Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/7c2ab1ed-54b7-4316-8b2f-d7467e01b540_ba706103-fef4-4462-9ee1-8c8022b3388b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\n[link] Search for flights -> CLICK\n[textbox] Flight origin input -> TYPE: madurai\n[div] Madurai, Tamil Nadu, India -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.101, 0.262, 0.106] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4f8a347-b288-4a00-9e6b-89cbccda42d2_2804c209-5ed1-40c8-9ed5-bc60068ae0fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a parking near any airport in california starting april 20 and ending april 23\nPrevious actions:\n[link] Reserve Now -> CLICK\n[textbox] Select Start Date -> CLICK\n[gridcell] Thu Apr 20 2023 -> CLICK\n[textbox] Select End Date -> CLICK\n[gridcell] Sun Apr 23 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.644, 0.321, 0.844, 0.35] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_4eaaee20-45f8-42fd-8046-0020ea934869.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[tab] Flights -> CLICK\n[tab] One-way -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.781, 0.108, 0.85, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/408cc1bd-0a76-4bad-b5f4-11db4405047f_b0e6bcb2-ebc1-47f3-959c-3cba6751f827.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Boston Logan Airport to North Station.\nPrevious actions:\n[tab] Trip Planner -> CLICK\n[combobox] From -> TYPE: Boston Logan Airport\n[option] Boston Logan Int'l Airport, 1 Harborside Dr, East ... -> CLICK\n[combobox] To  -> TYPE: North Station\n[link] T orange line green line D green line E commuter ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.663, 0.129, 0.825, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b2f241e-8d1f-4f22-be2f-5722ceff23a3_4e1f470d-9dfd-4136-9785-360b584f0683.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 treehouse in India with free cancellation and below $100 per night.\nPrevious actions:\n[img] -> CLICK\n[button] Location Anywhere -> CLICK\n[textbox] Where -> TYPE: India \n[div] India -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.898, 0.04, 0.97, 0.061] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/af8a7016-67db-4a6d-ab61-04eeb1f244cb_0387a16c-0486-4263-97b5-a8e3145814bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round trip from Phoenix to Miami with maximum budget of $2000.\nPrevious actions:\n[combobox] Flying from -> TYPE: Phoenix\n[button] Phoenix, AZ, US (PHX) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.68, 0.616, 0.813, 0.648] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a51b649f-15b4-4ce4-936e-0b76efa0dd2d_0f407117-ae70-42ea-9230-41fca96353ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel credits for the passenger Leon Sin with the record locator jcqnhd ans ticket number 1234567\nPrevious actions:\n[searchbox] Search AA.com® -> TYPE: travel credit" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.759, 0.003, 0.925, 0.026] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_eef7607c-2b44-4939-8098-d82b207e60f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[textbox] Where? -> TYPE: Europe\n[div] Europe -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] July -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.008, 0.82, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_69b182b6-f5e4-4aa1-85d5-a98b88129a7a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[combobox] Search by product -> TYPE: mirror\n[button] Search -> CLICK\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: atlanta georgia" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.917, 0.065, 0.948, 0.082] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_f5cb11a1-e04c-4d99-98f2-5c902d3c1283.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[span] -> CLICK\n[span] 1 -> CLICK\n[div] Sort by -> CLICK\n[div] Top rated -> CLICK\n[link] Get tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.457, 0.295, 0.614, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e84111f2-5193-421e-877a-9af8418b558a_a1bb6c97-bc21-4cbe-ba5b-6a8d0e0536e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.096, 0.215, 0.118] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_065612a0-3a86-4991-b06d-abb9ec4e1de3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[button] Find a Location -> CLICK\n[link] 1 Laguardia Airport (LGA)  -> CLICK\n[combobox] Pick Up Time -> SELECT: midnight\n[textbox] Enter your pick-up location or zip code -> CLICK\n[combobox] Return Time -> SELECT: noon" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.295, 0.5, 0.34] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d538537c-ff96-4918-8807-af09b26199d1_778f35dc-5a7c-4835-a404-f057a5b4311b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flights between SFO and EWR using the Boeing 787-9 aircraft\nPrevious actions:\n[textbox] Origin -> CLICK\n[textbox] Origin -> TYPE: SFO\n[div] San Francisco Int'l (San Francisco) - -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.257, 0.619, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f118238f-ef8f-4b63-9159-a81e981ef46e_3ed11a2a-8fd5-4f13-af2b-be976fd73a0c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 decorative LED Candles to the cart.