Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/78e346d2-3c80-4243-b921-ed35c4c4d923_3eec37dd-f749-468a-9e10-8cd36f12e224.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an order using the order number of 456481897 and phone number of 8984486417.\nPrevious actions:\n[link] Order Tracker -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.215, 0.459, 0.244] in the image\nAnd my action is Action: TYPE\nValue: 456481897" } ]

{ "bytes": "", "path": "./images/8a6f2641-9896-4657-b447-56927420e8c4_89d0a43a-593a-46f4-92e3-d1b1615293e2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Video Games -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Nintendo Switch -> CLICK\n[checkbox] Everyone Everyone -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.239, 0.375, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_e2bedd9a-7758-4d86-b0d2-517ee761c274.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 and add four items from the personal care category at Walgreens.\nPrevious actions:\n[img] -> CLICK\n[span] Add to list -> CLICK\n[checkbox] Walgreens New -> CLICK\n[button] Done -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.898, 0.25, 0.969, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aa1a4414-f141-42b8-9e8b-28d5bd1eeef2_21f8bfdc-d53f-40a3-8c4c-ee39f0f4a7d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 near Venice Beach that allows mobile coupons.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: Venice Beach\n[em] Venice -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.128, 0.336, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50bd08bd-989f-44ba-8a99-71e75ba602f1_e69a6088-4873-41f8-be56-5ee72a989dac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest monthly price for parking near Shubert Theatre.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Shubert Theatre\n[option] Shubert Theatre  225 West 44th Street, New York De... -> CLICK\n[link] MONTHLY -> CLICK\n[span] Distance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.226, 0.14, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_128f72a9-5531-4202-a730-5c09d7d9aaa0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[span] 17 -> CLICK\n[span] 20 -> CLICK\n[button] Done -> CLICK\n[button] 1 Room, 1 Guest -> CLICK\n[button] Add Rooms -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.189, 0.341, 0.207] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5cb859d-8460-4b27-b6c9-d6fea6de9889_15a35d9f-c3aa-44be-8f0f-4827042e2f95.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 kids 13Y size t shirts and add 3 to cart.\nPrevious actions:\n[link] KIDS -> CLICK\n[link] T-Shirts -> CLICK\n[gridcell] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.23, 0.471, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36ab5d78-2f6b-47a6-ad88-3f6c8fdc3513_f2510dca-2b8a-4d16-9824-8bd6f3e5274f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the movies playing today at the theater closest to zip code 10001\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.285, 0.164, 0.488, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0f9dd411-f3ab-494e-8a3a-5dc9a908f4ee_185d50aa-4bbf-4107-8913-200ee426102d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the cvs pharmacy nearest to zip code 45201 that provides hair loss evaluation and treatment.\nPrevious actions:\n[link] Schedule a women's health exam -> CLICK\n[link] Explore all MinuteClinic health services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.699, 0.274, 0.908, 0.34] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74f01011-9bcd-433b-8405-975ca5c3f356_c7548fe6-29eb-4ffb-a431-24ad7f535f5c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 address and store hours for the Armageddon Shop record store in Boston.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.557, 0.0, 0.645, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_665f4508-101d-406e-b5f6-ebfe574eb34d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[checkbox] 29 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 6:00 PM\n[combobox] Drop off time -> SELECT: 11:00 PM\n[div] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.611, 0.211, 0.682, 0.291] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5f09e15c-c987-4bdb-ab6e-5db39b18317d_df533272-7f21-43f3-a50f-89b97eb99bc1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3 tickets for a Special Event or Experience in Miami on may 4\nPrevious actions:\n[svg] -> CLICK\n[button] Miami -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> CLICK\n[button] View all Miami Restaurants › -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.31, 0.186, 0.342] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9c160e7-b179-4d42-8570-e6f3f85aa412_2918942d-cf82-4992-ac54-7ce758ca697f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 highest-rated adults-only romantic beach vacation deals and book the cheapest one.