Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/9e44c63b-2c7a-445c-b9c4-6580f4271268_a0fd3657-be32-476b-8d86-b7dd38afd2a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track the status of a rebate for Monty Lue, house number 4847, zip code 10019\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.917, 0.012, 1.0, 0.031] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_69c07f95-bec3-47b2-964c-db723e729b84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[div] £ -> CLICK\n[div] -> CLICK\n[textarea] -> TYPE: Happy Birthday Love\n[input] -> TYPE: Stuart Bloom\n[input] -> TYPE: Denise" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.346, 0.916, 0.393] in the image\nAnd my action is Action: TYPE\nValue: Bloom" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_4d289945-1ccb-4aca-9ca5-00c19003c28b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[div] Spain -> CLICK\n[textbox] When? -> CLICK\n[li] Summer -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.152, 0.442, 0.177] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a51b649f-15b4-4ce4-936e-0b76efa0dd2d_4c159fd1-de41-432a-8c93-4ffef904d093.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View travel credits for the passenger Leon Sin with the record locator jcqnhd ans ticket number 1234567\nPrevious actions:\n[searchbox] Search AA.com® -> TYPE: travel credit\n[searchbox] Search AA.com® -> ENTER\n[heading] Find your trip - Find a reservation - American Air... -> CLICK\n[textbox] Last name -> TYPE: sin\n[textbox] Trip Credit / Ticket number -> TYPE: 1234567" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.633, 0.35, 0.874, 0.38] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_548cec03-b81f-4bfd-8d26-a5bd57383fa0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] Departing April 11, 2023 -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Jul 1, 2023 -> CLICK\n[button] Jul 7, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.928, 0.43, 0.984, 0.458] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_694d5209-df32-4dd2-a885-72b559a39cb9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 motherboard under $200 and a compatible processor at any price to the shopping cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.016, 0.418, 0.048] in the image\nAnd my action is Action: TYPE\nValue: motherboard" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_d321135b-7227-4764-933b-d0ce804aa88a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[button] DONE -> CLICK\n[heading] $139 Vermont: Cozy Kimpton in the heart of Manches... -> CLICK\n[button] CHECK DATES -> CLICK\n[link] $189 -> CLICK\n[link] $259 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.371, 0.902, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cac423-4be9-4f74-9031-7cef1fe60ef9_394dcce1-2df9-4a3c-8088-31e132733f32.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fuel economy for a 2005 Toyota Corolla\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.141, 0.211, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_18379f86-26b5-4f32-8c38-cfd07d6f4ec8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] 8, Saturday, April 2023. Available. Select as chec... -> CLICK\n[span] -> CLICK\n[span] Castles -> CLICK\n[button] Filters -> CLICK\n[textbox] max price $ -> TYPE: 1000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.448, 0.786, 0.47] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_ccc8fff7-4673-4e12-b66d-87ebf14f3a02.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] pickup date input field -> CLICK\n[button] 29, March 2023 -> CLICK\n[button] pickup time input field -> CLICK\n[button] Confirm -> CLICK\n[combobox] Passengers -> SELECT: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.823, 0.199, 0.927, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_14413e25-3474-43a7-88a4-8c6017dfefc7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[span] -> CLICK\n[button] Show all 25 -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.803, 0.302, 0.913, 0.32] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c73b1674-9c61-46a3-84dd-8fad3622a035_d3ce6c2b-fa4b-473f-9d10-2980148592c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[textbox] To -> TYPE: miami\n[strong] Miami -> CLICK\n[span] 27 -> CLICK\n[textbox] Return Press DOWN ARROW key to select available da... -> CLICK\n[span] 31 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.752, 0.213, 0.853, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7cbd1771-ca62-47ed-97db-5577644d285c_445a3b2c-9bf3-48c9-bb84-97c89020d5e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my favorites a cruise for 4 people going to Caribbean.