Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/42657330-bfc5-425d-ae21-396a9ba1fb12_cfd7af8e-2b20-4e37-9c53-bc573db84b80.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find yellow t-shirts for women small size that are less than $20.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.004, 0.204, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_e4bfc892-619e-42af-a6d8-c208fbf54abc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[menuitem] View All -> CLICK\n[label] Ice Fishing -> CLICK\n[svg] -> CLICK\n[label] Medium Light -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.135, 0.051, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dc2aa3f8-eda0-455b-98dc-adc56089259a_31fa2e7e-646b-4f4b-aaca-fed108191241.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 route information for flights from Ohio and New York airports that have already arrived.\nPrevious actions:\n[textbox] Origin -> TYPE: Ohio\n[div] Ohio -> CLICK\n[textbox] Destination -> TYPE: New York\n[div] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.626, 0.338, 0.639, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0f9dd411-f3ab-494e-8a3a-5dc9a908f4ee_14b29326-0525-482c-a3f7-ac9b37978045.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the cvs pharmacy nearest to zip code 45201 that provides hair loss evaluation and treatment.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.199, 0.41, 0.24] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3bc6528-5fd5-45ac-81aa-7fafde757022_d1fd77e6-3905-49e3-8aee-58aa0a2df50d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 new laptops from $400 to $500 that offers free shippping.\nPrevious actions:\n[combobox] Search for anything -> TYPE: laptop\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.694, 0.027, 0.701] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/de1045f4-14ce-4de9-9aa8-601315b73b0e_50f46316-29db-42fb-9b52-320a814c5355.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most popular documentary tv series sorted by IMDB rating, see the details of the top result.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK\n[span] Browse TV Shows by Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.122, 0.786, 0.182, 0.797] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14a4e19d-d82d-45dd-b4f0-6b60ed87d085_62cf5905-dba2-4936-abd9-9b6e872672d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\n[img] -> CLICK\n[link] Deals -> CLICK\n[div] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.343, 0.626, 0.404, 0.654] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_0ee2e627-345c-4b15-8542-3c13034733b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[div] Wed, Apr 19 -> CLICK\n[checkbox] 26 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 2:00 PM\n[span] -> CLICK\n[div] Thu, Apr 27 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.62, 0.358, 0.647, 0.384] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36ab5d78-2f6b-47a6-ad88-3f6c8fdc3513_83929b11-5af8-4c6d-ad37-5ca0f73ad849.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the movies playing today at the theater closest to zip code 10001\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK\n[link] Find a Theatre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.163, 0.888, 0.192] in the image\nAnd my action is Action: TYPE\nValue: 10001" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_0200f0fe-002c-4088-8037-f34bfff4156c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\n[path] -> CLICK\n[combobox] Search by city or activity -> TYPE: Miami" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.364, 0.795, 0.378] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ba5e0124-b1c0-4116-968c-6b31a4c9c0a7_ba9f81d9-3f78-4f0c-95c4-5795d13a3183.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest bus for 2 persons from New York to Washington, DC.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: New York\n[span] New York, NY -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Washington\n[span] Washington, DC -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.763, 0.133, 0.831, 0.149] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/988ff1b8-c9e8-44af-a729-33f0e99c9dbf_8fb7f444-5f4c-47e0-998b-193424bfc319.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars with AWD with maximum budget of $50,000.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Cars for Sale -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.101, 0.301, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdc94e3a-caa3-42b0-aa1b-b99f728f6292_21aada65-2d3c-4713-abae-5b5693c2de68.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Last Name -> TYPE: Adams\n[textbox] First Name -> TYPE: Roy\n[textbox] Phone Number -> TYPE: 123-999-0000\n[textbox] Email Address -> TYPE: [email protected]\n[textbox] Zip Code -> TYPE: 90001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.152, 0.794, 0.401, 0.859] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/34e13beb-0235-41d4-b108-137cc7480904_f69045c0-0476-4c5d-9f6e-c84d5488fb80.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] CITIES -> CLICK\n[span] Find your state -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.115, 0.652, 0.487, 0.669] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab30c9e-f768-46e8-8174-83651d361b9e_36bdd9ba-ddea-4b12-81a7-7d1e8fb3a665.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the scores of today's NBA games.\nPrevious actions:\n[span] Scores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.589, 0.048, 0.611, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bb02400d-e9da-416a-839a-0068f511a630_a23b9fbd-1e7a-41fa-9116-32747b5b9649.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 WWE tickets for April 10 event happening in seattle, and book 4 cheapest lower level tickets.\nPrevious actions:\n[link] WWE Tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.864, 0.361, 0.941, 0.375] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4097c577-e637-4543-87a3-09b2f4734163_2c488a7d-0773-4c99-9420-d0e8103c6d3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pedicure salon in New York and add two to favorites.\nPrevious actions:\n[input] -> TYPE: New York\n[link] New York, NY -> CLICK\n[button] Find -> CLICK\n[link] Beauty & Youth Village Spa -> CLICK\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.007, 0.867, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_18ed9e91-64f4-4929-8827-5d7634c0101a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\n[span] organic strawberries -> CLICK\n[img] Driscoll's Organic Strawberries -> CLICK\n[span] All stores -> CLICK\n[textbox] Search -> TYPE: organic strawberries\n[span] organic strawberries -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.677, 0.154, 0.686] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4596152e-6589-4bf2-9c9f-dd3ed9e8c0dc_2e2727b7-9ba0-46a3-8338-849b1a5ed4fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 out details about cancellation fees.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.618, 0.24, 0.631] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_a957bb96-e539-4222-b03f-b8c371629b9e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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: 04/21/2023\n[button] Add another flight -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: CDG\n[a] CDG - Paris Charles de Gaulle, France -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.292, 0.492, 0.317] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_a148f761-c294-45ac-a94f-292cbf472e4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Date use format: 24-Mar-23 -> CLICK\n[link] 25 -> CLICK\n[listbox] hour -> SELECT: 08\n[group] RETURN -> CLICK\n[link] 25 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.184, 0.265, 0.2] in the image\nAnd my action is Action: SELECT\nValue: 23" } ]