\nPrevious actions:\n[link] Vacations -> CLICK\n[link] Beach Vacation Deals 95 DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.307, 0.396, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a919aa15-2acf-4090-8468-1d3a0d6450b1_3a673d2c-870c-483f-8337-b1359c2cd031.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] 10 -> CLICK\n[combobox] Return Time -> SELECT: 5:00 PM\n[generic] Vehicle Type * -> CLICK\n[p] Compact -> CLICK\n[button] Select My Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.757, 0.204, 0.882, 0.222] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_dc38e438-dc4a-4fea-8621-383fb449ebf2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[span] -> CLICK\n[div] Leather -> CLICK\n[button] Next -> CLICK\n[button] None -> CLICK\n[combobox] CONDITION -> SELECT: Good" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.129, 0.286, 0.149] in the image\nAnd my action is Action: SELECT\nValue: Good To Go" } ]

{ "bytes": "", "path": "./images/980d35af-6c00-4d6c-94cd-0c41e0fabb76_4559b512-72e0-43a0-93f8-38b7f1688a06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse mens Timberland boots in size 9 and under $100 and filter by lowest price.\nPrevious actions:\n[combobox] Search for anything -> TYPE: mens timberland boots\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.165, 0.312, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e91126e0-023d-4f96-9378-74efb5d6ecc3_4256fd38-43d4-49a8-a0da-618b5264ed20.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check reviews and research information about Audi A6 2020.\nPrevious actions:\n[menuitem] Research -> CLICK\n[combobox] Select Make -> SELECT: Audi\n[combobox] Select Model -> SELECT: A6" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.375, 0.222, 0.545, 0.253] in the image\nAnd my action is Action: SELECT\nValue: 2020" } ]

{ "bytes": "", "path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_27988d8a-0da4-41ff-bb40-f20d4a1a7749.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: mens black hoodie\n[span] mens black hoodie -> CLICK\n[div] Size Range -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.327, 0.114, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_8782d364-4e18-44ff-9aee-4e1c21c11ed6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[link] WOMEN -> CLICK\n[tab] Bottoms -> CLICK\n[link] Pants -> CLICK\n[gridcell] Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.387, 0.471, 0.408] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_e6cb09cb-edbd-44c6-a911-d51f39af7dfe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[button] set store -> CLICK\n[button] Make -> CLICK\n[span] (954) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Series -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.192, 0.045, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_6dec575d-ef6c-419c-98f4-c906218623e1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[generic] 16 -> CLICK\n[button] 11:30 -> CLICK\n[button] 11:00 -> CLICK\n[button] Let's go -> CLICK\n[link] Large cars 5 Seats 3 Large bags -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.16, 0.187, 0.34, 0.211] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c1a354a1-7990-4ca8-9fc5-2fdb1b5df337_67dad40a-d63a-4cbf-9271-85500b8de12d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book in Hindi with ISBN 1648926800.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.871, 0.043, 0.98, 0.075] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/644b7bed-b5fb-4090-b04f-a669d41ac93a_aa168c45-dd50-42df-acda-564969d01e5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule of the East Boston ferry, check connections, and fares and download the pdf schedule.\nPrevious actions:\n[button] Transit  -> CLICK\n[link] Ferry -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.193, 0.339, 0.214] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db203a3a-8e62-41aa-ac05-717a8c11508d_be2b8420-57de-4edb-8ee8-1316eabea49a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Brooklyn, NY to Staten Island, NY on March 25th mainly using bus and subway terminal. The trip should arive at 9:45 AM.\nPrevious actions:\n[link] 25, Saturday March 2023 -> CLICK\n[radio] Arrive by -> CLICK\n[select] 1 -> SELECT: 9\n[select] 00 -> SELECT: 45\n[select] AM -> SELECT: AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.343, 0.406, 0.348, 0.428] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b130a70-f03a-4f86-8f2a-44f1b44f3655_b651a6f3-40e8-4541-bb42-45c812a7017b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my trip for Smith and booking number X899987799.\nPrevious actions:\n[link] Manage trips / Check-in -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.13, 0.365, 0.146] in the image\nAnd my action is Action: TYPE\nValue: Smith" } ]