\nPrevious actions:\n[link] Products -> CLICK\n[button] Lighting -> CLICK\n[link] Decorative lighting -> CLICK\n[img] LED candles -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.821, 0.508, 0.938, 0.551] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_ccced979-b0e9-4efc-997c-d53364206c7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 premium car in Brooklyn for a day.\nPrevious actions:\n[tab] Travel Info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.792, 0.154, 0.842, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee9e993b-0254-465d-bb04-072e01e5f498_18cbba50-27fd-4d98-84c7-7b9802e028d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the selection of fishing reels that are power assisted and are in stock.\nPrevious actions:\n[link] Fishing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.181, 0.192, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e50b35f-7af9-4835-a741-158c2d941722_8838a017-236c-4418-8aa7-48ad6c0514bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] 1 -> CLICK\n[div] Choose date -> CLICK\n[generic] 3 -> CLICK\n[button] Search -> CLICK\n[button] Yes, I agree -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.051, 0.386, 0.074] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fcb50c4e-a89e-4f18-b7c0-423295e7c298_9b1378d8-3623-4724-a26a-b493469ca55c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a certified pre-owned front-wheel drive Jeep, Compass model car with single owner and the lowest mileage within 500 miles of zip 59316.\nPrevious actions:\n[button] Search Certified Pre-Owned -> CLICK\n[p] Four-Wheel Drive -> CLICK\n[p] Single Owner -> CLICK\n[combobox] Select Sort Order -> SELECT: Lowest mileage first\n[div] Request Info -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.318, 0.55, 0.682, 0.588] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_2c9106bd-de29-4ee2-a559-b876ebeec9de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] -> CLICK\n[div] Multi-city -> CLICK\n[span] Sat 13 May -> CLICK\n[checkbox] 1 June 2023 -> CLICK\n[span] Where from? -> TYPE: TOKYO" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.08, 0.232, 0.337, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_a5b8ee8c-a196-4fb7-b6c4-b3c98765d90c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 in New York City by month on July 5th start date.\nPrevious actions:\n[tab] Monthly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.082, 0.785, 0.104] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/d042ee7e-a2eb-448b-9942-b7aacc9115be_5e1ff95e-1727-43e6-9876-c4e2480529f4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] Near you -> CLICK\n[textbox] Location search -> TYPE: 90028" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.438, 0.157, 0.448] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_9e3771b1-9b5b-4f07-b3d7-ccd343968002.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the mystery vehicle to pick up at Bradenton in Mahattan, Florida on april 20 at 3 pm and return at 6pm\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Manhattan\n[div] Manhattan -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.261, 0.639, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1f4e4f7-3fb0-4aeb-8123-4882a1f39cb2_bf68b1e8-6439-482f-9667-b1bd3845d2e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new arrival of kids graphic t-shirt for 13 years old boy\nPrevious actions:\n[link] KIDS -> CLICK\n[tab] Tops -> CLICK\n[link] UT: Graphic Tees -> CLICK\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.891, 0.209, 0.91, 0.219] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1860601a-faef-4dba-8cbb-807ea8434dca_f31dd533-86bd-4d07-af19-fa8d0f61bb64.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[span] (HND) -> CLICK\n[combobox] Nationality -> CLICK\n[option] United States of America (USA) -> CLICK\n[combobox] Vaccination status Vaccination status -> CLICK\n[option] Fully vaccinated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.904, 0.15, 0.944, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_32c17d65-3a2c-4123-b579-31095e299b66.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[button] Water -> HOVER\n[link] Paddle Boards -> CLICK\n[img] TAHE Beach SUP-Yak Tandem Inflatable Stand Up Padd... -> CLICK\n[button] Add to cart—$799.95 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.269, 0.229, 0.494, 0.254] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_2e501862-ee92-4af0-8eb0-7594690edef9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[div] Filter -> CLICK\n[RootWebArea] Women's Sports Bras | Under Armour -> CLICK\n[button] Show more -> CLICK\n[div] Color -> CLICK\n[link] Refine by color: Purple -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.723, 0.233, 0.763] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_1335391d-8f77-4fc8-ab7e-983f67cc075a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated romantic summer vacations in Spain\nPrevious actions:\n[textbox] Where? -> CLICK\n[textbox] Where? -> TYPE: Spain\n[div] Spain -> CLICK\n[textbox] When? -> CLICK\n[li] Summer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.009, 0.82, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c7b0d1bc-2a0c-4060-92dd-cd4b8721b625_88c965f7-c3ca-411a-a58b-9c9db6803254.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.104, 0.434, 0.12] in the image\nAnd my action is Action: TYPE\nValue: Lansing" } ]

