Datasets:

---

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 86

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental for an economy car in Houston from Mar 10 to Mar 13.\nPrevious actions:\n[link] Car rentals -> CLICK\n[textbox] Pick up -> TYPE: Houston\n[a] Houston, US -> CLICK\n[button] Search -> CLICK\n[button] Economy cars 5 Seats 1 Large bag 1 Small bag From ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.474, 0.214, 0.768, 0.221] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.0, 0.44, 0.055] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[button] Transit  -> CLICK\n[link] Parking -> CLICK\n[link] Find Parking Lots -> CLICK\n[button] Stations G–K  -> CLICK\n[link] Gloucester -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.337, 0.514, 0.539, 0.546] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant that offers African Cuisine in east village under $30\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.111, 0.615, 0.129] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of all movies that are being released in May 2023\nPrevious actions:\n[button] Reviews -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.342, 0.037, 0.355] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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? -> CLICK\n[textbox] Where? -> TYPE: Europe\n[div] Europe -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.532, 0.082, 0.567, 0.104] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[textbox] Same as pick-up -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Pick-up date April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.609, 0.393, 0.664, 0.411] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button] START A NEW BUILD -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.234, 0.868, 0.244] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] US City,State or Zip Code -> TYPE: 07718\n[textbox] mm/dd/yyyy -> CLICK\n[div] -> CLICK\n[link] 20 -> CLICK\n[select] Select 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 [0.171, 0.273, 0.181, 0.281] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an hourly parking in New York City of lowest price.\nPrevious actions:\n[textbox] Search for parking -> TYPE: New York City" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.124, 0.914, 0.132] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.0, 0.169, 0.044] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search the actor who won the Oscars for best actor in a suuporing role ine 1990, and add his upcoming movies to my watchlist.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.009, 0.1, 0.023] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of flights between Abidjan and Accra.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.706, 0.199, 0.954, 0.222] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[span] Community -> HOVER\n[link] Highest Ranked -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.143, 0.269, 0.156] in the image\nAnd my action is Action: SELECT\nValue: Adam A-500 (twin-piston) (26)" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[svg] -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Mediterranean -> CLICK\n[button] Submit -> CLICK\n[button] Open additional search filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.334, 0.306, 0.356] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find vintage clothing and sort the results by price from high to low.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: vintage clothing" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.203, 0.643, 0.219] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the list of off-Broadway theatre shows on April 19\nPrevious actions:\n[button] THEATRE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.147, 0.218, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 popular free online fashion class events occurring this weekend in English, find details of the top result event, save the event and follow the organizer of this event.\nPrevious actions:\n[label] -> CLICK\n[label] -> CLICK\n[svg] -> CLICK\n[div] RawElegant.Life -> CLICK\n[div] Envy Yourself With Beauty Makeup MasterClass -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.489, 0.24, 0.575, 0.273] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.093, 0.763, 0.137] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List upcoming animation and anime movies in theaters\nPrevious actions:\n[link] MOVIES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.377, 0.305, 0.491, 0.34] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[label] Business center (11) -> CLICK\n[label] High-speed Internet (11) -> CLICK\n[button] APPLY -> CLICK\n[generic] Distance -> CLICK\n[label] 0 - 5 Miles (2) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.86, 0.944, 0.96, 0.985] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[generic] 2 -> CLICK\n[div] May 2023 -> CLICK\n[div] Apr -> CLICK\n[div] Choose date -> CLICK\n[generic] 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.151, 0.953, 0.184] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the page with information about luggage and what to bring.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.121, 0.286, 0.166] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.26, 0.029, 0.309, 0.059] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me RPG video games.