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.129, 0.285, 0.285, 0.321] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_0d7f064a-aa60-43bf-a75a-a1e7ff4351ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[img] undefined -> CLICK\n[button] Continue without a seat -> CLICK\n[div] 1 Small Bag only -> CLICK\n[label] -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.81, 0.316, 0.86, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5a15ea92-571d-4a45-ad18-5b4eddbc70a6_f9801b57-8f15-4dab-9e72-aa767e19f1c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the lowest priced plus size one piece active swimsuit in color black.\nPrevious actions:\n[link] Women's Plus -> CLICK\n[div] Color -> CLICK\n[link] Black (294) -> CLICK\n[link] Sort by: Featured -> CLICK\n[link] Price Low-High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.13, 0.583, 0.138, 0.592] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_7b90ff88-5507-4a4a-8c8b-52d348e46ff7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[link] Pop Rock -> CLICK\n[link] 958,222 United Kingdom -> CLICK\n[link] 246,685 CD -> CLICK\n[link] 122,512 Album -> CLICK\n[link] Show more… -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.233, 0.163, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_2fda5161-1368-4436-8d1f-fc75151db6ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[generic] 26 -> CLICK\n[generic] 2 -> CLICK\n[div] -> CLICK\n[button] Apply promo code -> CLICK\n[textbox] Apply promo code -> TYPE: 1000001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.205, 0.953, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_9e2ad598-a31c-48d7-809a-7482f0e22074.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] Seattle, WA -> CLICK\n[span] Dates -> CLICK\n[button] September 2023 -> CLICK\n[button] DURATION -> CLICK\n[button] 6 - 9 Days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.331, 0.871, 0.372] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_4c7c0d34-e5bd-4c51-b699-e4ff6f392fce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[img] Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK\n[img] Driscoll's Organic Strawberries -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.053, 0.045, 0.219, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27a8bf82-2e7e-48c3-8fb1-66909c13d585_645e7a33-cc4e-47ee-bbe7-06941488d9f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Buick for sale within 250 miles from 26807.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Car Sales -> CLICK\n[combobox] All Makes -> CLICK\n[textbox] Zip Code: 43085 -> TYPE: 26807" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.584, 0.206, 0.701, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a52774d2-550d-475a-922c-25c37d44557c_f463f8e4-acbf-45ce-b77a-59e6eadc7213.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[span] Mansions -> CLICK\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] Check in / Check out Any week -> CLICK\n[tab] Flexible dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.159, 0.598, 0.177] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_4c1a9de4-e5d4-4be6-80e0-1e60fcfb3386.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[span] Dates -> CLICK\n[button] September 2023 -> CLICK\n[button] DURATION -> CLICK\n[button] 6 - 9 Days -> CLICK\n[button] SEARCH CRUISES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.083, 0.212, 0.1] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_f02d5411-dd85-430b-a6fe-47ea3fc45474.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 24 June 2023 -> CLICK\n[textbox] Passengers / Class -> CLICK\n[button] Decrease number of infant passengers -> CLICK\n[button] Increase number of child passengers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.655, 0.629, 0.927, 0.656] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_557a0c86-28aa-4838-b6d5-84c2383074df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[span] Drive Type -> CLICK\n[checkbox] Front Wheel Drive (147) -> CLICK\n[span] Exterior Color -> CLICK\n[div] -> CLICK\n[checkbox] Online Paperwork (4) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.736, 0.296, 0.761] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_95141533-9d98-44d8-892a-27fafb078c64.