{ "bytes": "", "path": "./images/30d5f7dc-3650-4177-93bc-b59f1f5621f0_8dc97709-9a15-4255-b63f-010da99ade05.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pg-13 comedy movies currently in theatres with the highest audience scores\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.112, 0.587, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d7a29cf-7e66-4660-9b26-4eeba7c3f158_7ad70888-fa59-43d7-8787-aa207662d59a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of children's program events in Illinois.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Events -> CLICK\n[button] All -> CLICK\n[input] -> CLICK\n[button] All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.41, 0.625, 0.517, 0.64] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_34c6c7d3-aea8-4755-978d-ba476644df1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[polyline] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.736, 0.279, 0.757] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b1fa9bb3-6e2c-485b-90f1-2a54510bf358_5bebb9b8-5943-41f5-b871-76d06302dbfa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 near Disneyland that has EV charging.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: Disneyland\n[combobox]   Enter an Address or Venue to find parking -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.113, 0.336, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/862faed7-449c-4624-902b-6b512a977d0c_d25f3ac6-5b8b-4c1d-a4f1-905223ab9ea1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: surge protector\n[button] surge protector -> CLICK\n[link] Surge Protectors -> CLICK\n[link] 6 to 8 Outlets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.462, 0.067, 0.472] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_31cb54e5-737b-4c62-8e2f-b2b8b74d551d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[heading] $139 Vermont: Cozy Kimpton in the heart of Manches... -> CLICK\n[button] CHECK DATES -> CLICK\n[link] $189 -> CLICK\n[link] $259 -> CLICK\n[button] CONTINUE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.714, 0.259, 0.87, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/28d54466-de85-45e6-9649-2575d38adfd4_dffa71c7-91d4-4a03-8642-c9af8bc7a05c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse documentaries streaming on Netflix.\nPrevious actions:\n[link] What to Watch on Netflix -> CLICK\n[button] Filter -> CLICK\n[button] Documentary -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.334, 0.639, 0.353] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/619ba95b-5a27-4c53-841c-edc281aacf7a_fa28ad4c-66b5-46f6-8cdb-9f52c1ef5404.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a dome tent to my shopping cart.\nPrevious actions:\n[link] Camping -> CLICK\n[menuitem] View All -> CLICK\n[div] Type -> CLICK\n[label] Dome -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.494, 0.488, 0.535] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_5d992829-9076-470c-9e36-dd1dd1918ccd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[div] Car Hire -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.104, 0.713, 0.115] in the image\nAnd my action is Action: TYPE\nValue: berlin" } ]

{ "bytes": "", "path": "./images/eeeee9d8-5387-46bc-a741-5bcb66b46f31_3f4f7403-be24-4fc0-a33a-961f7dc478a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a job opening in sales in San Fransisco, and if found, apply for the job.\nPrevious actions:\n[link] See Open Roles -> CLICK\n[textbox] Select Department -> CLICK\n[option] Sales & Ad Ops -> CLICK\n[textbox] Locations -> CLICK\n[option] US, CA, San Francisco -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.272, 0.472, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36f2e415-356b-4e44-9ab1-6c3054d4de1f_6a8d7913-dea5-453b-b17d-6652f31792b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 if cars are available for tomorrow at Elevated Escape in North Carolina.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Elevated Escape\n[div] Elevated Escape -> CLICK\n[div] Tue, Mar 28 -> CLICK\n[checkbox] 24 March 2023 -> CLICK\n[div] Sat, Mar 25 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.599, 0.32, 0.627, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_e9377db7-e0c7-4d52-b555-c18621895092.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[div] Select Your Options -> CLICK\n[generic] Black image Black -> CLICK\n[button] Next -> CLICK\n[span] -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.103, 0.519, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fbe9f625-7b47-4e13-a2f5-6823195d7438_61810484-2d4f-4d88-b9b3-25dc95d9719b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find a cheapest direct flight From mumbai to new delhi, India, on june 1 and return travel on june 8.\nPrevious actions:\n[tab] Flights -> CLICK\n[generic] Round-trip -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.222, 0.452, 0.234] in the image\nAnd my action is Action: TYPE\nValue: MUMBAI" } ]

