Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 65

{ "bytes": "", "path": "./images/913b902b-37b7-4230-a0f2-a19931b06951_0d6383fc-e3a0-4402-ace2-f80e4c686a24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the fastest single stop flight fron JFK airport in New York to Male in Maldives on March 13\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.211, 0.128, 0.267, 0.141] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_1a8b410e-a1b9-42cb-9ac0-fa9515cf6140.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.068, 0.492, 0.097] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2adf8f1-547d-4671-96c1-4a21a56e135d_2bf233d9-c3f4-4d32-8f7c-fbfa4c810e2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 upcoming schedule from Otis St@Summer St to City Point of the transit near South Station for today.\nPrevious actions:\n[tab] Schedules -> CLICK\n[span] Transit Near Me -> CLICK\n[input] -> TYPE: South Station" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.138, 0.257, 0.562, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f4a020d-ac81-4d20-ae3a-02808faaba4e_b3159b0c-489d-49a5-86d8-e614669b3b88.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a birthday party package for a group of 10 at Arizona park with my address details. Group name is Neo, group leader's name is Thomas Anderson, birthday is May 5th, 1995. The phone number is2526545258. The email address is thomas.neo@gmail.com and address is po box 2846, Texas city in the state of Texas.\nPrevious actions:\n[button] Next -> CLICK\n[input] -> TYPE: Neo\n[input] -> TYPE: Thomas\n[input] -> TYPE: 05/05/1995\n[input] -> TYPE: Texas city" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.185, 0.487, 0.211] in the image\nAnd my action is Action: TYPE\nValue: 252-654-5258" } ]

{ "bytes": "", "path": "./images/e2142cde-5bec-46ee-8d17-9b6ee52a66e8_fe3572a1-398a-479d-ba14-aa4ce84f34cf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 inventory of the Tesla Model S within 200 miles from 10001\nPrevious actions:\n[link] Model S -> CLICK\n[link] View Inventory -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.048, 0.22, 0.273, 0.254] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_bee75aa3-6f7d-4626-be6f-1b217ac16733.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Update search -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Pizza -> CLICK\n[button] Submit -> CLICK\n[button] Open additional search filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.776, 0.713, 0.798] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_1579fed0-00b7-47db-bfb3-7098175a0ebd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Low to High\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.18, 0.331, 0.19] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cfe20a-f008-48d3-b683-002ce7790616_ca5a6e89-1bbb-4600-89e3-030ef9d18217.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 luxury car rental in New York for two with pickup from JFK airport at 9am, April 3 and drop off at JFK on 6pm, April 6\nPrevious actions:\n[tab] Cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.23, 0.495, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_6d149fca-3072-4909-90ba-487c98b599cd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[button] Meetings & Events -> CLICK\n[link] Group Travel -> CLICK\n[link] Group Travel for Students -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.206, 0.336, 0.244] in the image\nAnd my action is Action: TYPE\nValue: washington" } ]

