Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/a2b1d94b-5309-4c9b-bcdd-8048172af7b5_794a7443-6027-4bd4-bc18-229028decf0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 foldable over-ear headphone under 35 USD in certified refurbished condition with lowest price + shipping.\nPrevious actions:\n[link] Electronics -> HOVER\n[link] Headphones -> CLICK\n[link] Ear-Cup (Over the Ear) -> CLICK\n[button] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.848, 0.244, 0.989, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/70b3ef5b-d900-44cf-9b62-9ecece97954c_a134016b-dd49-4e6d-9c0a-f2a9c11f25f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 climbing gear and sort the results by price high to low.\nPrevious actions:\n[button] Climb -> CLICK\n[button] Climb -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.143, 0.546, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7bda9645-0b5f-470a-8dd7-6af0bff4da68_30732d9f-efee-4ba4-8b2a-a72e47d5bde6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[combobox] Reservation type -> SELECT: Pickup" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.499, 0.313, 0.518, 0.325] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1eb6602-3aa7-40ee-8968-69d83e7ef21c_8084a818-7884-4e70-90c3-6f94536efcb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[menuitem] Buy -> HOVER\n[menuitem] New Cars -> CLICK\n[p] SUV / Crossover -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.381, 0.223, 0.41] in the image\nAnd my action is Action: TYPE\nValue: 10017" } ]

{ "bytes": "", "path": "./images/a8de57df-b0be-400d-9211-931321c6500c_1596c7ad-f09a-48bc-b641-b66197b5b5d0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the best rated ukulele tab to my favorites\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.027, 0.838, 0.041] in the image\nAnd my action is Action: TYPE\nValue: ukulele" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_938f123e-a8b0-46fe-82bd-580041111df6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[button] Team -> CLICK\n[searchbox] Search -> CLICK\n[option] Finance -> CLICK\n[button] Time Type -> CLICK\n[searchbox] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.183, 0.29, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b30b9f84-0541-4826-a3af-98220b851f7c_e5be8100-215f-469b-bd1a-791ce30bfe16.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 women's sports wear, size S.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.014, 0.873, 0.057] in the image\nAnd my action is Action: TYPE\nValue: sports wear" } ]

{ "bytes": "", "path": "./images/6c107328-3ff6-4cb3-af16-5f9ca447fd66_aac2e48b-eaab-49e0-8d87-8fdf57bb909a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add documentary \"The Elephant Whisperers\" and \"The Magician's Elephant\" to the watchlist.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: The Elephant Whisperers" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.15, 0.196, 0.657, 0.272] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_43f085f3-b693-48ab-ac7a-3d9c3b9f7af2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[gridcell] Thursday, June 1, 2023 -> CLICK\n[button] Done -> CLICK\n[button] FIND TRAINS -> CLICK\n[span] Sort/Filter -> CLICK\n[checkbox] filter trains by Time of Day:6a-12p -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.738, 0.453, 0.944, 0.479] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_c3904d4c-b5f4-4a2d-9fdd-68dc50c3227b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[span] Car rentals -> CLICK\n[searchbox] Please type your destination -> TYPE: mexico city" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.34, 0.409, 0.391] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b18e5e4-4873-49bf-b422-c3f5bc5d1f33_eb8ba29f-90ce-4615-8e5b-92f140b46bf4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a WWE ticket for price range between $50 to $100.\nPrevious actions:\n[link] WWE Tickets -> CLICK\n[link] TICKETS -> CLICK\n[p] $41 - $1,255 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.756, 0.207, 0.796, 0.231] in the image\nAnd my action is Action: TYPE\nValue: 50" } ]

