Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/51221157-cb79-407e-95c8-b2c730e95e01_8f46db0b-776d-4841-b186-b3c0faa3dd27.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 music party in Ohio and follow its organizer\nPrevious actions:\n[combobox] autocomplete -> TYPE: ohio\n[div] Ohio -> CLICK\n[generic] Run Search -> CLICK\n[label] -> CLICK\n[div] RANG BARSEY- HOLI MUSIC FESTIVAL, CINCINNATI -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.489, 0.223, 0.575, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/33b57a14-f469-405c-8843-f7e8ceb5b1ed_76da21b1-1ead-496c-841d-d52583fcd675.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 10 of the cheapest green shirt to my cart\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.03, 0.553, 0.053] in the image\nAnd my action is Action: TYPE\nValue: shirt" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_82f59f60-849f-4b79-be21-114105330e2d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request a refund for the traveler Ian Lo and, his document number is 12345678912345 and email [email protected]\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.048, 0.566, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/96e95a76-4a1d-491c-82ff-fac663d89ddb_823fc50e-e7ed-41be-8e54-2d9088a4da28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of adventure games under 30 dollars.\nPrevious actions:\n[link] Categories -> CLICK\n[link] Adventure -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.411, 0.225, 0.434] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_c9345036-4aaf-4175-9cd9-1ea6debe5fe1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[img] GIFT CARDS -> CLICK\n[img] Happy Birthday -> CLICK\n[button] EUR -> CLICK\n[div] GBP -> CLICK\n[button] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.485, 0.916, 0.504] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86897828-35e8-4002-a98a-4e1dd26c6edb_47ed0fb1-3ad0-495a-858d-e826a4481c1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the lowest price ticket for All star stand up comedy event happen 6pm on the 25th March 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.122, 0.248, 0.141] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5a15ea92-571d-4a45-ad18-5b4eddbc70a6_12632bc3-c1f3-4dc7-8320-0923fcbe924b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the lowest priced plus size one piece active swimsuit in color black.\nPrevious actions:\n[link] Swimwear -> CLICK\n[link] Women's Plus -> CLICK\n[div] Color -> CLICK\n[link] Black (294) -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.719, 0.33, 0.866, 0.348] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_2e5cd3b2-dd5b-4055-bd2b-ffdfc93923ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[checkbox] Deluxe Bedroom -> CLICK\n[button] Continue -> CLICK\n[link] Close -> CLICK\n[textbox] *Preferred date of travel -> CLICK\n[link] 22 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.133, 0.447, 0.17] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf008019-bffd-42ad-a48b-054488e1458c_cbd106f6-33c7-4094-9edb-03c35153f4b3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking near any NBA arena to enter today after 5 pm and exit after 8 pm\nPrevious actions:\n[link] View All Stadiums -> CLICK\n[link] Book Now -> CLICK\n[tab] Hourly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.202, 0.345, 0.372, 0.365] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_cb88089d-5c77-4c71-b428-9815070ef35d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[listitem] Staten Island, NY, USA -> CLICK\n[button] Leave now Change Time -> CLICK\n[textbox] Select date (format month/day/year) -> CLICK\n[button] 03/18/2023 -> CLICK\n[link] 25, Saturday March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.239, 0.24, 0.344, 0.258] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_416946e2-39b4-459c-a21e-e3133c02fb04.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\n[button] Add to list -> CLICK\n[menuitem] Create new list -> CLICK\n[textarea] -> TYPE: Directors\n[textarea] -> TYPE: To Watch\n[combobox] Type of List * -> SELECT: People" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.555, 0.198, 0.583] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_4b90e183-4ddd-4768-a0b3-ba25a5dbd94a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: NIAGRA FALLS" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.22, 0.369, 0.258] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a2befd0-5e90-4bed-81b5-8ee0a93873df_31ffb3eb-ddb4-4ca0-ba8c-1a6dd6b4497b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 RPG video games.