Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_fadf5fda-b09f-4516-b1a7-9ec58dc23e1f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[link] Training -> CLICK\n[div] Size -> CLICK\n[link] YXL -> CLICK\n[div] Size -> CLICK\n[div] Sports -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.689, 0.233, 0.713] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_9c2f6d1a-a5c7-4094-97ed-0dfaf2eff284.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Main Menu -> CLICK\n[button] Consoles & Hardware chevron_right -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.162, 0.291, 0.204] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/05238c0f-514f-4af2-bc4c-f7521d649825_f48ac382-e936-49f1-944b-ed81052b0e12.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Dota 2 game and add all DLC to cart.\nPrevious actions:\n[textbox] search -> CLICK\n[textbox] search -> TYPE: Dota 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.085, 0.949, 0.111] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6fd2a5e9-12e7-4f3c-bf1b-42702d56105e_4aede9a4-0099-4d40-8b0d-4399bd3bd274.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 is related to the topics of Industry and also Laborer and Worker.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.461, 0.484, 0.539, 0.5] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8a6f2641-9896-4657-b447-56927420e8c4_7864d3db-532e-478a-b365-5533d458f2d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest educational trade-in Nintendo switch game rated for everyone, and print the details.\nPrevious actions:\n[link] repeat Trade-In -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.441, 0.256, 0.618, 0.487] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d743815d-b7be-43c5-99b6-a224bd2f6a1e_36aefdb1-aee2-4743-a3b8-54eaf1a6beed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show information on how to find lost AirPods.\nPrevious actions:\n[link] Support -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.327, 0.5, 0.371] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_253077b6-b883-4263-808e-e8cd35f2b6b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: [email protected]\nPrevious actions:\n[span] -> CLICK\n[button] Subscribe -> CLICK\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: Smith\n[textbox] Email Address -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.711, 0.354, 0.799, 0.393] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2e133e56-ac17-41dc-987a-257078d770c3_61738502-0b06-46b8-910b-266b5ccfbe97.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find on the water activities in Dubai from 5pm to 12am with a maximum duration of four hours\nPrevious actions:\n[textbox] Where to? -> TYPE: Dubai\n[button] Dubai United Arab Emirates -> CLICK\n[path] -> CLICK\n[button] -> CLICK\n[div] On the Water -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.32, 0.107, 0.333] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_d1079663-66c1-47c7-a0fa-6f0420a99469.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.246, 0.233, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/020bc054-a829-4af5-8f0a-6efce012c7ac_7949a928-22fa-4f0c-824a-d6b3ea062f7b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the number 4 ranked board game on the geekmarket.\nPrevious actions:\n[button] Browse -> CLICK\n[link] All Boardgames -> CLICK\n[link] Ark Nova -> CLICK\n[span] Ark Nova (English edition, third printing) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.814, 0.14, 0.97, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/240952bd-853b-4653-a358-49c2784cf568_d1d704cb-2130-4933-b894-6c0a492dc4c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train scheduled between Chicago to Los Angeles for the next day, and if a southwest chief train is available, then print the route details.\nPrevious actions:\n[link] SCHEDULES -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.084, 0.324, 0.098] in the image\nAnd my action is Action: TYPE\nValue: chicago" } ]

{ "bytes": "", "path": "./images/8634bbc0-7bcd-4c88-ad0f-5c73c3f69e53_b9746274-9171-4823-b007-455876cc5a17.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Join the waitlist for a ticket for the Hackney Clothes Swap - Earth Day event being held on April 22nd. Name: Joe Bloggs. Email: [email protected]\nPrevious actions:\n[div] Search for events -> CLICK\n[combobox] autocomplete -> TYPE: Hackney\n[div] Hackney -> CLICK\n[combobox] autocomplete -> CLICK\n[combobox] autocomplete -> TYPE: Hackney" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.403, 0.42, 0.463] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_39a01968-5e21-459c-82ec-924e69ae3041.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[LabelText] Sell My Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.255, 0.246, 0.5, 0.27] in the image\nAnd my action is Action: TYPE\nValue: YAW639" } ]

