Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/112459f9-10ea-44b5-affa-79008c2977e7_4498554c-48ae-409f-ab30-cdd208c0ae22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse check in with confirmation number 123456 for John.\nPrevious actions:\n[heading] Check-in -> CLICK\n[textbox] Confirmation or ticket number* -> TYPE: 123456\n[textbox] Last name* -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.276, 0.478, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b5885e-5454-465f-92bf-d8f7315c4a46_e1d11f3d-bddc-40e4-9b38-e2ab641223d8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[textbox] Enter a town, city or zipcode -> TYPE: Sheboygan\n[span] Sheboygan, WI -> CLICK\n[button] Search -> CLICK\n[input] -> CLICK\n[gridcell] March 26, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.285, 0.831, 0.309] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4097c577-e637-4543-87a3-09b2f4734163_ba8b539c-78b7-4c10-ad5d-a34107d8aa38.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pedicure salon in New York and add two to favorites.\nPrevious actions:\n[input] -> TYPE: pedicure salon\n[input] -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.408, 0.341, 0.585, 0.373] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fd460cc-679c-4d04-8816-c6460bdf895a_5c9d8232-4c6b-4537-923a-dd0727032022.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Confirm my vip tour at the six flags Discovery Kingdom\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Discovery Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.35, 0.844, 0.381] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_3c33b382-bf0c-4407-8f1d-128cd260334b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK\n[button] Update Search -> CLICK\n[button] Filter -> CLICK\n[checkbox] Self Park (1) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.678, 0.452, 0.715] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_fb405733-e00b-4fc3-b323-85e0f0a76157.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Los Angeles\n[span] , CA, USA -> CLICK\n[button] 1 NIGHT Sat, Apr 08 - Sun, Apr 09 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.674, 0.192, 0.709, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1db33c6-c414-438b-bbfc-cdaa6cfc6b68_2dcc9e7f-6127-4495-9e4a-c3a5d59725f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check reviews for best electric SUV and find the 1 star rated review and mark it helpful.\nPrevious actions:\n[link] Best Cars -> CLICK\n[img] Best SUVs image -> CLICK\n[div] SUVs -> CLICK\n[link] See Details -> CLICK\n[span] 11% -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.649, 0.515, 0.662, 0.534] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_971dc47e-71e7-475e-9eef-87d837b34356.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[tab] Toddler (6M-5Y) -> CLICK\n[link] All Toddler (6M-5Y) -> CLICK\n[heading] Category -> CLICK\n[input] -> CLICK\n[option] Socks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.891, 0.188, 0.959, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_18f516f8-beaa-4338-a0dd-659293279207.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Brooklyn\n[span] Brooklyn, New York, United States -> CLICK\n[span] Different drop-off -> CLICK\n[tab] Same drop-off -> CLICK\n[button] End date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.409, 0.39, 0.44] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9c160e7-b179-4d42-8570-e6f3f85aa412_fad7bc53-f4c5-435a-abee-ee54d8595ecd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest-rated adults-only romantic beach vacation deals and book the cheapest one.\nPrevious actions:\n[link] Vacations -> CLICK\n[link] Beach Vacation Deals 95 DEALS -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.18, 0.442, 0.214] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_bf884456-1c0e-4856-8141-57bf30f5da56.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] Miami (MIA - Miami Intl.) Florida, United States -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] Departing April 11, 2023 -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.959, 0.192, 0.984, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a11022ab-f733-4295-a2f2-0da19cccc1b4_c1fda10f-e5ef-47f2-852f-a6385a2ed99f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sign up for emails using the name Dick Smith and the email [email protected], select Six Flags Magic Mountain as the Park of Preference,\nPrevious actions:\n[textbox] First Name -> TYPE: Dick\n[textbox] Last Name -> TYPE: Smith\n[textbox] Email -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.84, 0.678, 0.877] in the image\nAnd my action is Action: SELECT\nValue: Six Flags Magic Mountain / Los Angeles, CA" } ]