\nPrevious actions:\n[button] Shop all -> CLICK\n[link] Filter -> CLICK\n[button] Genre -> CLICK\n[link] View More -> CLICK\n[checkbox] RPG RPG -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.025, 0.378, 0.043] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_b35e7803-4bfd-4c47-94eb-9055e61c98fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.212, 0.868, 0.223] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_a8676a33-d16d-4331-b300-a79c7d73f3ba.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.037, 0.817, 0.052] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b02e47ac-c1a6-4f5c-886f-f32af745e7f3_8a4a6571-1410-440e-a5f1-1ed1c39160a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View a reservation made under the last name Walker in Australia for a car using the reservation confirmation number A987654.\nPrevious actions:\n[link] close dialog -> CLICK\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.348, 0.28, 0.385] in the image\nAnd my action is Action: SELECT\nValue: AUSTRALIA" } ]

{ "bytes": "", "path": "./images/e7e1616e-dd5f-4eb4-a7f1-b757c7880877_fbfa94eb-b0f2-40b4-a0ec-c95ea564d036.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 up the scores for the previous day's NBA games\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.026, 0.178, 0.044] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_5746bc15-9d5b-484d-8f38-d15bdcbed1ad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[gridcell] Sat May 06 2023 -> CLICK\n[button] Update Search -> CLICK\n[button] Filter -> CLICK\n[checkbox] Self Park (1) -> CLICK\n[button] Show 1 Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.299, 0.548, 0.372, 0.563] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2623c8-ce74-4572-9eb6-89d0b216d0cf_9c71b00d-199e-437e-a510-ab151f6b1539.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow Taylor Swift and add a playlist to next up.\nPrevious actions:\n[searchbox] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.004, 0.561, 0.016] in the image\nAnd my action is Action: TYPE\nValue: Taylor Swift" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_905e2ca6-5659-4d6c-be5d-940a41712c87.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[label] October 08, 2023 -> CLICK\n[span] Nights -> CLICK\n[label] Miami -> CLICK\n[button] View details -> CLICK\n[link] Select package -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.787, 0.327, 0.965, 0.354] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/75db63ac-4fcf-400e-833f-d31f00cf6ab6_c6a46943-7ccf-4d6e-a06b-13264890131f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[link] Nearby Restaurants -> CLICK\n[div] Toronto -> CLICK\n[button] Chicago -> CLICK\n[button] Today -> CLICK\n[button] April 20, 2023. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.25, 0.562, 0.259] in the image\nAnd my action is Action: SELECT\nValue: 7 Guests" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_ac56a867-e610-41b4-a583-605eb29cd9c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.078, 0.32, 0.089] in the image\nAnd my action is Action: TYPE\nValue: NIAGRA FALLS" } ]

{ "bytes": "", "path": "./images/701bc7ed-4b55-4fd2-b333-128e55c0a4c2_21105c34-cac6-408f-b1ed-2ee9550a4dcd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an upcoming game which is releasing in August 2023 for PS5.\nPrevious actions:\n[button] Toggle Sidebar -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.2, 0.134, 0.209, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e84111f2-5193-421e-877a-9af8418b558a_79eb3b5b-854a-44b5-a115-c239a4d58c3f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gaming desktop with an rtx4000 GPU, available in stock.\nPrevious actions:\n[link]  Computer Systems  -> HOVER\n[link] Gaming Desktops -> CLICK\n[span] NVIDIA GeForce RTX 4000 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.2, 0.192, 0.217] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_eea26e1d-39b7-4781-b30d-dbdf56df77fa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[generic] Previous Month -> CLICK\n[gridcell] 31 -> CLICK\n[button] Update Chart -> CLICK\n[checkbox] Chevrolet  -> CLICK\n[checkbox] Ford  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.398, 0.509, 0.408, 0.521] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c7b0d1bc-2a0c-4060-92dd-cd4b8721b625_5d332384-8419-4484-8e27-3a97401f38f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] WHERE DO YOU WANT TO GO? -> TYPE: Lansing" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.228, 0.226, 0.52, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a2befd0-5e90-4bed-81b5-8ee0a93873df_e85f24b8-77cd-4c47-b407-05b6a636c04c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 RPG video games.