Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_fd9fe93d-6937-4027-89b5-20b0221d4c27.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 lin.lon@gmail.com\nPrevious actions:\n[link] Flight status -> CLICK\n[link] Create flight status notification -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK\n[textbox] To , required. -> TYPE: ewn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.242, 0.595, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_038b9509-b8b1-4e84-9426-a5377183ea28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[combobox]  -> SELECT: 1 Room\n[combobox]  -> SELECT: 2 Adults\n[combobox]  -> SELECT: 1 Child\n[select] Age -> SELECT: 0\n[link] Search Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.403, 0.123, 0.415] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb3e2b61-c14c-4a15-8de4-7c12256d52c7_d558e7ad-1abf-41ab-8a92-2e62cc399b43.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 concerts taking place in Los Angeles, CA in the next month.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: Los Angeles\n[option] Los Angeles, CA -> CLICK\n[span] Filter by -> CLICK\n[div] 16 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.438, 0.496, 0.47, 0.518] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e50b35f-7af9-4835-a741-158c2d941722_41966dc2-1c46-44f2-89da-4e108a52dbc1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for Athens, Attica, Greece 1 Apr 2023 - 3 Apr 2023, 2 nights, 1 Room, 1 Adult\nPrevious actions:\n[div] hotels -> CLICK\n[textbox] Destination or property -> TYPE: Athens, Attica, Greeece\n[div] , Greece -> CLICK\n[div] Choose date -> CLICK\n[generic] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.101, 0.5, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ff347e6-e911-4af5-8151-7805a9e91b28_e0a4ce5f-1ee3-4a27-a60e-5c7ca962277e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 current alerts for red line subway.\nPrevious actions:\n[tab] Alerts -> CLICK\n[link] red line -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.267, 0.295, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_d8f45da9-b931-4adc-b980-61fc1ecf4943.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[link] Search for cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.129, 0.421, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_d79f9228-b3a9-418d-add9-33ed60d96f36.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[span] Flights + Cruise -> CLICK\n[button] Search flights + cruise External Link should open ... -> CLICK\n[combobox] Departing from -> TYPE: ATLANTA\n[span] Atlanta, GA (ATL) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.181, 0.968, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3bc6528-5fd5-45ac-81aa-7fafde757022_1d109036-07b4-4d9e-83e3-9ec6c93111df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\n[combobox] Search for anything -> TYPE: laptop\n[button] Search -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.303, 0.069, 0.327] in the image\nAnd my action is Action: TYPE\nValue: 400" } ]

{ "bytes": "", "path": "./images/240952bd-853b-4653-a358-49c2784cf568_e165de37-91d8-4552-88cb-72773a2d61ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\n[option] Chicago, IL - Union Station (CHI) -> CLICK\n[input] -> TYPE: los angeles\n[option] Los Angeles, CA - Union Station (LAX) -> CLICK\n[textbox] Type a date, or use enter to open, escape to close... -> CLICK\n[gridcell] Saturday, March 25, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.843, 0.068, 0.957, 0.086] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b18e5e4-4873-49bf-b422-c3f5bc5d1f33_0cd2cdd2-052b-42c7-9e1d-f0bc04e54244.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a WWE ticket for price range between $50 to $100.\nPrevious actions:\n[link] WWE Tickets -> CLICK\n[link] TICKETS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.785, 0.177, 0.86, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7eff6c15-bab6-4ce4-abb8-72619f593ea1_758a6b1b-74f1-42c3-84ba-bae21ea8afd4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track my bus with service number SE4.\nPrevious actions:\n[button] Check my bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.418, 0.077, 0.515, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51b75f3d-b293-495d-a5a0-8ed5cc8270a2_185b383c-4764-413c-94db-33a69434174e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for 2 guests on april 21 at noon in a restaurant in Austin that is new on resy\nPrevious actions:\n[path] -> CLICK\n[button] Austin -> CLICK\n[heading] New On Resy -> CLICK\n[button] Sat., Apr. 22 -> CLICK\n[button] April 21, 2023. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.156, 0.562, 0.163] in the image\nAnd my action is Action: SELECT\nValue: 2 Guests" } ]