{ "bytes": "", "path": "./images/0245df99-2909-465a-861e-7fbca948e82f_83e37cb8-d3a2-4121-a740-a1d75d3dd80e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car guide info for economy car and reserve.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.02, 0.74, 0.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/60383804-a8e5-4e50-8715-da391d76617d_241b1896-c37f-452b-b824-73ff06f7df2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse candle holder red decor products.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.153, 0.055, 0.248, 0.074] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d538537c-ff96-4918-8807-af09b26199d1_59b4a48b-83b0-4522-a66e-fec2fa0c6069.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights between SFO and EWR using the Boeing 787-9 aircraft\nPrevious actions:\n[textbox] Origin -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.534, 0.469, 0.565] in the image\nAnd my action is Action: TYPE\nValue: SFO" } ]

{ "bytes": "", "path": "./images/63e3020c-bf52-4950-9e26-50f98a59b5e3_33a7ea3f-5ecb-4453-9465-1a9d3739e42a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fast responding highest-rated electrician, who is currently open for replacement of some light fixtures in Westminster, and request a quote.\nPrevious actions:\n[button] Fast-responding -> CLICK\n[button] Open Now -> CLICK\n[button] Request a Quote -> CLICK\n[radio] Installation or replacement -> CLICK\n[radio] Light fixture -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.595, 0.46, 0.722, 0.483] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_dfdb363b-157c-44ca-9aad-be92a8572f15.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[span] Atlanta, GA (ATL) -> CLICK\n[span] Jun 2023 -> CLICK\n[option] Oct 2023 -> CLICK\n[button] Search flights + cruise -> CLICK\n[label] October 08, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.29, 0.31, 0.304] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4008118a-68a1-4a9f-968c-8b92a979dff7_d9e3b9bf-8a2c-41c6-9c58-d3f0ae781f45.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 breakfast options on the Carnival Breeze ship.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.08, 0.203, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_a2078d5e-eaad-4060-a2e4-c26ecefb4a9a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.314, 0.512, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_58fb22af-7875-4218-861b-bfca9cc56c7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK\n[button] Departing April 11, 2023 -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.952, 0.183, 0.994, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_c0c80763-722c-4265-b734-24d8908b159c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[button] Get started -> CLICK\n[textbox] First name -> TYPE: john\n[textbox] Last name -> TYPE: doew\n[textbox] Email address -> TYPE: [email protected]\n[textbox] Phone number -> TYPE: 4533234565" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.514, 0.495, 0.531] in the image\nAnd my action is Action: TYPE\nValue: 234567895" } ]

{ "bytes": "", "path": "./images/3a231c03-d038-4b61-b5a2-685b77d9920e_1b9a4422-dbca-4194-9891-f0fefedd9e5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the bag charges for the passenger James Son for the flight with the confirmation number 10000002\nPrevious actions:\n[link] Baggage info -> CLICK\n[link] Baggage fee calculator -> CLICK\n[tab] My flights -> CLICK\n[textbox] Confirmation number (required) -> TYPE: 10000002\n[textbox] Last name (required) -> TYPE: Son" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.501, 0.392, 0.691, 0.434] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_cc2547c1-82f2-4e44-8419-61fc4536e234.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[link] Fitted -> CLICK\n[div] Size -> CLICK\n[span] Now Trending -> CLICK\n[li] Newest -> CLICK\n[button] Add to Wish List -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.694, 0.226, 0.716, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_40c833ba-e627-4bdc-9593-c749ee3807a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[span] Frozen Pizza -> CLICK\n[button] Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Flavor -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.111, 0.802, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58badcfc-343a-47c1-8aec-f609925eb4ed_0d993232-3746-4084-95fc-0dd93e7de7f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Tracks -> CLICK\n[link] Added any time -> CLICK\n[link] Past year -> CLICK\n[link] Any length -> CLICK\n[link] 2-10 min -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.514, 0.212, 0.537] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5871c3f-27c3-48d8-bdf9-8b49382a2719_a911199f-5c06-4042-8dff-d1d095ba7f21.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 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\n[link] select to navigate to New -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.19, 0.352, 0.333, 0.566] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c997e24-d185-4730-84d6-f8cb512f4c03_bc99632b-a2a3-4848-88cd-6917ff4e3596.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] mm/dd/yyyy -> CLICK\n[link] 12 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.139, 0.891, 0.16] in the image\nAnd my action is Action: SELECT\nValue: 3 00 AM" } ]