{ "bytes": "", "path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_2722ee03-60cc-45cc-8e74-a341b470de12.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.128, 0.846, 0.154] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_460dd5e5-220f-4476-a4fa-639b266566fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[menuitem] Prequalify for Financing -> CLICK\n[input] -> TYPE: 30000\n[input] -> TYPE: 6000\n[span] Good -> CLICK\n[span] 48 mo -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.661, 0.787, 0.683] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04ec089f-2ae1-4fa9-bfdf-4dff9ab710ad_58d10ad0-dc54-4dad-9f1e-4e11611a1176.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated white water rafting experience available in Montana from May 1 to May 7\nPrevious actions:\n[textbox] Where to? -> TYPE: Montana\n[button] Montana USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.764, 0.367, 0.777, 0.377] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4bc70fa1-e817-405f-b113-0919e8e94205_b1ec99ca-9953-4575-b633-8b9e6da0aee4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the cheapest Women's Sweaters to my shopping cart.\nPrevious actions:\n[span] Shop by Category -> CLICK\n[link] Women -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.312, 0.236, 0.414, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_d3696fd4-af25-471e-851b-6b0f1e991970.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[div] open -> CLICK\n[option] 6 -> CLICK\n[button] Update -> CLICK\n[button] Search -> CLICK\n[button] Search without signing in -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.593, 0.278, 0.606] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61563837-99af-45e2-a13f-9d6bd9f74a81_5bf7212f-6896-4585-addb-9f5a65a58eb8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the external solid state drives available with lowest price first.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.051, 0.054, 0.084] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e104a4ef-521f-4ca0-8e1a-098656207de2_bc27f335-5b49-47ef-8632-88d20acb5da2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 estimated monthly payments for a $10,000 vehicle with $500 down payment, 72 month term length and challenged credit score in the state of New Jersey\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK\n[textbox] Vehicle Price -> CLICK\n[textbox] Vehicle Price -> TYPE: 10000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.213, 0.459, 0.235] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_ca5e412b-7659-4de8-b48b-d24749857658.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: BWI\n[button] Baltimore, MD, US (BWI) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.164, 0.481, 0.185] in the image\nAnd my action is Action: TYPE\nValue: NYC" } ]

{ "bytes": "", "path": "./images/6d87b507-14dd-4903-a131-fa089499ccb5_3fb3d43d-eda2-454f-bd81-4beaabe0e47c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[textbox] To -> CLICK\n[button] Greece -> CLICK\n[button] Athens -> CLICK\n[div] Apr -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.254, 0.434, 0.281, 0.467] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdd9ef05-4d5b-4469-b001-8d73b6dc8120_c7822f35-404a-4681-8945-0b6ac3c36b54.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 documents required to sell a car in New Jersey for which payments are being paid and it has single person on the title who can come to the store\nPrevious actions:\n[link] Sell/Trade -> CLICK\n[combobox] In what state are you selling the car? -> SELECT: New Jersey\n[radio] Yes -> CLICK\n[radio] No -> CLICK\n[radio] Yes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.598, 0.798, 0.793, 0.831] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_52dfe9c5-b379-4ce0-8c66-dd85b7724207.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[span] Tel Aviv -> CLICK\n[textbox] To -> TYPE: VENICE\n[span] Venice Treviso -> CLICK\n[div] May -> CLICK\n[generic] 9 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.104, 0.299, 0.131, 0.318] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_3dafde2b-5c39-47e2-b9b3-0c1e19c6dc3e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[link] Search flights one way -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: JFK\n[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.351, 0.492, 0.374] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_bfa98fe8-342a-4833-b221-f1274a517937.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[div] Seoul, Republic Of Korea -> CLICK\n[svg] -> CLICK\n[path] -> CLICK\n[checkbox] 10 May 2023 -> CLICK\n[checkbox] 12 May 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.878, 0.238, 0.942, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1c6bfd10-4dcb-4a5c-bb2d-922ff9f20087_86eb051c-670a-49bb-b354-428ae03e2016.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an English language book on roman empire history in the Kindle store released in the last 90 days, it should be displayed according to its latest publication date, and add the top result to the shopping list.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.04, 0.054, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_9055b4da-fa8e-445e-ae40-52b8c5e24167.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[button] Next month -> CLICK\n[gridcell] June 18 -> CLICK\n[gridcell] June 21 -> CLICK\n[button] Search packages -> CLICK\n[button] Amenities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.486, 0.089, 0.494] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/02e7bae3-c67f-4227-b6ea-7b87d111202a_474d7869-7905-4b42-90a7-c75117862cbe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 latest documentaries on Netflix and add the one with 70+ metascore.\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, 0.246, 0.077, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/26a20a7b-cd98-4752-a9ea-fcaebb3ab56e_6b99a1ca-17aa-452a-9370-27bb2a175812.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 information about how to buy metro card on booth.\nPrevious actions:\n[link] Fares & Tolls -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.7, 0.5, 0.713] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4bce534f-3057-40ca-aecd-ffb07b3c9fcb_0ba0e97c-8b51-40e2-9387-368af44c654c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search the actor who won the Oscars for best actor in a suuporing role ine 1990, and add his upcoming movies to my watchlist.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Oscars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.757, 0.513, 0.779, 0.522] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc174cb2-520d-49c3-93da-f93a1c485c03_5df6fedf-afb3-4095-b06a-c9a3317e485a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the fare options to go from the south station to the north station\nPrevious actions:\n[button] Fares  -> CLICK\n[link] Fares Overview -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.677, 0.168, 0.845, 0.181] in the image\nAnd my action is Action: TYPE\nValue: south station" } ]