{ "bytes": "", "path": "./images/e437082b-8383-4322-aa58-a6a683113970_7ae94499-171d-4bee-a8f8-12cd500daf3f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.302, 0.002, 0.348, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_90692452-f027-4608-a74d-8382631f665f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[checkbox] Towels -> CLICK\n[button] Property style -> CLICK\n[checkbox] Beach -> CLICK\n[div] Recommended -> CLICK\n[tab] Price (low to high) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.742, 0.653, 0.84, 0.685] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_6219d481-0512-4dee-8054-a5a7b9fac49c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.523, 0.573, 0.611, 0.582] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_51dfec56-5700-4f95-b3dd-34a07aae5856.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[checkbox] Third-Party Certified (343) -> CLICK\n[span] Drive Type -> CLICK\n[checkbox] Front Wheel Drive (147) -> CLICK\n[span] Exterior Color -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.43, 0.277, 0.445] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_1b8d8699-8875-4d1e-a4b0-594a3f659771.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[span] Add -> CLICK\n[link] Herbs -> CLICK\n[div] Add -> CLICK\n[button] View Cart. Items in cart: 5 -> CLICK\n[button] View Cart. Items in cart: 5 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.6, 0.855, 0.994, 0.982] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_6bd9289f-2ad1-42a9-81fc-f1719e3e9d89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] hotels -> CLICK\n[div] Destination or property -> TYPE: jakarta\n[hp-input-button] Destination or property -> TYPE: jakarta\n[div] Jakarta, Special Capital Region of Jakarta -> CLICK\n[div] Choose date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.174, 0.264, 0.225, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/227054d0-24f1-4f8a-9dcb-5146fac623f4_4cc72811-d9b9-4f6f-8ae1-5556a8f76045.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Tablets -> CLICK\n[img] Samsung -> CLICK\n[span] 11\" & Larger -> CLICK\n[button] APPLY -> CLICK\n[span] 8.7\" -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.405, 0.192, 0.417] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_77ae34f7-69b8-4da8-90c9-5420ce7b170c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest SUV in Brooklyn for 1 day.\nPrevious actions:\n[button] End date -> CLICK\n[button] May 22, 2023 -> CLICK\n[svg] -> CLICK\n[img] SUV -> CLICK\n[div] $75 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.519, 0.345, 0.631, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_2cc502de-3f64-4412-9dfa-d6311cbc490a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.149, 0.122, 0.165] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd8f1f63-f6c3-4b1b-9ec9-3b13b9f0386c_af0979f8-d69c-48e8-a772-a069f0d24a84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Read the 1 star reviews of DayQuil Severe Cough Liquicaps.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.009, 0.804, 0.023] in the image\nAnd my action is Action: TYPE\nValue: dayquil" } ]

{ "bytes": "", "path": "./images/39b037ac-0a11-4b05-8919-b4f9863fd0cd_b05415f3-ea39-499f-b8d0-25e061aa16e3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 review of Prometheus movie.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.395, 0.104, 0.463, 0.117] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/05c4da5b-263d-40a4-9982-6cf6311b57a1_1fb87a1c-d99f-48e1-ae71-ba6f01482933.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an Xbox Wireless controller rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: xbox wireless controller" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.496, 0.016, 0.546, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d7ab9bf0-99e2-4f32-92c9-c1a10bc68f82_bdc9ce47-f8ec-422f-a746-44d33de2b5a9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Manchester City Performance Stats of 2022/2023 season in the champions league\nPrevious actions:\n[link] Champions League -> CLICK\n[link] Manchester City -> CLICK\n[link] Stats -> CLICK\n[select] English FA Community Shield -> SELECT: UEFA Champions League\n[select] 2022-23 -> SELECT: 2022-23" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.489, 0.253, 0.717, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_01ef4b13-5aec-4c24-9e21-67d5c3f3caeb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] set store -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Nationwide -> CLICK\n[menuitem] 100 miles -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.232, 0.249, 0.265] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00e83fae-f2f0-48ab-912c-32c03982642b_4abb3e7b-7920-47cd-9268-2df8e7a4c4c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 computer game reviews sorted by score.\nPrevious actions:\n[button] Reviews -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.142, 0.216, 0.167] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/70b3ef5b-d900-44cf-9b62-9ecece97954c_8b782e73-72f5-42e8-89e0-197104dfbedd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find climbing gear and sort the results by price high to low.\nPrevious actions:\n[button] Climb -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.128, 0.078, 0.181, 0.109] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92cd371-0bd2-4ac3-82e4-7fdaac46b626_4db51223-64ed-46ee-aee9-c61490715f38.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\n[combobox] Search products and services -> TYPE: zyrtec\n[button] Search for zyrtec -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.191, 0.176, 0.33, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_e26a7560-027d-4467-b206-33ac5f582855.