{ "bytes": "", "path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_ed4fbad4-bbb8-48a2-98b6-3f0b9cf383ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\n[menuitem] Golf -> CLICK\n[div] Product Category -> CLICK\n[link] Clothing -> CLICK\n[div] Product Type -> CLICK\n[link] Polos -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.345, 0.233, 0.38] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aab91310-0100-4a40-98e9-720c53199bff_43686440-2fc6-402a-baf6-13907700d8c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.168, 0.042, 0.187, 0.057] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a11022ab-f733-4295-a2f2-0da19cccc1b4_a504d03f-205a-4905-8823-9493469d0034.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 smith@gmail.com, 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: smith@gmail.com\n[combobox] Park of Preference -> SELECT: Six Flags Magic Mountain / Los Angeles, CA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.794, 0.678, 0.826] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_0e970a9f-f965-4bcd-8555-8f396193105e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: PARIS\n[span] Paris -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: MILAN" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.139, 0.326, 0.161] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6803cd71-78a9-4bff-a1a3-1153dcc28c11_d118ec61-bac9-44db-bf4d-acc261383072.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 organic dog food and add it to the cart.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: organic dog food\n[link] organic dog food -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.846, 0.945, 0.877] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c64dcaa1-555d-43f3-adb4-3452c4e5d09b_fd745a55-eadc-4aff-a3b3-fd9c98aafbb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 barbershops that have private lot parking.\nPrevious actions:\n[textbox] Find -> TYPE: barbershop\n[span] Barbershop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.123, 0.084, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_ba1b3830-c493-48da-9c25-87c05df40afb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Departing from -> TYPE: ATLANTA\n[span] Atlanta, GA (ATL) -> CLICK\n[span] Jun 2023 -> CLICK\n[option] Oct 2023 -> CLICK\n[button] Search flights + cruise -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.555, 0.31, 0.566] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/19847108-680f-4021-83a9-2548fab75fac_609ac7e9-480b-4b27-bfb7-6cecf26afdb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Mark a review in the best rated activity to do in Paris in May 12, 2023 as he\nlpful\nPrevious actions:\n[button] Next -> CLICK\n[gridcell] Fri May 12 2023 -> CLICK\n[circle] -> CLICK\n[svg] -> CLICK\n[span] Traveler Rating -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.503, 0.278, 0.565, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/39358d9c-6db2-4662-a91e-47a416eeacf7_765485e9-a5cf-4af2-b2b7-e1810fd891a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See what deals there are for Dish Outdoor.\nPrevious actions:\n[link] DEALS  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.174, 0.266, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_b9e37de8-55fb-4bdf-9bd3-a9fd20adb92d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[link] Kitchen Sinks -> CLICK\n[link] Drop In Two Bowl -> CLICK\n[checkbox] Ship to Home Eligible (97) -> CLICK\n[checkbox] Stainless Steel (75) -> CLICK\n[checkbox] Equal Bowl (69) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.716, 0.076, 0.734] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44bde32f-12bd-4c70-a1a5-37bdadfe872b_23f2c136-1524-48cd-a3cf-e66581e35dad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 target branded sprinkles for easter baking\nPrevious actions:\n[link] Categories -> CLICK\n[span] Grocery -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.209, 0.316, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_9a1f3e01-87cc-45c1-bb32-f90ce0bc5eed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of buckeye.foobar@gmail.com and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] Yes, I agree -> CLICK\n[span] Lowest price -> CLICK\n[button] Choose room -> CLICK\n[button] Book now -> CLICK\n[textbox] First name -> TYPE: Joe" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.637, 0.145, 0.95, 0.178] in the image\nAnd my action is Action: TYPE\nValue: Bloggs" } ]

{ "bytes": "", "path": "./images/d538537c-ff96-4918-8807-af09b26199d1_6dbd8788-9384-4c38-be4c-9511cdae63f7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] Origin -> TYPE: SFO\n[div] San Francisco Int'l (San Francisco) - -> CLICK\n[textbox] Destination -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.309, 0.619, 0.328] in the image\nAnd my action is Action: TYPE\nValue: EWR" } ]