{ "bytes": "", "path": "./images/9b18e5e4-4873-49bf-b422-c3f5bc5d1f33_a77dd692-2148-4a62-8cf9-b62a855abf40.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.274, 0.941, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/981fdb06-2352-439f-a6d0-ccaa857c7a54_2da08de7-e183-43a5-850b-1b41d9cdf907.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trade-in options for PS4.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[p] Consoles -> CLICK\n[link] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.26, 0.375, 0.281] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5b56e9a-afef-4d1a-bd62-dddc058fdc81_4a8b112d-25b2-4430-8ca3-275372e7ecbb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[textbox] Last Name (required) -> TYPE: Smith\n[textbox] Email (required) -> TYPE: [email protected]\n[checkbox] Career opportunity Career opportunity -> CLICK\n[checkbox] Office location Office location -> CLICK\n[checkbox] Company success Company success -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.531, 0.829, 0.55] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c73b1674-9c61-46a3-84dd-8fad3622a035_1ee44a3e-5f91-4a34-bbed-16b7b4fbb81d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[span] 31 -> CLICK\n[span] Search flights -> CLICK\n[button] Continue to flight results -> CLICK\n[link] Sort & Filter -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.775, 0.225, 0.84, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/867dc9d1-5017-4871-a52a-a1511f239628_fd6c3519-38ba-4091-be70-5c82a7f542f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movie trailers currently in theaters with \"fresh\" rating.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Trailers -> CLICK\n[link] VIEW ALL -> CLICK\n[span] Tomatometer -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.682, 0.305, 0.805, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bafd6a44-5938-431f-8e2e-17d680d5c48b_bd359ca1-6647-4b90-9465-583fbc71a119.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the page with information about Wi-Fi subscriptions.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.047, 0.664, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1f128c19-3093-4c49-bfc7-13589aa8e88a_6d3daffd-e582-43ec-9bde-6823e140ab89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[link] Toys -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.014, 0.086, 0.08, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/783d5a91-5f7e-4184-8467-e7ea88e81c5b_13ed3791-9c2f-4f2c-a0e5-2d2a472e1fd2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Set the 3rd top hip hop track as my current obsession\nPrevious actions:\n[link] Music -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.668, 0.331, 0.801, 0.49] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/563ec938-b259-45b7-b0d3-6360b74e601d_65751985-a337-44ea-92ee-e6539bda7fd1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 of WrestleMania single day Parking Passes on April 1st in California near LA.\nPrevious actions:\n[div] Sports -> HOVER\n[link] WWE -> HOVER\n[link] Wrestlemania -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.111, 0.161, 0.158, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a5c1095b-bba1-4029-8b8d-fa5848702827_ffd31f7b-a7cf-4c8b-9a96-5ca46768637c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City from June 5th to 9th.\nPrevious actions:\n[i] -> CLICK\n[i] -> CLICK\n[gridcell] 5 -> CLICK\n[span] Jun 5 -> CLICK\n[gridcell] 9 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.902, 0.09, 0.959, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/db289bef-3d18-43c6-8ee3-a1ebc5d285b4_ba175789-2fbd-4694-80a4-dc507e353aae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 news about the ps5.