Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_d953665b-60d3-4f3b-a12b-d55b929baddb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[link] Choose Another Hotel -> CLICK\n[button] Choose your room -> CLICK\n[button] Book Double Bed - Standard Room -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.896, 0.273, 0.977, 0.296] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_a4c79037-e990-4a7a-9d4a-c0f8936dba07.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox One -> 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, 0.272, 0.375, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_fb5b3b82-7410-4d95-b743-5441b8e24ece.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.006, 0.204, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/884a375b-e3f4-4f34-8e99-290f49141f9a_b8a690b2-a54c-43a4-9e9e-85a85f00eee7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a dog bed on Amazon that is machine-washable and has a diameter of at least 30 inches.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.005, 0.651, 0.024] in the image\nAnd my action is Action: TYPE\nValue: dog bed 30 inches" } ]

{ "bytes": "", "path": "./images/37c09901-63d4-4194-8a96-1d87ca8c37ae_50bd371f-78a5-443f-a626-2689e0c84de9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 washing machines available for free local pickup within 25 miles of zip code 90026.\nPrevious actions:\n[combobox] Search for anything -> TYPE: washing machine\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.729, 0.087, 0.749] in the image\nAnd my action is Action: TYPE\nValue: 90026" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_78d5767c-9755-4037-a6cc-b9395a07ba99.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] First name -> TYPE: Joe\n[textbox] Surname -> TYPE: Bloggs\n[textbox] Email address -> TYPE: buckeye.foobar@gmail.com\n[textbox] Confirm email address -> TYPE: buckeye.foobar@gmail.com\n[input] -> TYPE: 1111111111111111" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.545, 0.95, 0.584] in the image\nAnd my action is Action: TYPE\nValue: the home of joe bloggs" } ]

{ "bytes": "", "path": "./images/8d9e09e1-c31a-420b-ace8-079204db551a_912aaece-7d84-4401-bda8-02aa5289da82.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a ticket for an event similar to professional boxing\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.174, 0.782, 0.207] in the image\nAnd my action is Action: TYPE\nValue: professional boxing" } ]

{ "bytes": "", "path": "./images/29f47ddb-3d25-4cfb-b1d6-d3987e998a13_4f9882ac-080d-4657-a4ff-47696c6a4b29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movie \"65\" that is digital at the AMC Grove City 14 showing at 7:30 pm on Tuesday, March 28, 2023 and buy four tickets for seats J10 through J7\nPrevious actions:\n[select] AMC Grove City 14 -> SELECT: AMC Grove City 14\n[select] All Movies -> SELECT: 65\n[select] Sun, Mar 26 -> SELECT: Tue, Mar 28" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.355, 0.433, 0.451, 0.475] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_5700b7d0-ce16-4fb9-b77f-0546c08c8568.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] hotels -> CLICK\n[div] Destination or property -> TYPE: jakarta" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.095, 0.713, 0.108] in the image\nAnd my action is Action: TYPE\nValue: jakarta" } ]

{ "bytes": "", "path": "./images/1943febc-0635-4124-871c-578c4d9f5a44_62f82d6a-0799-49e5-9b06-3de4294ea2e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guitar tab for Absolute Beginners.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.039, 0.176, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_13a2c4e4-2eed-443e-9c1b-f9158831bce5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 buckeye.foobar@gmail.com. Employer's name is Gua AB.\nPrevious actions:\n[textbox] (###) ###-#### -> TYPE: 888888888\n[textbox] Email Address -> TYPE: buckeye.foobar@gmail.com\n[textbox] Email Address -> TYPE: buckeye.foobar@gmail.com\n[textbox] Employer Name -> CLICK\n[textbox] Employer Name -> TYPE: Gua AB" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.883, 0.73, 0.934, 0.754] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_bc0ec628-85e4-4548-9c22-79e966b51ed2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.077, 0.327, 0.101] in the image\nAnd my action is Action: TYPE\nValue: BRISTOL" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_7e717da9-b333-49a6-a9bd-b2f045d69cc7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Chennai\n[option] Chennai, Tamil Nadu, India -> CLICK\n[button] Monday