICK\n[link] Herbs -> CLICK\n[div] Add -> CLICK\n[button] View Cart. Items in cart: 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.917, 0.015, 0.981, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_07e08472-af90-4513-b934-c8893026dfc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[link] 22 -> CLICK\n[button] Continue -> CLICK\n[div] + -> CLICK\n[textbox] About Your Trip: -> TYPE: Wedding Anniversary\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.226, 0.711, 0.25] in the image\nAnd my action is Action: TYPE\nValue: John" } ]

{ "bytes": "", "path": "./images/4f069a59-c53b-4efe-bcfb-fc9fd864ea2e_c3c62fdc-7f5f-4b13-a9e0-2fce42f49db2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.202, 0.027, 0.665, 0.048] in the image\nAnd my action is Action: TYPE\nValue: rare books" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_33cacba9-a4ac-459b-a7a0-8010dfef19e4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[span] -> CLICK\n[combobox] Sort by -> SELECT: Most recent\n[span] Analyst - Sales Programs -> CLICK\n[button] Apply Now -> CLICK\n[textbox] Email * is a required field. -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.781, 0.132, 0.824] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8eae88ef-9641-43c6-be6d-f8abc96d99fa_d4367241-a990-4cdb-909e-2a0e80135606.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\n[link] PS5 Accessories -> CLICK\n[generic] Controller -> CLICK\n[span] Sony -> CLICK\n[button] APPLY -> CLICK\n[span] Free Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.318, 0.192, 0.328] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e0ff7945-56b0-487a-920b-cbf954e6fb72_a89299a2-03da-445f-bad6-2ab49df34fa8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] New York -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: indian\n[b] Indian -> CLICK\n[button] Today -> CLICK\n[button] April 12, 2023. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.176, 0.542, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a698566-2a8f-4d9d-9da9-17288b66917f_e63e526c-0f1e-4a26-8fb7-bcdabb7c51d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Tokyo for two adults and one child, with a budget of $500 per night for 2 nights starting on May 5th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.195, 0.491, 0.829, 0.508] in the image\nAnd my action is Action: TYPE\nValue: Tokyo" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_ea03253e-d374-4d74-ad87-4190b34c30c7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: Nintendo Switch Console\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.712, 0.147, 0.734] in the image\nAnd my action is Action: TYPE\nValue: 400" } ]

{ "bytes": "", "path": "./images/1203a016-d541-4914-9cdb-f042ad0abcf5_94b84afe-117d-4fd2-a611-616055f7a86a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Anime TV shows and sorty by Newest\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[svg] -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.34, 0.36, 0.36, 0.375] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2c19d467-4e44-4c0d-b050-a13823ca545d_89834bb1-075b-4540-8bbe-88224a51cb0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hard side Carry-on Luggage used for business in black color.\nPrevious actions:\n[svg] -> CLICK\n[button] Color -> CLICK\n[div] -> CLICK\n[svg] -> CLICK\n[button] Used for -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.106, 0.796, 0.12] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7c28f4e3-3dcf-477b-98c3-087c4fc16655_dc8e26e9-cdcf-4135-b829-4ef2137c2758.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store which is nearest to 10017 zip code.\nPrevious actions:\n[link] Store Locator -> CLICK\n[searchbox] Postal code, address, store name -> TYPE: 10017\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.45, 0.362, 0.997, 0.43] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/593830ff-fd2c-4479-abf8-8fddee2cdaea_a1454cf5-5c62-4137-82c2-813f8dd4073c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 brochure of Loss Damage Waiver Protection.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Products & Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.28, 0.93, 0.471] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81b6bba7-3d05-40a4-a475-48eaeacbda0d_de9053b8-703b-4782-a562-66e97a63276b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\n[div] Los Angeles -> CLICK\n[textbox] To -> TYPE: Miami\n[option] Mint. Miami area -> CLICK\n[button] Explore flights -> CLICK\n[span] 234 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.709, 0.196, 0.866, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_514bcfa3-e57a-4004-b98a-331a51bd1de1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[img] search icon -> CLICK\n[button] Trade in -> CLICK\n[link] Complete trade-in -> CLICK\n[button] Verify membership to continue -> CLICK\n[input] -> TYPE: Joe" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.396, 0.347, 0.438] in the image\nAnd my action is Action: TYPE\nValue: Bloggs" } ]