{ "bytes": "", "path": "./images/0fd460cc-679c-4d04-8816-c6460bdf895a_d469455a-3a83-4df8-a461-ebe480791b9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] Go! -> CLICK\n[link] Tickets, Passes, Tours  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.2, 0.493, 0.212] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ba5e0124-b1c0-4116-968c-6b31a4c9c0a7_83363272-ba05-42ae-b732-707f2ceeecf1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] To (type text or use the arrow keys) -> TYPE: Washington\n[span] Washington, DC -> CLICK\n[span] -> CLICK\n[button] Find tickets -> CLICK\n[combobox] Sort: -> SELECT: Price" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.397, 0.793, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4272e233-3440-4572-bd86-b3a2b22a4061_c42d4ac2-8268-4a2e-95c1-399ab2e7ae1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular tours and attractions in Kyoto, Japan from May 25 with free cancellation option, check availability for 2 adults and 1 infant, and book.\nPrevious actions:\n[checkbox] 25 May 2023 -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[label] Most popular -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.239, 0.92, 0.417] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_0ab53b01-e6f9-417c-87e4-bde4e5ba5393.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] SAIL TO -> CLICK\n[button] Hawaii -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Los Angeles, CA -> CLICK\n[button] DATES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.389, 0.194, 0.441, 0.22] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_d75139cd-0143-414a-83ba-e2fdd4372c5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[button] + 11 more -> CLICK\n[button] Furniture sets 138 -> CLICK\n[button] Outdoor dining sets 46 -> CLICK\n[button] Add to bag, TÄRNÖ, Table+2 chairs, outdoor -> CLICK\n[link] Shopping bag, 1 items -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.686, 0.266, 0.969, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6fc427d-c2fd-4f1b-8f7d-8bb8647e63e9_e0567d5e-e397-4a09-bfb2-83578e05ae26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 deals in New York.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.0, 0.417, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/30d5f7dc-3650-4177-93bc-b59f1f5621f0_a14c70a0-22cb-4218-9f3f-281c20bcfd0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[select-label] Audience score (highest) -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[span] Rating -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.399, 0.243, 0.645, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a8474730-82eb-4f12-b947-db64ac08660b_d229d3ba-1804-4ac9-ab0f-8fff81657d28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most recently posted job opening in customer service in Ireland with a remote working option.\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.3, 0.317, 0.479, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5092fad7-ff8a-481e-bb0b-fe83590193ce_206ec9bd-b2fe-4964-8dcb-c593a923ad7d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reviews of top critics for lowest rated Tom Hanks work\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.239, 0.169, 0.525, 0.189] in the image\nAnd my action is Action: TYPE\nValue: Tom Hanks" } ]

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_fc909f7d-4360-4b36-8cb3-086b4a086b5a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 email alerts for a flight from BHZ to EWN leaving on april 30 on the email lin.lon@gmail.com\nPrevious actions:\n[link] Create flight status notification -> CLICK\n[textbox] From , required. -> TYPE: bhz\n[a] BHZ - Belo Horizonte, Brazil -> CLICK\n[textbox] To , required. -> TYPE: ewn\n[a] EWN - Coastal Carolina Regional, NC -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.673, 0.217, 0.687, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_5728ce0c-5baf-4b2c-98c4-dac3a0343b10.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[link] Products -> CLICK\n[button] Kitchenware & tableware -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.355, 0.261, 0.605, 0.281] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5199e802-2fce-448d-8859-3cdf57b8dada_d2462cfe-1b26-4571-be84-5f838fdcbd5f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the list of ballet event for the next 30 days.\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: Ballet" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.781, 0.275, 0.871, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/904bd858-1c40-4d22-9a5b-e2974c3b5a7e_1245d53c-a9f4-4a43-b386-dfbdf4e4aed6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most expensive ticket for New York Knicks game on April 9\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> CLICK\n[textbox] Search for artists, teams or venues... -> TYPE: New york knicks\n[option] New York Knicks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.32, 0.941, 0.336] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/45ae95ac-e539-4314-a0ca-8947b1843890_b30b7141-b970-418b-ac3d-3069ae385e86.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly parking with valet service at the New York University.\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: New York University\n[li] New York University, New York, NY, USA -> CLICK\n[button] Filter -> CLICK\n[checkbox] Valet (15) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.488, 0.458, 0.544] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c7b0d1bc-2a0c-4060-92dd-cd4b8721b625_b444233b-12da-405d-b489-b08e50eeecc0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 KOA near Lansing, Michigan for June 7, 2023 to June 12, 2023.\nPrevious actions:\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: Lansing\n[list] KOA Logo Icon Auburn Hills / Holly KOA Holly, MI K... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.248, 0.547, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_e9b98033-42d1-478a-ba2b-e7e73105a6f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email sellmycar@mail.com.\nPrevious actions:\n[button] No -> CLICK\n[button] No -> CLICK\n[radio] Owned -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.802, 0.284, 0.828] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_76fd2922-8aaf-4d4b-9266-d53fa5daf0de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[button] Show more filters modal -> CLICK\n[button] Sort Best match -> CLICK\n[radio] Price: low to high -> CLICK\n[button] Sort -> CLICK\n[button] Shape -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.226, 0.966, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f14fb44-31d8-49f3-b5fb-95826175bcb8_aa0d6885-065b-4dfe-8471-916d90dc4f57.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new books from Jk Rowling available for kids within the age from 3 to 5 that are below $20\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.042, 0.746, 0.061] in the image\nAnd my action is Action: TYPE\nValue: Jk rowling" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_2e5b9bce-a220-413b-bf5b-eb0cc86e8fef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[textbox] To , required. -> TYPE: CDG\n[a] CDG - Paris Charles de Gaulle, France -> CLICK\n[textbox] Depart , required. -> TYPE: 04/21/2023\n[button] Add another flight -> CLICK\n[textbox] From , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.408, 0.29, 0.423] in the image\nAnd my action is Action: TYPE\nValue: CDG" } ]