{ "bytes": "", "path": "./images/fbefeb82-f3e6-4db4-acc6-a68b1d519ba7_65943829-04b2-47f0-8962-29ec916f9463.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking button code for my company Boston Legal located near Boston Navy Yard, and the button should be 160x400 pixels, and the parking spot should be within 15 miles of my address.\nPrevious actions:\n[combobox] STEP 2:Enter an address to search and select a loc... -> TYPE: BOSTON NAVY YARD\n[em] Navy -> CLICK\n[span] 300 pixels x 150 pixels -> CLICK\n[span] 160 pixels x 400 pixels -> CLICK\n[span] Default -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.163, 0.768, 0.493, 0.791] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0592744b-ea69-4724-80f8-3924916b7758_021fde47-dd12-4ac5-b8f5-224b962a26ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find out the cancellation policy\nPrevious actions:\n[link] Help -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.485, 0.945, 0.511] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b743c63-2a99-4c29-93ef-af920dab9535_57cbe038-dfd5-40a1-a06b-ac5867355b3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly parking rates near the Museum of Modern Art.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: MOMA\n[option] Museum of Modern Art (MoMA)   11 West 53rd St, New... -> CLICK\n[link] MONTHLY -> CLICK\n[button] See options -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.378, 0.11, 0.622, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c7b0d1bc-2a0c-4060-92dd-cd4b8721b625_977bba29-aae4-4a39-b861-3078f910070e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 KOA near Lansing, Michigan for June 7, 2023 to June 12, 2023.\nPrevious actions:\n[textbox] CHECK IN -> CLICK\n[link]  Next -> CLICK\n[link]  Next -> CLICK\n[link] 7 -> CLICK\n[textbox] CHECK OUT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.56, 0.32, 0.594, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/52a8bace-f14c-41ce-980f-50d95e5ac259_39ed9e93-b3b0-4010-88bf-a0f716059c7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the list of countries with the highest number of seen aircrafts.\nPrevious actions:\n[link] ADS-B -> HOVER\n[link] Statistics -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.322, 0.437, 0.347] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_71312214-c558-4c47-a70e-f32e1f74f9a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: abc@abc.com\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.748, 0.66, 0.872, 0.672] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/839ad551-da04-4c8e-96c3-093e762ea167_9de9bac3-ef0b-4042-b991-1b1dfc157d6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and book the cheapest daytime only monthly parking option in Seattle near Stripe, 5th Avenue\nPrevious actions:\n[textbox] Search for parking -> TYPE: stripe, 5th avenue\n[li] Stripe, 5th Avenue, Seattle, WA, USA -> CLICK\n[tab] Monthly -> CLICK\n[select] All Parking Options -> SELECT: Daytime Only Parking\n[select] Sort by Distance -> SELECT: Sort by Price" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.474, 0.32, 0.492] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_df33373b-2ae4-4f6e-8f22-a1b84bde50a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\n[link] Smart Lighting -> CLICK\n[button] Indoor Lighting (7) -> CLICK\n[checkbox] Strip Light (3) -> CLICK\n[button] Sort By: Best Match -> CLICK\n[button] Price Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.435, 0.394, 0.449] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_f981234b-29f6-451d-b795-ad8216ee453f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.05, 0.117, 0.067] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_03e8b74e-3cf6-4077-9339-84aefa9f9237.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.06, 0.181, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54112d86-1d85-4abf-9e12-86f526d314c2_a3c7b2db-75e5-41d9-a23b-b01d06ba008f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 BGG rules for Game Submissions?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.475, 0.007, 0.52, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f52ba76c-e5fc-48e5-85f3-41d4234a5c5f_152064fc-85f5-4364-aa81-6f9a6fa9941c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find used Xbox series X available.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox Series X|S -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.122, 0.094, 0.137] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_9c69f639-37d4-4a10-b271-a86ad3892709.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[strong] Colombo -> CLICK\n[textbox] To 2180 results are available, use up and down arr... -> TYPE: new york\n[strong] New York -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 24 June 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.267, 0.94, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_e9c512bc-6241-4452-a4ec-3ad2237375a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[textbox] * Amount: -> TYPE: 50\n[button] VIEW ALL -> CLICK\n[img] -> CLICK\n[textbox] To: -> TYPE: John\n[textbox] From: -> TYPE: James" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.582, 0.286, 0.99, 0.342] in the image\nAnd my action is Action: TYPE\nValue: Congrats on your new home." } ]