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[button] Location Anywhere -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.188, 0.147, 0.392, 0.162] in the image\nAnd my action is Action: TYPE\nValue: belo horizonte" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_77c7b44a-4641-49f4-8c49-b7268e7e1c6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[div] 10 -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[span] 0 -> TYPE: 7" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.845, 0.437, 0.908, 0.462] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_56a0811a-d418-4d40-a9c6-3db908dfbfe7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[link] Trade In -> CLICK\n[link] Trade in by mail -> CLICK\n[combobox] search input -> TYPE: Nemo Front Porch 2P Tent\n[img] search icon -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.297, 0.743, 0.449, 0.784] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3110612f-63fe-4a7a-98d0-29c806d6a34f_d36af357-3992-4fdc-af97-755183ecfd0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Trains in Spain guide that will help you learn about Renfe fare types\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK\n[menuitem] European trains -> CLICK\n[menuitem] Spain train tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.702, 0.226, 0.794, 0.235] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/904bd858-1c40-4d22-9a5b-e2974c3b5a7e_bc05be9f-e46b-4654-83c0-862c601f263f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive ticket for New York Knicks game on April 9\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.191, 0.782, 0.227] in the image\nAnd my action is Action: TYPE\nValue: New york knicks" } ]

{ "bytes": "", "path": "./images/bc45669b-6bed-4240-9d9b-6b5e45a7e6f3_f69f089a-e5a4-4995-9df6-4b564436b806.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse xbox series x consoles that are used and between $200 and $400.\nPrevious actions:\n[combobox] Search for anything -> TYPE: xbox series x console\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.762, 0.027, 0.777] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_9e20b613-6f39-45e4-b248-a3383bb160bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[checkbox] 1 June 2023 -> CLICK\n[span] Where from? -> TYPE: TOKYO\n[span] TYO -> CLICK\n[span] Where to? -> TYPE: NEW DELHI\n[b] DEL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.669, 0.262, 0.906, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b390b60-5c04-40ee-a5af-353def43ffbc_b512eb3a-d22d-4b97-9602-8accf6088ddc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me japanese restaurants in Fresno with online delivery.\nPrevious actions:\n[link] Fresno -> CLICK\n[img] -> CLICK\n[span] Order Online -> CLICK\n[link] All -> CLICK\n[label] Japanese Restaurants -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.441, 0.559, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_7e75bead-d0bb-4243-ab8b-7c062cd37053.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[label] 100 - 200 USD (6) -> CLICK\n[button] APPLY -> CLICK\n[combobox] Sort by: -> CLICK\n[option] Price -> CLICK\n[link] VIEW RATES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.843, 0.601, 0.943, 0.633] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/747429fa-7dac-4ab0-b604-13cb9bf787fe_eb660037-cbb5-4b1a-be71-d1b5ad6fd160.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[searchbox] Search Site -> TYPE: wireless keyboard\n[button]  -> CLICK\n[span] New -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.524, 0.158, 0.533] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/39937001-8af2-4727-bb2a-6997981cf50d_916bd8e4-c9a3-4837-8144-c9fc5cbdcf41.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of tours available at the Coliseum with free cancellation.\nPrevious actions:\n[span] Top activities -> HOVER\n[span] Colosseum -> CLICK\n[link] Tours & Tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.144, 0.143, 0.156] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/28d54466-de85-45e6-9649-2575d38adfd4_14d0b2bf-2ab6-4ab6-abad-772760082d0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 documentaries streaming on Netflix.\nPrevious actions:\n[link] What to Watch on Netflix -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.213, 0.077, 0.251] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccf98191-100e-441a-93e8-8ff4076aeaa0_e3cf226c-7d99-41ea-89d5-a56659d29b84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\n[tab] Tops -> CLICK\n[link] T-Shirts -> CLICK\n[heading] Price -> CLICK\n[label] $0-$10 -> CLICK\n[polygon] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.293, 0.256, 0.49] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2b159c8-86d0-4b76-9244-f19cc41d5ad8_8782a791-9cd8-4ff2-be7e-865859dd7fc5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Medical book related to Diseases & Disorders to basket.