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated romantic summer vacations in Spain\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.086, 0.492, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13a676be-2f4f-4abf-83fb-4ab641793801_20f7373e-4912-4000-aab2-2097e31b32e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a list of Administrative and Clerical jobs MTA is currently recruiting for in Brooklyn\nPrevious actions:\n[link] Careers -> CLICK\n[link] See all open MTA positions. -> CLICK\n[textbox] Enter a Location -> TYPE: brooklyn\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.043, 0.206, 0.254, 0.219] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3bb1c925-71ef-4713-a139-a3be65f8a7a5_8b3ecf8e-9155-4d96-9c07-4068e5782c66.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for Fallout 4 and mark the first one as helpful.\nPrevious actions:\n[textbox] search -> TYPE: Fallout 4\n[link] Fallout 4 $19.99 -> CLICK\n[select] 1900 -> SELECT: 1995\n[link] View Page -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.3, 0.716, 0.34, 0.734] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fb04bb83-9ad5-4186-a0da-17af9ba2a63d_da0b4cb1-d93d-4810-a74b-cb1a47baded5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers for VIFP Club loyalty number 9016467685 and show the ones that are for members only.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.286, 0.093, 0.39, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_f9650777-77a8-4cf0-9fc6-788cb349e8e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[label] Pick-up location -> TYPE: BANGKOK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.206, 0.438, 0.234] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1860601a-faef-4dba-8cbb-807ea8434dca_74a7bdfb-8e01-47ae-8251-2c1ee845131e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\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 [0.512, 0.073, 0.613, 0.085] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_9b472dc3-9d6c-466a-ac5b-3b787e64dbd8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[select] June 2023 -> SELECT: June 2023\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 1:00 PM\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.746, 0.409, 0.777, 0.431] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_82d3b3a2-ab6a-4d43-be93-b933685cab2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[div] -> CLICK\n[button] 1, Saturday, April 2023. Available. Select as chec... -> CLICK\n[button] 8, Saturday, April 2023. Available. Select as chec... -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.083, 0.237, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_aa3adabf-f4e4-4b54-ab6d-9e8fbf8b11e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[button] 2 travelers -> CLICK\n[img] Increase children -> CLICK\n[img] Increase infants -> CLICK\n[combobox] Child 1 age -> SELECT: 4\n[combobox] Infant 1 age -> SELECT: Under 1" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.566, 0.558, 0.841, 0.597] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4272e233-3440-4572-bd86-b3a2b22a4061_b14fb2e2-d8b2-41f2-9cf2-517a4a832935.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] -> CLICK\n[label] Most popular -> CLICK\n[span] See availability -> CLICK\n[button] Show more dates -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.762, 0.177, 0.801, 0.193] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_f8261747-9bb4-4b98-98a2-f34f5eaba467.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Braintree to Boston Airport on April 14, 12 pm, and see the fair calculator.\nPrevious actions:\n[button] Get trip suggestions -> CLICK\n[button] Depart at 8:40 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 14, 2023 -> CLICK\n[combobox] Hour -> TYPE: 12" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.199, 0.304, 0.246, 0.326] in the image\nAnd my action is Action: TYPE\nValue: 00" } ]

{ "bytes": "", "path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_1063a7d1-40b8-4b02-a6cb-f320875209b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find trade in value for PS4 console\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.697, 0.046, 0.722, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f45b0783-4325-4b3e-959d-c181971d72f6_fbd5b363-535a-4675-9c4f-ce3b14af687e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest news and rumors about the NBA team the Los Angeles Lakers.\nPrevious actions:\n[link] NBA . -> CLICK\n[link] Teams -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.406, 0.364, 0.498, 0.378] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/16886ec7-3301-4103-b175-9fa817335984_672dc62a-a88d-468f-9b1e-eee5818cb7a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NBA team with the highest average points scored in the current season\nPrevious actions:\n[button] NBA -> HOVER\n[link] Stats -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.036, 0.563, 0.062, 0.57] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c987dd1d-9ade-4701-8cdb-a31f8f3bf673_3169cbf4-b8dd-4854-af0b-bad280e9950d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a best rated Thai restaurant in Westminster, California, that provides takeout, and whose staff is fully vaccinated and accepts Apple pay.