{ "bytes": "", "path": "./images/66d12284-5525-42d2-a66f-fe5c460b7764_0a45420f-cf51-42a2-82da-24ffd4e8dba5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order popcorn at AMC Grove City 14\nPrevious actions:\n[link] Visit the Food & Drinks page -> HOVER\n[link] Order Food & Drinks -> CLICK\n[select] AMC Columbus 10 -> SELECT: AMC Grove City 14" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.277, 0.637, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56d210ec-22eb-4b3f-ba76-ee531403701a_e1e17c9e-26b5-4a08-a7ad-8e999a9870d2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[menuitem] Boston, MA, USA -> CLICK\n[textbox] Start Date -> CLICK\n[button]  -> CLICK\n[gridcell] Tue, May 30, 2023 -> CLICK\n[gridcell] Thu, Jun 1, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.68, 0.314, 0.943, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b831239-435b-494e-9aa8-a49e8605d0b3_163e98c4-a7ef-42c2-b151-5cc75d670ca5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What is trending now on AMC on-demand?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.54, 0.026, 0.633, 0.062] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ac59be41-36c3-44c5-8e1f-ffb9461ba980_321b75fd-1b65-443f-ba11-fcc65a6007b9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all Alternative Concerts taking place in New York City.\nPrevious actions:\n[button] Change Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.097, 0.203, 0.231, 0.214] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/f804150b-c2e9-40ca-b71f-d0d0d95e0c46_3c33e494-db1f-4561-ac74-d928cd7cca26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in New York City for 2 adults from Apr7 to Apr 8.\nPrevious actions:\n[option] New York (New York City) New York State, United St... -> CLICK\n[checkbox] 7 April 2023 -> CLICK\n[checkbox] 8 April 2023 -> CLICK\n[button] Search -> CLICK\n[menuitem] Price (lowest first) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.295, 0.344, 0.547, 0.354] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_9fd6dca3-1d20-46bb-814e-0786016ce859.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is buckeye.foobar@gmail.com, and phone number is 6157075521.\nPrevious actions:\n[link] Car Repair -> HOVER\n[link] Auto Repair Prices -> CLICK\n[combobox] Year -> SELECT: 2022\n[combobox] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Corolla" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.195, 0.712, 0.215] in the image\nAnd my action is Action: SELECT\nValue: L Sedan 4D" } ]

{ "bytes": "", "path": "./images/1337eca1-4ca6-4102-964e-e7f6ecebcd0b_3151a491-e1ce-480a-9cfb-d389ee8624df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\n[tab] Things to do -> CLICK\n[textbox] Things to do in -> TYPE: singapore\n[button] Singapore Singapore -> CLICK\n[button] From April 5, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.389, 0.308, 0.431, 0.338] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_1f81f2b6-3fc7-4827-aeee-4a41116ee19d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[label] VIN -> CLICK\n[textbox] Enter VIN (17 digits) Where can I find the VIN -> TYPE: 1HGCM66543A064159\n[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 49102\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.533, 0.31, 0.553] in the image\nAnd my action is Action: TYPE\nValue: 155000" } ]