{ "bytes": "", "path": "./images/c0eeead1-f8ea-4819-a6da-ef0108b40c89_3b6ab224-8bd0-4206-ada8-7e14e8308314.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sign Allan Smith for email offers with the email [email protected] and zip code 10001\nPrevious actions:\n[textbox] First Name (required) -> TYPE: Allan\n[textbox] Last Name (required) -> TYPE: Smith\n[textbox] Email Address (required) -> TYPE: [email protected]\n[textbox] Confirm Email Address (required) -> TYPE: [email protected]\n[textbox] ZIP Code (required) -> TYPE: 10001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.668, 0.448, 0.754, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_cb175ec6-1b33-4e7b-a205-3e5fae52fd07.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Flight origin input -> TYPE: NEW YORK\n[span] All airports -> CLICK\n[textbox] Flight destination input -> TYPE: PARIS\n[span] All airports -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.609, 0.294, 0.641, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/690eedad-706c-4c48-a803-45b4f1c069bb_dfc898b1-8a15-4482-8e9f-563a8d77ae89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bestsellers under $20 and available in hardback.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.155, 0.082, 0.208, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_07db340a-8bc6-410d-9856-4888318261b4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[svg] -> CLICK\n[gridcell] 1 June 2023 -> CLICK\n[gridcell] 8 June 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.193, 0.157, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/920f240d-77a9-476b-a1d4-dcc88d199bfa_6cb303c4-1ce6-481a-aea4-4579b0be918e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rock music events in Canada, happening this weekend and save top three popular events for my record.\nPrevious actions:\n[link] Music -> CLICK\n[svg] -> CLICK\n[div] Canada -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.063, 0.407, 0.243, 0.44] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_76377685-cdd6-4780-bfd8-b03bd4dec0cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[span] Dublin -> CLICK\n[button] France -> CLICK\n[span] Paris Beauvais -> CLICK\n[generic] 26 -> CLICK\n[generic] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.706, 0.208, 0.725, 0.22] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf8da12a-e1fd-48b5-8c53-b88f301ca1e0_65009bac-a256-4768-969f-c64e4ac76638.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 video game consoles and filter the results to show only those that have Wi-Fi Capability.\nPrevious actions:\n[link] Electronics -> CLICK\n[button] Video Games & Consoles -> CLICK\n[link] Video Game Consoles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.902, 0.374, 0.955, 0.402] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/76514d5c-cc1c-40b0-8c08-427cedb106e4_6a5d4462-eb16-4b06-9b5d-e146aed21024.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for queen-size pillow protectors from the Marriot shop, and if found, add two pieces to the cart and checkout.\nPrevious actions:\n[button] Special Offers -> CLICK\n[link] Shop Marriott Opens a new window -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.196, 0.138, 0.248, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549452ab-637a-4997-bce1-5898541bb288_1cba5090-1401-4ce5-ab29-6dbb9aaaac26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all NFL tickets\nPrevious actions:\n[button] SPORTS -> HOVER\n[tab] NFL -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.342, 0.068, 0.455, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc27fdda-c68f-4d43-bbcb-6c7954bf00ec_ce1dba77-1add-4cad-889f-7a90b54c5ccb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[textbox] City -> CLICK\n[textbox] City -> TYPE: Cincinnati\n[combobox] State -> SELECT: OH\n[button] find store -> CLICK\n[button] filter by services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.247, 0.744, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/373dec75-7278-4d12-bcc3-0e802e337c4a_3f558697-ab28-4d4e-b047-333054eb40cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search for Tree stands with at least 3 stars, and sort the results by price from low to high.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Climbing Stands -> CLICK\n[svg] -> CLICK\n[label] .Stars::before { -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.221, 0.981, 0.24] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_0d3428c6-2527-45c7-9bb4-64c3bca723bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: BWI\n[button] Baltimore, MD, US (BWI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: NYC\n[button] New York, NY, US (NYC - All Airports) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.225, 0.144, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f804150b-c2e9-40ca-b71f-d0d0d95e0c46_c88bb1ab-d1fe-4205-af84-9542a145f787.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest hotel in New York City for 2 adults from Apr7 to Apr 8.\nPrevious actions:\n[link] Hotel , Opens another site in a new window that ma... -> CLICK\n[searchbox] Type your destination -> TYPE: New York City" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.212, 0.409, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_0bb44b72-6b4c-4892-a91f-d640f266ff44.