\nPrevious actions:\n[link] Shop by category∨ -> CLICK\n[link] Shop by category∨ -> CLICK\n[link] Medical -> CLICK\n[link] Diseases & Disorders -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.382, 0.366, 0.402] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/401c4e6f-6b0b-47b4-8157-92d7ca468bbc_4762d735-9dc2-4717-ae8b-baab0b3446e5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[heading] CAR -> CLICK\n[combobox] Enter pick up city, airport name, or airport code. -> TYPE: Brooklyn Central\n[div] Brooklyn - Central (New York), US -> CLICK\n[textbox] Pickup -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.282, 0.143, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54d60a7c-f52d-4d79-b879-34698507e22c_f5a28d3e-5195-4f57-9cb0-b69fc4e39b1a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[span] New York, NY -> CLICK\n[input] -> CLICK\n[gridcell] March 18, 2023 -> CLICK\n[input] -> CLICK\n[gridcell] March 19, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.12, 0.213, 0.279, 0.235] in the image\nAnd my action is Action: TYPE\nValue: 3" } ]

{ "bytes": "", "path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_20dce0e2-8e16-4412-aa55-23f7a1d13681.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[link] SHOP HOTELS -> CLICK\n[button] Going to -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.139, 0.42, 0.181] in the image\nAnd my action is Action: TYPE\nValue: Ohio" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_40137cca-0d78-4d63-9635-8352aa17f0c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[generic] 15 -> CLICK\n[generic] 16 -> CLICK\n[button] 11:30 -> CLICK\n[button] 11:00 -> CLICK\n[button] Let's go -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.13, 0.625, 0.251] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f118238f-ef8f-4b63-9159-a81e981ef46e_2e3da2eb-62df-434d-b787-bbb106ebfb4b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add decorative LED Candles to the cart.\nPrevious actions:\n[link] Products -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.439, 0.32, 0.463] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/000c2828-e8ce-4b18-bfe0-89ed333add06_7dcf08f4-e760-4be7-be8c-0a533074883e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $25 digital gift card for Tim Stebee, whose email address is [email protected]. Fill in sender name Jeerimiah Waton\nPrevious actions:\n[img] -> CLICK\n[img] GameStop Digital Gift Cards -> CLICK\n[textbox] Recipient Name -> TYPE: Tim Stebee\n[textbox] Recipient Email -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.683, 0.975, 0.729] in the image\nAnd my action is Action: TYPE\nValue: Jeerimiah Waton" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_763f2654-e332-4ba0-b78b-81110a53ff6a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: GOA\n[div] Goa -> CLICK\n[checkbox] 25 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.378, 0.263, 0.389] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20d38a9-8c0f-4ed5-becc-f0f54fb90798_906c8603-da25-403f-b16b-7258c1f73735.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the page with information about the NBA Finals schedule.\nPrevious actions:\n[div] Sports -> HOVER\n[link] NBA -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.104, 0.101, 0.161, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ea9ac0d-8c31-49bc-aa3d-e85b80580409_8368fa5f-1af2-4abb-bcf6-cf089a8ca346.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight schedule between London and New York for April 7 and check the upgrade details of the noon flight.\nPrevious actions:\n[heading] Flight status -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.222, 0.272, 0.255] in the image\nAnd my action is Action: TYPE\nValue: london" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_9b195a60-73db-47f5-a2f0-d5a47fbdeb06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[input] -> TYPE: 1111111111111111\n[textbox] Address 1 -> TYPE: the home of joe bloggs\n[textbox] City -> TYPE: new york\n[textbox] Postcode/ZIP code -> TYPE: 10001\n[combobox] State -> TYPE: new york" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.445, 0.609, 0.484] in the image\nAnd my action is Action: TYPE\nValue: 1234" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_57f7d43c-5d53-4a00-8fa7-5feafe218409.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[tab] 7 -> CLICK\n[path] -> CLICK\n[div] 8+ -> CLICK\n[div] 3 -> CLICK\n[checkbox] Free internet -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.402, 0.226, 0.413] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29d6b448-a688-4c2f-8f6d-a13546d506d8_e4610afd-1311-4ec1-97ee-3ecf4c573381.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 jazz albums released in 1890.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Jazz -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.063, 0.599, 0.093, 0.609] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4af615be-4472-4357-8737-5286b06b385d_e8bc0cef-e7f2-447c-8393-356a10b812b7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 listings for a used 2006 Honda Civic.