{ "bytes": "", "path": "./images/957878ba-cb47-40d1-bf37-23039b2dff27_c219dddc-bdf3-4b52-b770-2f8c34504fc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 CarMax in Michigan, 49107 and book an appointment for a car repair on April 7th..\nPrevious actions:\n[button] Open helpful links menu -> CLICK\n[link] Service & Repairs -> CLICK\n[link] FIND A SHOP NEAR YOU -> CLICK\n[link] Find a Shop -> CLICK\n[li] 43065 -> TYPE: 49107" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.1, 0.294, 0.117] in the image\nAnd my action is Action: TYPE\nValue: 49107" } ]

{ "bytes": "", "path": "./images/988ff1b8-c9e8-44af-a729-33f0e99c9dbf_45697305-9fe5-4695-9ccf-4a73a68552e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show cars with AWD with maximum budget of $50,000.\nPrevious actions:\n[link] Cars for Sale -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.059, 0.673, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_ed9a300a-422a-4ee9-ac12-b6e26509649d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] Events & Activities -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.47, 0.289, 0.52, 0.307] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3eae65d9-7778-4cf2-bc3d-f666b5e43bce_331cc579-44f2-4e80-ace7-f8b7909fd044.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Notify me about availability for 2 guests on april 17 at the High Tide restaurant\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.021, 0.418, 0.048] in the image\nAnd my action is Action: TYPE\nValue: high tide" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_8aeecea7-7ffa-475a-9844-2b49f26b6ce1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[button] Search -> CLICK\n[button] Search without signing in -> 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 [0.028, 0.751, 0.278, 0.767] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_e3c9691e-c9cc-44c9-b2ca-c8f93c388a5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my parking space in Houston. Name: James Smith, Email: buckeye.foobar@gmail.com, phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[link] Rent My Parking Space -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.805, 0.787, 0.824] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

{ "bytes": "", "path": "./images/2e133e56-ac17-41dc-987a-257078d770c3_7d42e63b-49be-41b1-a453-28707cb28367.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on the water activities in Dubai from 5pm to 12am with a maximum duration of four hours\nPrevious actions:\n[textbox] Where to? -> TYPE: Dubai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.23, 0.729, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_21334cc2-269f-4dd5-898b-f2cab62a8b19.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[button] Our Company -> CLICK\n[link] Careers  -> CLICK\n[link] Students & Grads -> CLICK\n[link] INTERNSHIP PROGRAMS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.517, 0.168, 0.813, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2959cdb-fbc4-435f-ba89-85d50d22298c_c94f5e1a-4d22-4c21-90b6-164dcee297dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces in JFK airport between April 18-20 that have lowest shuttle times\nPrevious actions:\n[tab] Airport -> CLICK\n[searchbox] Airport Name, Code or City -> TYPE: jfk" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.169, 0.914, 0.189] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_212a36a7-c358-4fd7-9122-8c6721b7ed7a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[link] MEN -> HOVER\n[link] Sale -> CLICK\n[heading] Category -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.436, 0.48, 0.47] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/969f36c3-52e7-42da-80bd-11a2d04d53ae_b80dae22-0311-4f5c-9aed-76f14574703d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the Biography of the NFL player named Michael Jordan\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Michael Jordan\n[textbox] Search -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.158, 0.207, 0.198] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f464de6d-9923-4e8e-8046-56751a90a9a8_d48017ee-76d2-4d21-8bd8-112aa9cb8bc8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track a bus leaving from Abbotsford.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.443, 0.0, 0.559, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1eb6602-3aa7-40ee-8968-69d83e7ef21c_f626fb4a-bfe2-443e-aaaf-663f8eae8055.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[menuitem] New Cars -> CLICK\n[p] SUV / Crossover -> CLICK\n[textbox] ZIP -> TYPE: 10017\n[button] Search -> CLICK\n[combobox] Select Minimum Year -> SELECT: 2022" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.137, 0.235, 0.156] in the image\nAnd my action is Action: SELECT\nValue: 2023" } ]