{ "bytes": "", "path": "./images/1684f224-47d5-45ed-9a26-821b98b851cd_f5e72948-efaa-4d29-88d8-b29de4097021.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[img] Add -> CLICK\n[i] -> CLICK\n[span] SEARCH -> CLICK\n[textbox] Minimum price filter -> TYPE: 150\n[textbox] Maximum price filter -> TYPE: 200" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.204, 0.089, 0.219] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_8ee9e907-8abc-4563-b292-038c3e0e5edf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] SAIL TO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.655, 0.274, 0.688] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a440d5f-1cc8-43de-86f5-ea181b0d12f8_146148dd-b0a6-4ee8-a061-0ecbe585e606.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Who were the NBA season leaders from the 2020-21 regular season?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.028, 0.178, 0.046] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_96e8f2c6-30ca-4af9-9cad-68c16acf5eff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK\n[gridcell] 31 -> CLICK\n[button] Update Chart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.398, 0.617, 0.408, 0.622] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_75c668c5-0c35-4978-83b5-45de8d786e2c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\n[option] Chennai, Tamil Nadu, India -> CLICK\n[button] Monday March 20, 2023 -> CLICK\n[button] Search -> CLICK\n[svg] -> CLICK\n[tab] Review score -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.745, 0.081, 0.757] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_0f984b4b-992d-4e92-b019-f3e933eb6465.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 denise.bloom@bbt.com and Debbie Wolowitz on email id debbie.wo@bbt.com.\nPrevious actions:\n[textarea] -> TYPE: Happy Birthday Love\n[input] -> TYPE: Stuart Bloom\n[input] -> TYPE: Denise\n[input] -> TYPE: Bloom\n[input] -> TYPE: denise.bloom@bbt.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.639, 0.339, 0.677] in the image\nAnd my action is Action: TYPE\nValue: Debbi" } ]

{ "bytes": "", "path": "./images/a92a83ca-25ff-4751-8754-c65ef858699d_0428fa36-92d7-4cc9-8e63-e5e07cfa06e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Lava Hot Springs East KOA photo gallery.\nPrevious actions:\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: Lave Hot Springs East KOA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.236, 0.225, 0.306, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_49946c93-dc95-4827-97d8-1d4712866ae9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[button] Find & Reserve -> CLICK\n[link] Book Meetings & Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.266, 0.476, 0.28] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_4ddbdea8-b5ac-4696-820c-befd4dff83c6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[checkbox] No Accidents (4) -> CLICK\n[combobox] Sort By: -> SELECT: Price - Lowest\n[link] Confirm Availability for Used 2019 Buick Encore Pr... -> CLICK\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.357, 0.254, 0.493, 0.283] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9dfba9af-d79e-4a75-83b4-0f85ab04c2e6_4b230fe6-7974-432d-89e3-e9d599c8b47e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a price quote for new Kia Carnival for 11101.\nPrevious actions:\n[link] Cars for Sale -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.03, 0.673, 0.03] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0ff1648e-28bb-4014-9b8a-3c050c25e334_d1e667d6-a1c0-4ea4-8af5-2197e32eef24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 women's hiking boots section and filter the results to show only those that are waterproof and have a rating of at least 4 stars and size 6.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.052, 0.128, 0.072] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_f77f54bb-e260-4d62-a12d-3e8f3df35306.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 blazer for men with L size and add to wishlist.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: blazer\n[span] blazer -> CLICK\n[heading] Gender > Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.153, 0.471, 0.178] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2142cde-5bec-46ee-8d17-9b6ee52a66e8_a8f5854f-36b5-45ff-94b0-1a79573adb4e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 inventory of the Tesla Model S within 200 miles from 10001\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, 0.473, 0.491, 0.493] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5a0a291-ef9c-408d-9505-af7aeb6f5280_2aa336c5-81e8-426c-b8cc-18d8ed689c5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.838, 0.009, 0.863, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ecb649da-0ca7-4707-8ebb-8707296e28b7_0f4264dd-1f6e-4313-b1e6-c3f392fc27c9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for flights available from Calgary (CYYC) to New York (ZNY).\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.336, 0.469, 0.355] in the image\nAnd my action is Action: TYPE\nValue: Calgary" } ]