{ "bytes": "", "path": "./images/a11022ab-f733-4295-a2f2-0da19cccc1b4_4af813e6-fc10-468a-bc8e-cba17f545e06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sign up for emails using the name Dick Smith and the email [email protected], select Six Flags Magic Mountain as the Park of Preference,\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.729, 0.678, 0.772] in the image\nAnd my action is Action: TYPE\nValue: Dick" } ]

{ "bytes": "", "path": "./images/03103341-f9d3-40a8-8435-f7946dd707b3_a3e5cb5c-e864-45c7-98d1-9518af067926.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 budget price for the vehicle with most seats availible at Roanoke Regional Airport from April 5-6.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Roanoke\n[span] Roanoke Regional Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.24, 0.567, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_a86258c1-e7d5-4cb9-9e2f-2ed9966b5cf8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cruises to Hawaii departing from Los Angeles in January 2024 with a duration of 12 days.\nPrevious actions:\n[button] Los Angeles, CA -> CLICK\n[button] DATES -> CLICK\n[button] January 2024 -> CLICK\n[button] DURATION -> CLICK\n[button] 10+ Days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.302, 0.871, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aab91310-0100-4a40-98e9-720c53199bff_42d37c11-0990-4059-8327-9f2c132e1b28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mens hiking shoes under $100 in size 10 that has biggest discount.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: mens hiking shoes\n[input] -> CLICK\n[div] Price -> CLICK\n[link] $10 to $25 (3) -> CLICK\n[link] $25 to $50 (18) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.397, 0.121, 0.406] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_24f091f2-2302-45cf-8a3b-6926028a8c8a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK\n[textbox] Pick-up location -> TYPE: Brooklyn\n[span] Brooklyn, New York, United States -> CLICK\n[span] Different drop-off -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.168, 0.414, 0.207] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_29c3163c-4c53-49b0-a0a1-49bc3b1e21ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Fashion -> HOVER\n[link] Men's Shoes -> CLICK\n[link] Nike -> CLICK\n[button] US Shoe Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.494, 0.509, 0.51] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b16b42c-dea7-4079-a2a8-79eb23447193_f16dc8f3-48c9-43db-9468-9db70f01934a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[link] Within sight of downtown Miami, yet worlds away, B... -> CLICK\n[link] Fly to Miami (MIA) -> CLICK\n[button] New York/Newark (EWR) Miami (MIA) Roundtrip|Econom... -> CLICK\n[textbox] Departure -> CLICK\n[gridcell] Saturday, May 13, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.348, 0.748, 0.38, 0.769] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_224ce086-9076-4f11-8961-b3ccb3285081.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: [email protected]\nPrevious actions:\n[link] Careers -> CLICK\n[link] Sign up for job posting alerts -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.873, 0.399, 0.941, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8428085-905f-4190-9404-3e28fb691252_314dfd22-8e83-4475-b8eb-430c8eb22cef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest on-demand releases.\nPrevious actions:\n[link] Visit the On Demand page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.285, 0.106, 0.488, 0.125] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_2755eead-c61e-4ce0-b14c-e041ca4d1562.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Departure station, London selected. -> TYPE: edinburg\n[span] Edinburgh (Waverley) -> CLICK\n[combobox] Arrival station, Sheffield selected. -> TYPE: manchester\n[span] Manchester -> CLICK\n[radio] Return -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.146, 0.194, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ef23fbf3-f05e-41e2-b847-a27028f42470_bb1ae489-b33e-475a-83fd-3ecabe7d1fab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me “pizza” restaurants near Atlanta\nPrevious actions:\n[svg] -> CLICK\n[button] Atlanta -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: pizza" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.032, 0.659, 0.072] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/360eeaa8-0077-42f4-8200-1e3cf6414cda_b740bff0-dc6c-49fc-8895-96b5959e3fc1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a message to Joe Bloggs who has the username 'boredcelt'.\nPrevious actions:\n[button] Community -> CLICK\n[link] Find Users -> CLICK\n[link] User Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.392, 0.131, 0.614, 0.143] in the image\nAnd my action is Action: TYPE\nValue: Joe Bloggs" } ]