{ "bytes": "", "path": "./images/44dcda68-082c-455a-a409-7091470cc006_e964b7d2-296b-49f0-9a08-4813d10b5a46.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets from Edinburgh Waverly to Glagsgow Central on May 18, leaving nearest 3PM for 1 adult with a Veterans Railcard\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: Edinburgh\n[span] Edinburgh (Waverley) -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: Glasgow\n[span] Glasgow Central -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.132, 0.194, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a9708ad7-bec8-4435-b055-8ef6da520b8c_df64899f-f2f6-4a81-99ec-a0029e9790a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play the top track for the top indie artist in the last 30 days\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.762, 0.008, 0.791, 0.038] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e2cb6d9-560c-4258-baed-82e0ed5b5dbc_e6bb3bac-2055-4e4d-b429-cf5310a8955a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bus stop information at Abbotsford, WI.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Bus stops -> CLICK\n[button] Abbotsford, WI  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.321, 0.13, 0.335] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_78d05d85-15c8-4638-b44f-b3bcdade5119.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Rock -> CLICK\n[img] David Bowie -> CLICK\n[link] David Bowie -> CLICK\n[button] Add to List -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.227, 0.419, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_c31831cf-fcb1-4fc6-a696-aa5540372aa1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Brooklyn\n[span] Brooklyn, New York, United States -> CLICK\n[span] Different drop-off -> CLICK\n[tab] Same drop-off -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.762, 0.097, 0.877, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35cf31d3-c88d-45fe-9959-4cf1de72bc7d_03b9d01e-5454-4f71-88b8-20e5c41872f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for trending women sports bras and add 3 trending black bras to Wishlist.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK\n[div] Color -> CLICK\n[link] Refine by color: Black -> CLICK\n[button] Add to Wish List -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.694, 0.22, 0.716, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/59bdd427-c34b-4b93-a8b8-0c3a49acdcfa_1967f971-1242-4c07-8421-62e434f90fef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from Santa Fe, New Mexico to Phoenix, Arizona for 1 adult on August 13th and returning on August 28th.\nPrevious actions:\n[button] Phoenix, AZ, US (PHX) -> CLICK\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[span] 13 -> CLICK\n[span] 28 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.479, 0.478, 0.516] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c50985ee-d4d0-4a9e-ac6f-97bede200abd_700030bb-f584-4e85-91bd-357f444c6051.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the lowest price ticket including fees to the next M3 Rock Festival - 2 Day Pass\nPrevious actions:\n[link] Music -> HOVER\n[link] Festivals -> HOVER\n[link] M3 Rock Festival -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.456, 0.358, 0.553, 0.384] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/69661946-6c3e-4e26-95ed-1f7641a31f22_d9c1648c-f508-47c9-83d1-5649ca2da7df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Toyota Corolla near 10019 and sort by cheapest.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.332, 0.135, 0.432, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4775a0e3-3dad-46f2-b719-b1c0dae9e147_a702b9eb-d196-46e6-b587-372a8c3c648a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[button] MAKE MY STORE -> CLICK\n[button] Departments -> HOVER\n[button] Grocery & Home -> HOVER\n[link] Grocery -> CLICK\n[link] Bread -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.134, 0.122, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/60383804-a8e5-4e50-8715-da391d76617d_b48691e5-ea8b-45b3-8bef-d5389d03b4a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 candle holder red decor products.\nPrevious actions:\n[link] Marketplace -> CLICK\n[link] Shop by Color -> CLICK\n[link] Shop red -> CLICK\n[button] Show filter modal Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.375, 0.135, 0.563, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c987dd1d-9ade-4701-8cdb-a31f8f3bf673_6f943877-135c-4690-bc5b-ee941b3a8565.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[button] See all -> CLICK\n[checkbox] All staff fully vaccinated -> CLICK\n[checkbox] Accepts Apple Pay -> CLICK\n[button] Search -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.518, 0.137, 0.612, 0.157] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/920f240d-77a9-476b-a1d4-dcc88d199bfa_5c1e2823-28b4-4884-9036-1d917f7a70e2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rock music events in Canada, happening this weekend and save top three popular events for my record.\nPrevious actions:\n[link] Music -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.246, 0.247, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4947d606-626e-4da3-a595-bfedacbed3ec_ca273023-d776-42ee-b189-656af8e4a2f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request ticket receipt for ticket no. 1234567890123 and last name Davis\nPrevious actions:\n[link] Receipts and refunds -> CLICK\n[link] Receipts for tickets and fees -> CLICK\n[textbox] Ticket number -> CLICK\n[textbox] Ticket number -> TYPE: 1234567890123" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.24, 0.656, 0.293] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d29e8a14-ee66-4330-b282-09cb1955aad0_98f2a61d-1e65-44d2-b21b-8856adfb16c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the weekly ad in List View.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.347, 0.022, 0.497, 0.042] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_d9a6085d-eed6-4737-bec7-50f8e2953d86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking with EV charging for month with lowest price in Chicago.\nPrevious actions:\n[li] Chicago, IL, USA -> CLICK\n[button] Filter -> CLICK\n[checkbox] EV Charging (10) -> CLICK\n[button] Show 10 Results -> CLICK\n[select] Sort by Distance -> SELECT: Sort by Price" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.299, 0.402, 0.372, 0.422] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_1ad4f2f9-ba55-482c-bda8-b879589bdb54.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[link] Drop In Two Bowl -> CLICK\n[checkbox] Ship to Home Eligible (97) -> CLICK\n[checkbox] Stainless Steel (75) -> CLICK\n[checkbox] Equal Bowl (69) -> CLICK\n[checkbox] 19 inch (7) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.795, 0.096, 0.99, 0.111] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31c12c59-d9b8-4d9a-8456-9f1107d0e5f8_8c67fc5e-0ba2-4649-b99f-249f1310f9c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation made by James Smith in the United States with Confirmation Number 123456\nPrevious actions:\n[button] Reservations -> CLICK\n[link] View / Modify / Cancel -> CLICK\n[combobox] Select Residency -> SELECT: UNITED STATES\n[input] -> TYPE: smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.581, 0.421, 0.902, 0.469] in the image\nAnd my action is Action: TYPE\nValue: 123456" } ]