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[checkbox] Resident Evil Resident Evil -> CLICK\n[button] Done -> CLICK\n[heading] Resident Evil 4 - Xbox Series X -> CLICK\n[span] Digital -> CLICK\n[li] Deluxe -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.266, 0.975, 0.286] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fb9c0e7f-02dd-453f-8c73-da19282abf84_4b195391-b9c2-4913-bfba-18cb820a9858.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ford Mustang with lowest price and save it.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.0, 0.605, 0.056] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8865ca64-0df2-4e3f-905d-a9e07e1eeb68_aa09ebe7-4fa3-49cd-9fd2-84b5ead50fa1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bike service charges for store at Lafayette St, 10013.\nPrevious actions:\n[button] Cycle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.747, 0.333, 0.944, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f3bf7fe9-6987-4153-81b4-4b51fe25bbbc_112135b7-86d9-4229-9794-e472f3ca4544.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental cars in Seattle, WA and filter the results by the Best score.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Seattle" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.163, 0.573, 0.2] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f122e4c9-7634-4193-94f9-8623cd75d1f1_61803cf9-7251-4771-ae40-e0694bec96e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Manchester Piccadilly to any station in London on April 8, leaving nearest 10 AM for 1 adult\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> CLICK\n[combobox] Departure station, none selected. Select a station... -> TYPE: Manchester\n[span] Manchester Piccadilly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.092, 0.326, 0.108] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5098c679-dacc-4abd-9331-18b898f936dd_cd74b537-1276-4126-bf2e-d2135aba47ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the St louis park policies regarding security?\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags St. Louis -> CLICK\n[button] Go! -> CLICK\n[link] Plan Your Visit  -> CLICK\n[link] Park Policies -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.359, 0.106, 0.372] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_03b96773-9634-4493-b857-612a778193b0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[div] 8+ -> CLICK\n[div] 3 -> CLICK\n[checkbox] Free internet -> CLICK\n[button] Style -> CLICK\n[checkbox] Family -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.541, 0.226, 0.554] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_ad4ae519-c48d-4921-9da8-b102cae1e64f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] 2010 -> CLICK\n[menuitem] 2017 -> CLICK\n[button] 2023 -> CLICK\n[menuitem] 2017 -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.321, 0.253, 0.362] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_e8ebcee6-59f0-4613-a5c7-fb120ac0a491.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] Going to -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.195, 0.568, 0.254] in the image\nAnd my action is Action: TYPE\nValue: national university of singapore" } ]

{ "bytes": "", "path": "./images/978760ca-7ec3-4b78-86c6-98b173c1a00e_72755349-6b54-4449-b255-f2560b342cae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow an artist from the chill category.\nPrevious actions:\n[searchbox] Search -> TYPE: Chill\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.169, 0.199, 0.191] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bd729e8-abb2-4649-bb81-8c790c04f8ad_0f8922cc-c34b-40d7-a6f4-4c095f40a94f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Paint -> CLICK\n[link] Painting Tools -> CLICK\n[button] 43229 -> TYPE: 44240\n[button] UPDATE -> CLICK\n[checkbox] Pickup at Store Eligible (86) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.346, 0.132, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4f8a347-b288-4a00-9e6b-89cbccda42d2_39e0fe3d-64be-40eb-a9b5-65dcf8a97695.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.318, 0.344, 0.337] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd057bda-33ea-40b8-9865-771242e22f40_33ed3481-1a77-422e-8dc8-adf0c11bec5a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Audio Books -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.49, 0.196, 0.515] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8027aa8-c193-47c8-a97b-432836093939_ebb6e2a1-73dd-4ef0-9dae-4f80fc30e110.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Las Vegas, NV that offer free airport shuttle service.\nPrevious actions:\n[link] Search for hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.17, 0.478, 0.212] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_c6afb333-db4f-4c5e-a453-f71572c34a7b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[textbox] To , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] Depart , required. -> TYPE: 04/19/2023\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: Heathrow" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.421, 0.393, 0.436] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a63b891b-4703-46ab-8633-b151b26574d1_00ea167e-ab9c-4cb5-ad27-3e2a9d4808c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 software requirements for iPhones that support live tv on demand streaming.