{ "bytes": "", "path": "./images/747429fa-7dac-4ab0-b604-13cb9bf787fe_7d650769-7360-42e5-9686-c24cfbaf2a2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest unused wireless Logitech Keyboard under $70.\nPrevious actions:\n[button] APPLY -> CLICK\n[span] Logitech -> CLICK\n[button] APPLY -> CLICK\n[textbox] price to -> TYPE: 70\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.132, 0.4, 0.145] in the image\nAnd my action is Action: SELECT\nValue: Lowest Price" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_03937750-0402-4b65-b1c4-f83e6b72cca9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Select passenger age -> SELECT: 16\n[button] Done -> CLICK\n[listbox] hour -> SELECT: 12\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.743, 0.179, 0.926, 0.225] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4132002e-5ba6-4e36-a1b7-6bbe61503be5_a0ec89c8-5b88-4f8e-9547-e6f22bed7148.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 living History event to attend in in April .\nPrevious actions:\n[button] Open Menu -> CLICK\n[button] All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.391, 0.595, 0.404, 0.602] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81fb481b-a234-4e25-b494-9ed26a03e977_be4e1af7-e734-4d31-bba3-fd751a4fd8a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the second most popular horror series to my watchlist.\nPrevious actions:\n[path] -> CLICK\n[span] Most Popular TV Shows -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.645, 0.591, 0.673, 0.6] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_d02d1e0d-1558-49ea-a007-fd43a7560a30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[link] NEW PLAYLIST -> CLICK\n[button] START FROM SCRATCH -> CLICK\n[h1] My New Playlist -> CLICK\n[h1] My New Playlist -> TYPE: Dirty\n[button] ADD TRACK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.183, 0.699, 0.199] in the image\nAnd my action is Action: TYPE\nValue: Doja Cat" } ]

{ "bytes": "", "path": "./images/30d5f7dc-3650-4177-93bc-b59f1f5621f0_6aa2eb7f-be4a-467b-b5c5-96e9dd543d22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List pg-13 comedy movies currently in theatres with the highest audience scores\nPrevious actions:\n[link] MOVIES -> CLICK\n[svg] -> CLICK\n[select-label] Audience score (highest) -> CLICK\n[span] Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.56, 0.128, 0.58, 0.14] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ec472065-2913-40df-bbbf-ee95bc76485a_df54b5a8-f70c-4695-9c8c-5780019eedb1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list named New that includes thr\nee albums, one each from the genres pop, rock and electronic.\nPrevious actions:\n[textbox] Title -> TYPE: New\n[button] Save -> CLICK\n[button] Explore -> CLICK\n[link] Electronic -> CLICK\n[img] Madonna -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.237, 0.203, 0.297, 0.211] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f3850ec8-bf7c-42c3-9469-457836914f77_56682bee-956b-4d10-ab12-b895346b9589.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for events in Boston.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.057, 0.464, 0.104] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31a74ae0-4b8a-407b-8f3d-a094a6966254_2efe3302-5f5f-4b26-ba7b-7348f700afe8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show books of Dr Seuss with price range of $20 to $40 and add 2 to basket.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.098, 0.129, 0.131] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dd13bc51-f582-4004-8641-eb4e62cabfc7_a56e7cd6-7657-431b-8ae4-cb15032e2f97.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get prequalified with a good credit score for a $30000 car with a $6000 down payment for 48 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Prequalify for Financing -> CLICK\n[input] -> TYPE: 30000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.6, 0.473, 0.62] in the image\nAnd my action is Action: TYPE\nValue: 6000" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_68d2bf36-92a5-4fc5-a7c0-5c1f2fe3cffb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[button] Filter -> CLICK\n[checkbox] EV Charging (1) -> CLICK\n[button] Show 1 Results -> CLICK\n[textbox] Start Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.301, 0.191, 0.338] in the image\nAnd my action is Action: SELECT\nValue: 9 00 AM" } ]