{ "bytes": "", "path": "./images/09675529-c12d-42dc-a260-c1e046f87256_36eaf5a7-66ea-447c-87c7-8db65126fffa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Trade in a Nemo Front Porch 2P Tent via mail with my membership info Joe Bloggs, phone number 123456789\nPrevious actions:\n[combobox] search input -> TYPE: Nemo Front Porch 2P Tent\n[img] search icon -> CLICK\n[button] Trade in -> CLICK\n[link] Complete trade-in -> CLICK\n[button] Verify membership to continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.396, 0.192, 0.438] in the image\nAnd my action is Action: TYPE\nValue: Joe" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_5c53350f-286b-4be8-b37e-346ce0772af0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[div] London Heathrow Airport (LHR) -> CLICK\n[div] Wed, Apr 19 -> CLICK\n[checkbox] 26 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 2:00 PM\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.649, 0.155, 0.753, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b130a70-f03a-4f86-8f2a-44f1b44f3655_931b38e6-e860-43fa-9d36-5b864e1ff95b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check my trip for Smith and booking number X899987799.\nPrevious actions:\n[link] Manage trips / Check-in -> CLICK\n[textbox] Passenger last name , required. -> TYPE: Smith\n[textbox] Confirmation / Record locator , required. -> TYPE: X899987799" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.636, 0.299, 0.875, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/08a998f9-82f7-48c8-b6ba-72a58d39b457_2bc8e547-5166-4076-90bc-4c1d37ee725b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all Uniqlo's located in Chicago, IL.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.562, 0.2, 0.587] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e72f9c32-4633-4fcf-abd7-b7cc4a9aaba3_3bb8a4f7-e32f-4613-ba9a-f72be20a839b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 similar artists to the Weekend.\nPrevious actions:\n[link] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.906, 0.028] in the image\nAnd my action is Action: TYPE\nValue: the weeknd" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_dff4e313-9134-4041-a303-6eb0720df8be.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[div] View deal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.324, 0.862, 0.475, 0.918] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/767faaa6-220e-4e6c-ac1d-39b1501c69cf_40f1da67-fce1-4c14-9e24-9b3f57fe90cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a large car with air conditioning for a small group to pick up from Berlin on May 15, 11:30 am, and drop off at the exact location on May 16, 11 am, book with full protection and payment with a credit card.\nPrevious actions:\n[div] Car Hire -> CLICK\n[textbox] I need a car in -> TYPE: berlin" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.198, 0.366, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_46d1aec9-efcf-40c7-bfeb-13d5c0db36c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\n[button] Search -> CLICK\n[link] TICKETS -> CLICK\n[span] -> CLICK\n[label] 2 -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.221, 0.837, 0.245] in the image\nAnd my action is Action: TYPE\nValue: 200" } ]

{ "bytes": "", "path": "./images/a39f20a6-4d31-4f5f-b0ac-be8d548d7fa5_513ceb8e-6771-4ee4-850a-2aabe2c17e0c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hot deals within 500 miles from 10001\nPrevious actions:\n[link] DEALS  -> CLICK\n[link] HOT DEALS  -> CLICK\n[textbox] City, State or Zip -> TYPE: 10001\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.62, 0.094, 0.717, 0.113] in the image\nAnd my action is Action: SELECT\nValue: 500 Miles" } ]