\nPrevious actions:\n[link] Navigate to on-demand -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.192, 0.193, 0.312, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c73b1674-9c61-46a3-84dd-8fad3622a035_847bd686-a068-494a-b37e-7d5679ff8cd4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[textbox] From -> TYPE: new york\n[strong] New York -> CLICK\n[textbox] To -> TYPE: miami" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.329, 0.224, 0.615, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf008019-bffd-42ad-a48b-054488e1458c_69323266-e943-4d87-a9a3-c38c6a97683d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 near any NBA arena to enter today after 5 pm and exit after 8 pm\nPrevious actions:\n[link] View All Stadiums -> CLICK\n[link] Book Now -> CLICK\n[tab] Hourly -> CLICK\n[combobox] Start Time -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.161, 0.566, 0.181] in the image\nAnd my action is Action: SELECT\nValue: 8 00 PM" } ]

{ "bytes": "", "path": "./images/f2f531ff-94d5-4320-8594-7ae5d3a52af5_03e8e495-0e91-49be-902c-3a0f659ec428.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show top 50 Movies and TV shows by Sci fi genre.\nPrevious actions:\n[path] -> CLICK\n[span] Top 250 Movies -> CLICK\n[link] Sci-Fi -> CLICK\n[button] Open Navigation Drawer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.08, 0.628, 0.094] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/30d5f7dc-3650-4177-93bc-b59f1f5621f0_18882ce8-7875-4663-93ec-0807ef95ce96.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List pg-13 comedy movies currently in theatres with the highest audience scores\nPrevious actions:\n[link] MOVIES -> CLICK\n[svg] -> CLICK\n[select-label] Audience score (highest) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.179, 0.376, 0.198] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9e9c178-e945-49fe-9d06-a01cf02ab2db_ec54679e-f5df-407b-abb0-a75b7fe45356.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the highest rated spas that are $$ dollar signs and under.\nPrevious actions:\n[textbox] Find -> TYPE: spa\n[span] Spa -> CLICK\n[button] Price: -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.107, 0.122, 0.123, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a88676d0-c252-408f-b796-93c95f6b71fc_e8963296-becc-47f3-ad53-3d823ede9da4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open my trade offers.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.482, 0.0, 0.589, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6fd2a5e9-12e7-4f3c-bf1b-42702d56105e_f4d8f5c8-3590-4a21-a09a-085d4d732c2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.44, 0.141, 0.56, 0.149] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/708cbe51-b493-41da-afa8-648564133972_93da400b-38b2-4337-9b42-dae5b8caf0b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Flight schedules and notifications for a flight outside the us from BHZ to EWN leaving on april 30\nPrevious actions:\n[span] -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK\n[textbox] To , required. -> TYPE: ewn\n[a] EWN - Coastal Carolina Regional, NC -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.673, 0.231, 0.687, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55518089-52b9-4504-8e4f-885a9b2943a8_a0404d19-6c64-4ba4-943c-303f416d93ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of comedy movies, sorted by user ratings.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Browse Movies by Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.176, 0.278, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/93f3a9a1-2fd8-4457-b689-d70b3249b99b_03ea992d-d5ed-4a7f-a6a3-1d66a15aec50.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 with flight number 2819 on 18th of March.\nPrevious actions:\n[tab] FLIGHT STATUS -> CLICK\n[button]  Search by date required selected as 15 March 202... -> CLICK\n[link] 18 March 2023, Saturday -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.476, 0.45, 0.536, 0.478] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_03b3771e-2a05-4a39-8770-852b2e28652c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[button] Springfield, IL, US (SPI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: AUSTIN\n[button] Austin, TX, US (AUS) -> CLICK\n[span] -> CLICK\n[button] Find flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.101, 0.56, 0.145] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_5ad16225-5e2c-4a50-97f0-c7742c5bc261.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.668, 0.395, 0.699, 0.415] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_2a784ab8-38ce-492f-8942-69b903f33a57.