\nPrevious actions:\n[button] Video Games chevron_right -> CLICK\n[button] Shop all -> CLICK\n[link] Filter -> CLICK\n[button] Genre -> CLICK\n[link] View More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.679, 0.063, 0.692] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58badcfc-343a-47c1-8aec-f609925eb4ed_121024fb-90f8-4d41-be93-5f26d9dabfc3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ricky Kej track to listen and share which has been added in the last year and is between 2 to 10 minutes.\nPrevious actions:\n[searchbox] Search -> TYPE: Ricky Kej\n[link] Search for “Ricky Kej” -> CLICK\n[link] Tracks -> CLICK\n[link] Added any time -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.472, 0.212, 0.492] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e44c63b-2c7a-445c-b9c4-6580f4271268_aab2a04e-c41e-4057-abc6-d839f51cfcc6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the status of a rebate for Monty Lue, house number 4847, zip code 10019\nPrevious actions:\n[link] Rebate Center -> CLICK\n[link] Track your rebates -> CLICK\n[textbox] * Required Fields First Initial * Required Fields... -> TYPE: Monty" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.32, 0.476, 0.348] in the image\nAnd my action is Action: TYPE\nValue: Lue" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_f785e1b7-a569-4764-9ed9-af5a405d8962.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Limited Time Offers -> CLICK\n[button] Show filter modal Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.628, 0.311, 0.81, 0.326] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9f5f0d0-7241-4a28-b387-c65a0ce52a61_82cc36d2-5e6b-4fff-b30e-4cea1a55c919.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental car in Miami, FL for pick up at the airport and drop off at a different location within the same city.\nPrevious actions:\n[tab] Different drop-off -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Miami Airport\n[span] Miami -> CLICK\n[textbox] Drop-off location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.413, 0.175, 0.554, 0.218] in the image\nAnd my action is Action: TYPE\nValue: Miami" } ]

{ "bytes": "", "path": "./images/56d210ec-22eb-4b3f-ba76-ee531403701a_b4b72b7a-2b9a-4bc6-9d43-34f2094f2bb1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[button] Meetings & Events -> CLICK\n[link] Book An Event Book a Meeting or Event -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.247, 0.336, 0.297] in the image\nAnd my action is Action: TYPE\nValue: Boston" } ]

{ "bytes": "", "path": "./images/401c4e6f-6b0b-47b4-8157-92d7ca468bbc_dad6690b-9b3e-4395-bd06-9aa065bf4027.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[heading] CAR -> CLICK\n[combobox] Enter pick up city, airport name, or airport code. -> TYPE: Brooklyn Central" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.252, 0.329, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f52ba76c-e5fc-48e5-85f3-41d4234a5c5f_1bc4d405-9f40-47ef-80b3-eaf62e4f49a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.142, 0.291, 0.164] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/851998b2-fda2-4bd4-a822-f1871a9fde12_7a51a447-19e0-40e9-9568-7af78ea6557b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of action figure items available for pre order.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.118, 0.084, 0.126] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_09c7f72f-1512-4342-b3c3-ae639ae8cdfc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[span] Washington County Regional Apo -> CLICK\n[link] Make a Reservation -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] Next -> CLICK\n[link] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.639, 0.233, 0.666, 0.246] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/76294719-e146-4f92-986f-42b86a9808c7_9b6f677f-1342-423b-bb5f-68412e75b9ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Los Angeles, California, and set Riverside as my store and add a card from that store to my favorites\nPrevious actions:\n[link] Find a store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.204, 0.371, 0.796, 0.409] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c254dcec-bd9b-4cf0-9225-9d2bf1345f38_f7d7601c-aa74-4cfc-a9c4-2f08fe628d44.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check Real Madrid player Vinicius Junior bio\nPrevious actions:\n[button] MORE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.18, 0.165, 0.467, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b431888-9909-40b5-8351-be52905e4d5a_ec42f184-f160-4f42-94d4-6789b2afea9b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Real Madrid team schedule of the UEFA Champions League championship.\nPrevious actions:\n[button] Open Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.04, 0.931, 0.063] in the image\nAnd my action is Action: TYPE\nValue: Real Madrid" } ]