\nPrevious actions:\n[link] Restaurants -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.166, 0.186, 0.197] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35cf31d3-c88d-45fe-9959-4cf1de72bc7d_662d83be-f7cd-4480-ae69-20aeaf275ce8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for trending women sports bras and add 3 trending black bras to Wishlist.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.291, 0.233, 0.34] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/37c09901-63d4-4194-8a96-1d87ca8c37ae_b7bcc68c-c9f7-4069-84c1-6c3fe43d24ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse washing machines available for free local pickup within 25 miles of zip code 90026.\nPrevious actions:\n[combobox] Search for anything -> TYPE: washing machine\n[button] Search -> CLICK\n[textbox] Zip code -> TYPE: 90026\n[button] Apply within filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.757, 0.027, 0.764] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2ef470ab-b06a-4479-883f-78b4e3b94a04_5e934cdf-7af9-40d2-a4f0-ada6b371432e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[textbox] Location-Search -> TYPE: New York\n[link] New York City New York, USA -> CLICK\n[button] Select Activities -> CLICK\n[span] Cultural Tours -> CLICK\n[span] Any -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.565, 0.21, 0.728, 0.236] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e8637690-bb8c-4596-a608-5b40a29d77c9_4a582ba5-4347-4b8b-8e83-40d48174cd24.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a large store in Washington that has kids' and maternity products, also check if they have a parking lot, and see the directions of the nearest store.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.721, 0.2, 0.736] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e437082b-8383-4322-aa58-a6a683113970_01b4466a-8da6-4894-9b73-283acd8a8d89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel in Las Vegas that will cost two people the least for a week starting from 10, April\nPrevious actions:\n[button] Book -> CLICK\n[link] Hotels -> CLICK\n[searchbox] Type your destination -> TYPE: Las Vegas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.073, 0.451, 0.409, 0.489] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_25614f00-cfb4-4d96-9189-80974032e6bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[combobox] Party size -> SELECT: 4 guests\n[svg] -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Mediterranean -> CLICK\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.666, 0.095, 0.797, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/53b4ca73-c05b-4609-98c8-a0a62072bdb5_c75460c1-761c-4db0-ae39-226820fe160b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest vitamin C and D to cart.\nPrevious actions:\n[button] Shop -> CLICK\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK\n[link] Vitamin C -> CLICK\n[div] Relevance -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.823, 0.479, 0.98, 0.508] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_31f5929e-78b5-4fb3-9722-4fe9085bf63b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[label] Ice Fishing -> CLICK\n[svg] -> CLICK\n[label] Medium Light -> CLICK\n[svg] -> CLICK\n[label] 32\" -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.257, 0.222, 0.273] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f2258a-07c3-46ed-a974-01543606b31b_eac36fe2-54cf-4f5c-b064-426223357844.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for Honolulu from New York with budget of $1300 for premium economy.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.855, 0.055, 0.9, 0.069] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/60383804-a8e5-4e50-8715-da391d76617d_06967b32-70d8-492b-8521-dbfafd2504f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse candle holder red decor products.\nPrevious actions:\n[link] Marketplace -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.117, 0.112, 0.32, 0.126] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b33554f-eb29-4f8d-93cf-5e947e4f8e47_708d6e85-370a-4de2-b507-35df29ee9a42.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurants near my location with pizza and for 6 customers.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.183, 0.029, 0.456, 0.065] in the image\nAnd my action is Action: TYPE\nValue: Pizza" } ]

{ "bytes": "", "path": "./images/117b1d5c-1e54-4588-ba84-aa173887b067_1874df15-0121-4c6c-9489-9ca06fbc20fd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Renew a existing KOA rewards account with the rewards number 1000000001 e postal code 10023\nPrevious actions:\n[link] REWARDS PROGRAM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.449, 0.219, 0.521] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_8e2b91b9-de9e-4e98-8b53-a53d238427cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\n[link] Search for hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.157, 0.478, 0.196] in the image\nAnd my action is Action: TYPE\nValue: Chennai" } ]