{ "bytes": "", "path": "./images/2ff0909b-a8bb-4370-8428-9d355f5c6a67_75c1a95a-3206-4beb-9527-099e88355322.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the most popular photos of the Adam A-500 model aircraft.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.678, 0.047, 0.742, 0.068] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_d9a18977-172e-40e0-8bf9-513bbdf8ce7b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 denise.bloom@bbt.com and Debbie Wolowitz on email id debbie.wo@bbt.com.\nPrevious actions:\n[input] -> TYPE: Bloom\n[input] -> TYPE: denise.bloom@bbt.com\n[input] -> TYPE: Debbi\n[input] -> TYPE: Wolowitz\n[input] -> TYPE: debbi.wo@bbt.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.57, 0.809, 0.809, 0.844] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7bdf34b4-2aa0-4387-9f6a-f7d7c5d17119_4b74b3ef-b1db-41c2-a207-02fec15b8daa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the alerts and conditions for the Alagnak Wild River.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[combobox] Park Name -> TYPE: Alagnak" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.188, 0.784, 0.221] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4970cd99-ce6b-42e3-bc78-695c9d510f6c_662c8c2a-d32f-4265-85c2-2c854b72c7e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[link] FIND A CAMPGROUND  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.122, 0.266, 0.137] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ad0f114-6cea-4f61-af3d-f9f4d4096d6c_6474e85f-0cdf-4124-be63-64495755c3dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.204, 0.677, 0.246] in the image\nAnd my action is Action: TYPE\nValue: Uncharted Legacy of Thieves Collection" } ]

{ "bytes": "", "path": "./images/3b390b60-5c04-40ee-a5af-353def43ffbc_a5ebdd01-9df5-4350-a0cd-bdc3f2ca1173.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 japanese restaurants in Fresno with online delivery.\nPrevious actions:\n[link] CITY PAGES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.43, 0.131, 0.571, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1db33c6-c414-438b-bbfc-cdaa6cfc6b68_1aa6829d-0535-4794-be5c-4f934498abeb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check reviews for best electric SUV and find the 1 star rated review and mark it helpful.\nPrevious actions:\n[link] Car Reviews -> HOVER\n[link] Best Cars -> CLICK\n[img] Best SUVs image -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.232, 0.829, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_dda39a16-4008-4904-8895-51a26c5f8e31.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[option] United States of America -> CLICK\n[button] Team -> CLICK\n[searchbox] Search -> CLICK\n[option] Finance -> CLICK\n[button] Time Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.387, 0.307, 0.408] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc27fdda-c68f-4d43-bbcb-6c7954bf00ec_96dab6e9-ebf8-4646-813a-ded293589c49.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Target Stores located near Cincinnati, Ohio and filter by those that have a Starbucks.\nPrevious actions:\n[link] Find Stores -> CLICK\n[button] enter zip or city, state -> CLICK\n[textbox] City -> CLICK\n[textbox] City -> TYPE: Cincinnati\n[combobox] State -> SELECT: OH" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.656, 0.509, 0.697] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1202e28a-361d-4704-979a-526c599b4859_d1797a5c-2b21-43af-8036-66c4b2fa4941.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a fully electric car pickup at Athens Airport (ATH) Sat, Apr 1, 2023 and return to the same palce at Mon, Apr 3, 2023.\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: Athens\n[button] Athens Airport (ATH) Athens, Greece -> CLICK\n[div] Apr -> CLICK\n[generic] 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.341, 0.321, 0.362] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_7a897c64-a917-42b1-9c88-4587761e7767.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[gridcell] Fri, May 12, 2023 -> CLICK\n[div] Purpose of your event -> CLICK\n[li] Social -> CLICK\n[textbox] Guest rooms -> TYPE: 7\n[textbox] Event space -> TYPE: 50" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.663, 0.367, 0.959, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_c776cdbf-4c36-4f53-9966-ee977e4f6309.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[button] FIND TRAINS -> CLICK\n[span] Sort/Filter -> CLICK\n[checkbox] filter trains by Time of Day:6a-12p -> CLICK\n[mat-pseudo-checkbox] -> CLICK\n[button] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.705, 0.212, 0.831, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_5baed715-106d-4b5c-b7b0-353a8b06f423.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] Search -> CLICK\n[button] Select -> CLICK\n[button] Continue for $ 148 . 