{ "bytes": "", "path": "./images/9cd20dc6-d2a5-4e8f-9252-549f2c51413c_8be9df77-6ac7-4962-bc6b-b8084033cc94.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View inventory of Tesla Model S that are blue and new with 19\" wheels within 50 miles of zip code 60602.\nPrevious actions:\n[link] Model S -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.26, 0.491, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1943febc-0635-4124-871c-578c4d9f5a44_a0acf9c4-877d-41bf-b856-126033533bdb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular guitar tab for Absolute Beginners.\nPrevious actions:\n[link] Tabs -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.825, 0.231, 0.97, 0.247] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/969f36c3-52e7-42da-80bd-11a2d04d53ae_97b3ffde-528a-43c7-8306-22f3294f8b0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Biography of the NFL player named Michael Jordan\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Michael Jordan" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.039, 0.931, 0.062] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a35becb-e07b-4235-8cd3-fc2a29f8dd6f_31d78d33-b4df-433c-8033-62c738f1a8a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the most most popular of all time tab to a playlist\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Tab -> CLICK\n[svg] -> CLICK\n[link] Most popular of all time -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.38, 0.255, 0.485, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a919aa15-2acf-4090-8468-1d3a0d6450b1_2a72834c-741f-4059-8cb2-0a6769c33a32.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.302, 0.234, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c254dcec-bd9b-4cf0-9225-9d2bf1345f38_daaa0ead-b5e3-4a9e-91aa-d9cadc1b97dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check Real Madrid player Vinicius Junior bio\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.895, 0.109, 0.942, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_bc8c7895-1ab4-407c-85e6-11dfd925cfa6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.34, 0.411, 0.397] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6760de22-dc0e-4b29-916f-a6a78f2c0551_b65f2754-439c-42c9-a484-846c10998517.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 prices for upcoming Los Angeles Lakers games.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.095, 0.012, 0.156, 0.04] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d042ee7e-a2eb-448b-9942-b7aacc9115be_a6eff9d8-88ca-429b-9bdf-a7955bd4eb06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 soonest upcoming event near zip code 90028.\nPrevious actions:\n[link] Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.169, 0.293, 0.187] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_728205e5-9af6-447c-8866-339071d7f193.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[radio] New List -> CLICK\n[textbox] Title -> TYPE: New\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] Electronic -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.154, 0.362, 0.271, 0.444] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b56d5b8-1f41-43ca-9f21-369d849f1aa0_edb09eb7-6a8c-4aeb-9b52-796762ca821d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the season pass prices for Hurricane HarborLos Angeles.\nPrevious actions:\n[span] Hurricane Harbor Los Angeles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.653, 0.844, 0.721] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e1a344d-a27b-4613-8863-7afad0829b23_0cb8de0b-1d19-4944-9449-4e01d24cb987.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Rugs -> CLICK\n[link] Washable Rugs Washable Rugs -> CLICK\n[span] Color -> CLICK\n[link] Blue (237) -> CLICK\n[span] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.289, 0.111, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_5b60b5ed-44e7-434e-8908-e11418f9e4dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[img] Increase children -> CLICK\n[img] Increase infants -> CLICK\n[combobox] Child 1 age -> SELECT: 4\n[combobox] Infant 1 age -> SELECT: Under 1\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.868, 0.103, 0.931, 0.12] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e50b35f-7af9-4835-a741-158c2d941722_c78075a6-7141-410a-82c2-a1fdd561cf38.