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.198, 0.677, 0.231] in the image\nAnd my action is Action: TYPE\nValue: ps5" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_d1c03c4f-03c1-42df-a1eb-752d2d674a7f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\n[link] TICKETS -> CLICK\n[span] -> CLICK\n[label] 2 -> CLICK\n[span] -> CLICK\n[input] -> TYPE: 200" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.877, 0.175, 0.965, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_f36f8381-72f0-49e3-b691-c855827719b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[option] Mexico City - Benito Juarez Intl, MX (MEX) Mexico -> CLICK\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Low to High" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.475, 0.331, 0.486] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e62d1f6c-d98c-4ea2-b699-527eeedf3e9b_7ff13337-9f2f-4ca3-874a-76cacb179479.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.37, 0.508, 0.492, 0.534] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_e1c57852-be09-49d4-b6c5-8b08ffa4dbc1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[menuitem] Kids -> HOVER\n[menuitem] Pants & Leggings -> CLICK\n[div] Sports -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.284, 0.194, 0.293] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fa2828c5-44b3-446e-ae42-a26438ed8343_8b009b24-ae1b-40ce-b188-25c36447b588.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 upcoming departures for the oak grove station going southbound direction\nPrevious actions:\n[combobox] Search MBTA.com -> TYPE: oak grove station\n[button] search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.443, 0.261, 0.455, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50f1e384-4b63-4827-a670-cd19f5a2c710_f86868ba-77b6-40ce-afe6-ec0cdbf31f08.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 schedule for Long Island Rail Road & Metro-North Railroad from Bay Shore to Breakneck Ridge on Thu, Mar 23, 08:37 AM.\nPrevious actions:\n[listitem] Bay Shore -> CLICK\n[searchbox] To -> TYPE: Breakneck ridge\n[span] Breakneck Ridge -> CLICK\n[button] 03/18/2023 -> CLICK\n[link] 23, Thursday March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.67, 0.253, 0.727, 0.277] in the image\nAnd my action is Action: SELECT\nValue: 8" } ]

{ "bytes": "", "path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_e8dcebbf-9804-4061-9c08-d4008deb715e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[span] Select store -> CLICK\n[link] Flatware -> CLICK\n[button] Show more filters modal -> CLICK\n[button] Sort Best match -> CLICK\n[radio] Price: low to high -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.95, 0.062, 0.969, 0.072] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_5b3eb865-638b-48aa-8415-2acfb4905ade.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[button] Search flights + cruise External Link should open ... -> CLICK\n[combobox] Departing from -> TYPE: ATLANTA\n[span] Atlanta, GA (ATL) -> CLICK\n[span] Jun 2023 -> CLICK\n[option] Oct 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.716, 0.238, 0.972, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f395aad-6f10-4055-932a-d2af443e6bfa_8dada5a6-6c79-452b-9908-de98a25c6f5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Star Wars The Mandalorian statue and add to cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.006, 0.613, 0.023] in the image\nAnd my action is Action: TYPE\nValue: Star Wars The Mandalorian statue" } ]

{ "bytes": "", "path": "./images/fca09c13-5e6c-49d5-b3ee-b620a70b19f5_93ed2d34-334e-4c25-9bdd-b1ed285fdd11.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[option] Top destination Tokyo, Japan (City) -> CLICK\n[div] 10 -> CLICK\n[span] 12 -> CLICK\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.295, 0.686, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c3b2a4f-4b54-4724-9d8a-0ea95ab180c5_fe665efe-5d42-48d3-ae92-66c30e8134ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 forum threads which include the name Taylor Swift in the title within last month\nPrevious actions:\n[link] Forums -> CLICK\n[link] Advanced search -> CLICK\n[textbox] Search by keyword -> TYPE: Taylor Swift\n[combobox] Find Posts from -> SELECT: 1 Months Ago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.177, 0.412, 0.223, 0.427] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b3fbf029-aa63-4dd1-879f-47d8abbae4d4_247a11f8-00a7-4f2d-a549-c4bafb74faf9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 attorney for divorce in Union City, NJ.\nPrevious actions:\n[link] Attorneys -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.006, 0.789, 0.026] in the image\nAnd my action is Action: TYPE\nValue: Union City Nj" } ]