{ "bytes": "", "path": "./images/ccf98191-100e-441a-93e8-8ff4076aeaa0_b2a2f8a2-4de6-48e2-bbf7-6eef4fff3631.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my cart a women's T-shirt priced under 10 dollars\nPrevious actions:\n[link] WOMEN -> HOVER\n[tab] Tops -> CLICK\n[link] T-Shirts -> CLICK\n[heading] Price -> CLICK\n[label] $0-$10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.138, 0.463, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7cbd1771-ca62-47ed-97db-5577644d285c_e7501c60-a8f3-453a-8f8b-bbb68c545ace.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to my favorites a cruise for 4 people going to Caribbean.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Caribbean -> CLICK\n[button] SEARCH CRUISES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.121, 0.212, 0.146] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_ed26e713-359e-4d11-b4ac-600a1d0d1610.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Samsung-made and larger than 11-inch screen Android tablet, in the price range of 200 to 300 dollars and add it to the cart.\nPrevious actions:\n[link]  Electronics  -> CLICK\n[link] Tablets -> CLICK\n[img] Samsung -> CLICK\n[span] 11\" & Larger -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.441, 0.192, 0.456] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d18cb36-5628-49e8-a336-c25c153c5527_38057c1f-4752-4761-a83d-b914e6702b85.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 John Atas's trip with the confirmation number 1000001\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[li] My trips -> CLICK\n[link] My trips -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.432, 0.426, 0.472] in the image\nAnd my action is Action: TYPE\nValue: Atas" } ]

{ "bytes": "", "path": "./images/ba5e0124-b1c0-4116-968c-6b31a4c9c0a7_2151f674-7324-4d95-a39d-4fdf73e0b0ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest bus for 2 persons from New York to Washington, DC.\nPrevious actions:\n[label] One way -> CLICK\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Washington\n[span] Washington, DC -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.311, 0.312, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_e474adb2-ec08-4464-b477-30f533b43209.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[div] Depart Date -> CLICK\n[button] Next month -> CLICK\n[gridcell] Thursday, June 1, 2023 -> CLICK\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.824, 0.082, 0.957, 0.102] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b6385ea-0cdc-4ed8-be93-dc90113d2255_017f0e17-837f-451d-aed3-0c99dd21581f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Apple Stores close to zip code 90028\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.153, 0.0, 0.191, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d92911a-b208-4d68-ad00-46d2d67f9efa_74ff6222-caf3-40c2-abc4-2ec3029d571e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store in spring, Texas.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.311, 0.676, 0.368, 0.694] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c02c193-2aef-4817-92b4-56722edc6b57_50b39168-3d21-4d0d-8664-8a507729784e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: skirt" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.026, 0.553, 0.046] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9dfba9af-d79e-4a75-83b4-0f85ab04c2e6_eff68b62-ec7c-4049-8586-0a770d5b987d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 price quote for new Kia Carnival for 11101.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Free Dealer Price Quote -> CLICK\n[select] Make -> SELECT: Kia\n[select] Model -> SELECT: Carnival" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.491, 0.192, 0.711, 0.233] in the image\nAnd my action is Action: TYPE\nValue: 11101" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_a94ff5fd-45f1-46e0-bfba-90fd5f6dc7d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight status for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.048, 0.664, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/229199b4-9988-485f-8175-b5efd8faf08b_cba1e975-0bdf-4726-b146-be1142353fe5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Ask a question regarding Health Insurance Top Up plans beneficial or not?\nPrevious actions:\n[link] QUESTIONS & ANSWERS -> CLICK\n[link] Insurance -> CLICK\n[textbox] Ask a Question -> TYPE: Health Insurance Top Up plans beneficial or not?" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.489, 0.18, 0.588, 0.198] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1f4e4f7-3fb0-4aeb-8123-4882a1f39cb2_5e676867-a433-4845-8aa2-777f5e66b86e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new arrival of kids graphic t-shirt for 13 years old boy\nPrevious actions:\n[tab] Tops -> CLICK\n[link] UT: Graphic Tees -> CLICK\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK\n[button] Sort by -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.761, 0.264, 0.943, 0.297] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/932c0ec6-d500-495a-a7a7-0f632acbf6a5_e9b80c7a-04d6-40ee-87d9-c678b93317d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 camping stoves that have an auto ignition feature.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.051, 0.128, 0.071] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c997e24-d185-4730-84d6-f8cb512f4c03_85649f4f-ff05-45bf-870c-6154412c5750.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] mm/dd/yyyy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.584, 0.273, 0.611, 0.287] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/afa1f70c-c0ff-4e4d-a5c2-0c0d292ee066_d0df5da7-08b6-4ba6-a359-e6f4de52d074.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[li] Summer -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Airfare Included -> CLICK\n[button] All-inclusive -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.304, 0.772, 0.34] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1df0723c-f732-4ecb-b202-8e1854b7c079_45d4c97a-1f19-4b89-9069-3f4820b8484d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a list of rental vehicles for Brooklyn, OH, US for 18 year old renter.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: Brooklyn\n[option] Brooklyn, OH, US Select -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.218, 0.84, 0.238] in the image\nAnd my action is Action: SELECT\nValue: 18" } ]