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.043, 0.036, 0.064] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\n[button] Broadcast TV Spokane (3) -> CLICK\n[textbox] Search -> TYPE: 99201\n[button] Antenna -> CLICK\n[button] Broadcast TV Spokane (3) -> CLICK\n[button] Apply -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.092, 0.494, 0.107] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 upcoming MLB games taking place on Sunday, 3/19.\nPrevious actions:\n[link] MLB . -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.093, 0.218, 0.102] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[textbox] Search events -> TYPE: pet festival\n[generic] Run Search -> CLICK\n[label] -> CLICK\n[label] -> CLICK\n[label] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.126, 0.581, 0.159] in the image\nAnd my action is Action: TYPE\nValue: portland" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the Recommended Gaming PCs for someone who plays Fortnite, Overwatch and GTA V at 4k\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] icon of Gaming PC Finder Gaming PC Finder -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.513, 0.179, 0.523] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 year that Tom Brady had the most touchdowns in a single seasson.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.021, 0.353, 0.033] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all English Reading and Writing skills Educational Books for Ages 6-8 currently in stock that are available in hardback under 20$.\nPrevious actions:\n[span] English Language -> CLICK\n[link] English Language: Reading & Writing Skills -> CLICK\n[select] All -> SELECT: In Stock (41,088)\n[select] All -> SELECT: Hardback (13,067)\n[select] All -> SELECT: Under US$20" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.562, 0.196, 0.597] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[button] Meetings & Events -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.729, 0.105, 0.852, 0.121] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[combobox] Select Minimum Year -> SELECT: 2022\n[combobox] Select Maximum Year -> SELECT: 2023\n[combobox] select-filter -> SELECT: 50 mi\n[span] Silver -> CLICK\n[p] Black -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.435, 0.226, 0.451] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 blue iPad to your cart and select the option for free engraving with \"hello world\" with no other accessaries.\nPrevious actions:\n[link] Buy iPad 10.9-inch -> CLICK\n[img] Blue -> CLICK\n[span] for 12 -> CLICK\n[div] Every iPad can connect to Wi‑Fi, so you can stay c... -> CLICK\n[radio] Add engraving It won’t impact returns or trade-in ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.176, 0.691, 0.214] in the image\nAnd my action is Action: TYPE\nValue: Hello World" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of a flight between San Antonio, Texas, and Bellingham, Washington on April 8.\nPrevious actions:\n[link] Flight status -> CLICK\n[textbox] From , required. -> TYPE: san antonio" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.093, 0.25, 0.385, 0.266] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK\n[button] Increase Quantity -> CLICK\n[button] ADD TO CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.655, 0.312, 0.797, 0.328] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 English language book on roman empire history in the Kindle store released in the last 90 days, it should be displayed according to its latest publication date, and add the top result to the shopping list.\nPrevious actions:\n[button] Open Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.162, 0.285, 0.192] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Chicago to London on 20 April and return on 23 April.\nPrevious actions:\n[textbox] To -> TYPE: London\n[a] LON - London, United Kingdom -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 20 -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.202, 0.408, 0.235] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 deals for Hotels in Mexico.\nPrevious actions:\n[textbox] What type of deals? -> TYPE: Hotels\n[div] Hotels -> CLICK\n[textbox] Where? -> TYPE: Mexico\n[div] Mexico -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.918, 0.108, 0.964, 0.154] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 channel number for the local CBS in Spokane Washington in 99201.\nPrevious actions:\n[link] Live TV -> CLICK\n[button] Broadcast TV Spokane (3) -> CLICK\n[textbox] Search -> TYPE: 99201\n[button] Antenna -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.238, 0.773, 0.263] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Limited Time Offers -> CLICK\n[button] Show filter modal Category -> CLICK\n[button] Furniture 356 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.651, 0.418, 0.897, 0.433] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[span] Chicago -> CLICK\n[span] Mar 18 -> CLICK\n[button] 30th March (Thursday) -> CLICK\n[combobox] Time -> SELECT: 8:15 PM\n[combobox] Size -> SELECT: 10 guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.4, 0.495, 0.526, 0.562] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.111, 0.819, 0.146] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[button] Plan -> CLICK\n[link] Try Somewhere New -> CLICK\n[link] Destinations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.171, 0.086, 0.178] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 California city for Limos which also offers military discounts and free wi-fi.