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Destination or property -> TYPE: Athens, Attica, Greeece\n[div] , Greece -> CLICK\n[div] Choose date -> CLICK\n[generic] 1 -> CLICK\n[div] Choose date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.344, 0.095, 0.368] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/988ff1b8-c9e8-44af-a729-33f0e99c9dbf_4581fcd6-7468-4230-b488-bcaac1055d22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars with AWD with maximum budget of $50,000.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.0, 0.605, 0.046] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c987dd1d-9ade-4701-8cdb-a31f8f3bf673_999f432e-b9a3-4a3f-87fc-7f3e4c568500.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[checkbox] Offers Takeout -> CLICK\n[button] Thai -> CLICK\n[button] See all -> CLICK\n[checkbox] All staff fully vaccinated -> CLICK\n[checkbox] Accepts Apple Pay -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.321, 0.658, 0.336] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b6385ea-0cdc-4ed8-be93-dc90113d2255_de4459d6-26bf-4a32-9099-9880aab98615.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Apple Stores close to zip code 90028\nPrevious actions:\n[link] Store -> HOVER\n[link] Find a Store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.331, 0.042, 0.669, 0.073] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_f485178c-d6c3-4937-b013-bafc9d8fe989.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[link] EXPLORE MULTI-RIDE PASSES -> CLICK\n[textbox] From -> TYPE: WASHINGTON\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] To -> TYPE: NEW YORK\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.362, 0.826, 0.389] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_6b113310-2e4d-4c97-b6e3-51d42e406e3b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] -> CLICK\n[button] close -> CLICK\n[button] Material -> CLICK\n[div] -> CLICK\n[button] close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.172, 0.237, 0.218] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_fbe6ff6d-5197-4a28-8a47-777faa60d37b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: BIRMINGHAM\n[span] Birmingham -> CLICK\n[checkbox] Return to a different location -> CLICK\n[searchbox] Return Location (ZIP, City or Airport) (required) -> TYPE: MONTGOM\n[span] Montgom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.589, 0.271, 0.635] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2cdee3d3-54d9-4f55-a8de-79ba9e2da28c_8734306f-5a8a-4671-a560-5850fbb319a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 theaters for Creed III within 20 miles of zip code 90028.\nPrevious actions:\n[img] movie poster for Creed III -> CLICK\n[link] get tickets for Creed III -> CLICK\n[select] AMC Columbus 10 -> SELECT: Change Location..." }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.092, 0.711, 0.121] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

{ "bytes": "", "path": "./images/e62d1f6c-d98c-4ea2-b699-527eeedf3e9b_b9e28e22-0524-4e6b-a3f2-13059124e719.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[link] Beverage Packages -> CLICK\n[button] add Bottomless Bubbles to the cart with price $9.5... -> CLICK\n[div] I want to give a gift to a booked cruiser -> CLICK\n[textbox] first-name -> TYPE: Joe\n[textbox] last-name -> TYPE: Bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.3, 0.434, 0.322] in the image\nAnd my action is Action: TYPE\nValue: 101010" } ]

{ "bytes": "", "path": "./images/632bb279-036c-48e5-b40a-962b2e90d6d1_fdca6b87-1298-4b66-bbfa-d325894b0f2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 winter coats featured in the weekly ad and is at least 15% off.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.028, 0.821, 0.047] in the image\nAnd my action is Action: TYPE\nValue: winter coat" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_471f0a54-bca2-48ac-91d6-7b20917a0ec8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[span] 48 mo -> CLICK\n[span] Get pre-qualified -> CLICK\n[button] Get started -> CLICK\n[textbox] First name -> TYPE: john\n[textbox] Last name -> TYPE: doew" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.419, 0.495, 0.459] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_1a324d9d-69b2-4367-9576-c0f051d94050.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.256, 0.255, 0.292] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab139e9d-eb99-47f7-8d0b-f93479fadadf_b3e14891-f17f-4a02-9c65-53333af0daf6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a bus using service number 5456165184.