\nPrevious actions:\n[link] Price New/Used -> CLICK\n[combobox] Year -> SELECT: 2006\n[combobox] Make -> SELECT: Honda\n[combobox] Model -> SELECT: Civic\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.784, 0.264, 0.981, 0.283] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_72ec56be-d53d-4b32-acb8-ac991e6ca999.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[link] Fares & Tolls -> CLICK\n[link] See railroad fare details. -> CLICK\n[link] Plan a trip to see fares. -> CLICK\n[searchbox] From -> TYPE: grand central" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.347, 0.474, 0.377] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d5c4d19-c2cc-4e68-9f51-71ba6cd6e38a_fd1d5d23-7a0f-4576-be97-833ebf8126bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with 4 star and above rating in Los Angeles for 3 days next week and save it.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.06, 0.181, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7e501a4-5dee-406e-b6ba-00eed783df0c_43f63fb5-a96b-4da5-a251-cf7829d4501f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 KOA campground in California that has RV sites.\nPrevious actions:\n[link] Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.239, 0.232, 0.249, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_94bad45f-8cab-4d3f-9c10-ede8de8da2a5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Alinea\n[span] Chicago, IL - Lincoln Park -> CLICK\n[i] -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.88, 0.448, 0.908, 0.47] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92cfe78f-0385-4ef6-b829-ae34291e766f_93138842-6d51-48af-aa67-d6214bc11bfa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 LED TV below $1000.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] TV & Home Theater  -> CLICK\n[div] TV & Accessories -> CLICK\n[link] LED TV -> CLICK\n[dt] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.125, 0.672, 0.192, 0.687] in the image\nAnd my action is Action: TYPE\nValue: 1000" } ]

{ "bytes": "", "path": "./images/913b902b-37b7-4230-a0f2-a19931b06951_26337816-766e-4897-b7df-e4d62ea83cda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fastest single stop flight fron JFK airport in New York to Male in Maldives on March 13\nPrevious actions:\n[span] Round-trip -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.109, 0.292, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_ffc2d7ad-0691-466b-b825-956744be5a2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight destination input -> CLICK\n[textbox] Flight origin input -> TYPE: new york\n[button] Remove -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.218, 0.573, 0.273] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27a8bf82-2e7e-48c3-8fb1-66909c13d585_4ed75775-bdd0-455f-abf7-f105531035b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Buick for sale within 250 miles from 26807.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Car Sales -> CLICK\n[combobox] All Makes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.372, 0.472, 0.383] in the image\nAnd my action is Action: TYPE\nValue: 26807" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_796c803d-8f81-4cfe-a335-d7313478fdb0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] Military & Veterans -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: nevada city\n[span] Nevada City -> CLICK\n[span] 4831 Granite Dr -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.205, 0.691, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_2190574e-5045-4a7c-aeab-5f9d88e544cd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[textbox] Return to same location -> TYPE: washington\n[div] Washington Dulles Intl Airport -> CLICK\n[generic] Vehicle Type * -> CLICK\n[p] SUVs & Wagons -> CLICK\n[button] Select My Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.757, 0.701, 0.882, 0.717] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/21e5c264-df85-4055-a566-ecb65cdd8c63_2fd38569-ac81-4db5-8534-ac8b52302caf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my basket tickets for 3 people from New York to Alfred.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Alfred" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.469, 0.388, 0.482] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4970cd99-ce6b-42e3-bc78-695c9d510f6c_7e00abe3-6fa7-4b74-b2be-7505a7270e33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[link] FIND A CAMPGROUND  -> CLICK\n[link] TRIP PLANNER  -> CLICK\n[textbox] Enter your Origin -> TYPE: Cheyenne\n[textbox] Enter your Destination -> TYPE: Helena" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.139, 0.367, 0.238, 0.401] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/75db63ac-4fcf-400e-833f-d31f00cf6ab6_054fab53-5095-4ef9-a358-ccfae23ddabf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[link] Nearby Restaurants -> CLICK\n[div] Toronto -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.115, 0.237, 0.239, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3a85b415-9e68-4cf0-91be-386d4d8f0710_e7bb4a75-73a7-4320-95ec-03516f734caa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: download pdf for list of accessible station in NYC.