{ "bytes": "", "path": "./images/fe6b5531-ce29-4ba1-8e98-43b5fecf57fa_3c7bf6a2-a75f-434d-8bc2-e34824e43dbb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest flight from London to New York on 9th May.\nPrevious actions:\n[tab] Flights -> CLICK\n[combobox] Flying from -> TYPE: London\n[option] Destination London -> CLICK\n[combobox] Flying to -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.139, 0.792, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a831fb6-3110-4ffb-8687-1d2acab09873_21d16a48-dcdb-4226-92ba-31ea01da9118.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a park that has a campground and is located in the state of Colorado.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[link] Search by Activity or Topic -> CLICK\n[combobox] By State -> SELECT: Colorado\n[button] Activity -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.191, 0.154, 0.21] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_43e06d15-4af3-477d-8d5a-2be93ca570e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.346, 0.043, 0.448, 0.07] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ef23fbf3-f05e-41e2-b847-a27028f42470_6d29058c-c968-4817-a15a-99a4667e39f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 “pizza” restaurants near Atlanta\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.13, 0.223, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4970cd99-ce6b-42e3-bc78-695c9d510f6c_39e9097a-7ac8-4543-8ad6-91b40f932b34.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the trip planner for a trip between Cheyenne, WY and Helena, MT.\nPrevious actions:\n[link] TRIP PLANNER  -> CLICK\n[textbox] Enter your Origin -> TYPE: Cheyenne\n[textbox] Enter your Destination -> TYPE: Helena\n[button] Get Directions -> CLICK\n[li] Cheyenne, WY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.41, 0.43, 0.578, 0.456] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_1654a37a-cc71-4bac-88f3-efe73a2675f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Age of Child 2(Child's age (years)) -> SELECT: 5\n[img] Add -> CLICK\n[combobox] Age of Child 3(Child's age (years)) -> SELECT: 8\n[img] Add -> CLICK\n[combobox] Age of Child 4(Child's age (years)) -> SELECT: 12" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.454, 0.686, 0.497] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e12f51f6-c8c5-4a68-9586-d77927bca79c_f74e6f89-7fd4-4a49-9204-750b69c96b67.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a Tesla Shop Gift Card for April May with the email [email protected] to my cart\nPrevious actions:\n[link] Shop -> CLICK\n[menuitem] Lifestyle -> CLICK\n[img] Tesla Shop Gift Card -> CLICK\n[textbox] Name of Recipient -> TYPE: April May" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.339, 0.929, 0.356] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/4fe76361-f0e3-458f-a3d5-453da3c7cecc_dcf6e978-dc7f-436d-80c6-2f8ad9445bcf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.051, 0.17, 0.06] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27a8bf82-2e7e-48c3-8fb1-66909c13d585_1ae1d6c7-b4d4-4b78-a3f9-5e6974eb5bde.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Buick for sale within 250 miles from 26807.\nPrevious actions:\n[button] Cars & Services -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.026, 0.83, 0.039] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6c7934b-6949-46ee-8f72-edb46abd3da7_2b807397-c070-4c9f-9438-75fe88d865d9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 winning odds in the Champions League for Real Madrid against Chelsea.\nPrevious actions:\n[span] Odds -> CLICK\n[heading] SOCCER -> CLICK\n[heading] ENGLISH PREMIER LEAGUE -> CLICK\n[link] UEFA CHAMPIONS LEAGUE -> CLICK\n[heading] GAMES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.197, 0.846, 0.211] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_e0790ebc-b02a-4b78-abb2-ec03cf320458.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[button] Substract one Adult -> CLICK\n[button] Substract one Child -> CLICK\n[generic] Economy -> CLICK\n[option] Premium economy -> CLICK\n[button] Find flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.532, 0.402, 0.636, 0.441] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/779cec8e-eef5-4de8-a42e-b449363664df_05b42c16-2b58-423e-9f0d-c4ef3203b528.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 theatre near 10001\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.147, 0.888, 0.173] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_07eaf7cf-bc33-4fd1-9e7a-5b4c915112c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[menuitem] Research -> HOVER\n[menuitem] Price Trends -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.324, 0.193, 0.335, 0.199] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a83c14aa-1a0b-4aaf-a801-ac828d2e81ca_a0620450-f297-4f91-9643-1324d3373687.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 4 star rated Hotel in New York Timesquare for 2 adults.