{ "bytes": "", "path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_08dce56f-9e31-44cc-b247-2ff269bbd19e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy tv shows on netflix sorted by audience score.\nPrevious actions:\n[img] netflix -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[span] Sort: Most popular -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.089, 0.27, 0.232, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_3bef15a6-9466-4ee9-b485-4f7dd16e1291.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Depart , required. -> TYPE: 04/19/2023\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] To , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.199, 0.492, 0.22] in the image\nAnd my action is Action: TYPE\nValue: CDG" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_27fa3863-1da9-4a0e-849c-837c9f0abeaf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[button] US Shoe Size -> CLICK\n[link] 9 -> CLICK\n[button] Condition -> CLICK\n[link] Pre-owned -> CLICK\n[button] Sort: Best Match -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.735, 0.225, 0.923, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdc94e3a-caa3-42b0-aa1b-b99f728f6292_c99ec0f1-3a4a-4e38-bc04-4ecab395b872.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 [email protected] and zip code 90001 in the United States.\nPrevious actions:\n[link] Demo Drive -> CLICK\n[button] Model Y -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.705, 0.659, 0.718] in the image\nAnd my action is Action: TYPE\nValue: Adams" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_fad534dc-b5e4-4d2b-85ae-4b2f16b7dce8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 return tickets from Leeds to Sheffield leaving at 8:30 am on Mar 25, 2023 and returning at 23:00 pm on same day for 1 adult and 2 child.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: Leeds\n[span] Leeds -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.319, 0.326, 0.347] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/298c854d-2987-498b-b43e-6a6452fb11c7_6d93218f-905d-4f25-a513-a1e03c29eed5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 unique experiences in London of maximum one hour duration which are rated four stars and above\nPrevious actions:\n[textbox] Where to? -> TYPE: London" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.22, 0.729, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_bbad698b-ef52-4fda-85eb-5df447581cf7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[button] 1 NIGHT Sat, Apr 08 - Sun, Apr 09 -> CLICK\n[span] 7 -> CLICK\n[span] 14 -> CLICK\n[button] Done -> CLICK\n[button] Lowest Regular Rate -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.229, 0.255, 0.359, 0.267] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50f1e384-4b63-4827-a670-cd19f5a2c710_96dbde61-5327-46c8-8e3d-d2380577f324.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find schedule for Long Island Rail Road & Metro-North Railroad from Bay Shore to Breakneck Ridge on Thu, Mar 23, 08:37 AM.\nPrevious actions:\n[searchbox] From -> TYPE: Bay Shore\n[listitem] Bay Shore -> CLICK\n[searchbox] To -> TYPE: Breakneck ridge\n[span] Breakneck Ridge -> CLICK\n[button] 03/18/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.627, 0.236, 0.649, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_1cf0e95f-e911-42e3-a18f-a2c4ae24e04b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[select] April 2023 -> SELECT: July 2023\n[link] 7 -> CLICK\n[link] 15 -> CLICK\n[combobox] Pick Up Time -> SELECT: 1:00 PM\n[combobox] Return Time -> SELECT: 2:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.225, 0.463, 0.256] in the image\nAnd my action is Action: SELECT\nValue: Vietnam" } ]

{ "bytes": "", "path": "./images/9653dc0d-96d9-414f-a711-3af94bd7cf5b_45f50459-f551-4081-8177-ecefc94cae72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 playstation controller for cash credit on GameStop in 43240.\nPrevious actions:\n[link] repeat Trade-In -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.547, 0.184, 0.594] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13d78369-994a-4202-a9ed-8361e1fdea9d_df45ef47-c2eb-4bb6-9b1d-aac6c641c2e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bluetooth headphones with active noise-cancellation.\nPrevious actions:\n[searchbox] Search Site -> TYPE: headphones\n[button]  -> CLICK\n[span] Active -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.592, 0.192, 0.61] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/957878ba-cb47-40d1-bf37-23039b2dff27_8bc96816-a9be-4f98-b864-15092427a0b3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find a CarMax in Michigan, 49107 and book an appointment for a car repair on April 7th..\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.012, 0.384, 0.042] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_a8c71db4-4c7d-45a0-befd-2bf4ea75e2fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.372, 0.447, 0.418] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_7128c85b-93dc-496e-9ffc-d8e624bf9036.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] START FROM SCRATCH -> CLICK\n[h1] My New Playlist -> CLICK\n[h1] My New Playlist -> TYPE: Dirty\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.668, 0.199, 0.699, 0.217] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e8603513-2740-485e-adf9-86361dd015f4_f12321ef-5a11-4132-ab68-7660be13e08c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare FlightAware subscriptions and signup for Enterprise plan.