\nPrevious actions:\n[span] Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.183, 0.234, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10593972-6b1d-4b07-ba61-cb56ca0f06e3_78b56f22-a09c-4cbf-8e7e-fe5dd97a1305.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Lenovo laptop under $800 and create a price alert for $400.\nPrevious actions:\n[searchbox] Search Site -> TYPE: lenovo laptop\n[button]  -> CLICK\n[div] Newest Lenovo Ideapad 3i Laptop, 14\" FHD Display, ... -> CLICK\n[div] Price Alert -> CLICK\n[textbox] price from -> TYPE: 400" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.292, 0.727, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_b0204daf-d53c-416b-bbf3-fe924f4d9d25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Add to List -> CLICK\n[radio] New List -> CLICK\n[textbox] Title -> TYPE: New\n[button] Save -> CLICK\n[button] Explore -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.337, 0.088, 0.485, 0.108] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9653dc0d-96d9-414f-a711-3af94bd7cf5b_95ec1d75-39b4-41c3-bdd2-fd4404dbe49f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: sell playstation controller for cash credit on GameStop in 43240.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.697, 0.059, 0.722, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_4c9dfd61-fbf4-424e-a505-a20212944a9c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[label] Pick-up location -> TYPE: Heathrow\n[div] London Heathrow Airport (LHR) -> CLICK\n[div] Wed, Apr 19 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.287, 0.539, 0.308] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_a2e3ce74-6960-44a8-9352-ce292abb6b25.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[heading] Barboursville -> CLICK\n[link] More info about Barboursville store -> CLICK\n[button] make it my store -> CLICK\n[path] -> CLICK\n[span] Easter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.66, 0.118, 0.819, 0.22] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29fde741-075c-446c-8e8a-f432e81e7ac0_02461d6b-dd73-4855-9d43-5545b559e29c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate vehicle price with a challenge credit score, monthly payment of $250 with a $3000 down payment and 24% APR for 48 months in Tennessee.\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK\n[tab] Vehicle Price -> CLICK\n[textbox] Monthly Payment -> TYPE: 250" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.117, 0.459, 0.14] in the image\nAnd my action is Action: TYPE\nValue: 3000" } ]

{ "bytes": "", "path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_5fdc4213-5ec5-4e87-9984-4b602c1a2368.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[link] Show more… -> CLICK\n[link] 1,342 2016 -> CLICK\n[link] 98 £15 - £20 -> CLICK\n[link] Condition -> CLICK\n[link] Phil Collins - Both Sides (CD, Album, RE + CD + Dl... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.706, 0.072, 0.897, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/789b7d2d-fb01-453c-b933-383965e6123c_5e40a7b5-18ac-44c8-959a-a530a564942a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cast and crew of Titanic and add to watchlist\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.111, 0.594, 0.123] in the image\nAnd my action is Action: TYPE\nValue: Titanic" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_cffee1ce-d1d4-44c7-8978-a4a91b399818.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Children's Books -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.383, 0.196, 0.412] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_905be250-0f48-4c69-a6c0-82997c490294.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] 1, Saturday, April 2023. Available. Select as chec... -> CLICK\n[button] 8, Saturday, April 2023. Available. Select as chec... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.062, 0.819, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_1ef89271-0828-431c-8ad2-83ba8b886666.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.054, 0.491, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42657330-bfc5-425d-ae21-396a9ba1fb12_490963a7-541a-4739-836f-b305f77e41ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[searchbox] Search by keyword -> TYPE: women t-shirts\n[div] WOMEN / Tops -> CLICK\n[gridcell] Size -> CLICK\n[label] S -> CLICK\n[gridcell] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.063, 0.465, 0.139, 0.479] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d963cc0-90d3-4908-bee4-29a8530536af_604638dc-e4b7-4183-9b31-ea41921cdd3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my offers for 2-5 day cruises\nPrevious actions:\n[button] Plan -> HOVER\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.609, 0.779, 0.645] in the image\nAnd my action is Action: SELECT\nValue: 2 - 5 Days" } ]