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.484, 0.013, 0.601, 0.061] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5098c679-dacc-4abd-9331-18b898f936dd_eaf07f0c-2487-42fc-9bae-98d8979b6192.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the St louis park policies regarding security?\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags St. Louis -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.402, 0.844, 0.453] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/254a67f6-3e37-4f12-838d-2d9fb0cedbf0_c99edf07-d6a6-46ea-a1da-f1cdbea62441.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 stats of the Athletic Club from spanish Laliga\nPrevious actions:\n[li] Soccer -> CLICK\n[link] Teams  -> CLICK\n[select] UEFA Champions League -> SELECT: Spanish LaLiga" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.111, 0.337, 0.131, 0.344] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/62c5067e-daff-4af6-bd79-83f6a969f4d6_7d5bb406-d247-416d-8e13-dd2cf463b43e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details of the fastest trip between 52nd Street,Brooklyn and 74th Street, Brooklyn, leaving now, that is accessible for a disabled person.\nPrevious actions:\n[searchbox] From -> TYPE: 52nd street, brooklyn\n[listitem] 52nd Street, Brooklyn, NY, USA -> CLICK\n[searchbox] To -> TYPE: 74th street, brooklyn\n[listitem] 74th Street, Brooklyn, NY, USA -> CLICK\n[label] Accessible Trip -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.389, 0.359, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/41cd71cb-cae5-41c8-abe8-67e42fabd4a5_0e2c3790-5fc1-451f-bc5a-f9e29750564c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details of Grand National Parks tour.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.26, 0.022, 0.309, 0.045] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_076445f7-fdd3-49f9-a7d9-642f2d7090a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[link] Fresh Fruits -> CLICK\n[span] Add -> CLICK\n[span] Add -> CLICK\n[path] -> CLICK\n[link] Fresh Vegetables -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.903, 0.208, 0.964, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f84075a2-9d97-4964-9c80-70f5bee8a418_47176cdb-d2c8-4197-8b6c-cb83c22fe1ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my trip with ticket number 3329456534543 along with my name John Green\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[combobox] Find Your Trip By -> CLICK\n[option] Ticket Number -> CLICK\n[input] -> TYPE: 3329456534543" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.582, 0.095, 0.707, 0.129] in the image\nAnd my action is Action: TYPE\nValue: John" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_68c92172-9b4e-41fd-866d-129ce1846de4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.183, 0.592, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff6ff6e5-e73c-4ba2-809e-59a1e269d68f_0e448126-506e-4091-91af-91117f73e5d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hair Loss Evaluation and Treatment in 10018 and show directions.\nPrevious actions:\n[button] Hair Loss Evaluation & Treatment -> CLICK\n[link] Hair Loss Evaluation & Treatment -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> TYPE: 10018\n[button] Find care -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.385, 0.43, 0.448, 0.464] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1df0723c-f732-4ecb-b202-8e1854b7c079_55207068-c425-4a70-ad93-db28b62041e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse a list of rental vehicles for Brooklyn, OH, US for 18 year old renter.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: Brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.739, 0.83, 0.786] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_9d457ae2-7f3a-454c-9bcd-38738fdc80e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Pre-owned -> CLICK\n[button] Sort: Best Match -> CLICK\n[link] Time: newly listed -> CLICK\n[button] Price -> CLICK\n[link] Under $75.00 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.299, 0.214, 0.412, 0.231] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5a0a291-ef9c-408d-9505-af7aeb6f5280_266eb157-7298-4781-b591-f73f82a00451.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the Railcard options for a 20 year old couple traveling within London and the South East\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.145, 0.579, 0.187] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b7cead3-475d-41a4-a018-db89c7ace632_17db9ef9-89fe-482a-bfe0-9e2bf9d76253.