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: Timesqure New York\n[button] Times Square, New York, NY, USA -> CLICK\n[button] 1 adult · 0 children · 1 room -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.588, 0.301, 0.811, 0.319] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5b56e9a-afef-4d1a-bd62-dddc058fdc81_2b8696c1-be11-47de-af3c-141664f86b58.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an engineering open job in Madrid, Spain, if found apply with my details after picking office location, company success and career oppurtunity as applying reason. My name is James Smith and email is [email protected]\nPrevious actions:\n[checkbox] Spain (18 items) -> CLICK\n[checkbox] Madrid (2 items) -> CLICK\n[link] Title: IT Support Engineer -> CLICK\n[textbox] First Name (as per passport) (required) -> TYPE: James\n[textbox] Last Name (required) -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.673, 0.569, 0.92, 0.591] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/29fde741-075c-446c-8e8a-f432e81e7ac0_2b73cbf1-4de3-4555-9070-0c329cd919b7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate vehicle price with a challenge credit score, monthly payment of $250 with a $3000 down payment and 24% APR for 48 months in Tennessee.\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.257, 0.656, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_552ceafa-2cc7-46fc-a178-1ffd27f5ef89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK\n[button] Continue with this address -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.119, 0.692, 0.2, 0.716] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5d47068-b773-4061-b7ba-17bd25e88e06_d0560cf3-9b90-4a29-a8b8-08577ec0c19b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Save two deals and offers for US.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.038, 0.598, 0.057] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b040b35d-cfd3-41b8-8b8b-851ab151a9cc_464ec933-1237-478f-a390-08e1168b4498.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the complexity rating for Frosthaven.\nPrevious actions:\n[combobox] Search -> TYPE: frosthaven\n[link] Frosthaven (2023) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.658, 0.144, 0.773, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1337eca1-4ca6-4102-964e-e7f6ecebcd0b_e1fe0472-1d20-446d-a70d-80ff72131b1c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.152, 0.568, 0.179] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54d60a7c-f52d-4d79-b879-34698507e22c_66342372-6689-4084-8008-5bdd51746855.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[input] -> CLICK\n[gridcell] March 18, 2023 -> CLICK\n[input] -> CLICK\n[gridcell] March 19, 2023 -> CLICK\n[spinbutton] How many travelers? -> TYPE: 3" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.754, 0.124, 0.919, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_93b6ddac-92d1-4133-9adc-86d8ce49f9d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[link] SEARCH CARS -> CLICK\n[div] Best match -> CLICK\n[label] Nearest distance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.263, 0.249, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/998d121b-c858-485d-9dd3-4609575d144b_afaeea13-bdcc-4dfb-820b-5ca847f3103e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular song this week by the no. 1 weekly charts ranked artist\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.806, 0.005, 0.838, 0.026] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4623be1-31c6-4546-a567-92bfd1da9cd7_b845c300-477d-4935-97cc-1ea84ec96398.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Upgrade the count of the current SSD in my cart to 10\nPrevious actions:\n[link] Shopping Cart -> CLICK\n[textbox] qty -> TYPE: 10" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.48, 0.147, 0.523, 0.165] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_12c1b3bf-3325-4612-9902-b097acc4a6e4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[generic] Previous Month -> CLICK\n[generic] Previous Month -> CLICK\n[gridcell] 1 -> CLICK\n[span] -> CLICK\n[generic] Previous Month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.183, 0.3, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7180c4d1-971b-418d-8a64-87ab0d29c20e_489a9668-fabb-4591-aa4f-a235753a96fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[button] Browse Vehicles -> CLICK\n[checkbox] Trucks -> CLICK\n[combobox] SORT BY -> SELECT: Low to High\n[checkbox] 4+ -> CLICK\n[button] Select Chevrolet Colorado Vehicle -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.799, 0.163, 0.951, 