{ "bytes": "", "path": "./images/2a440d5f-1cc8-43de-86f5-ea181b0d12f8_7e8dffb8-17a7-40c5-9344-b115886fd488.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Who were the NBA season leaders from the 2020-21 regular season?\nPrevious actions:\n[link] NBA -> CLICK\n[link] Stats  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.392, 0.104, 0.403, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d6dd19a2-c57e-4e4d-b7e1-8919a86f1157_7412202e-0c5f-47b7-a72f-0570cd883473.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 likely to sell out activity in Los Angeles on April 2\nPrevious actions:\n[textbox] Where to? -> TYPE: Los Angeles\n[b] Los Angeles -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.519, 0.502, 0.556, 0.531] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fa2828c5-44b3-446e-ae42-a26438ed8343_56328637-4511-4d5f-87dd-f73738934bf5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the upcoming departures for the oak grove station going southbound direction\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.73, 0.008, 0.83, 0.022] in the image\nAnd my action is Action: TYPE\nValue: oak grove station" } ]

{ "bytes": "", "path": "./images/5b433cc4-26bf-4e62-b406-f00dc09c274d_eb2f0b10-9e1a-410a-b238-358836e1ed04.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a CVS brand covid home test kit to the cart.\nPrevious actions:\n[img] -> CLICK\n[span] Shop all at-home COVID-19 tests -> CLICK\n[div] CVS Health At Home COVID-19 Test Kit, 2 CT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.828, 0.219, 0.969, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_03783199-4419-495a-897f-12d1d1e5b7f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[combobox] Departure station, none selected. Select a station... -> TYPE: BRISTOL\n[span] Bristol Airport (By Bus) -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: LONDON\n[span] London Paddington -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.299, 0.194, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/102c50a4-23f8-44ae-8300-43822b271dbf_236326dd-e3a4-4b2a-98b0-a495fe869504.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 places from OMG! below $500 to Wishlist and name it \"Togo\".\nPrevious actions:\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.886, 0.086, 0.957, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81b6bba7-3d05-40a4-a475-48eaeacbda0d_88b3d2aa-9a00-423e-9dcf-8527c310e228.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 route map and flight cost from Los Angeles to Miami on 12 April.\nPrevious actions:\n[div] -> CLICK\n[link] Route Map -> CLICK\n[textbox] From -> CLICK\n[textbox] From -> TYPE: Los Angeles\n[div] Los Angeles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.106, 0.28, 0.158] in the image\nAnd my action is Action: TYPE\nValue: Miami" } ]