{ "bytes": "", "path": "./images/cf8b2846-ac33-46aa-887c-174de6184057_360a4b82-5666-4d87-8b10-2ea3b37f78ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of my order with order number X123456789 and email buckeye.foobar@gmail.com\nPrevious actions:\n[link] 🚚Order Status -> CLICK\n[textbox] Order number * -> TYPE: X123456789\n[textbox] E-mail used on order * -> TYPE: buckeye.foobar@gmail.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.657, 0.418, 0.766, 0.459] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bc45669b-6bed-4240-9d9b-6b5e45a7e6f3_6ec19c62-07fe-42e9-99da-b36682d1ab92.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse xbox series x consoles that are used and between $200 and $400.\nPrevious actions:\n[combobox] Search for anything -> TYPE: xbox series x console\n[button] Search -> CLICK\n[input] -> CLICK\n[textbox] Minimum Value in $ -> TYPE: 200\n[textbox] Maximum Value in $ -> TYPE: 400" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.656, 0.176, 0.678] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/712d9d7f-d7ee-4554-affa-133449231ae4_716b1d6d-07d1-4ace-b6af-d1fa67a344c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 latest medical audiobook on complementary medicine for under 20 dollars and add the top book to the cart.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Medical -> CLICK\n[link] Complementary Medicine -> CLICK\n[select] All -> SELECT: Audio (376)\n[select] All -> SELECT: Under US$20" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.34, 0.196, 0.365] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_68d7bbb8-fe62-4300-9f0e-cc06b85a6552.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Distance & Shipping -> CLICK\n[button] Nationwide -> CLICK\n[menuitem] 100 miles -> CLICK\n[input] -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.196, 0.249, 0.218] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bafd6a44-5938-431f-8e2e-17d680d5c48b_76adfe82-7943-40af-9121-513e8de299ef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the page with information about Wi-Fi subscriptions.\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.17, 0.348, 0.181] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff82e848-f29e-477b-a286-c807cbd0d8fa_2c87ab6d-07c9-414a-856c-558889e7cd0d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[textbox] Location -> TYPE: india\n[link] Mumbai - BOM, India - IN 2 jobs -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[span] Customer Experience- Customer Services Agent (Cont... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.715, 0.246, 0.844, 0.296] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_a433db85-74f7-4865-aef9-fcf866f4a035.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: atlanta georgia\n[button] Submit -> CLICK\n[span] Select store -> CLICK\n[button] Show more filters modal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.95, 0.075, 0.969, 0.086] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_e9b55aac-5518-472f-b369-9fd23371f29f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: add a motherboard under $200 and a compatible processor at any price to the shopping cart.\nPrevious actions:\n[textbox] price to -> TYPE: 200\n[button] APPLY -> CLICK\n[link] GIGABYTE B450M DS3H WIFI AM4 AMD B450 SATA 6Gb/s M... -> CLICK\n[a] Processors - Desktops -> CLICK\n[div] AMD Ryzen 5 5600 - Ryzen 5 5000 Series Vermeer (Ze... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.693, 0.689, 0.717] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_71990241-9b93-43ab-8200-e6ea3063bca2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.859, 0.304, 0.902, 0.312] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/29f47ddb-3d25-4cfb-b1d6-d3987e998a13_b82ef559-4765-4aea-9ff7-59980a30a227.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the movie \"65\" that is digital at the AMC Grove City 14 showing at 7:30 pm on Tuesday, March 28, 2023 and buy four tickets for seats J10 through J7\nPrevious actions:\n[select] AMC Grove City 14 -> SELECT: AMC Grove City 14" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.455, 0.049, 0.633, 0.096] in the image\nAnd my action is Action: SELECT\nValue: 65" } ]