{ "bytes": "", "path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_2f0192ff-5e1a-44a6-8649-bfff77330b42.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find trade in value for PS4 console\nPrevious actions:\n[link] repeat Trade-In -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.258, 0.352, 0.435, 0.505] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/85706225-aa42-43c1-8cfa-8696118698a2_062d3d9a-c1d4-47c7-8192-39cfc6fcf0a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of flights from Los Angeles area to Boston area tomorrow\nPrevious actions:\n[button] Travel Info -> CLICK\n[link] Flight Tracker -> CLICK\n[textbox] From -> TYPE: Los Angeles\n[option] Los Angeles area -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.401, 0.219, 0.601, 0.267] in the image\nAnd my action is Action: TYPE\nValue: Boston" } ]

{ "bytes": "", "path": "./images/3f0988e0-e3a4-4dd7-a89f-482175a474a8_c1406787-2858-4cfd-9ff0-18dd822ec56a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Wheelchair accessible parking for April 09 event in Barclays Center that allows entry after 10am\nPrevious actions:\n[textbox] Search for parking -> TYPE: Barclays Center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK\n[textbox] Select Event Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK\n[p] Philadelphia 76ers at Brooklyn Nets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.33, 0.384, 0.359] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_d81b3416-82ef-4ec6-b938-3da5c2548270.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[button] Search -> CLICK\n[img] humangear GoBites Uno Spork 0 -> CLICK\n[button] Color: Magenta -> CLICK\n[span] -> CLICK\n[button] Change store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.269, 0.194, 0.716, 0.212] in the image\nAnd my action is Action: TYPE\nValue: Seattle, WA" } ]