{ "bytes": "", "path": "./images/78e346d2-3c80-4243-b921-ed35c4c4d923_1f3155ce-428a-4cd1-bb4a-b7fbf7469ddd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track an order using the order number of 456481897 and phone number of 8984486417.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.838, 0.008, 0.917, 0.021] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fca09c13-5e6c-49d5-b3ee-b620a70b19f5_39e3abcc-6e56-4032-b225-9e56cbd89bb7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[option] Top destination Tokyo, Japan (City) -> CLICK\n[div] 10 -> CLICK\n[span] 12 -> CLICK\n[img] Add -> CLICK\n[span] SEARCH -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.236, 0.686, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ce76343-dafe-4cf6-9bfd-918834d0c641_71afffe2-cba0-43d4-abc9-095a2bcd083a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated fast responding phone repair shop for data recovery in Houston.\nPrevious actions:\n[link] More -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.075, 0.449, 0.098] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42f64db7-c573-4ba8-9cab-a390e2f5e535_897fecac-fd54-4b7f-bfeb-5ed4dcc72950.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] From Departure Airport or City Your Origin -> TYPE: Mumbai\n[link] BOM Mumbai, India -> CLICK\n[link] To Destination Airport or City Your Destination -> CLICK\n[textbox] Destination City or Airport -> TYPE: New York City" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.257, 0.187, 0.51, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_ccf8e5a6-cc0b-46b9-93a9-a725eb195bc0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.046, 0.271, 0.062] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/58394242-6531-4791-a7fc-6f279037706c_d77a38e2-0f86-4a9e-8466-acaa6d9b8aa6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Favorite a shared room in Belo Horizonte costing up to $100 to stay in a weekend in May\nPrevious actions:\n[textbox] Where -> TYPE: belo horizonte\n[div] Belo Horizonte, Minas Gerais, Brazil -> CLICK\n[tab] Flexible dates -> CLICK\n[label] Weekend -> CLICK\n[div] May -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.129, 0.819, 0.17] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fe6b5531-ce29-4ba1-8e98-43b5fecf57fa_9284698b-67c4-43a4-8150-0bf06a0fd54e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest flight from London to New York on 9th May.\nPrevious actions:\n[tab] Flights -> CLICK\n[combobox] Flying from -> TYPE: London" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.2, 0.338, 0.476, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1337eca1-4ca6-4102-964e-e7f6ecebcd0b_c6088520-5a6b-4e2e-bbdb-d9a7e1f5a605.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\n[button] Singapore Singapore -> CLICK\n[button] From April 5, 2023 -> CLICK\n[button] Apr 2, 2023 -> CLICK\n[button] Apr 2, 2023 selected, current check in date. -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.265, 0.568, 0.304] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/da386775-280b-4a84-9801-4ae3098044b0_8b42d9a9-7e40-4030-bda3-b84edc4d852b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in California city for Limos which also offers military discounts and free wi-fi.\nPrevious actions:\n[link] Auto Services -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.485, 0.217, 0.587, 0.254] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bb8d48f-dac7-472d-b2b2-651ab184baf2_ad546f94-f9c4-4693-9e29-6dab15f82b4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a hybrid job at Resy in software development, if the job is open apply immediately.\nPrevious actions:\n[link] Careers -> CLICK\n[link] View All Open Positions -> CLICK\n[span] Filters -> CLICK\n[a] Software Development -> CLICK\n[a] Hybrid -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.634, 0.091, 0.769, 0.112] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff173880-e7f5-4b4e-b941-79e9c3504add_98aca18e-749f-4dcb-a26a-02f3c7b20917.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wall mirrors for under $20.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.053, 0.153, 0.071] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a8de57df-b0be-400d-9211-931321c6500c_2dc6fa55-e5aa-4511-92b2-71dde630cdcd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the best rated ukulele tab to my favorites\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: ukulele" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.07, 0.897, 0.095] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_6ae8e6ca-ed17-4af9-937c-cd2666364100.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[span] Airport taxis -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.166, 0.284, 0.192] in the image\nAnd my action is Action: TYPE\nValue: O'hare Airport" } ]