16 -> CLICK\n[button] Continue with Value fare -> CLICK\n[button] Log in later -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.69, 0.166, 0.728] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c7058499-3dc9-4175-9142-d22416d25a1f_f2307de6-5b1d-42b8-9bc9-b568deacc0e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the best VIP seat to the Red Hot Chili Peppers 2023 Tour\nPrevious actions:\n[link] Music -> HOVER\n[a] Genres -> HOVER\n[link] Jazz -> CLICK\n[img] Image for Red Hot Chili Peppers 2023 Tour -> CLICK\n[button] VIP -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 1.01, 0.08, 1.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_3afea1db-55b2-42ec-bbce-86728f28a0ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK\n[checkbox] Microsoft Microsoft -> CLICK\n[button] Color -> CLICK\n[link] White -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.674, 0.375, 0.723] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/64779409-c396-4779-a574-b219c3b22282_4952ce05-c06b-458e-b0ac-da5925c2ac39.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the longest skiing activity in August 10\nPrevious actions:\n[textbox] Where to? -> TYPE: skiing\n[button] When -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.307, 0.777, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_5f391dd3-bf59-4f55-8776-180a9fd6dc48.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] 1, Saturday, April 2023. Available. Select as chec... -> CLICK\n[button] 8, Saturday, April 2023. Available. Select as chec... -> CLICK\n[span] -> CLICK\n[span] Castles -> CLICK\n[button] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.19, 0.739, 0.2] in the image\nAnd my action is Action: TYPE\nValue: 1000" } ]

{ "bytes": "", "path": "./images/1b74fa2c-3236-45ac-9b4d-ff913112db52_87659e64-52c9-4193-842b-6676a7d6bf73.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking near Sofi stadium that allows to pay with phone.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: sofi stadium\n[span] SoFi Stadium -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.128, 0.336, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/551ab381-5bfe-4491-9602-0b0c584d1346_d71a5ed7-97e4-49b1-b3e5-d64c46ae7a24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Give me the IMDB recommendations of what to watch.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.288, 0.628, 0.31] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4cf5835-4726-4a84-bc8f-5023e95ddec9_416731f8-343d-415b-8f98-b01beae69685.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SkyMiles domestic Award Deals from Philadelphia to Atlanta.\nPrevious actions:\n[combobox] Origin -> CLICK\n[option] PHL Philadelphia, PA -> CLICK\n[combobox] Destination -> CLICK\n[option] ATL Atlanta, GA -> CLICK\n[button] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.365, 0.488, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14a4e19d-d82d-45dd-b4f0-6b60ed87d085_e63aff02-4d6c-4289-b897-91262275d712.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.172, 0.193, 0.189] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/759d1c94-3314-481f-8763-5918b00567c4_39ca15cc-f268-42e1-ba92-de0f199ac70b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Mexican restaurants in Concord, CA and start an order at La Pinata Mexican Restaurant.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.249, 0.023, 0.39, 0.037] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd2e9403-3201-4bb7-a19d-f475960cf5be_87e392a0-87a0-45b7-9c89-069cc86317ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Thai restaurants that offer delivery and have vegan options available.\nPrevious actions:\n[span] Thai Restaurants -> CLICK\n[button] Offers Delivery -> CLICK\n[span] 1 -> CLICK\n[button] See all -> CLICK\n[checkbox] Vegan -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.124, 0.688, 0.14] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9723022-04b9-4778-ad33-cf54eac3d393_bb12a018-b966-477f-8fec-249635e955eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find events starting from April 1, 2023 within 100 miles of New York and see who are going in the top listed event and follow all of them who are going.\nPrevious actions:\n[textbox] Location search -> TYPE: new york\n[span] New York -> CLICK\n[combobox] SEARCH RADIUS -> SELECT: 100 km\n[button] APPLY -> CLICK\n[button] From today -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.264, 0.287, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb3e2b61-c14c-4a15-8de4-7c12256d52c7_1c128c7d-67c5-454c-9aaa-82cd82e5e69d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for concerts taking place in Los Angeles, CA in the next month.\nPrevious actions:\n[option] Los Angeles, CA -> CLICK\n[span] Filter by -> CLICK\n[div] 16 -> CLICK\n[div] 16 -> CLICK\n[button] Apply -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.31, 0.264, 0.405] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a513befc-46c3-4bb6-87c0-8f219107c756_f7834a7a-41e6-48ab-9ed4-922a1940da9e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a NBA basketball game for the PS5 to the shoping cart\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: nba2k23\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.218, 0.179, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58f811fd-0f17-430b-befc-885605e13e41_53a1b63c-5d8d-48eb-a2b4-7246f1da4b0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\n[link] Cancel my order -> CLICK\n[input] -> TYPE: James Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.25, 0.759, 0.279] in the image\nAnd my action is Action: TYPE\nValue: buckeye.foobar@gmail.com" } ]