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK\n[generic] Increase -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.115, 0.777, 0.141] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc202d2-4c12-48ca-b04b-b667aac49156_44b4fb46-9ac1-4433-a49f-92c78000593a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 benadryl items for Allergy Treatments in Liquid form.\nPrevious actions:\n[combobox] Search products and services -> TYPE: benadryl\n[button] Search for benadryl -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.551, 0.143, 0.564] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9723022-04b9-4778-ad33-cf54eac3d393_8b97f306-2eff-498a-8a45-2e113edfc5dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events starting from April 1, 2023 within 100 miles of New York and see who are going in the top listed event and follow all of them who are going.\nPrevious actions:\n[link] Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.198, 0.293, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aae9804-0765-4e14-ab71-4dc13ada32f7_2be5e5da-b142-4be7-9aca-8573136aa54e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.06, 0.128, 0.084] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eee72e78-71bd-434b-ba74-33888ea5522d_e4fe74f4-0455-4d58-a108-1d2820295a1a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: book the cheapest hotel in Le maraise neighborhood in paris with 2 room for 3 adult on March 27th to April 2nd.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Le maraise\n[span] Le Marais, Paris, France -> CLICK\n[div] 27 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.463, 0.209, 0.496, 0.231] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f738b393-9234-4c07-8baf-20f05627d5ed_5af0f370-33fa-497b-a075-0a6acbc1cb7f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-reviewed landscaper in West Hollywood for the design of lawn, who gives fast responses, and make sure he has a license verified by Yelp.\nPrevious actions:\n[span] West Hollywood -> CLICK\n[radio] Lawns or greenscapes -> CLICK\n[button] Fast-responding -> CLICK\n[button] Recommended -> CLICK\n[span] Most Reviewed -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.202, 0.519, 0.287, 0.532] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_cb306aa7-a977-4b22-a191-4e7ff1683495.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.515, 0.454, 0.535] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b54b029-bff8-49a7-acca-c57163f14279_69d92e43-3d66-42f1-b437-29280a51214b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find music events in Los Angeles today\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.152, 0.007, 0.491, 0.041] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4bce534f-3057-40ca-aecd-ffb07b3c9fcb_826632f8-5f08-404f-855b-b7b3374dfde3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the actor who won the Oscars for best actor in a suuporing role ine 1990, and add his upcoming movies to my watchlist.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Oscars -> CLICK\n[link] 1990 -> CLICK\n[link] Denzel Washington -> CLICK\n[button] Expand Upcoming -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.457, 0.059, 0.467] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c1a354a1-7990-4ca8-9fc5-2fdb1b5df337_40f87c26-9448-4531-b356-b08bfe0e831d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book in Hindi with ISBN 1648926800.\nPrevious actions:\n[link] Advanced Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.349, 0.342, 0.651, 0.374] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cd20dc6-d2a5-4e8f-9252-549f2c51413c_d06ad609-36ae-4f0b-8623-247fa123cbb0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 inventory of Tesla Model S that are blue and new with 19\" wheels within 50 miles of zip code 60602.\nPrevious actions:\n[link] Model S -> CLICK\n[link] View Inventory -> CLICK\n[image] -> CLICK\n[checkbox] 19\" Wheels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.048, 0.117, 0.273, 0.133] in the image\nAnd my action is Action: TYPE\nValue: 60602" } ]

{ "bytes": "", "path": "./images/cd8d723a-7a9f-4bd6-a8b9-75babb60835c_08a60925-4f62-45da-aa46-c69d90ef1915.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information on how to get a ticket refund.\nPrevious actions:\n[span] Help -> HOVER\n[div] Visit the help center -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.683, 0.607, 0.693] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_6cc4b85e-f193-43cb-a661-b6a4f7cb1c59.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[path] -> CLICK\n[combobox] Search by city or activity -> TYPE: Miami\n[generic] United States -> CLICK\n[button] SEARCH -> CLICK\n[span] Sort and filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.234, 0.137, 0.766, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4a9a05f8-6c23-46c5-bb38-eec63a477475_63c62cac-1560-44ee-baab-e349ce9a7fc5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adults only, airfare included vacations in Mexico during the month of May\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.193, 0.486, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_d4393929-345e-460d-859a-1600973ae800.