{ "bytes": "", "path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_329bca7f-0638-4eff-83b5-50f793f10541.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[div] Downtown Bangkok -> CLICK\n[div] Thu, Apr 20 -> CLICK\n[checkbox] 24 May 2023 -> CLICK\n[checkbox] 28 May 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 9:30 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.759, 0.091, 0.846, 0.118] in the image\nAnd my action is Action: SELECT\nValue: 9 00 AM" } ]

{ "bytes": "", "path": "./images/af6655c8-0047-4c93-8da2-aeb04ff06b17_c33315e7-7e2d-4dc0-a06d-06ad4e82dbab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 climbing courses within 50 miles of 90028.\nPrevious actions:\n[link] Classes & Events -> CLICK\n[combobox] Activity -> SELECT: Climbing" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.378, 0.234, 0.561, 0.258] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

{ "bytes": "", "path": "./images/b02e47ac-c1a6-4f5c-886f-f32af745e7f3_30484980-8301-4a3a-ae0f-f2ea7df58336.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View a reservation made under the last name Walker in Australia for a car using the reservation confirmation number A987654.\nPrevious actions:\n[link] close dialog -> CLICK\n[button] Reservations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.091, 0.628, 0.12] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf8da12a-e1fd-48b5-8c53-b88f301ca1e0_561a3105-2605-4f2f-abbe-2b622948cf16.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] All Filters -> CLICK\n[tab] Features -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.109, 0.666, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a513befc-46c3-4bb6-87c0-8f219107c756_feefcb3a-19ea-438c-9bfa-b4c99631dcbb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NBA basketball game for the PS5 to the shoping cart\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: nba2k23\n[button] Search -> CLICK\n[img] NBA 2K23 - PlayStation 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.713, 0.975, 0.757] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c4538b84-ca81-413a-8f3d-7ce87e42b4f6_29164d9e-ba63-4d06-8c46-c482d44a416b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Saturday park hours for Six Flags, Magic Mountain.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.519, 0.233, 0.788, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ce34bc61-e3d2-40c8-b02b-b149efc4b115_82b45e0c-6d98-47d6-9691-3d2d8a21abe6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[button] 04/08/2023 -> CLICK\n[combobox] Renter Age -> SELECT: 22\n[button] Vehicle Class -> CLICK\n[radio] Minivans -> CLICK\n[button] Apply Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.365, 0.837, 0.391] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_def2773e-0727-493c-916f-407e36da2dec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.216, 0.221, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b079ace-b202-4d78-a9b0-4cde39e58934_9f7ab3a7-9b90-42cc-969b-9cd4d687d6a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a vehicle at New York JFK International Airport May 2-May 5 for an owner above 25 years.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: New York JFK\n[option] New York JFK International Airport JFK Jamaica, 11... -> CLICK\n[button] Selected Pick-Up Date 03/19/2023 -> CLICK\n[button] Next Month -> CLICK\n[button] 05/02/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.228, 0.517, 0.25] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4132002e-5ba6-4e36-a1b7-6bbe61503be5_3a0d5ccb-3636-49a5-898b-80a18673958a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 living History event to attend in in April .\nPrevious actions:\n[button] Open Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.381, 0.108, 0.93, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_fefcbed0-8fa1-4592-88d3-8bdab9e18fd2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.186, 0.699, 0.202] in the image\nAnd my action is Action: TYPE\nValue: Doja Cat" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_c79b7700-6a68-429c-b616-d0151bd9bb47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[img] Add -> CLICK\n[img] Add -> CLICK\n[combobox] Age of Child 1(Child's age (years)) -> SELECT: 3\n[img] Add -> CLICK\n[combobox] Age of Child 2(Child's age (years)) -> SELECT: 5" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.293, 0.393, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f567f79-e197-4d7e-9a49-877daae6dde5_5feef698-f267-4190-a94a-3cc69cfae45f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\n[combobox] Search for anything -> TYPE: iPhone 12 Pro\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.21, 0.261, 0.225] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1f28fed3-bed9-444a-bf2b-3700b516b97f_39a1e694-4b56-4f10-845c-e3d03dc73e11.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 garage near Thalia Hall in Chicago that offers pre purchasing.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.246, 0.288, 0.754, 0.311] in the image\nAnd my action is Action: TYPE\nValue: Thalia Hall" } ]