March 20, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.935, 0.092, 0.977, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4775a0e3-3dad-46f2-b719-b1c0dae9e147_6d39e04d-cc1b-4633-9459-350a37def42a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.015, 0.284, 0.021] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_6b277741-9a89-48d0-9635-b0323bb1270d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[tab] One-way -> CLICK\n[generic] Thursday May 18th -> CLICK\n[div] 24 -> CLICK\n[button] Search -> CLICK\n[div] $141 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.643, 0.354, 0.728, 0.38] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d173ebb-ff7a-4e6b-9911-0f0349f9a174_baed0e46-faa0-4f15-aa46-f27dd88f6e33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City by month on July 5th start date.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York\n[li] New York, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.279, 0.384, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d042ee7e-a2eb-448b-9942-b7aacc9115be_4164e2f1-5ef8-43d2-bb38-176244354c7f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the soonest upcoming event near zip code 90028.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.854, 0.004, 0.887, 0.022] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b2dd00ff-3f09-46bf-a043-7b996f3815da_06821f17-f373-4854-9f11-fdf64b7a44f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 holiday campground in Alaska.\nPrevious actions:\n[link] CAMPING AT KOA  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.157, 0.266, 0.192] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_6cf0b91a-fc8d-4494-a0c8-fb11ed928aaa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[link] WOMEN -> HOVER\n[tab] Innerwear & Underwear -> CLICK\n[link] Bras -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.23, 0.585, 0.277, 0.602] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_74e72084-66fc-48b6-adb1-1795475571ae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, james.john@gmail.com. It is a family trip organized by Johnson.\nPrevious actions:\n[link] Group Tickets -> CLICK\n[i] -> CLICK\n[button] Buy Tickets -> CLICK\n[button] April 30, 2023 -> CLICK\n[button] Buy Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.75, 0.047, 0.777, 0.063] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/913b902b-37b7-4230-a0f2-a19931b06951_ad0e2c07-6812-4507-8b98-f82b0d619fd6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the fastest single stop flight fron JFK airport in New York to Male in Maldives on March 13\nPrevious actions:\n[span] Round-trip -> CLICK\n[tab] One-way -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.137, 0.432, 0.169] in the image\nAnd my action is Action: TYPE\nValue: new york" } ]

{ "bytes": "", "path": "./images/b3fbf029-aa63-4dd1-879f-47d8abbae4d4_a3caa31c-759f-4764-ba35-39db38cc3e33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[input] -> TYPE: Union City Nj\n[link] Union City, NJ -> CLICK\n[button] Find -> CLICK\n[link] All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.423, 0.216, 0.575, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_da34e6ef-01dc-47ce-8f12-3a771d0ad4be.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[option] Tops -> CLICK\n[heading] Size -> CLICK\n[label] L -> CLICK\n[heading] Color -> CLICK\n[label] BLACK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.169, 0.473, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_cabd36a8-0a4b-43c8-a930-64ae46695583.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[span] 25 -> CLICK\n[svg] -> CLICK\n[checkbox] 15 June 2023 -> CLICK\n[checkbox] 20 June 2023 -> CLICK\n[span] 2 adults -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.3, 0.74, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_513911cb-10e9-44d7-9254-252734b92b6c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[checkbox] Nonstop (1) -> CLICK\n[checkbox] 1 Stop (49) -> CLICK\n[checkbox] Seat choice included -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.226, 0.048, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/942e315d-b494-469c-93df-cd69c88ea2d2_72aebfb6-ea05-4023-b171-cd398ebf61b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information regarding Fastbreak program.