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[tab] Trip Planner -> CLICK\n[combobox] From -> TYPE: brain\n[link] T red line bus commuter rail Zone 2 Braintree -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.544, 0.169, 0.807, 0.189] in the image\nAnd my action is Action: TYPE\nValue: boston" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_d571bd82-235d-4db6-a852-0ad4320383e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[link] HOTEL INTERNSHIPS INTERNATIONAL -> CLICK\n[button] Locations -> CLICK\n[button] Germany -> CLICK\n[button] Posting Dates -> CLICK\n[button] Less than 7 days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.11, 0.338, 0.89, 0.433] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e3c7ad0-f138-490e-918e-42bcce9f55a9_aac1c895-4aba-4a70-92e5-fcc5fb7e46e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a harry potter book to my wishlist.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.042, 0.746, 0.06] in the image\nAnd my action is Action: TYPE\nValue: Harry Potter" } ]

{ "bytes": "", "path": "./images/39fd14c2-3bdd-4ca6-8a3a-1a6e7374c8e6_563fa026-5ccb-4530-ba47-2733ea4e3f73.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a woman t-shirt in xl size from merchandise section, add 2 pieces to the cart and check out.\nPrevious actions:\n[span] Women's Last.fm Spiral Hex Tee -> CLICK\n[select] S -> SELECT: XL\n[svg] -> CLICK\n[button] ADD TO CART -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.417, 0.953, 0.454] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_d4035166-f027-406d-a033-54f1537852f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Add Rooms -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Adults -> CLICK\n[button] Add Children -> CLICK\n[button] Add Age -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.151, 0.341, 0.171] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_d9c7b18b-2aed-4aa2-9e8f-1a2cb9fc509c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[link] Trip Ideas -> CLICK\n[div] Pacific Coast Highway Road Trip -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: LOS ANGELES\n[span] Los Angeles Intl Airport -> 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, 0.308, 0.691, 0.321] in the image\nAnd my action is Action: SELECT\nValue: July 2023" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_4852e3fe-905f-4e27-9a12-35d97fabc229.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cruises to Hawaii departing from Los Angeles in January 2024 with a duration of 12 days.\nPrevious actions:\n[button] SAIL FROM -> CLICK\n[button] Los Angeles, CA -> CLICK\n[button] DATES -> CLICK\n[button] January 2024 -> CLICK\n[button] DURATION -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.623, 0.254, 0.861, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_f73bb3ec-e0ee-4c9a-88f4-067c971d74af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.193, 0.271, 0.217] in the image\nAnd my action is Action: TYPE\nValue: new york" } ]

{ "bytes": "", "path": "./images/58f811fd-0f17-430b-befc-885605e13e41_e049fd1b-420c-4d5a-8879-da5d9e7c436d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\n[textbox] Email address used to place your order * -> TYPE: [email protected]\n[textbox] Order number * -> TYPE: X123456\n[textbox] Date you received your order (DD/MM/YY) * -> TYPE: 08/04/23\n[textbox] Please cancel my order for the following products ... -> TYPE: Harry Potter Box Set\n[textbox] Reason for cancellation (optional) * -> TYPE: Not available at address" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.649, 0.589, 0.759, 0.624] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee9e993b-0254-465d-bb04-072e01e5f498_05693c99-fd4d-4edb-8bc6-928ce06772f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the selection of fishing reels that are power assisted and are in stock.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.17, 0.26, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_9c2290bc-9528-494c-b4b2-6c24d402f0ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless printer\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.164, 0.192, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bef473f1-82a1-4359-a2c0-59b6dc2f6abb_93d10c01-8038-4307-a588-04ff78151bb4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Alaska that is also a National Heritage Area.\nPrevious actions:\n[button] Find a Park by State -> CLICK\n[link] Alaska -> CLICK\n[link] 1 National Heritage Area » -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.187, 0.391, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_a0511245-165d-42d4-984b-d22c988d5742.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Vacations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.085, 0.902, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86897828-35e8-4002-a98a-4e1dd26c6edb_21d23ff9-ab59-4c28-9f7b-4c08ee362138.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the lowest price ticket for All star stand up comedy event happen 6pm on the 25th March 2023.