{ "bytes": "", "path": "./images/9326b908-cbe6-41f6-957f-00b84c26bfcc_865bb951-c7cd-439d-8d45-50b44019491b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recently added guitar pro non-acoustic tab intros\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.031, 0.176, 0.038] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/884a375b-e3f4-4f34-8e99-290f49141f9a_068d6834-e98b-463c-a33b-df3480f7731d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dog bed on Amazon that is machine-washable and has a diameter of at least 30 inches.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: dog bed 30 inches\n[button] Go -> CLICK\n[RootWebArea] Amazon.com : dog bed 30 inches -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.79, 0.032, 0.796] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b99412b-6be2-4274-8843-4fc97f0c8247_47173eeb-574c-43c5-a937-a7da3b445094.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track the bus with service number 10000001\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK\n[tab] Service Number -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.212, 0.715, 0.255] in the image\nAnd my action is Action: TYPE\nValue: 10000001" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_07cf23ef-c4c8-4f6e-8ea7-acd2ea457987.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a black blazer for men with L size and add to wishlist.\nPrevious actions:\n[heading] Gender > Category -> CLICK\n[input] -> CLICK\n[option] MEN -> CLICK\n[svg] -> CLICK\n[heading] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.311, 0.471, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_97773a8e-0f6a-46e6-b900-726dc84c0b7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NAPA VALLEY\n[span] Napa Valley -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.283, 0.292, 0.319] in the image\nAnd my action is Action: SELECT\nValue: Wineries" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_59161f2b-4e6d-4fb2-be23-4c27eeedefce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[link] Car Values -> HOVER\n[link] My Car's Value -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.102, 0.23, 0.112, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/53b4ca73-c05b-4609-98c8-a0a62072bdb5_b76a522b-8917-4f56-a7bd-f0ff4fa2cabf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest vitamin C and D to cart.\nPrevious actions:\n[div] Relevance -> CLICK\n[div] Price Low to High -> CLICK\n[img] CVS Health Vitamin C Tablets 250mg, 100CT -> CLICK\n[button] Add CVS Health Vitamin C Tablets 250mg, 100CT to B... -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.081, 0.186, 0.087] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3c9442f9-5542-4395-918a-6551dbba3e3a_9a0801ff-e639-4dd4-98a9-fa35268526a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Massively Multiplayer games which can be played on VR.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.342, 0.143, 0.349] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b040b35d-cfd3-41b8-8b8b-851ab151a9cc_cb45e6f4-73da-49fe-85ca-746a2424c6c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the complexity rating for Frosthaven.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.76, 0.006, 0.995, 0.025] in the image\nAnd my action is Action: TYPE\nValue: frosthaven" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_b37d0499-8f2c-42f3-98a1-93d81e2cae6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: Nintendo Switch Console\n[button] Search -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 400\n[button] Submit price range -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.49, 0.027, 0.5] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31a74ae0-4b8a-407b-8f3d-a094a6966254_38ab39b0-d855-4990-91e4-801450b4c9ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 books of Dr Seuss with price range of $20 to $40 and add 2 to basket.