\nPrevious actions:\n[button] Fastbreak -> CLICK\n[link] Fastbreak Program -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.169, 0.19, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/945ac29d-8e65-4e14-8bab-21742ac92a47_84fd0117-d99b-47e0-96ea-08945d9fadb1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest bananas at Kroger\nPrevious actions:\n[img] -> CLICK\n[textbox] Search Kroger... -> TYPE: bananas\n[span] bananas -> CLICK\n[span] Best match -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.816, 0.132, 0.963, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_e8584aab-e315-4f72-b91f-bf7e76a7d1b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> CLICK\n[searchbox] Search -> CLICK\n[option] United States of America -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.502, 0.32, 0.514] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_f8cc67b4-274d-4aeb-9012-d1e307deb997.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.143, 0.008, 0.189, 0.026] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58badcfc-343a-47c1-8aec-f609925eb4ed_d6cb8acb-5af8-4ed1-9b71-eb36c19e63dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ricky Kej track to listen and share which has been added in the last year and is between 2 to 10 minutes.\nPrevious actions:\n[link] Added any time -> CLICK\n[link] Past year -> CLICK\n[link] Any length -> CLICK\n[link] 2-10 min -> CLICK\n[link] To listen to -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.473, 0.212, 0.492] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fbaa5c83-11ed-40d8-b5e6-d4ddb9a1cbde_baeb278e-2713-42b7-9253-d5c13138436f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy shows taking place in Chicago, IL and expand the results once.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: Chicago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.367, 0.266, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_d2be2e1a-e5ba-44a6-bbee-83c29f97f07a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a black blazer for men with L size and add to wishlist.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Search by keyword -> TYPE: blazer" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.198, 0.887, 0.238] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0d6b0ed-82e4-4ba7-9a9b-7b874dacf19c_b6a55c9d-ad1f-4ef5-aca1-093ccb6731d0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 map of Cleveland's animal shelters.\nPrevious actions:\n[link] CITY PAGES -> CLICK\n[link] Cleveland -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.842, 0.11, 0.921, 0.128] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4a4ecf18-e7a3-448a-b8cb-b337ee20048d_7f6709ef-e981-466c-93ef-0fca08b49eba.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 table for 3 in Los angeles for diner at 09 PM on Mar 10\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.062, 0.347, 0.08] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_a4d6ed68-2cee-458e-92d7-a10c85cf0636.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.308, 1.0, 0.35] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd2494f3-fe7d-4c58-81e4-742c72b4e1f2_e6d16748-7363-4ea8-88d5-d84d200ed602.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 order status using an order number of24124124091. The email address is boobear@gmail.com\nPrevious actions:\n[link] Store -> HOVER\n[link] Order Status -> CLICK\n[textbox] Order number -> TYPE: 24124124091" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.389, 0.872, 0.441] in the image\nAnd my action is Action: TYPE\nValue: boobear@gmail.com" } ]

{ "bytes": "", "path": "./images/6d87b507-14dd-4903-a131-fa089499ccb5_636947f5-7244-4149-8c6b-21830f9574ae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\n[div] Apr -> CLICK\n[div] Choose date -> CLICK\n[generic] 5 -> CLICK\n[button] Search -> CLICK\n[button] Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.862, 0.475, 0.922, 0.525] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b28e6a37-6e9c-46bb-8012-18ca742a521f_19c1d885-fd92-43a9-b9a6-091054ce4e46.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 28 May 2023 -> CLICK\n[button] Continue -> CLICK\n[textbox] Passengers / Class -> CLICK\n[button] Increase number of infant passengers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.658, 0.298, 0.93, 0.343] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_1298e843-2ed2-4cff-a3bb-95cf25587d71.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[link] Fishing -> CLICK\n[menuitem] View All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.753, 0.089, 0.766] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d6a0ab7c-f0d7-4ff7-9d42-55b44b5e7f74_e94d39fa-877b-4289-81f9-0762467b1315.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 artist profile of M S Subbulakshmi and play all from the top tracks.