{ "bytes": "", "path": "./images/f863168b-1d7e-4f51-9681-79891abc4b45_7872a569-29b2-44ff-9e06-811c8577edff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 park in the National Park System that has a Junior Ranger Program for kids.\nPrevious actions:\n[link] FIND A PARK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.44, 0.163, 0.56, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_85e3c094-4c46-499f-90fa-05b2a66d9a39.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK\n[link] Tickets, Passes, VIP Tours  -> CLICK\n[link] Tickets & Passes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.456, 0.241, 0.465] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eb609e15-ff10-4b3d-82ce-348c439548ca_5caef1d1-97f5-4407-b1f3-5cbfc6655121.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 UA outlet clothing and find a outdoor sports jacket in size ymd.\nPrevious actions:\n[menuitem] Outlet -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.342, 0.097, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87d1206c-a16b-4816-9c1e-6e1a04f30bf6_904633a2-814a-4074-830e-bf4096bc461a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 games with the title Atlantis to my collection.\nPrevious actions:\n[combobox] Search -> TYPE: Atlantis\n[svg] -> CLICK\n[link] Atlantis -> CLICK\n[button]  Add To Collection -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.254, 0.638, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/844f8d77-e12e-4d68-8c4c-9146bd5b1530_24eb707a-5e41-4be7-8b4f-b7d2233b07e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open gift list for beauty products.\nPrevious actions:\n[path] -> CLICK\n[button] More ways to shop -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.052, 0.5, 0.075] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_0c1dc335-6547-4426-bfed-610421e2c194.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 premium car in Brooklyn for a day.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Rent A Car -> CLICK\n[button] Pick-up -> TYPE: Brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.202, 0.495, 0.235] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_93aaf6df-5228-4992-b532-9613a18117d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[tab] Flights -> CLICK\n[tab] One-way -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.121, 0.35, 0.142] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_5cb18345-d17d-4d6a-9db8-dbfe0d3cd3bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: street taco" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.078, 0.194, 0.83, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e6bdb364-4327-44f0-a6d8-94eb00b36ca7_ec2892e2-3184-4086-bef5-33ba043db515.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the page with help in choosing a solar energy product for homes.\nPrevious actions:\n[link] Solar Panels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.639, 0.579, 0.798, 0.689] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_067334cd-e49b-45ac-8a32-31cdec47b52b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Make -> CLICK\n[listitem] Honda (116) Honda (116) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Model -> CLICK\n[listitem] Civic (35) Civic (35) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.154, 0.249, 0.173] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2ef75333-ca40-454f-a65c-88b6b60e2497_f35539ff-43bf-48f6-af52-483fc39a7cc8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tour to the statue of liberty for 3 adult on march 27th\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.395, 0.098, 0.43, 0.114] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4bad8a9-72c9-4237-83fa-5673a0e139e9_de5d2cb5-2deb-4b0f-817c-5a1f3d8f6b1a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 2 at a restaurant that was featured on the latest Hit List\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.833, 0.143, 0.988, 0.155] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ad0369b6-cfd5-4555-bb4f-d84a942be555_d35d8236-d15b-4fde-b1a4-cb2250309b2c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order the cheapest climbing shoes in today's deals.\nPrevious actions:\n[link] Climbing -> CLICK\n[combobox] Sort By -> SELECT: Price: Low - High\n[img] Black Diamond Zone Climbing Shoes 0 -> CLICK\n[button] Add to cart—$46.73 -> CLICK\n[link] Cart & Checkout -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.671, 0.238, 0.956, 0.254] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8fb78266-8862-4608-9ff3-92f81e58b2ff_ecaed200-95a2-4e5a-b81d-7e4638985800.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest non-stop or 1 stop flight from JFK, New York to Changi, Singapore for 1 traveler on April 11 which includes seat selection and free cancellation\nPrevious actions:\n[tab] Flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.092, 0.254, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e638beb6-059f-40ea-8653-929221e997db_f933ceb6-cb8e-401e-a15f-74121d8541ff.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comprehensive health screening for women in 10003.\nPrevious actions:\n[span] Schedule a women's health exam -> CLICK\n[link] Comprehensive health screening Available in-person -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> TYPE: 10003" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.279, 0.514, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_a9c6510b-8e65-41cb-b24e-eee23f722354.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[svg] -> CLICK\n[span] Pickup -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.095, 0.248, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4d311ce8-c660-43dc-bde9-d06e85f6a12c_203ab1c5-86ca-4185-87ee-b74643fa9e97.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a room for a business meeting from Apr 30 to May 1 with 7 people within 5 miles of New Delhi. The hotel must have a business center and offer high-speed internet, select the nearest hotel.\nPrevious actions:\n[gridcell] Sat, Apr 29, 2023 -> CLICK\n[div] 30 -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.607, 0.336, 0.64] in the image\nAnd my action is Action: TYPE\nValue: 1" } ]