{ "bytes": "", "path": "./images/fb9c0e7f-02dd-453f-8c73-da19282abf84_68aa9c94-69f6-4512-996c-58c416c098ec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] Cars for Sale -> HOVER\n[link] Cars for Sale -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.037, 0.851, 0.054] in the image\nAnd my action is Action: TYPE\nValue: Mustang" } ]

{ "bytes": "", "path": "./images/c73b1674-9c61-46a3-84dd-8fad3622a035_4c00ab57-f61c-4d58-804f-25da94282151.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Sort & Filter -> CLICK\n[svg] -> CLICK\n[label] Points -> CLICK\n[link] Sort & Filter -> CLICK\n[button] Default   -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.255, 0.438, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c53a4a47-d155-42fc-b9a8-6b37d092d9aa_6d02d310-1f7b-45f6-b680-73edaeff707b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 release date and supported platforms for the game \"Elden Ring.\"\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.059, 0.047, 0.068] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bd729e8-abb2-4649-bb81-8c790c04f8ad_28a61364-9726-4983-96f8-f68988ba8da5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[checkbox] Pickup at Store Eligible (86) -> CLICK\n[checkbox] Multi-Purpose Tool (11) -> CLICK\n[checkbox] Red Devil (2) -> CLICK\n[label] Add -> CLICK\n[combobox] Select a list -> SELECT: Wish List" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.661, 0.349, 0.781, 0.367] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1282a011-194c-40c4-8f76-875e502cdd53_1d412587-c49d-49e7-aa72-4b12e47b9c59.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse laptops with at least 16gb of ram and under $700.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.009, 0.39, 0.027] in the image\nAnd my action is Action: TYPE\nValue: laptop" } ]

{ "bytes": "", "path": "./images/a83c14aa-1a0b-4aaf-a801-ac828d2e81ca_d5c61581-da19-4144-a5a5-540bb4ab10d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 4 star rated Hotel in New York Timesquare for 2 adults.\nPrevious actions:\n[button] 1 adult · 0 children · 1 room -> CLICK\n[svg] -> CLICK\n[button] Done -> 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, 0.716, 0.263, 0.724] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3a231c03-d038-4b61-b5a2-685b77d9920e_63575c7f-68ce-498c-a1fe-1bfefa463455.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the bag charges for the passenger James Son for the flight with the confirmation number 10000002\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Baggage info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.212, 0.205, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_66e0df08-da51-4405-a484-0d02219ec44d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse used BWM cars made in 2010 and compare the four cheapest listings\nPrevious actions:\n[div] BMW -> CLICK\n[span] -> CLICK\n[select] 1992 -> SELECT: 2010\n[button] Close dialog -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.153, 0.493, 0.255, 0.525] in the image\nAnd my action is Action: SELECT\nValue: 2010" } ]

{ "bytes": "", "path": "./images/cdb6b70d-6083-49b5-908c-a6c0f711c175_10cae0d4-c04c-40c7-ace9-d4a0bd6a2993.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces near Warner Theatre in Washington DC.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.006, 0.348, 0.02] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/48ca542f-5346-40b9-b586-9294a2f64519_943a0122-f698-44fa-a09a-a51b0b364862.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Like a game mix album.\nPrevious actions:\n[searchbox] Search -> TYPE: game mix\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.126, 0.199, 0.14] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db53ba89-9cff-441a-a703-053e89e32961_241e6556-a874-4125-b694-5bc8b8bc4e26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\n[path] -> CLICK\n[span] Browse Movies by Genre -> CLICK\n[link] Superhero -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.321, 0.331, 0.329] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7bdf34b4-2aa0-4387-9f6a-f7d7c5d17119_c829579a-b47f-4091-a86e-57467ac96607.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 alerts and conditions for the Alagnak Wild River.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[combobox] Park Name -> TYPE: Alagnak\n[option] Alagnak Wild River -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.714, 0.234, 0.73, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c577375b-ecca-42f8-920c-b06809eef2b4_247b7cf9-68ad-4c76-b6f9-179be7ce2b29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 retired players named James Smith\nPrevious actions:\n[link] Players -> CLICK\n[link] RETIRED -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.29, 0.491, 0.315] in the image\nAnd my action is Action: TYPE\nValue: James Smith" } ]