\nPrevious actions:\n[link] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.906, 0.048] in the image\nAnd my action is Action: TYPE\nValue: m s subbulakshmi" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_83ac91e9-e83c-49e2-aa02-8a6085f50d84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[tab] One-way -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] 2 travelers -> CLICK\n[img] Increase children -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.133, 0.828, 0.14] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ecb649da-0ca7-4707-8ebb-8707296e28b7_6b1edaaf-3328-41f0-a8dc-462e1d2cb8c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for flights available from Calgary (CYYC) to New York (ZNY).\nPrevious actions:\n[textbox] Origin -> TYPE: Calgary\n[div] Calgary -> CLICK\n[textbox] Destination -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.352, 0.532, 0.364] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_4a795c4f-8cd7-4d8b-8dfb-747268abf852.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[textbox] Destination -> TYPE: new delhi\n[menuitem] New Delhi, Delhi, India -> CLICK\n[textbox] Start Date -> CLICK\n[gridcell] Sat, Apr 29, 2023 -> CLICK\n[div] 30 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.68, 0.404, 0.943, 0.411] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1202e28a-361d-4704-979a-526c599b4859_ed843127-7acc-4756-96f7-ef0177b3e64a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a fully electric car pickup at Athens Airport (ATH) Sat, Apr 1, 2023 and return to the same palce at Mon, Apr 3, 2023.\nPrevious actions:\n[textbox] I need a car in -> TYPE: Athens\n[button] Athens Airport (ATH) Athens, Greece -> CLICK\n[div] Apr -> CLICK\n[generic] 1 -> CLICK\n[generic] 3 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.14, 0.953, 0.171] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/91f56f3b-e3de-4d57-95df-f976a11c64f7_fd35e11d-5eb9-48c1-a193-bf04d51813b9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 veterinarian emergency service for dogs in Hawaii with a BBB rating of A+\nPrevious actions:\n[link] Veterinarians -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.007, 0.789, 0.031] in the image\nAnd my action is Action: TYPE\nValue: hawaii" } ]

{ "bytes": "", "path": "./images/c55b9949-b785-4d9e-8b20-b626cb595623_74bf98d9-7598-4103-8a25-8fb7859700e7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events in Phoenix for the next 3 days.\nPrevious actions:\n[button] CITY GUIDES -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.66, 0.238, 0.782, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_2b69e7d2-66ed-486b-8ae2-2e763e1f7d6d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[button] Continue to Location -> CLICK\n[select] Select a Pick-up Time -> SELECT: 04:00 PM\n[select] 04:30 PM -> SELECT: 04:30 PM\n[button] Select Pick-up Location -> CLICK\n[button] Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.798, 0.122, 0.928, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_0b060218-50cb-4545-bf81-04f57be2db97.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[span] Lowest price -> CLICK\n[button] Choose room -> CLICK\n[button] Book now -> CLICK\n[textbox] First name -> TYPE: Joe\n[textbox] Surname -> TYPE: Bloggs" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.243, 0.631, 0.276] in the image\nAnd my action is Action: TYPE\nValue: buckeye.foobar@gmail.com" } ]

{ "bytes": "", "path": "./images/2a8ae104-6f06-47cb-80a0-045188125868_fc3816cd-1221-4d65-a475-ef22b1771303.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Display details of new lanched iPad pro 11-inch\nPrevious actions:\n[link] iPad -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.081, 0.343, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8eef04e2-3d51-4a0e-84f2-db017a69050b_564cb934-0518-4171-9ef4-ddc0e0d42251.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Promo Code for Spring Break Savings and packages.\nPrevious actions:\n[button] Special Offers -> CLICK\n[link] Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.089, 0.348, 0.457, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cd20dc6-d2a5-4e8f-9252-549f2c51413c_05ba30e9-0691-4d0c-9307-8af2746cc476.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 inventory of Tesla Model S that are blue and new with 19\" wheels within 50 miles of zip code 60602.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.054, 0.261, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_d471e93f-d8de-4dd3-8d20-e0d660259ade.