\nPrevious actions:\n[link] Auto Services -> HOVER\n[span] Parking -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.026, 0.564, 0.042] in the image\nAnd my action is Action: TYPE\nValue: CALIFORNIA" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 blue iPad to your cart and select the option for free engraving with \"hello world\" with no other accessaries.\nPrevious actions:\n[radio] Add engraving It won’t impact returns or trade-in ... -> CLICK\n[textbox] First line -> TYPE: Hello World\n[button] Save -> CLICK\n[span] No Apple Pencil -> CLICK\n[span] No USB-C to Apple Pencil Adapter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.681, 0.65, 0.938, 0.712] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[li] Summer -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK\n[button] Romantic -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.43, 0.772, 0.46] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 popular tracks from the rock band Nirvana.\nPrevious actions:\n[searchbox] Search -> TYPE: Nirvana\n[link] Search for “Nirvana” -> CLICK\n[link] Nirvana -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.288, 0.171, 0.319] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.391, 0.285, 0.44] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[button] Buy Now -> CLICK\n[button] Next -> CLICK\n[input] -> TYPE: Neo\n[input] -> TYPE: Thomas\n[input] -> TYPE: 05/05/1995" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.118, 0.487, 0.137] in the image\nAnd my action is Action: TYPE\nValue: Texas city" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[span] London -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: sheffield\n[span] Sheffield -> CLICK\n[textbox] Date use format: 24-Mar-23 -> CLICK\n[link] 29 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.18, 0.194, 0.198] in the image\nAnd my action is Action: SELECT\nValue: Leaving at" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chicago Bulls team schedule for the month of April.\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> TYPE: Chicago Bulls\n[div] Chicago Bulls -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.051, 0.601, 0.076] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of baby products that are on sale and under 10 dollars.\nPrevious actions:\n[link] BABY -> HOVER\n[link] Sale -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.161, 0.481, 0.175] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find vinyl records at the lowest price.\nPrevious actions:\n[button] Marketplace -> CLICK\n[link] Vinyl -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.784, 0.108, 0.898, 0.122] in the image\nAnd my action is Action: SELECT\nValue: Price Lowest" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[label] Senior Discount -> CLICK\n[button] Find Hotels -> CLICK\n[combobox] Sort by: -> CLICK\n[option] Guest Rating -> CLICK\n[link] Pets welcome (118) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.257, 0.169, 0.38, 0.183] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 white water rafting experience available in Montana from May 1 to May 7\nPrevious actions:\n[gridcell] Sun May 07 2023 -> CLICK\n[button] Apply -> CLICK\n[circle] -> CLICK\n[button] -> CLICK\n[button] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.284, 0.142, 0.294] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What is the cheapest luxury car to pickup on the second closest nearby location to New York, United States, 100\nPrevious actions:\n[link] Luxury Car Rental -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.008, 0.086, 0.426, 0.13] in the image\nAnd my action is Action: TYPE\nValue: New York, United States, 100" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comprehensive health screening for women in 10003.\nPrevious actions:\n[span] Schedule a women's health exam -> CLICK\n[link] Comprehensive health screening Available in-person -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.263, 0.34, 0.283] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pair of diamond stud earrings to the cart.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: diamond stud earrings\n[span] diamond stud earrings -> CLICK\n[img] 10k Gold 1 Carat T.W. Black Diamond Stud Earrings -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.768, 0.34, 0.931, 0.377] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: skirt\n[textbox] Search by keyword or web id -> ENTER\n[span] Gender -> CLICK\n[link] Neutral (7) -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.126, 0.974, 0.143] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book in Hindi with ISBN 1648926800.\nPrevious actions:\n[link] Advanced Search -> CLICK\n[input] -> CLICK\n[input] -> TYPE: 1648926800" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.667, 0.342, 0.969, 0.374] in the image\nAnd my action is Action: SELECT\nValue: Hindi" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 developer jobs in Dallas, Texas, and review details of the latest job then create an 8-day alert after signing in.