{ "bytes": "", "path": "./images/8d9e09e1-c31a-420b-ace8-079204db551a_d5f3fc99-7306-4bf6-8f6f-d0efa393636a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a ticket for an event similar to professional boxing\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: professional boxing" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.232, 0.392, 0.247] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_1463c3d8-4e6e-4c2f-897f-4ad740d598d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[link] SSD Storage -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[link] Fan & Heatsink CPU Cooler -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.285, 0.868, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_9d601e7e-2e4f-42d0-a3d4-8e24b865fed4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] 8 -> CLICK\n[listbox] hour -> SELECT: 14\n[listbox] minutes -> SELECT: 00\n[button] Get cheapest tickets -> CLICK\n[span] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.346, 0.256, 0.377] in the image\nAnd my action is Action: SELECT\nValue: Forward facing" } ]

{ "bytes": "", "path": "./images/cdd64586-2f2e-4000-89fa-200feefcd97d_8183f7ea-b058-4050-9a78-7d016c2f1e14.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newly arrived Batting Gloves for women\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.292, 0.362, 0.35, 0.399] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5098c679-dacc-4abd-9331-18b898f936dd_f8551872-cb70-46ad-b3d7-435fef6cf6ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the St louis park policies regarding security?\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.283, 0.846, 0.318] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/725c38e7-7987-40b3-8f19-8450f8277f06_5c7395ff-ffb0-411f-a8a1-bd2d6f51d101.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 event to attend in Athens, Greece on April 2nd\nPrevious actions:\n[div] Events & Activities -> CLICK\n[input] -> CLICK\n[button] Greece -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.616, 0.211, 0.672, 0.225] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/712d9d7f-d7ee-4554-affa-133449231ae4_9c650bd4-031f-4287-8751-f277c6861d52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 latest medical audiobook on complementary medicine for under 20 dollars and add the top book to the cart.\nPrevious actions:\n[link] Shop by category∨ -> HOVER\n[link] Medical -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.153, 0.196, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff173880-e7f5-4b4e-b941-79e9c3504add_f39d7ec8-50c8-4394-b48e-97e4a42e0dac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] Products -> CLICK\n[button] Home décor -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.355, 0.201, 0.605, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/913b902b-37b7-4230-a0f2-a19931b06951_61dce3f4-e036-403d-b3c3-bc956eb57807.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the fastest single stop flight fron JFK airport in New York to Male in Maldives on March 13\nPrevious actions:\n[textbox] Flight origin input -> TYPE: new york\n[div] John F Kennedy Intl -> CLICK\n[textbox] Flight destination input -> TYPE: male\n[span] Malé, Maldives -> CLICK\n[button] Start date calendar input -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.317, 0.391, 0.344] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd2494f3-fe7d-4c58-81e4-742c72b4e1f2_fd9fc151-a496-427a-ab5b-a46920baf5cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the order status using an order number of24124124091. The email address is boobear@gmail.com\nPrevious actions:\n[link] Store -> HOVER\n[link] Order Status -> CLICK\n[textbox] Order number -> TYPE: 24124124091\n[textbox] Email address -> TYPE: boobear@gmail.com" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.497, 0.872, 0.549] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab1ae27a-029c-4f0c-9e01-82715e08d518_860311ce-e09d-4946-99fa-8af11abde481.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tables at Chianti - MG Road restaurant on March 30,1:30 PM for 4 Guests.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.021, 0.526, 0.048] in the image\nAnd my action is Action: TYPE\nValue: CHIANTI" } ]