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[li] Wedding -> CLICK\n[textbox] Destination -> TYPE: Venice Beach\n[menuitem] Venice Beach, Los Angeles, CA, USA -> CLICK\n[textbox] Event space -> TYPE: 100\n[textbox] Start Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.61, 0.387, 0.648, 0.4] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/22e33a38-902c-4f62-9e9a-822b2370b6d1_1148e403-4327-47a0-ba61-c781b3c53813.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK\n[button] Selected Pick-Up Date 03/31/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 5:00 PM\n[button] Browse Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.485, 0.059, 0.497] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aeace1e7-0460-4f4e-99fb-2a8c867b97ef_7dd29122-5aa7-4e40-a2a3-6193dd6eb05d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 highest rated Last-Minute Flights & Car Rentals\nPrevious actions:\n[link] Last-Minute Deals -> CLICK\n[heading] Last-Minute Flights & Car Rentals -> 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 [0.708, 0.267, 0.772, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/08a998f9-82f7-48c8-b6ba-72a58d39b457_95bdb2f9-afcd-4088-bb07-12fb2b494992.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all Uniqlo's located in Chicago, IL.\nPrevious actions:\n[link] Store Locator -> CLICK\n[searchbox] SEARCH BY KEYWORD -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.2, 0.759, 0.234] in the image\nAnd my action is Action: TYPE\nValue: Chicago" } ]

{ "bytes": "", "path": "./images/b4872f0e-9d9e-4259-8b1e-844509b85712_82cc8845-bf93-4eeb-bf4b-56ec11926ae4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all campgrounds located in California.\nPrevious actions:\n[link] FIND A CAMPGROUND  -> CLICK\n[link] FIND BY STATE/PROVINCE  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.102, 0.538, 0.154, 0.548] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_e2ae9f11-253a-4887-856a-20a5f2a77659.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id denise.bloom@bbt.com and Debbie Wolowitz on email id debbie.wo@bbt.com.\nPrevious actions:\n[img] GIFT CARDS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.511, 0.448, 0.552] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_af730851-81f0-4bb7-b065-a2c06a4d7121.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\n[path] -> CLICK\n[combobox] Search by city or activity -> TYPE: Miami\n[generic] United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.319, 0.686, 0.365] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_c04a9026-e147-4c97-8589-5ef46bd0f224.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Rent a 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[select] Select Pick-up Time -> SELECT: 04:00 PM\n[input] -> CLICK\n[button] Find Your Truck -> CLICK\n[button] Select Truck -> CLICK\n[input] -> TYPE: 250" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.755, 0.475, 0.927, 0.513] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_8c2ccd6f-96dd-45ff-821e-eb2dc0a30b49.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Limited Time Offers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.616, 0.305, 0.72, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_56ae15c7-ae7b-4d02-aa81-ade2de73778c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Berlin Berlin Federal State, Germany (City) -> CLICK\n[div] -> CLICK\n[generic] 15 -> CLICK\n[generic] 16 -> CLICK\n[button] 11:30 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.609, 0.477, 0.715, 0.521] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/330d5618-9db4-447b-9b56-0d2c33f414d5_a7fa1b89-a997-48b0-9e33-4f34fcca5f69.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 full menu for AMC dine-in locations.\nPrevious actions:\n[link] Visit the Food & Drinks page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.285, 0.087, 0.488, 0.102] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42657330-bfc5-425d-ae21-396a9ba1fb12_0f57acd6-e046-4943-9760-1aa47a966503.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find yellow t-shirts for women small size that are less than $20.\nPrevious actions:\n[link] WOMEN -> CLICK\n[RootWebArea] Women's, Men's & Kids' Clothing & Accessories | UN... -> CLICK\n[searchbox] Search by keyword -> TYPE: women t-shirts\n[div] WOMEN / Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.341, 0.336, 0.36, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_c43e32b7-d7af-4d60-b11f-d2f9c45da006.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the most popular Women's Athletic Shoes.