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.121, 0.037, 0.17, 0.053] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4775a0e3-3dad-46f2-b719-b1c0dae9e147_3badcc5d-9a3e-408d-92d6-46206293a333.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[link] Grocery -> CLICK\n[link] Bread -> CLICK\n[label] In Stock Today -> CLICK\n[checkbox] Tortillas (4) -> CLICK\n[button] Increase Quantity -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.969, 0.463, 0.99, 0.481] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_ddcf9faa-d926-4c7b-bdc8-ac481e2daddc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: calculate a car loan payment for a $25000 car with a $5000 down payment and 12 percent interest rate for 48 months.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.0, 0.279, 0.03] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cfb351f8-804b-4074-9826-0b3525f68727_c01c84b0-81b3-4e6a-93f8-d1d319e101c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2022 highest goal scorer in the MLS league\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.064, 0.44, 0.09] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2ef470ab-b06a-4479-883f-78b4e3b94a04_71a6b122-0c7f-49f6-8f00-496bc997c596.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 five star rated cultural tours in New York on May 7 with a max price of $75\nPrevious actions:\n[link] Activities  -> CLICK\n[textbox] Location-Search -> TYPE: New York\n[link] New York City New York, USA -> CLICK\n[button] Select Activities -> CLICK\n[span] Cultural Tours -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.578, 0.148, 0.741, 0.16] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_88c6723c-7217-4add-893d-bf5d72b68db8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[span] -> CLICK\n[button] Sort by:Top picks for solo travellers -> CLICK\n[button] Price (lowest first) -> CLICK\n[link] See availability -> CLICK\n[button] Reserve -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.595, 0.923, 0.61] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc21339a-5dc0-489c-b348-2fac79483f76_a726af10-e02c-4e08-846c-e5d79fc1f8cd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Metformin 1000mg tablet price and details.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] See All -> CLICK\n[link] Amazon Health -> CLICK\n[link] Amazon Pharmacy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.177, 0.425, 0.741, 0.455] in the image\nAnd my action is Action: TYPE\nValue: Metformin 1000mg" } ]

{ "bytes": "", "path": "./images/74f01011-9bcd-433b-8405-975ca5c3f356_acdbfdec-a930-4e6c-bbb3-2734441739b7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the address and store hours for the Armageddon Shop record store in Boston.\nPrevious actions:\n[button] Community -> CLICK\n[link] Record Stores -> CLICK\n[link] Explore the directory -> CLICK\n[searchbox] Refine Location -> TYPE: Boston\n[span] MA, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.492, 0.151, 0.517] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_233a182b-880c-4fc2-883d-b5f7db449fa8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[listbox] Leaving at or Arrive by selector -> SELECT: Leaving at\n[listbox] hour -> SELECT: 10\n[listbox] minutes -> SELECT: 45\n[svg] -> CLICK\n[listbox] select adults -> SELECT: 2" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.269, 0.391, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/000c2828-e8ce-4b18-bfe0-89ed333add06_eb050362-242d-4e15-bf1a-82c746f71bc8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $25 digital gift card for Tim Stebee, whose email address is [email protected]. Fill in sender name Jeerimiah Waton\nPrevious actions:\n[img] -> CLICK\n[img] GameStop Digital Gift Cards -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.519, 0.975, 0.56] in the image\nAnd my action is Action: TYPE\nValue: Tim Stebee" } ]

{ "bytes": "", "path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_ad3cdc43-66c2-4833-b233-5df774bfceab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the mystery vehicle to pick up at Bradenton in Mahattan, Florida on april 20 at 3 pm and return at 6pm\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.163, 0.5, 0.188] in the image\nAnd my action is Action: TYPE\nValue: Manhattan" } ]

{ "bytes": "", "path": "./images/bef473f1-82a1-4359-a2c0-59b6dc2f6abb_b68ec086-9eaf-4b7d-977a-b2a6a6417d65.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Alaska that is also a National Heritage Area.\nPrevious actions:\n[button] Find a Park by State -> CLICK\n[link] Alaska -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.675, 0.856, 0.687] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f41d9db-29fd-4c1b-9cbd-0f74fecdf520_05468c6a-dee3-4b1e-a923-9004409dc1ee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show information about careers with MBTA and signup for customer service job alerts. Name: James Smith. Email: [email protected]\nPrevious actions:\n[link] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.653, 0.521, 0.823, 0.536] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc194d4-2f71-496a-b378-e18ab698ab0f_12af0a4e-ac29-4730-9fef-81f52558f981.