\nPrevious actions:\n[link] We're hiring! Join our team , Opens another site i... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.597, 0.05, 0.674, 0.086] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade in value for PS4 console\nPrevious actions:\n[p] Consoles -> CLICK\n[searchbox] Find values for games and more -> CLICK\n[searchbox] Find values for games and more -> TYPE: PS4\n[button] SEARCH -> CLICK\n[link] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.204, 0.375, 0.22] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Rock -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.024, 0.48, 0.141, 0.573] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a demo drive for Model Y for Roy Adams with phone number 123-999-0000, email address [email protected] and zip code 90001 in the United States.\nPrevious actions:\n[button] Model Y -> CLICK\n[textbox] Last Name -> TYPE: Adams\n[textbox] First Name -> TYPE: Roy\n[textbox] Phone Number -> TYPE: 123-999-0000\n[textbox] Email Address -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.162, 0.742, 0.391, 0.755] in the image\nAnd my action is Action: TYPE\nValue: 90001" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] CITIES -> CLICK\n[span] Find your state -> CLICK\n[link] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.304, 0.406, 0.387, 0.422] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is [email protected] and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Hurricane Harbor Phoenix -> CLICK\n[button] Go! -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.065, 0.443, 0.077] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.21, 0.007, 0.256, 0.049] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] -> CLICK\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK\n[gridcell] 1 -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.197, 0.3, 0.361] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[button] Saturday, July 1, 2023 -> CLICK\n[button] Wednesday, July 5, 2023 -> CLICK\n[button] 1 Adult -> CLICK\n[button] Substract one Adult -> CLICK\n[button] Substract one Child -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.396, 0.272, 0.432] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[textbox] To -> CLICK\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] Depart Date -> CLICK\n[gridcell] Tuesday, April 18, 2023 -> CLICK\n[img] Add travelers and discounts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.242, 0.256, 0.264, 0.276] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most expensive things to do anywhere in December in a map\nPrevious actions:\n[div] Anywhere -> CLICK\n[textbox] When? -> CLICK\n[tab] Select a Month -> CLICK\n[li] December -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.555, 0.171, 0.662, 0.216] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to cart 2 bottles of vitamin D that are buy 1 get 1 free and new arrival.\nPrevious actions:\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK\n[link] Vitamin D -> CLICK\n[checkbox] Buy 1, Get 1 Free 33 items, On Sale list 3 items -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.613, 0.397, 0.682, 0.442] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for places to stay in Santa Fe, New Mexico for a weekend starting on Jun 16th for 3 guests and 2 rooms.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Santa Fe\n[span] Santa Fe, New Mexico, United States -> CLICK\n[div] 16 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.176, 0.23, 0.209, 0.25] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking 1234567890 booked by Jason Smith\nPrevious actions:\n[tab] My Trips -> CLICK\n[textbox] booking reference -> TYPE: 1234567890\n[textbox] last name -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.222, 0.94, 0.246] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[link] Used -> CLICK\n[button] Style -> CLICK\n[link] French -> CLICK\n[button] Material -> CLICK\n[link] Oak -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.612, 0.253, 0.767, 0.277] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[tab] Year Manufactured -> CLICK\n[checkbox] 1990 -> CLICK\n[button] Apply -> CLICK\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.168, 0.905, 0.191] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[button] Apr 11, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[checkbox] Nonstop (1) -> CLICK\n[checkbox] 1 Stop (49) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.23, 0.048, 0.24] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Departments -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.011, 0.25, 0.187, 0.266] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurants, open 24 hours, and sorted by rating.\nPrevious actions:\n[link] Restaurants -> CLICK\n[link] OPEN 24 Hours -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.118, 0.672, 0.128] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a job opening in sales in San Fransisco, and if found, apply for the job.