{ "bytes": "", "path": "./images/c5070129-37b1-4f87-930f-c45049a70e97_50e901a3-dcef-4026-a6b6-282ba62561c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 FareFinder to find flights for $150 or less from Dublin to anywhere.\nPrevious actions:\n[div] Dublin -> CLICK\n[textbox] To: -> CLICK\n[div] Anywhere -> CLICK\n[svg] -> CLICK\n[div] $ 150 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.718, 0.403, 0.862, 0.448] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_318ea7e0-6ab8-4357-9d9a-e407c2f4dfad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[DisclosureTriangle] All locations -> CLICK\n[li] NYC -> CLICK\n[DisclosureTriangle] All Categories -> CLICK\n[li] Outdoors -> CLICK\n[DisclosureTriangle] All Dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.329, 0.165, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_d0539316-5a09-4304-a9c2-2beef62f1c93.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[button] Property style -> CLICK\n[checkbox] Beach -> CLICK\n[div] Recommended -> CLICK\n[tab] Price (low to high) -> CLICK\n[div] View Deal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.672, 0.56, 0.959, 0.603] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/401c4e6f-6b0b-47b4-8157-92d7ca468bbc_6c7a7082-2897-41c7-9688-4b0f3d778cdb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.221, 0.116, 0.294, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/627a99f1-b2e4-4ce4-93f5-89e691f8c879_ba3ec399-f548-4454-b3f0-eaf53fce1d3b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Kevin Durant's bio\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.931, 0.043, 0.966, 0.072] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_cc4e6036-7475-48cc-99dd-d130b01c3dea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[button] Search without signing in -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.866, 0.222, 0.942, 0.232] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_66e14c21-122f-4ff8-af51-9510d38fef5f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Meetings & Events -> CLICK\n[link] Group Travel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.279, 0.142, 0.487, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0991035b-6acb-4dca-aaef-5384a0739781_cdb3023c-a1e1-4791-aeb1-ecfdcd3e3c26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 careers at the company on the Product Management team\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.826, 0.035, 0.879, 0.05] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c7a69f9-989d-4899-a3fe-94c952859007_84a83797-c89b-4fe8-a1d3-e2198a825f0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Chicago to London on 20 April and return on 23 April.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.301, 0.365, 0.317] in the image\nAnd my action is Action: TYPE\nValue: Chicago" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_588f22df-6300-45c1-839a-bdaf09f6b27b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[textbox] Going to -> TYPE: Miami, FL\n[button] Miami (MIA - Miami Intl.) Florida, United States -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] Departing April 11, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.963, 0.17, 0.981, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_a60ce1f0-5d1f-4a3b-a4fb-251b1c51f61b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[link] Rent a Moving Truck Budget Truck -> CLICK\n[textbox] US City,State or Zip Code -> TYPE: 07718" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.172, 0.352, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fe6b5531-ce29-4ba1-8e98-43b5fecf57fa_2a015d4e-2e74-4a02-ae2e-1e529eabf668.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest flight from London to New York on 9th May.\nPrevious actions:\n[combobox] Flying to -> TYPE: New York\n[option] Destination New York (NY) -> CLICK\n[span] 9 -> CLICK\n[button] SEARCH FLIGHTS -> CLICK\n[span] Price per person -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.01, 0.808, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a83c14aa-1a0b-4aaf-a801-ac828d2e81ca_ed47769d-ee72-44f7-bdc9-f58989e4f21d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 4 star rated Hotel in New York Timesquare for 2 adults.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: Timesqure New York\n[button] Times Square, New York, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.612, 0.108, 0.83, 0.125] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_deb51466-b520-47d8-bba4-841ca652c58f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[path] -> CLICK\n[span] -> CLICK\n[path] -> CLICK\n[span] -> CLICK\n[button] Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.221, 0.966, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_e2fccb19-f1cf-467f-9917-1202c07e965e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Eo -> CLICK\n[button] ​Jerzy Skolimowski -> CLICK\n[button] Add to list -> CLICK\n[menuitem] Create new list -> CLICK\n[textarea] -> TYPE: Directors" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.415, 0.609, 0.451] in the image\nAnd my action is Action: TYPE\nValue: To Watch" } ]