{ "bytes": "", "path": "./images/3b7cead3-475d-41a4-a018-db89c7ace632_6c2dbd75-a9bb-416a-a351-191e84c7897e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 is the purchase price for powerwalls to install in a 200sqr feet 2 story house in the address 7528 East Mechanic Ave.Fargo, ND 58102\nPrevious actions:\n[link] Powerwall -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.639, 0.22, 0.798, 0.238] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c107328-3ff6-4cb3-af16-5f9ca447fd66_b9a3579d-b988-4a98-97d1-9bdc1abcfb2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 documentary \"The Elephant Whisperers\" and \"The Magician's Elephant\" to the watchlist.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: The Elephant Whisperers\n[div] The Elephant Whisperers -> CLICK\n[div] Add to Watchlist -> CLICK\n[textbox] Search IMDb -> TYPE: The Magician's Elephant" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.15, 0.028, 0.657, 0.078] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a11022ab-f733-4295-a2f2-0da19cccc1b4_4463379b-ecb8-4fd3-a871-b3ba26ce27bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 up for emails using the name Dick Smith and the email smith@gmail.com, select Six Flags Magic Mountain as the Park of Preference,\nPrevious actions:\n[textbox] First Name -> TYPE: Dick" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.644, 0.678, 0.672] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_ccb50965-fe39-45c7-8e51-1f00048585d7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[button] Show all 25 -> CLICK\n[span] -> CLICK\n[button] Sort by:Top picks for solo travellers -> CLICK\n[button] Price (lowest first) -> CLICK\n[link] See availability -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.369, 0.917, 0.387] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/160fc162-7f03-4f59-83e1-5502d00806f2_44c6392e-a186-4eaa-8760-eb0ab0f1688a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See what is playing on Showtime sorted by newest.\nPrevious actions:\n[link] TV SHOWS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.652, 0.157, 0.691, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cfe20a-f008-48d3-b683-002ce7790616_60083201-3aa9-4224-ba53-064f1337c834.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[combobox] Pick-up time -> SELECT: 9:00 am\n[combobox] Drop-off time -> SELECT: 6:00 pm\n[button] Search -> CLICK\n[input] -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.6, 0.125, 0.825, 0.152] in the image\nAnd my action is Action: SELECT\nValue: Total Price" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_a8b0b04f-7a57-4daa-9501-dcc668509760.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] Book now -> CLICK\n[textbox] First name -> TYPE: Joe\n[textbox] Surname -> TYPE: Bloggs\n[textbox] Email address -> TYPE: buckeye.foobar@gmail.com\n[textbox] Confirm email address -> TYPE: buckeye.foobar@gmail.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.699, 0.282, 0.949, 0.314] in the image\nAnd my action is Action: TYPE\nValue: 1111111111111111" } ]

{ "bytes": "", "path": "./images/d3ca5294-89aa-4028-8776-be08edc63783_0727b0e3-b43e-4257-91fe-d0522d9f95ae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 campground in Phoenix with wi-fi to check in today.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.223, 0.434, 0.256] in the image\nAnd my action is Action: TYPE\nValue: Phoenix" } ]