\nPrevious actions:\n[textbox] Select Department -> CLICK\n[option] Sales & Ad Ops -> CLICK\n[textbox] Locations -> CLICK\n[option] US, CA, San Francisco -> CLICK\n[link] Manager, Field Sales - West -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.3, 0.131, 0.334] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check Real Madrid player Vinicius Junior bio\nPrevious actions:\n[div] Soccer -> CLICK\n[link] La Liga La Liga -> CLICK\n[div] Real Madrid -> CLICK\n[heading] ROSTER -> CLICK\n[heading] Vinicius Junior -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.556, 0.063, 0.574, 0.093] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 today's deals on video games and find the best deal on the lowest-priced mouse.\nPrevious actions:\n[link] Video Games -> CLICK\n[link] Today's Deals -> CLICK\n[link] PC -> CLICK\n[link] Accessories -> CLICK\n[link] Gaming Mice -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.934, 0.072, 0.968, 0.078] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 smartwatch to the cart that is compatible with an iPhone.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: smartwatch\n[button] smartwatches -> CLICK\n[i] -> CLICK\n[img] Sponsored Ad - SKG V9C Smart Watch for Men Women, ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.7, 0.236, 0.838, 0.249] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 unused wireless Logitech Keyboard under $70.\nPrevious actions:\n[button]  -> CLICK\n[span] New -> CLICK\n[button] APPLY -> CLICK\n[span] Logitech -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.434, 0.192, 0.454] in the image\nAnd my action is Action: TYPE\nValue: 70" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy movie streaming on Netflix and add to watchlist.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Netflix streaming -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.416, 0.43, 0.429] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Hot Dogs in Oakland, CA that Offers Delivery.\nPrevious actions:\n[textbox] Near -> TYPE: Oakland, CA\n[span] Oakland, CA -> CLICK\n[textbox] Find -> CLICK\n[textbox] Find -> TYPE: Hot Dogs\n[span] Hot Dogs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.095, 0.313, 0.108] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[combobox] Reservation type -> SELECT: Pickup\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: Boston" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.133, 0.734, 0.16] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[span] Airport taxis -> CLICK\n[textbox] Pick-up location -> TYPE: O'hare Airport\n[heading] Chicago O'Hare International Airport -> CLICK\n[textbox] Drop-off location -> TYPE: 123 Main St, West Chicago, IL\n[heading] 123 Main St -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.294, 0.641, 0.34] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[checkbox] 26 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 2:00 PM\n[span] -> CLICK\n[div] Thu, Apr 27 -> CLICK\n[checkbox] 30 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.759, 0.126, 0.846, 0.164] in the image\nAnd my action is Action: SELECT\nValue: 1 00 PM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 popular news which is at number one in comics.\nPrevious actions:\n[button] News -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.418, 0.216, 0.45] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.139, 0.84, 0.17] in the image\nAnd my action is Action: TYPE\nValue: BIRMINGHAM" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.029, 0.158, 0.053] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 direct flight From mumbai to new delhi, India, on june 1 and return travel on june 8.\nPrevious actions:\n[button] Next Month -> CLICK\n[use] -> CLICK\n[div] 1 -> CLICK\n[span] 8 -> CLICK\n[span] SEARCH FLIGHTS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.499, 0.151, 0.516] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[link] Price (lowest first) -> CLICK\n[button] Add Filter -> CLICK\n[link] Ship Location -> CLICK\n[button] Ship Location: Any -> CLICK\n[link] Canada -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.256, 0.312, 0.27] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Los Angeles\n[span] , CA, USA -> CLICK\n[button] 1 NIGHT Sat, Apr 08 - Sun, Apr 09 -> CLICK\n[span] 7 -> CLICK\n[span] 14 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.835, 0.46, 0.912, 0.49] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Women's t-shirt for $40-$60 and add it to Wishlist, stop at the Login screen.\nPrevious actions:\n[link] WOMEN -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.157, 0.257, 0.195] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order popcorn at AMC Grove City 14\nPrevious actions:\n[link] Visit the Food & Drinks page -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.181, 0.969, 0.203] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[span] Las Vegas, NV -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: san francisco\n[span] San Francisco, CA -> CLICK\n[textbox] Departure -> CLICK\n[button] Tuesday, April 11, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.243, 0.237, 0.273, 0.263] in the image\nAnd my action is Action: CLICK" } ]

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of games I've played recently.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.412, 0.0, 0.519, 0.056] in the image\nAnd my action is Action: CLICK" } ]