{ "bytes": "", "path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_2a57a0b2-0e58-4fd9-b6b2-eaf59e4e6d5c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[link] 29 -> CLICK\n[listbox] Leaving at or Arrive by selector -> SELECT: Leaving at\n[listbox] hour -> SELECT: 10\n[listbox] minutes -> SELECT: 45\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.101, 0.391, 0.118] in the image\nAnd my action is Action: SELECT\nValue: 2" } ]

{ "bytes": "", "path": "./images/8c5ccffa-b88e-4928-9394-6d46cfd36e59_de075009-e20b-4800-8460-2bb57f6db9c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 today's Limited Time Offers deals?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.523, 0.082, 0.533] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/28f6ac29-940a-4ec6-a8bd-16ae2ce69a1c_e50a5cc2-36cd-44a5-8540-32d37ae310bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 receipt with the eTicket 12345678 for the trip reserved by Jason Two\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Find a receipt -> CLICK\n[radio] Confirmation or eTicket number -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.244, 0.271, 0.269] in the image\nAnd my action is Action: TYPE\nValue: 12345678" } ]

{ "bytes": "", "path": "./images/627a99f1-b2e4-4ce4-93f5-89e691f8c879_32a87b2c-3e26-45ba-9fe9-32c4dc3949b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Kevin Durant's bio\nPrevious actions:\n[button] Open Search -> CLICK\n[textbox] Search -> TYPE: Kevin Durant\n[link] Kevin Durant Phoenix Suns -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.228, 0.164, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_c09c8617-efb7-47b0-b638-3aa6dab6eb6e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\n[link] Customer Service -> CLICK\n[div] Need an extra part? -> CLICK\n[link] Read more -> CLICK\n[span] Order spare parts -> CLICK\n[input] -> TYPE: 105307" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.302, 0.617, 0.349] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7e501a4-5dee-406e-b6ba-00eed783df0c_3bce3264-f5ca-4d47-9ab5-95af75dd15ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a KOA campground in California that has RV sites.\nPrevious actions:\n[link] Filters -> CLICK\n[checkbox] RV Site -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.106, 0.434, 0.122] in the image\nAnd my action is Action: TYPE\nValue: California" } ]

{ "bytes": "", "path": "./images/d0d6b0ed-82e4-4ba7-9a9b-7b874dacf19c_6f9d42c6-bb53-4235-aae9-30a81afc7180.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.13, 0.43, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2b562465-e325-4743-8e68-6e7852594f93_02557082-babe-4a38-a66a-4b2f4a170b35.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 terms and conditions of Amtrak RideReserve for Multi-Ride Passes\nPrevious actions:\n[button] DEALS -> CLICK\n[link] MULTI-RIDES & RAIL PASSES USA Rail passes, monthly... -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.064, 0.494, 0.299, 0.513] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f1f085b-5765-40f8-86c7-8df6e8b68053_43ab932b-04e2-4282-86c2-2e7af016655b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information about baggage allowance for business class.\nPrevious actions:\n[button] Experience -> CLICK\n[link] Baggage allowance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.488, 0.641, 0.569] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_9311ff44-ee59-4214-a920-2b5fb38d43f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] 1 room, 2 travelers -> CLICK\n[img] Decrease adults in room 1 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.152, 0.568, 0.173] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_766c0830-7e36-42fb-8f3e-9473f6322736.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: SMith\n[textbox] Address1 -> TYPE: 133 st avenue\n[textbox] City Name -> TYPE: New York\n[select] Alabama -> SELECT: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.49, 0.685, 0.518] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/f8027aa8-c193-47c8-a97b-432836093939_4da18a4b-7a48-4342-aced-13ac7ea17785.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Las Vegas, NV that offer free airport shuttle service.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Las Vegas\n[span] Las Vegas, Nevada, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.948, 0.128, 0.964, 0.142] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2c19d467-4e44-4c0d-b050-a13823ca545d_da185646-5517-4406-ad3b-28bae9edf30a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hard side Carry-on Luggage used for business in black color.\nPrevious actions:\n[link] Categories -> CLICK\n[span] Luggage -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.238, 0.316, 0.257] in the image\nAnd my action is Action: CLICK" } ]