\nPrevious actions:\n[link] concerts. -> CLICK\n[textbox] Search by Name -> TYPE: all star stand up comedy\n[p] All Star Stand Up Comedy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.636, 0.881, 0.66] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc98662-4405-4a30-9854-9301c98fdb37_7b1492bb-0d9e-4311-ba8d-402a5ed99076.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the parking options in Florida to book to enter on may 6 at 5 pm and leave the same day at 6pm?\nPrevious actions:\n[textbox] Start Date -> CLICK\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK\n[combobox] Start Time -> SELECT: 5:00 PM\n[combobox] End Time -> SELECT: 6:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.353, 0.3, 0.39] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_502edf50-b8f9-44ea-8313-42addffed44f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: washington\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[div] Depart Date -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.204, 0.764, 0.223] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3016f6f-b0fe-46df-a5ae-d0ad80a6996c_fe721d29-2b19-4c71-8bdf-3be63712c52e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule for the Dallas Mavericks.\nPrevious actions:\n[link] NBA -> HOVER\n[link] Dallas Mavericks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.079, 0.185, 0.137, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_416cbb3e-b141-477f-b75a-2e4b3da93394.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[svg] -> CLICK\n[span] -> CLICK\n[path] -> CLICK\n[span] -> CLICK\n[heading] Car specs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.159, 0.331, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_ed3c1666-d006-4dfa-8ba0-9b84253364e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Find Parking Lots -> CLICK\n[button] Stations G–K  -> CLICK\n[link] Gloucester -> CLICK\n[link] Plan a trip from this station -> CLICK\n[combobox] To  -> TYPE: NORTH PLYMOUTH" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.149, 0.249, 0.34, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_dcad1685-0929-496c-b434-2f408805f4bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.124, 0.868, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/763deda0-f51c-4520-b102-5277f702e8bd_49717bd1-bd15-48ca-a3e7-6e3bffe0ed44.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 initial release date for Guardians of the Galaxy Vol. 3 the movie.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.068, 0.047, 0.079] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_60e413f8-5da1-49af-9a07-7b8caaa3de3e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: laguardia airport\n[span] LaGuardia Airport -> CLICK\n[button] Find a Location -> CLICK\n[link] 1 Laguardia Airport (LGA)  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.137, 0.891, 0.163] in the image\nAnd my action is Action: SELECT\nValue: midnight" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_e0a29b99-5021-409d-b09e-cbf39a4b1dd8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[checkbox] 30 April 2023 -> CLICK\n[combobox] Drop off time -> SELECT: 1:00 PM\n[div] Search -> CLICK\n[div] Premium -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.566, 0.331, 0.58] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/93d0190f-ff39-4b69-82fc-58cddac42006_9163c12d-351c-4892-bd5f-8918723bcf44.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 safety rating for 2012 Honda Civic\nPrevious actions:\n[link] Price New/Used -> CLICK\n[combobox] Year -> SELECT: 2012\n[generic] Your Opinion Counts! -> CLICK\n[img] Close -> CLICK\n[combobox] Make -> SELECT: Honda" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.278, 0.248, 0.508, 0.274] in the image\nAnd my action is Action: SELECT\nValue: Civic" } ]

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_35301bd1-f6f4-42b1-811c-f35b27afdc8b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 email alerts for a flight from BHZ to EWN leaving on april 30 on the email [email protected]\nPrevious actions:\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 30 -> CLICK\n[button] Search -> CLICK\n[button] Get alerts for this flight for flight 906 American... -> CLICK\n[textbox] Email -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.644, 0.358, 0.828, 0.386] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_caf11e97-b1ea-4f59-aaf8-02f7a18f9536.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Age of Child 3(Child's age (years)) -> SELECT: 8\n[img] Add -> CLICK\n[combobox] Age of Child 4(Child's age (years)) -> SELECT: 12\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.413, 0.089, 0.423] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1202e28a-361d-4704-979a-526c599b4859_e1c980b4-954f-44d5-8288-8b27eb6c7f24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fully electric car pickup at Athens Airport (ATH) Sat, Apr 1, 2023 and return to the same palce at Mon, Apr 3, 2023.\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: Athens\n[button] Athens Airport (ATH) Athens, Greece -> CLICK\n[div] Apr -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.25, 0.221, 0.267] in the image\nAnd my action is Action: CLICK" } ]