{ "bytes": "", "path": "./images/ce34bc61-e3d2-40c8-b02b-b149efc4b115_18a087b4-2e0a-4bb1-828e-6eabfe01b850.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[button] Selected Pick-Up Date 03/19/2023 -> CLICK\n[button] 04/05/2023 -> CLICK\n[svg] -> CLICK\n[button] 04/08/2023 -> CLICK\n[combobox] Renter Age -> SELECT: 22" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.32, 0.84, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1bb8d48f-dac7-472d-b2b2-651ab184baf2_aa73fdd1-6124-47ae-b9a4-922e2cf5c1b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.693, 0.301, 0.796, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31df4f0d-8852-4694-b6cf-5f337bd26d39_66f6a6e6-f08f-40b2-95a6-0ad325c3aa2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking 1234567890 booked by Jason Smith\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.293, 0.479, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fb36232-0d2a-4115-9012-99dbaad25a5e_516711a6-50e7-4f43-a97a-38b6442f384d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flights from New York to Toronto.\nPrevious actions:\n[span] -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: New York\n[button] New York, NY, US (NYC - All Airports) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.18, 0.481, 0.204] in the image\nAnd my action is Action: TYPE\nValue: Toronto" } ]

{ "bytes": "", "path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_d39863cc-1c9b-4c24-bccf-c7f95e0ade4b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\n[button] Marketplace -> CLICK\n[link] Pop Rock -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.118, 0.163, 0.13] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5070129-37b1-4f87-930f-c45049a70e97_fcd0a544-caa9-4349-bbaa-c79b998d2979.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the FareFinder to find flights for $150 or less from Dublin to anywhere.\nPrevious actions:\n[button] Plan -> CLICK\n[link] Fare Finder -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.138, 0.262, 0.342, 0.287] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78c52592-76e4-4c45-afd5-f94cf213314e_9149d122-ada8-4f08-98c1-30557c30f762.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play a star wars movie trailer.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: Star Wars" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.631, 0.007, 0.649, 0.016] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aedabbf-a7b4-4da7-8eaf-9e159a3ec99b_6aa2eb8f-0a6a-4844-8aa0-f1a9e66a2deb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: review the dinner menu of La Bergamote restaurant in Hell's Kitchen.\nPrevious actions:\n[i] -> CLICK\n[textbox] Search by restaurant name, cuisine, or anything be... -> TYPE: La Bergamote\n[button] Search -> CLICK\n[heading] La Bergamote — Midtown -> CLICK\n[link] Reservation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.253, 0.285, 0.28, 0.297] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdc94e3a-caa3-42b0-aa1b-b99f728f6292_40c1286c-8c7e-4b32-b160-227c9e2ef1f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Schedule a demo drive for Model Y for Roy Adams with phone number 123-999-0000, email address RA@gmail.com and zip code 90001 in the United States.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.454, 0.808, 0.638, 0.842] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9cd20dc6-d2a5-4e8f-9252-549f2c51413c_9dbba049-3068-4fc1-853d-a48205645473.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View inventory of Tesla Model S that are blue and new with 19\" wheels within 50 miles of zip code 60602.\nPrevious actions:\n[link] Model S -> CLICK\n[link] View Inventory -> CLICK\n[image] -> CLICK\n[checkbox] 19\" Wheels -> CLICK\n[textbox] Registration Zip Code Where you will register the ... -> TYPE: 60602" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.048, 0.313, 0.282, 0.343] in the image\nAnd my action is Action: SELECT\nValue: 50 miles" } ]

{ "bytes": "", "path": "./images/6b54b029-bff8-49a7-acca-c57163f14279_24a30d96-2890-4243-9595-14ea4999444c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 music events in Los Angeles today\nPrevious actions:\n[div] Search for events -> CLICK\n[textbox] Search events -> TYPE: music\n[combobox] autocomplete -> TYPE: los angeles" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.13, 0.42, 0.165] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/82f654ab-fbfe-43f2-a2fe-0001b2ac853f_24ad4f85-593a-4b4e-bbfc-ecec0c6f3e00.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for flights from New York City to London and filter the results to show only non-stop flights.\nPrevious actions:\n[svg] -> CLICK\n[tab] One-way -> CLICK\n[path] -> CLICK\n[textbox] Flight origin input -> TYPE: New York City\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.198, 0.702, 0.245] in the image\nAnd my action is Action: CLICK" } ]