{ "bytes": "", "path": "./images/e0ff7945-56b0-487a-920b-cbf954e6fb72_da89b808-f145-4860-a45f-450834fba4e4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dinner table in the first restaurent in the results, any time after 8 pm tomorrow for two in New York in any available Indian cuisine-serving restaurant.\nPrevious actions:\n[div] Columbus, OH -> CLICK\n[button] New York -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: indian" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.179, 0.063, 0.228, 0.079] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a919aa15-2acf-4090-8468-1d3a0d6450b1_b2e7c3b2-0fa3-49bc-8478-4cea20de1dc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Need the cheapest small car on April 7, 10 am at Auckland airport for pick-up, return will be on April 10 at approx 5 pm.\nPrevious actions:\n[link] 7 -> CLICK\n[combobox] Pick Up Time -> SELECT: 10:00 AM\n[textbox] mm/dd/yyyy -> CLICK\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.381, 0.891, 0.414] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d64cbfc6-7ace-4cad-9f0a-6643cd83de6e_e238e976-5417-483a-bff6-e54699142179.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 full-sized Amazon basic comforter with 4+ average customer reviews and priced between 50 to 100 dollars, if red color availabe in the cheapest product then add one to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: COMFORTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.651, 0.007, 0.686, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4fe76361-f0e3-458f-a3d5-453da3c7cecc_ccf4155a-d9ed-4ede-a1a6-010e16f61ea7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List of Broadway events sorted by date.\nPrevious actions:\n[link] broadway. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.694, 0.221, 0.894, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_1a23c4b3-11dc-419a-a0c3-e4d328690204.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[link] Search for packages -> CLICK\n[textbox] From -> TYPE: Birmingham\n[span] Birmingham, England, United Kingdom -> CLICK\n[textbox] Enter destination or airport -> TYPE: Paris\n[span] City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.591, 0.141, 0.76, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_745f0ada-af2d-4846-ae61-94bc84783005.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Shop Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.248, 0.571, 0.286] in the image\nAnd my action is Action: TYPE\nValue: New Delhi" } ]

{ "bytes": "", "path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_309508ef-3fbc-4301-898a-906c004937a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: trash can automatic lid\n[option] automatic trash can lid -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 60" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.224, 0.176, 0.238] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_bdc9a239-d845-44f2-ac6d-a78a43ce85a5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[img] humangear GoBites Uno Spork 0 -> CLICK\n[button] Color: Magenta -> CLICK\n[span] -> CLICK\n[button] Change store -> CLICK\n[searchbox] Search by location -> TYPE: Seattle, WA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.691, 0.24, 0.709, 0.254] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f75897b-8df4-4f4c-88c3-72d440f6a4ee_0dbe031f-7330-4084-81bd-d133f5f5014a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[button] Plan -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.215, 0.154, 0.313, 0.163] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/844f8d77-e12e-4d68-8c4c-9146bd5b1530_97649533-7183-42a1-ae1f-275a69e171b9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open gift list for beauty products.\nPrevious actions:\n[path] -> CLICK\n[button] More ways to shop -> CLICK\n[link] Send gifts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.058, 0.26, 0.178, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c577209-47dc-4645-8d10-0b659663a969_2e7bca75-da1d-4ae9-a4e3-63c8a0469fdd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 score of the latest nba game played by the phoenix suns.\nPrevious actions:\n[combobox] Search query -> TYPE: phoenix suns\n[link] Phoenix Phoenix NBA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.319, 0.976, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d7c3103a-c195-4503-ab20-ecae4d4ce419_14510cda-06ca-4191-bea4-39e0e54bb281.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 motorcycle toll fee for the Queens midtown tunnel.\nPrevious actions:\n[link] Fares & Tolls -> CLICK\n[div] Bridges and Tunnels tolls -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.239, 0.367, 0.335] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_1f5cb659-0c88-4f0e-a389-97e9e90a0893.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[span] Charleston -> CLICK\n[textbox] zip or city, state -> TYPE: 25504" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.201, 0.081, 0.281, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ad0369b6-cfd5-4555-bb4f-d84a942be555_51c840cc-adac-4cc2-a914-b07bcef81959.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order the cheapest climbing shoes in today's deals.\nPrevious actions:\n[button] Deals -> HOVER\n[link] Explore Deals -> CLICK\n[link] Climbing -> CLICK\n[combobox] Sort By -> SELECT: Price: Low - High" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.298, 0.956, 0.442] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/706d0ccd-c0ec-423d-88c0-a5716700a855_04e9cc0d-00d8-48a5-b493-a9b27a1aa465.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BMW X5 Crossovers and compare the mileage of the first two cars.\nPrevious actions:\n[link] Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.259, 0.397, 0.353, 0.451] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e62bcf45-0be3-4195-b234-37755d6d715e_4c487c29-f51f-47a4-b521-08bb8e2c8253.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book by Sam Harris that has a rating of at least 4 stars and is available in paperback format.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Sam Harris\n[button] sam harris -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.326, 0.219, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51e85ea8-7a75-40f3-8f35-ed255f87171f_6484f6b2-1c3b-438a-b60d-739032df779a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to cart 2 bottles of vitamin D that are buy 1 get 1 free and new arrival.\nPrevious actions:\n[button] Shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.268, 0.234, 0.574, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2f8b054-59b5-4fd8-bd58-9f95b29f979d_dacb180b-b588-4ff6-982a-c9294c11bddb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.0, 0.605, 0.038] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9a9b1b45-cb23-4073-897f-67410087df9d_ddeea3d8-a96c-4584-8dae-084e4a76aaae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule COVID-19 test appointment at 90028.\nPrevious actions:\n[span] COVID-19 booster, testing, treatment & records -> CLICK\n[link] COVID-19 testing Schedule a COVID-19 test -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.633, 0.308, 0.844, 0.335] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]