{ "bytes": "", "path": "./images/66a5b212-cf94-4917-8015-58970dc54187_6afdf927-8e32-47d0-a8a1-3197de949c01.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 amtrak national route map\nPrevious actions:\n[button] DESTINATIONS -> CLICK\n[link]  SEE ALL ROUTES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.235, 0.655, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_7e768de4-2cc5-4d90-8eb6-7b30dc596f7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[button] Find Your Truck -> CLICK\n[button] Select Truck -> CLICK\n[input] -> TYPE: 250\n[button] Continue to Location -> CLICK\n[select] Select a Pick-up Time -> SELECT: 04:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.236, 0.915, 0.254] in the image\nAnd my action is Action: SELECT\nValue: 04 30 PM" } ]

{ "bytes": "", "path": "./images/ff173880-e7f5-4b4e-b941-79e9c3504add_d0f8939d-9053-4418-a49a-b8bbb6bae5d9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find wall mirrors for under $20.\nPrevious actions:\n[link] Products -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.267, 0.32, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2ef470ab-b06a-4479-883f-78b4e3b94a04_1c3d2eff-3a63-4757-bdbf-48e0f4ba8d4d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[button] For Guests -> CLICK\n[link] Activities  -> CLICK\n[textbox] Location-Search -> TYPE: New York\n[link] New York City New York, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.127, 0.552, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7082615-e6e1-4981-b51b-9259671d1adf_765d1395-6d7e-496e-96ad-ce9fa6367197.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 your store to the one nearest to 07055\nPrevious actions:\n[span] Your store for 43219 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.67, 0.17, 0.847, 0.189] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/46a3683f-fbe0-40d0-8729-6c7964d994e6_11731204-34aa-4719-a789-eae83d26586a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[link] Mens -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Short Sleeves -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.74, 0.233, 0.788] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_7c149935-f2e7-47f5-beca-303dc388238e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[button] Style -> CLICK\n[link] French -> CLICK\n[button] Material -> CLICK\n[link] Oak -> CLICK\n[button] Time Period Manufactured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.612, 0.254, 0.752, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9f57055d-c269-47d7-99be-3525d725439e_6dc6377a-e668-4b3b-8e93-5f5f1899b8f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NBA team with the best odds to win the NBA title.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.056, 0.335, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_5df6d848-d5b7-4202-ac80-1959faf35581.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[button] Our Company -> CLICK\n[link] Careers  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.007, 0.317, 0.047, 0.324] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_bdc2d235-fba7-4911-a120-56b4a3e32410.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[generic] Saturday March 25th -> CLICK\n[button] Saturday March 25, 2023 -> CLICK\n[generic] Saturday April 1st -> CLICK\n[button] Saturday April 1, 2023 -> CLICK\n[button] Noon -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.285, 0.745, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ff347e6-e911-4af5-8151-7805a9e91b28_d0e2ec63-357b-4237-9476-b54c6feba4e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show current alerts for red line subway.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.582, 0.093, 0.722, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3786bf-56a4-4b4a-a94e-a4c1620cd0b2_7a9111bf-ea91-4f63-b47b-e1117bc84494.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 videos from the Oscar 2023.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Oscars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.197, 0.357, 0.221] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bef473f1-82a1-4359-a2c0-59b6dc2f6abb_7b768457-fd7e-478f-b7a5-e5b3b31acd34.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a park in Alaska that is also a National Heritage Area.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.298, 0.789, 0.32] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3cb44998-5a0c-44c5-84b7-ffb729a356d8_e1c0c2da-37ad-41aa-a735-8768c02f6928.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule between New York and Washington DC sorted by shortest trip.\nPrevious actions:\n[textbox] From -> TYPE: New York\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: Washington" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.327, 0.247, 0.559, 0.28] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_03315d1e-dfa4-4cc0-b5ee-7a7b8f4cf799.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: seattle" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.147, 0.491, 0.845, 0.514] in the image\nAnd my action is Action: CLICK" } ]