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Shipping Address -> ENTER\n[spinbutton] Home Square Footage -> TYPE: 200\n[combobox] Number of Stories -> SELECT: Two-Story\n[button] Next -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.854, 0.403, 0.959, 0.436] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_2161ad6c-0a74-439a-ad07-2493fe8039c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.633, 0.701, 0.867, 0.899] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36ab5d78-2f6b-47a6-ad88-3f6c8fdc3513_625191e5-adcb-4948-a105-2c4e95dad39f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movies playing today at the theater closest to zip code 10001\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.325, 0.022, 0.424, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_3b88c290-cc6d-40d9-8de4-2f891e6650c7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[img] james9091 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.072, 0.411, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6f4e562e-91f9-401d-8730-af947985b821_8815465b-cee1-4d62-bd97-da432f3cf972.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3 most rated to watch tv shows or movies on Amazon Prime to watchlist.\nPrevious actions:\n[link] What to Watch on Amazon Prime -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.3, 0.638, 0.317] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e72f9c32-4633-4fcf-abd7-b7cc4a9aaba3_cb08d3e8-86b1-44c5-9bee-0261182c7acd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 similar artists to the Weekend.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: the weeknd\n[button] Search -> CLICK\n[a] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.888, 0.398, 0.957, 0.414] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3edc9c7-397d-478b-a0b9-0ffa0897acca_971e520c-3d24-499b-9111-fd67d7d1a884.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 person named John Smith in New York.\nPrevious actions:\n[link] Find People -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.228, 0.336, 0.246] in the image\nAnd my action is Action: TYPE\nValue: John" } ]

{ "bytes": "", "path": "./images/581da9fe-4d75-42a7-b138-9b287a153575_71a88ba7-ab8d-470d-bcab-c04236870135.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pair of mens running shoes in black, size 7 extra wide, 4+ stars and under $50 and add them to my cart\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.009, 0.651, 0.039] in the image\nAnd my action is Action: TYPE\nValue: mens black running shoes" } ]

{ "bytes": "", "path": "./images/5ad0f114-6cea-4f61-af3d-f9f4d4096d6c_d248d946-05c5-485a-bb16-dd322317f149.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Uncharted: Legacy of Thieves Collection to my guide and find the Queen's bracelet information.\nPrevious actions:\n[link] Guides -> CLICK\n[svg] -> CLICK\n[searchbox] Search -> TYPE: Uncharted Legacy of Thieves Collection" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.272, 0.677, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f57e6c0a-8f8b-4756-9f1d-1bdea7a0af5c_b955660b-1f8d-4a21-b953-dac02bb5c70c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pack of toilet paper and a bottle of laundry detergent to your Amazon cart with the lowest total price.\nPrevious actions:\n[option] Price: Low to High -> CLICK\n[button] Add to Cart -> CLICK\n[textbox] Search Amazon -> TYPE: laundry detergent\n[button] Go -> CLICK\n[span] Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.785, 0.086, 0.917, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/73960473-941b-4e09-8eb1-f059b85c2dba_fb963821-351c-4418-8bbc-a5f87f916ed8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of one-way flights today (April 17) from Chicago to Paris.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: Chicago\n[menuitem] Chicago United States of America ORD OHare Interna... -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: Paris\n[menuitem] Paris France CDG Charles De Gaulle Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.266, 0.634, 0.28] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a4397261-95a5-4d57-a531-6082b2af8ac3_fe15d851-e3ca-40c2-bc4a-afb820d1d12c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 black sleeping pad that is under $40.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.258, 0.055, 0.798, 0.075] in the image\nAnd my action is Action: TYPE\nValue: black sleeping bag" } ]