{ "bytes": "", "path": "./images/be5e5f14-c875-4cfd-a517-175619491b90_430ba357-5e86-4d8c-a1a0-66fe657b0197.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[link] NFL -> CLICK\n[link] Scores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.698, 0.199, 0.717, 0.214] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_b4b0eb8a-8008-4e51-8b11-0f2dc0fb6013.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[generic] 9 -> CLICK\n[generic] 16 -> CLICK\n[button] Search -> CLICK\n[button] Select -> CLICK\n[button] Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.969, 0.702, 1.017] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_3e0071a1-0e7a-4dcc-afaf-8d49bc8ba14b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Samsung-made and larger than 11-inch screen Android tablet, in the price range of 200 to 300 dollars and add it to the cart.\nPrevious actions:\n[link]  Electronics  -> CLICK\n[link] Tablets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.378, 0.389, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1282a011-194c-40c4-8f76-875e502cdd53_45555477-fab7-4449-b1ff-66433e3230ff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse laptops with at least 16gb of ram and under $700.\nPrevious actions:\n[searchbox] Search Site -> TYPE: laptop\n[button]  -> CLICK\n[textbox] price to -> TYPE: 700\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.267, 0.192, 0.287] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/46a3683f-fbe0-40d0-8729-6c7964d994e6_5dcf5117-8341-4ea2-a6eb-a516c41a71b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a men's UA outlet T-shirt of XL size and add to cart.\nPrevious actions:\n[div] Product Type -> CLICK\n[link] Short Sleeves -> CLICK\n[div] Size -> CLICK\n[link] XL -> CLICK\n[img] Men's UA Tech™ 2.0 Short Sleeve -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.867, 0.375, 0.924, 0.393] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_614535fe-72dd-44fb-bb5e-97d4a2547a1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless printer\n[button]  -> CLICK\n[dt] Customer Ratings -> CLICK\n[i] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.279, 0.192, 0.29] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/21e5c264-df85-4055-a566-ecb65cdd8c63_fc871d4d-aa26-42a3-a595-7ec4b6c676ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.28, 0.148, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e200503-9b49-48aa-aaf6-3d6692b5cb50_e043291f-ff92-42c8-a9d2-016c8f3469f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 locksmiths near Texas City, Texas that provide virtual consultations and are open now.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.158, 0.023, 0.243, 0.042] in the image\nAnd my action is Action: CLICK" } ]