\nPrevious actions:\n[link] Shop by category∨ -> CLICK\n[link] Dr. Seuss -> CLICK\n[select] All -> SELECT: US$20 to US$40" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.384, 0.196, 0.409] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/351568c6-452d-4f32-9375-2b6301f0cb36_0f8f7d21-0a40-44f8-8683-ca8d046e3e2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 next available subway train to Grand central station, NY departing from Queensboro plaza station, Long Island, NY.\nPrevious actions:\n[searchbox] To -> TYPE: Grand Central, NY\n[listitem] Grand Central Terminal, East 42nd Street, New York... -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[label] Bus -> CLICK\n[label] Express Bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.397, 0.12, 0.609, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d76a0fc-7ba9-4a74-ac52-db0cea359553_8f341320-6179-4cb0-b145-5d5b9d59e8a2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced round trip flight with hotel on May 2 from Kathmandu, Nepal KTM to Shanghai, China PVG and return on May 5. Book a double room and check out with the default flights.\nPrevious actions:\n[div] Tribhuvan Intl Airport (KTM), Nepal -> CLICK\n[textbox] Where to? -> TYPE: SHANGHAI\n[div] Pudong Intl Airport (PVG), China -> CLICK\n[span] Sat 8 Apr - Sat 15 Apr -> CLICK\n[checkbox] 2 May 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.738, 0.556, 0.767, 0.598] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_79f76036-6a56-4ff6-8f25-49bda6beaa0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: seattle\n[option] Seattle (WA), United States (City) -> CLICK\n[button] Next Month -> CLICK\n[span] 11 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.575, 0.38, 0.584, 0.391] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00cef5a2-4d07-4dd9-837d-5b85ac3a63d8_04943aa9-b541-411a-8ed3-e4c259733e76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.169, 0.031, 0.37, 0.041] in the image\nAnd my action is Action: TYPE\nValue: Chicago Bulls" } ]

{ "bytes": "", "path": "./images/9e44c63b-2c7a-445c-b9c4-6580f4271268_270f2f26-4be9-4b51-8347-ec9ed1712b35.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track the status of a rebate for Monty Lue, house number 4847, zip code 10019\nPrevious actions:\n[link] Rebate Center -> CLICK\n[link] Track your rebates -> CLICK\n[textbox] * Required Fields First Initial * Required Fields... -> TYPE: Monty\n[textbox] * Required Fields Last Name * Required Fields Las... -> TYPE: Lue\n[textbox] * Required Fields House Number -> TYPE: 4847" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.262, 0.23, 0.476, 0.247] in the image\nAnd my action is Action: TYPE\nValue: 10019" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_81adcddc-419d-4f81-b70c-348be8137bae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link]  All Filters -> CLICK\n[heading] Amenities  -> CLICK\n[label] Business center (11) -> CLICK\n[label] High-speed Internet (11) -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.792, 0.13, 0.853, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_019508db-f61f-4343-93fe-7df53859be47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: resident evil" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.099, 0.668, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/783d5a91-5f7e-4184-8467-e7ea88e81c5b_61cb1a42-d50a-4a13-a642-4519069dae8d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Set the 3rd top hip hop track as my current obsession\nPrevious actions:\n[link] Music -> CLICK\n[link] hip-hop -> CLICK\n[gridcell] Clint Eastwood -> CLICK\n[button] More -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.704, 0.724, 0.734] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/945ac29d-8e65-4e14-8bab-21742ac92a47_f1dbd69a-ff2d-4ee1-8fd8-6773599ab87b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bananas at Kroger\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.104, 0.109, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112459f9-10ea-44b5-affa-79008c2977e7_578dd203-e4de-4ea6-bb5a-d65d7c71e63d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 check in with confirmation number 123456 for John.\nPrevious actions:\n[heading] Check-in -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.168, 0.481, 0.192] in the image\nAnd my action is Action: TYPE\nValue: 123456" } ]

{ "bytes": "", "path": "./images/980d35af-6c00-4d6c-94cd-0c41e0fabb76_98bafeb7-8d43-4fe8-bdd5-a3b1aaf920d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mens Timberland boots in size 9 and under $100 and filter by lowest price.\nPrevious actions:\n[combobox] Search for anything -> TYPE: mens timberland boots\n[button] Search -> CLICK\n[link] 9 - apply US Shoe Size filter -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 100\n[button] Submit price range -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.088, 0.906, 0.108] in the image\nAnd my action is Action: CLICK" } ]