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reggae concerts this weekend.\nPrevious actions:\n[button] CONCERTS -> CLICK\n[link] Reggae -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.262, 0.881, 0.278] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e133f6c-155d-4ba4-89f5-16f569d6e918_da39254d-694d-449a-9fd4-61d73f28d2a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 food tour in Paris which offers free cancellation\nPrevious actions:\n[textbox] Where to? -> TYPE: Paris\n[button] Paris France -> CLICK\n[circle] -> CLICK\n[button] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.417, 0.093, 0.429] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a5c1095b-bba1-4029-8b8d-fa5848702827_0a60f460-55f6-4c2d-a535-36cdf07eeebe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking in New York City from June 5th to 9th.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> TYPE: New York City\n[option] New York City   City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.567, 0.096, 0.628, 0.112] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_e4951d09-66ec-4136-bac3-44a43647d534.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\n[button] Departments -> HOVER\n[button] Electrical -> HOVER\n[link] Smart Home -> CLICK\n[link] Smart Lighting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.015, 0.444, 0.098, 0.457] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_a559a3c5-70ba-425d-a2c7-ee28846020dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] SEARCH CARS -> CLICK\n[button] Distance & Shipping -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.264, 0.237, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2f8b054-59b5-4fd8-bd58-9f95b29f979d_41cf4d7a-1f81-42f6-8711-5c1a16ed9d72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest 2018 Honda Civic for sale within 100 miles of 07055\nPrevious actions:\n[link] Cars for Sale -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.224, 0.134, 0.277, 0.15] in the image\nAnd my action is Action: TYPE\nValue: 07055" } ]

{ "bytes": "", "path": "./images/1bb8d48f-dac7-472d-b2b2-651ab184baf2_638d3c1a-7e71-476f-bd07-42cfcf96f211.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.765, 0.457, 0.78] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5d69e640-7765-4381-979c-9881afc048dd_178b5b80-98d2-4169-895c-8e4eada72f72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the monthly payment of a 15k car with a down payment of 5k in Michigan for a fair-rated person for a term length of 48 months, then shop with this budget for the cheapest car and add it to the favorites.\nPrevious actions:\n[link] Finance -> CLICK\n[link] Car payment calculator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.159, 0.248, 0.459, 0.278] in the image\nAnd my action is Action: TYPE\nValue: 15000" } ]

{ "bytes": "", "path": "./images/e2adf8f1-547d-4671-96c1-4a21a56e135d_98318d24-fc5b-4031-bff4-008759505c93.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.623, 0.307, 0.875, 0.343] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7685e8ad-3989-4316-85dd-746fac2956be_562c577d-ae8f-4c46-bb04-2877a53444f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recently posted part-time Job in Gamestop stores in Fresno, California, and apply.\nPrevious actions:\n[link] Careers -> CLICK\n[link] View Jobs Stores -> CLICK\n[button] State / Province -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.532, 0.138, 0.543] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5cc7e71-6fd6-4a33-b450-89565dcff0a3_b1ca9ca5-f756-40f0-9e77-3ee9207a3e2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for Hotels in Mexico.\nPrevious actions:\n[textbox] What type of deals? -> TYPE: Hotels\n[div] Hotels -> CLICK\n[textbox] Where? -> TYPE: Mexico" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.134, 0.536, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c64dcaa1-555d-43f3-adb4-3452c4e5d09b_2da8d261-db2a-478c-b02d-cd0694309653.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] All -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.221, 0.066, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a9708ad7-bec8-4435-b055-8ef6da520b8c_529bf27f-0365-49a0-a525-a223e2d1d091.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play the top track for the top indie artist in the last 30 days\nPrevious actions:\n[link] Music -> CLICK\n[link] indie -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.431, 0.127, 0.449] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_2f0b502b-6280-4361-9d9b-77f44c23c9c7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an available full-time job in USA finance, save all the accountant jobs.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK\n[button] Country -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.099, 0.579, 0.307, 0.594] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d92911a-b208-4d68-ad00-46d2d67f9efa_9a0c78ef-cc11-4975-8d79-e59d7a5e6d84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store in spring, Texas.\nPrevious actions:\n[link] Store Locator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.029, 0.129, 0.266, 0.151] in the image\nAnd my action is Action: TYPE\nValue: SPRING, TX" } ]