0.197] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_a9d256e6-2222-4953-8e33-4444408df4ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Sort/Filter -> CLICK\n[checkbox] filter trains by Time of Day:6a-12p -> CLICK\n[mat-pseudo-checkbox] -> CLICK\n[button] Close -> CLICK\n[button] First from $722 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.82, 0.236, 0.945, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7180c4d1-971b-418d-8a64-87ab0d29c20e_610a704a-42dd-43c7-b6f6-8800697dc2d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: JFK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.216, 0.533, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_2d2144f4-0a3d-482e-95f0-7f07ca0bbf5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.172, 0.259, 0.195] in the image\nAnd my action is Action: TYPE\nValue: BWI" } ]

{ "bytes": "", "path": "./images/6407babe-fe48-492a-8211-1f22a81b9ac0_b5b09d80-00ed-4295-82de-d967b31efaa5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 men's running shoes of size 9 with lowest price and add to bag.\nPrevious actions:\n[link] Running -> CLICK\n[div] Size -> CLICK\n[link] 9 -> CLICK\n[span] Now Trending -> CLICK\n[li] Price (Low - High) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.277, 0.215, 0.495, 0.45] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6f4e562e-91f9-401d-8730-af947985b821_86abe01d-3a02-4f50-86be-bc8454ad2f8c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 3 most rated to watch tv shows or movies on Amazon Prime to watchlist.\nPrevious actions:\n[link] What to Watch on Amazon Prime -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK\n[button] View Results -> CLICK\n[span] Watchlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.342, 0.466, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a45ede7-6449-40b2-b032-149ddbe205a9_342bae0c-0a5a-4040-8b4e-238906800a1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\n[combobox] autocomplete -> TYPE: New Orleans\n[div] LA, USA -> CLICK\n[button] Food & Drink -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.061, 0.341, 0.262, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f0988e0-e3a4-4dd7-a89f-482175a474a8_aa68d1df-0533-407f-b2e3-6f8118babb0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.375, 0.254, 0.625, 0.291] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_2bb85139-e8e3-45ca-8e49-d99aea4df215.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[button] Search -> CLICK\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: atlanta georgia\n[button] Submit -> CLICK\n[span] Select store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.607, 0.197, 0.71, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_5d09b93b-3839-4e67-83bc-9cfde7194124.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[button] Add to cart—$799.95 -> CLICK\n[link] Cart & Checkout -> CLICK\n[link] Proceed to checkout -> CLICK\n[button] Continue without membership -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.298, 0.462, 0.325] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_58359ff4-73dd-45ee-b703-026fd4666acf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: stewart hotel" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.262, 0.748, 0.283] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f5d4d405-9714-47a5-a66a-49a899b16b97_6ac79817-591c-4763-b856-e3a201786417.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check all available tickets within $100 to $200 for the New York Knicks first game on April2 nd.\nPrevious actions:\n[link] sports. -> CLICK\n[textbox] Search by Name -> TYPE: New york knicks\n[p] New York Knicks -> CLICK\n[link] View Tickets -> CLICK\n[span] (0) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.872, 0.435, 0.972, 0.468] in the image\nAnd my action is Action: TYPE\nValue: 200" } ]

{ "bytes": "", "path": "./images/862faed7-449c-4624-902b-6b512a977d0c_77f619a4-6625-416b-823f-da4c81e06018.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 surge protector with 6 to 8 outlets under 25 dollars with customer reviews above 4+, add 2 pieces to the cart.\nPrevious actions:\n[link] Surge Protectors -> CLICK\n[link] 6 to 8 Outlets -> CLICK\n[link] Under $25 -> CLICK\n[region] 4 Stars & Up -> CLICK\n[link] New -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.832, 0.088, 0.866, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ba5e0124-b1c0-4116-968c-6b31a4c9c0a7_6564754c-cf0b-4099-a320-28dabde5f587.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bus for 2 persons from New York to Washington, DC.\nPrevious actions:\n[label] One way -> CLICK\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.191, 0.568, 0.208] in the image\nAnd my action is Action: TYPE\nValue: Washington" } ]