\nPrevious actions:\n[span] Shop by Category -> CLICK\n[link] Women -> HOVER\n[link] Shoes & Sandals -> CLICK\n[link] Athletic Shoes & Sneakers Athletic Shoes & Sneaker... -> CLICK\n[link] Sort by: Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.808, 0.321, 0.974, 0.338] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/91e18ec8-5eae-4b14-a49e-9ed7ee1ebb10_4d90c658-8e5c-4f33-abda-abb115083116.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the list of playstation 5 games available for pre-orders.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Video Games chevron_right -> CLICK\n[button] PlayStation 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.129, 0.094, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_2ed0e2bc-5efb-4f91-af60-ce5031a71a68.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[button] Our Company -> CLICK\n[link] Careers  -> CLICK\n[link] Students & Grads -> CLICK\n[link] INTERNSHIP PROGRAMS -> CLICK\n[link] HOTEL INTERNSHIPS INTERNATIONAL -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.374, 0.085, 0.465, 0.097] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff82e848-f29e-477b-a286-c807cbd0d8fa_59dcc93a-860e-48a6-8b81-8097c3fee4ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[link] Careers This link will take you away from the Qata... -> CLICK\n[span] 64 -> CLICK\n[textbox] Location -> TYPE: india" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.133, 0.603, 0.147] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_9bd8b189-7a5b-4d0e-96ef-ac97d7b147af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[textbox] Drop-off location -> TYPE: new york\n[span] New York, United States -> CLICK\n[generic] Saturday March 25th -> CLICK\n[button] Saturday March 25, 2023 -> CLICK\n[generic] Saturday April 1st -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.827, 0.148, 0.859, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_e9e59734-447c-445e-bdb7-bea4db2729a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[link] Fan & Heatsink CPU Cooler -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.447, 0.512, 0.459] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9e9c178-e945-49fe-9d06-a01cf02ab2db_d03e7438-57ba-4030-84f8-8f933491cd6d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the highest rated spas that are $$ dollar signs and under.\nPrevious actions:\n[textbox] Find -> TYPE: spa\n[span] Spa -> CLICK\n[button] Price: -> CLICK\n[input] -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.238, 0.209, 0.256] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8082086a-10a7-4631-9792-b57337426f9a_88037d8e-d35e-43e7-b65b-3effca4aaeee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SUV with automatic transmission in New York drop off at March 30.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: New York\n[div] New York, NY -> CLICK\n[div] Sat, Apr 1 -> CLICK\n[checkbox] 30 March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.164, 0.923, 0.216] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a338a731-596c-456e-9a9f-25f9e284309e_fddf88e2-6ba5-4b77-94a6-aa4c1b5c0c67.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a playlist and add 3 songs from popular Selena Gomez tracks and name it Love.\nPrevious actions:\n[button] Add to playlist -> CLICK\n[a] Create a playlist -> CLICK\n[textbox] Playlist title * -> TYPE: Love\n[button] Save -> CLICK\n[button] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.407, 0.653, 0.456, 0.673] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61563837-99af-45e2-a13f-9d6bd9f74a81_d2cd0379-7409-47f4-aeb6-8c3b3a889a8d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show all the external solid state drives available with lowest price first.\nPrevious actions:\n[button] Open Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.525, 0.285, 0.55] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8710addc-5ff3-4aaf-b397-4c6165f285ee_78a8a34b-3cf0-4509-b428-953fd4f0c3de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 service options for cars under warranty.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.008, 0.384, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/563ec938-b259-45b7-b0d3-6360b74e601d_7ea26b28-5c62-473d-b458-360617fef404.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Parking -> CLICK\n[span] From $62 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.176, 0.136, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c997e24-d185-4730-84d6-f8cb512f4c03_4c5b26b1-21bb-4ba7-a996-a9609b832e1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car options to pick up at any location near 10023 on april 12 at 3 am\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: 10023\n[span] , 10023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.301, 0.691, 0.347] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_519ead86-64a8-4df9-a1d2-6bd89a9f8f54.