{ "bytes": "", "path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_9cab69a1-12c1-4b8a-96b6-6677977b0efb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.358, 0.671, 0.477, 0.702] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b2c18588-b115-4937-b69f-8feeab22c387_2403f621-0e06-4828-bd85-e88920da6630.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the list of movies \"at home\", sorted by most recent.\nPrevious actions:\n[link] AT HOME -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[span] Sort -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.089, 0.21, 0.13, 0.222] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8027aa8-c193-47c8-a97b-432836093939_e4a42325-a654-487d-84c7-bf3df4ef3fdd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] Enter a city, hotel, airport, address or landmark -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Las Vegas\n[span] Las Vegas, Nevada, United States -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.821, 0.081, 0.831] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_b66d3924-665c-4d00-89ce-3af5bbdefa0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\n[span] -> CLICK\n[label] 2 -> CLICK\n[span] -> CLICK\n[input] -> TYPE: 200\n[span] Prices with Fees -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.272, 0.978, 0.302] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bc45669b-6bed-4240-9d9b-6b5e45a7e6f3_a7113861-fe5b-4489-9bf1-74d8e911bdac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 xbox series x consoles that are used and between $200 and $400.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.027, 0.652, 0.048] in the image\nAnd my action is Action: TYPE\nValue: xbox series x console" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_26e640a9-4ea1-4d49-91b5-c85e6f60afff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is buckeye.foobar@gmail.com, and phone number is 6157075521.\nPrevious actions:\n[combobox] Style -> SELECT: L Sedan 4D\n[button] Select Vehicle -> CLICK\n[button] No thanks -> CLICK\n[textbox] Other Ways We Can Help -> TYPE: ac recharge\n[button] See Pricing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.348, 0.314, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d86d5cc1-50f7-4bfd-8e5b-60db84e87956_73553ffc-fbfe-498e-bd3c-0f29651390e2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the trade-in value for Call of Duty: Black Ops III for Xbox One.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: trade in\n[button] Search -> CLICK\n[p] Video Games -> CLICK\n[searchbox] Find values for games and more -> TYPE: Black Ops" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.201, 0.975, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e1a344d-a27b-4613-8863-7afad0829b23_e0d490bf-0f05-41af-a25c-2c1607beb5f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest washable blue rug under 2'x3' size.\nPrevious actions:\n[link] Shop by Category -> CLICK\n[link] For the Home -> HOVER\n[link] Rugs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.344, 0.568, 0.504, 0.597] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bafd6a44-5938-431f-8e2e-17d680d5c48b_68ac02d5-a995-46a4-91fc-cc364d6a9585.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 page with information about Wi-Fi subscriptions.\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Pre-paid Wi-Fi -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.66, 0.32, 0.943, 0.373] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_eea2294a-9dc9-46e6-bffe-3a79e7bf7339.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[tab] Flights -> CLICK\n[button] Leaving from -> TYPE: Los Angeles, CA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.156, 0.362, 0.181] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d738d01-507e-46ff-8d4d-d4a7dffed936_a222958a-28e5-4650-a828-970e8418f440.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 weekly chart-topper artist and play the number 1 track of that artist after liking the track.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.806, 0.004, 0.838, 0.022] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_f8f537b6-6859-4811-870b-70ea8462e472.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[button] return Friday, May 5, 2023 -> CLICK\n[span] -> CLICK\n[span] Search flights -> CLICK\n[link] Sort & Filter -> CLICK\n[button] Default   -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.184, 0.171, 0.438, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_01f9edf6-29ed-4d92-a014-f3130a29558b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is buckeye.foobar@gmail.com, and phone number is 6157075521.\nPrevious actions:\n[button] No thanks -> CLICK\n[textbox] Other Ways We Can Help -> TYPE: ac recharge\n[button] See Pricing -> CLICK\n[button] Get Service Estimates -> CLICK\n[textbox] Your Name * -> TYPE: James Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.495, 0.557, 0.515] in the image\nAnd my action is Action: TYPE\nValue: buckeye.foobar@gmail.com" } ]

{ "bytes": "", "path": "./images/13d78369-994a-4202-a9ed-8361e1fdea9d_1012b462-c850-48cc-9aec-b52c613c9815.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bluetooth headphones with active noise-cancellation.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.008, 0.418, 0.025] in the image\nAnd my action is Action: TYPE\nValue: headphones" } ]