{ "bytes": "", "path": "./images/c497534c-76a5-4ffb-af9a-10ee7afcc784_648d07dc-b2c7-47e8-b6b9-2c603d07455d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a car to book with miles to pick up on Caldwell (Ohio) on april 8 at 8 am and return on april 13 on noon at the same location\nPrevious actions:\n[LabelText] Enter pick up city, airport name, or airport code. -> TYPE: caldwell\n[div] Caldwell -> CLICK\n[textbox] Pickup -> CLICK\n[button] Saturday, April 8, 2023 -> CLICK\n[button] Thursday, April 13, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.625, 0.266, 0.658] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_eada1fe6-09c0-45de-a024-e035bf9aa036.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[span] -> CLICK\n[button] Sort by:Our top picks -> CLICK\n[div] Price (lowest first) -> CLICK\n[link] See availability -> CLICK\n[button] Reserve -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.666, 0.923, 0.692] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/370a037c-c397-4adb-ab7c-0c388f448f68_5e4409af-2205-49f1-a595-13b9617f85a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find vinyl records at the lowest price.\nPrevious actions:\n[button] Marketplace -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.054, 0.183, 0.069] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_47aabd28-f643-4dbd-96ca-fcd0b7cbaae2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.24, 0.5, 0.276] in the image\nAnd my action is Action: TYPE\nValue: Harrt Reid Intl Airport, LAS" } ]

{ "bytes": "", "path": "./images/33064851-00d9-46c8-b0b7-6b5048005c51_ac2a90b7-0655-4a0e-afc6-64e9c8c133ba.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[link] Registry -> CLICK\n[button] Find a registry -> CLICK\n[textbox] First name -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.17, 0.197, 0.37, 0.222] in the image\nAnd my action is Action: TYPE\nValue: SHELDON" } ]

{ "bytes": "", "path": "./images/09660a8d-b01d-4e93-9dd2-0b4af256bc80_e22f283f-8da1-4294-ac2c-90e0d472d487.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Change the language to UK English and the currency to Euros\nPrevious actions:\n[svg] -> CLICK\n[combobox] Language -> SELECT: 🇬🇧 English (UK)\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.438, 0.206, 0.639, 0.237] in the image\nAnd my action is Action: SELECT\nValue: Euro (EUR/€)" } ]

{ "bytes": "", "path": "./images/74cb088a-06d9-4a5e-9b00-61fd6b874e89_21a13bd7-0205-4eb5-bf16-53f77d303977.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 exercise events taking place in San Francisco between July 10-31.\nPrevious actions:\n[link] Sports & Fitness -> CLICK\n[svg] -> CLICK\n[combobox] autocomplete -> TYPE: San Francisco\n[div] CA, USA -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.224, 0.273, 0.248] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_6c06c719-5c8f-4536-bf8c-e31d5d14af89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Samsung-made and larger than 11-inch screen Android tablet, in the price range of 200 to 300 dollars and add it to the cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.304, 0.215, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61563837-99af-45e2-a13f-9d6bd9f74a81_7f372b63-9007-46eb-9765-517c2ca4b480.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the external solid state drives available with lowest price first.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] See All -> CLICK\n[link] Computers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.241, 0.285, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5e5f14-c875-4cfd-a517-175619491b90_d7cbd9b8-6505-43f7-a163-d7c00bfd62a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[link] NFL -> CLICK\n[link] Scores -> CLICK\n[button] Calendar -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.211, 0.514, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8308d10f-3904-473a-a186-c6b8f939f018_8f546563-ff13-45a3-8764-50c7781f81b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest private sightseeing trip of India in the month of June\nPrevious actions:\n[textbox] Where to? -> TYPE: India\n[button] India Asia -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.33, 0.777, 0.344] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4786982f-25f5-4bf8-bb91-522656489f63_424f88c5-1dc6-439d-8cba-43b2225ac064.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[searchbox] Please type your destination -> TYPE: washington\n[option] Washington District of Columbia, United States -> CLICK\n[span] 25 -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.457, 0.26, 0.463, 0.267] in the image\nAnd my action is Action: CLICK" } ]