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[link] Search for flights -> CLICK\n[svg] -> CLICK\n[tab] One-way -> CLICK\n[button] 1 adult -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.132, 0.532, 0.142] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d73937b-3be7-4f5f-950f-b1905244a2ac_eb57cac8-928c-4777-8c81-103790610108.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 MLB tickets for this weekend and select the next one.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.032, 0.28, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_9be7b356-89b9-40c0-827e-a23d85da1644.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id denise.bloom@bbt.com and Debbie Wolowitz on email id debbie.wo@bbt.com.\nPrevious actions:\n[img] GIFT CARDS -> CLICK\n[img] Happy Birthday -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.453, 0.916, 0.472] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9300d50-11fa-4f98-8c39-424630668ab9_66a995c0-14dc-4dc8-8e8f-adfdd0247b88.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the popular online Health events for tomorr\now?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.727, 0.419, 0.939, 0.455] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a7eaba3-f6ec-4eba-9e04-ff974b228ef4_bc650861-2931-44a1-8ee6-9a22468604df.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select an event from the 2019 UFC schedule and show me the full profile from one of the athletes\nPrevious actions:\n[link] MMA -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.096, 0.52, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b467797c-5fab-4ee6-9b1f-ac6dc50c05cf_ca8df4fe-9e2b-49ea-9eb4-cb71f99749a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[button] APPLY -> CLICK\n[span] Magenta -> CLICK\n[button] APPLY -> CLICK\n[span] Single Pack -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.232, 0.4, 0.254] in the image\nAnd my action is Action: SELECT\nValue: Lowest Price" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_a3741eaf-81d7-4424-8aa6-4171091b1faf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.263, 0.044, 0.366, 0.07] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/afb693cd-57cb-4468-9f7f-d965ee530913_4ff311df-0d3b-4e91-aa58-1fa0219c8834.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 discount black insulated hunting boots for Men with average ratings over 3.5 stars\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.867, 0.119, 0.941, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/caafd610-202e-49d2-85d1-3f167f3ab443_8ca7bf3c-75bf-4fbc-80d1-7d527c476669.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 map of a Six flags park in mexico\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags México -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.12, 0.844, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/efa705c1-f836-4704-b6c8-6e114a2eb865_96c2ecf0-d98a-4fd3-af03-4eefb8ccf225.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a service estimate on AC recharge of my 2022 Toyota Corrola, L Sedan 4D. My name is James Smith, email is buckeye.foobar@gmail.com, and phone number is 6157075521.\nPrevious actions:\n[button] Select Vehicle -> CLICK\n[button] No thanks -> CLICK\n[textbox] Other Ways We Can Help -> TYPE: ac recharge\n[button] See Pricing -> CLICK\n[button] Get Service Estimates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.55, 0.557, 0.575] in the image\nAnd my action is Action: TYPE\nValue: James Smith" } ]

{ "bytes": "", "path": "./images/2089ee5c-1ccd-495e-9a80-f62e129554ed_7c725110-9b24-416e-bf34-1566ee5fd7a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the deals in California\nPrevious actions:\n[button] DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.043, 0.266, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_0392b523-ff32-4400-98ff-9da00b7cda72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a black blazer for men with L size and add to wishlist.