{ "bytes": "", "path": "./images/265cd715-0607-4ebe-8420-046b1a165239_fd52e1f0-8e62-4dfe-87ba-46653af03edd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Jerry Trainor's upcoming projects?\nPrevious actions:\n[textbox] Search IMDb -> TYPE: Jerry Trainor\n[button] Submit Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.154, 0.18, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_2c0514e7-0198-47f6-9cc4-579b8d94d4b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[span] New York -> CLICK\n[span] Mar 18 -> CLICK\n[button] 20th March (Monday) -> CLICK\n[combobox] Time -> SELECT: 8:00 PM\n[combobox] Size -> SELECT: 4 guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.42, 0.609, 0.546, 0.661] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a919aa15-2acf-4090-8468-1d3a0d6450b1_c2e21f02-9b52-4af0-a516-8ded4f5667d8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Need the cheapest small car on April 7, 10 am at Auckland airport for pick-up, return will be on April 10 at approx 5 pm.\nPrevious actions:\n[button] Reservations -> HOVER\n[link] Make a Reservation -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: AUCKLAND\n[span] Auckland 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 [0.639, 0.361, 0.666, 0.379] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_59aefbe2-91fb-454b-9776-e882facf39e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[button] Go! -> CLICK\n[input] -> CLICK\n[div] All dates -> CLICK\n[span] -> CLICK\n[span] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.615, 0.234, 0.664, 0.251] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fbefeb82-f3e6-4db4-acc6-a68b1d519ba7_fae28de0-5ad5-40f9-9957-f28a133d78ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking button code for my company Boston Legal located near Boston Navy Yard, and the button should be 160x400 pixels, and the parking spot should be within 15 miles of my address.\nPrevious actions:\n[em] Navy -> CLICK\n[span] 300 pixels x 150 pixels -> CLICK\n[span] 160 pixels x 400 pixels -> CLICK\n[span] Default -> CLICK\n[li] .15 miles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.729, 0.39, 0.775] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_131d877b-75a0-4877-af95-39ad3de38bd4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email sellmycar@mail.com.\nPrevious actions:\n[LabelText] Sell My Car -> CLICK\n[textbox] Enter license plate -> TYPE: YAW639" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.513, 0.177, 0.583, 0.213] in the image\nAnd my action is Action: SELECT\nValue: LA" } ]

{ "bytes": "", "path": "./images/af6655c8-0047-4c93-8da2-aeb04ff06b17_a053edd4-1209-4989-9b99-86fba90a1817.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 climbing courses within 50 miles of 90028.\nPrevious actions:\n[link] Classes & Events -> CLICK\n[combobox] Activity -> SELECT: Climbing\n[textbox] Location -> TYPE: 90028\n[combobox] Distance -> SELECT: Within 50 miles" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.717, 0.318, 0.779, 0.351] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_b90bfd21-8292-4a30-b820-0e7294539949.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: JFK\n[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[span] -> CLICK\n[textbox] To , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.29, 0.492, 0.309] in the image\nAnd my action is Action: TYPE\nValue: Heathrow" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_6661dc2d-7358-4707-b483-256abecef314.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[option] Sweatpants -> CLICK\n[heading] Sweatpants -> CLICK\n[checkbox] PINK -> CLICK\n[checkbox] XXL -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.214, 0.802, 0.255] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_b1b808d1-e980-4885-9add-57e9801759d2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Charleston -> CLICK\n[textbox] zip or city, state -> TYPE: 25504\n[button] Look up -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.326, 0.215, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7bdebbfa-2512-48e2-93b1-d92e2c87c6e1_bcbd4fa2-dfa8-49db-9c12-836d1369cb1e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vintage clothing and sort the results by price from high to low.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: vintage clothing\n[option] vintage clothing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.14, 0.906, 0.171] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a16a98f-4e8f-4ff9-9fa2-b97d2d403cc3_bbaa21de-6ebe-4cb2-b0f1-5f078bc25883.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 set of sonoma bath towels to the cart and apply a coupon code for free shipping.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: bath towels\n[span] bath towels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.171, 0.385, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_ecf837ac-8efb-4881-ba8c-0468980e8236.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.204, 0.359, 0.227] in the image\nAnd my action is Action: TYPE\nValue: brooklyn" } ]

{ "bytes": "", "path": "./images/6b4aa5a9-79c5-49a3-9cc6-ead02159a3dd_6d2e17fb-6fa7-41b5-b3ad-e06febea811f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Queen size memory foam mattress with lowest price.\nPrevious actions:\n[link] Mattresses -> CLICK\n[img] Foam and memory foam mattresses -> CLICK\n[button] Show sorting options modal -> CLICK\n[span] Price: low to high -> CLICK\n[button] Show filter modal size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.201, 0.281, 0.382, 0.313] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_dd9f943d-ec6a-4c26-ab14-1e616956da46.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox One -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.191, 0.091, 0.2] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/673841c2-de8c-4417-bdcc-dc48753a539f_2c2aec1c-480f-4da8-ab1d-5b869f7da824.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 current standings for the western conference in the NBA and find the top team.\nPrevious actions:\n[link] NBA . -> HOVER\n[link] Standings . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.619, 0.109, 0.646] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_f2a963c3-0f8b-4bad-b7ab-4298c4bf0d48.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[label] VIN -> CLICK\n[textbox] Enter VIN (17 digits) Where can I find the VIN -> TYPE: 1HGCM66543A064159\n[button] Get your offer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.196, 0.124, 0.217] in the image\nAnd my action is Action: TYPE\nValue: 49102" } ]

{ "bytes": "", "path": "./images/76514d5c-cc1c-40b0-8c08-427cedb106e4_9620c2bd-5128-408a-83d5-9cdbcb8313c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[menuitem] category pillows -> CLICK\n[span] Pillow Protector -> CLICK\n[combobox] Select a Size -> SELECT: Queen" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.877, 0.231, 0.918, 0.253] in the image\nAnd my action is Action: TYPE\nValue: 2" } ]

{ "bytes": "", "path": "./images/f9723022-04b9-4778-ad33-cf54eac3d393_734546b2-50bd-404e-9a03-995d32d7a59b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Near you -> CLICK\n[textbox] Location search -> TYPE: new york\n[span] New York -> CLICK\n[combobox] SEARCH RADIUS -> SELECT: 100 km\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.117, 0.2, 0.132] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90a0f029-c1af-4dd7-8ccd-c4c2a74e8731_5e2410e0-53cc-4f38-9183-503099b46c3b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[tab] BOOK -> CLICK\n[link] Award travel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.171, 0.5, 0.289, 0.529] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51e85ea8-7a75-40f3-8f35-ed255f87171f_e16396d8-5c1b-48e4-a7a1-5fbdea6617d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to cart 2 bottles of vitamin D that are buy 1 get 1 free and new arrival.\nPrevious actions:\n[button] Shop -> CLICK\n[button] load Vitamins Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.28, 0.574, 0.303] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f0f8088f-46dc-453a-b695-772b30421ece_07dd93fe-4727-49e8-9b21-323de3c1d691.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip for 123456 last name Smith.\nPrevious actions:\n[button] MY TRIP -> CLICK\n[textbox] Reservation/Ticket Number -> TYPE: 123456\n[div] -> CLICK\n[option] Last Name -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.384, 0.176, 0.616, 0.186] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_6838a03a-5a15-4837-801d-1217ce23b10b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[button] Back to all categories -> CLICK\n[heading] Distance & Shipping -> CLICK\n[button] Any -> CLICK\n[menuitem] $99 or less -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.183, 0.249, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_ae8a6811-3d44-443b-8bae-878a6f545432.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] From -> CLICK\n[searchbox] From -> TYPE: empire state building\n[listitem] Empire State Building, West 34th Street, New York,... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.296, 0.359, 0.331] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9f76268f-9a4e-4eab-ab2c-262d2fe7bdee_d6d9d6a9-2059-43c5-8b87-7b7bf2cbfeb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 crossbows on sale with limited stock.\nPrevious actions:\n[link] Hunting -> CLICK\n[menuitem] Crossbows and Accessories -> CLICK\n[label] Limited Stock -> CLICK\n[label] Sale -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.192, 0.09, 0.204] in the image\nAnd my action is Action: CLICK" } ]