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.013, 0.873, 0.052] in the image\nAnd my action is Action: TYPE\nValue: blazer" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_4058fdcb-00c9-479e-a343-0bf9db5ff23e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[li] NYC -> CLICK\n[DisclosureTriangle] All Categories -> CLICK\n[li] Outdoors -> CLICK\n[DisclosureTriangle] All Dates -> CLICK\n[li] This month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.484, 0.179, 0.553, 0.204] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_9c70ec38-dd91-4342-a324-41ede6034a26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[label] BLACK -> CLICK\n[svg] -> CLICK\n[heading] Supima® Cotton V-Neck Short-Sleeve T-Shirt (2022 E... -> CLICK\n[checkbox] L -> CLICK\n[button] ADD TO CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.376, 0.491, 0.397] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14a4e19d-d82d-45dd-b4f0-6b60ed87d085_2da19bbe-dd62-482e-bbf3-24f0ecc52e72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\n[img] -> CLICK\n[link] Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.343, 0.329, 0.404, 0.356] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_5d534eb2-9235-4e29-9b92-955b87be94bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: seattle\n[option] Seattle (WA), United States (City) -> CLICK\n[button] Next Month -> CLICK\n[span] 11 -> CLICK\n[span] 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.471, 0.419, 0.522, 0.435] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_4230e0d5-3c05-4f5e-a84b-380081e7d025.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[div] 30 -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK\n[span] -> CLICK\n[textbox] Guest rooms -> TYPE: 1" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.407, 0.648, 0.432] in the image\nAnd my action is Action: TYPE\nValue: 7" } ]

{ "bytes": "", "path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_c3faae7a-eb45-4287-a15e-dc3226ffb69f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[input] -> TYPE: beauty salons\n[link] Beauty Salons -> CLICK\n[input] -> TYPE: Seattle, WA\n[link] Seattle, WA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.046, 0.788, 0.064] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b39c9ac-a965-4902-a7d9-ec7fb36ca096_89a10228-542e-43ea-be51-914770f17ff5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of a flight between San Antonio, Texas, and Bellingham, Washington on April 8.\nPrevious actions:\n[textbox] From , required. -> TYPE: san antonio\n[a] SAT - San Antonio International, TX -> CLICK\n[textbox] To , required. -> TYPE: washington\n[a] WAS - Washington, DC -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.777, 0.219, 0.843, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5871c3f-27c3-48d8-bdf9-8b49382a2719_a1e01f2e-743a-423b-b3b2-8c89b8775b7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 movies from At the Kiosk which are new to Wishlist.\nPrevious actions:\n[link] Navigate to at-the kiosk -> CLICK\n[link] Navigate to New Releases At The Kiosk See More -> CLICK\n[img] Plane (2023) -> CLICK\n[button] Click to add title to wishlist. -> CLICK\n[link] Navigate to at-the kiosk -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.057, 0.162, 0.085, 0.173] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_b2e40a74-71d8-4594-963c-04d6c99d9924.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: PARIS\n[span] Paris -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.142, 0.327, 0.176] in the image\nAnd my action is Action: TYPE\nValue: MILAN" } ]

{ "bytes": "", "path": "./images/afa1f70c-c0ff-4e4d-a5c2-0c0d292ee066_9d29bcf6-38dc-4fc3-b54b-c79ad0c7b672.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cruise deals to Europe this summer that includes airfare and are all-inclusive.\nPrevious actions:\n[link] Cruises -> CLICK\n[textbox] Where? -> CLICK\n[div] Europe -> CLICK\n[textbox] When? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.52, 0.078, 0.58, 0.106] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5418beec-bc06-4e11-9664-4038fbdeefe9_cdeb8a94-6f22-4f9a-9224-861a9f9518c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\n[link] Filter -> CLICK\n[checkbox] Same Day Delivery Same Day Delivery -> CLICK\n[generic] Refine by Category: Collectibles -> CLICK\n[generic] Refine by Category: Figures -> CLICK\n[link] $0 - $10 $0 - $10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.322, 0.375, 0.371] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/df73be67-e81a-444f-82cc-e69d54a72734_a709ab3a-f10a-4d4c-adda-404e37e3755d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gift shops available at a park in New York\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Darien Lake -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.287, 0.844, 0.331] in the image\nAnd my action is Action: CLICK" } ]