{ "bytes": "", "path": "./images/9223ed29-5abb-4f4d-8108-1c3a584a7017_71c0293f-f272-4abb-96b5-f08d24560f51.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find information about reduced bus fares.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.375, 0.01, 0.441, 0.03] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/49372757-4c58-4cb5-bdb4-eed0c3e83199_0d1d347a-d1b1-4f96-884b-502fa81b3184.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 electrician that serves the 94115 zip code and is considered Fast Responding\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.021, 0.564, 0.034] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0cbdfafd-822f-4f61-bb57-05fc146752ce_a3a1bddc-b996-4166-829c-41ba7edc29a0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car toll rate for bridges and tunnels\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.062, 0.058] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_da47c157-9f8f-414e-a839-ea1a2dfb5244.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BWM cars made in 2010 and compare the four cheapest listings\nPrevious actions:\n[div] BMW -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.029, 0.102, 0.13, 0.126] in the image\nAnd my action is Action: SELECT\nValue: 2010" } ]

{ "bytes": "", "path": "./images/5418beec-bc06-4e11-9664-4038fbdeefe9_528e9700-0759-4a2e-a6b2-b5eceaa76ec4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\n[span] BATMAN -> CLICK\n[link] Filter -> CLICK\n[checkbox] Same Day Delivery Same Day Delivery -> CLICK\n[generic] Refine by Category: Collectibles -> CLICK\n[generic] Refine by Category: Figures -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.042, 0.35, 0.084, 0.372] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1f128c19-3093-4c49-bfc7-13589aa8e88a_fc5ded8c-80f4-42d5-b087-79319e6d4d09.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get a Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[button] All Filters -> CLICK\n[tab] Character -> CLICK\n[checkbox] Hulk -> CLICK\n[tab] Year Manufactured -> CLICK\n[checkbox] 1990 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.327, 0.757, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/22e33a38-902c-4f62-9e9a-822b2370b6d1_b81f2774-e594-49a0-a9fc-07df56177c9b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select the cheapest exotic car for two from Beverly Hills at 11 am on March 31 and return on the same day at 5 pm.\nPrevious actions:\n[link] Beverly Hills -> CLICK\n[button] Selected Pick-Up Date 03/21/2023 -> CLICK\n[button] 03/31/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.39, 0.387, 0.429, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e2adf8f1-547d-4671-96c1-4a21a56e135d_a79f5fc4-c635-43b6-8229-911c45a5874c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the upcoming schedule from Otis St@Summer St to City Point of the transit near South Station for today.\nPrevious actions:\n[tab] Schedules -> CLICK\n[span] Transit Near Me -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.13, 0.165, 0.524, 0.184] in the image\nAnd my action is Action: TYPE\nValue: South Station" } ]

{ "bytes": "", "path": "./images/f7b93dc1-2f19-419e-a6e0-a701008c17fa_23f0080b-9e6b-46fe-8c36-a1ea6f957e0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 booking with ticket 123456 under the name James Buck.\nPrevious actions:\n[button] View / Modify / Cancel Reservation -> CLICK\n[textbox] Confirmation Number (required) -> TYPE: 123456\n[textbox] First Name (required) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.166, 0.521, 0.488, 0.565] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

{ "bytes": "", "path": "./images/61fa0552-66ac-4572-95f2-800537cfee7b_121e1a49-f7dc-441e-a922-e668447ccb12.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant with delivery service available 6pm on Mar 25th in Detroit, MI.\nPrevious actions:\n[combobox] Reservation type -> SELECT: Delivery\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: detroit\n[span] MI, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.629, 0.302, 0.648, 0.314] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04ec089f-2ae1-4fa9-bfdf-4dff9ab710ad_804c3901-8299-4c08-b8b9-3ec0bee96528.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 white water rafting experience available in Montana from May 1 to May 7\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.185, 0.463, 0.192] in the image\nAnd my action is Action: TYPE\nValue: Montana" } ]

{ "bytes": "", "path": "./images/74f01011-9bcd-433b-8405-975ca5c3f356_d5c808ea-5cdc-4d6e-b820-2b1a6406910b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.139, 0.287, 0.169] in the image\nAnd my action is Action: TYPE\nValue: Boston" } ]

{ "bytes": "", "path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_e6655c90-5529-4167-9f8b-b3f458a83f8a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[heading] Weddings -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Wedding -> CLICK\n[textbox] Destination -> TYPE: Venice Beach\n[menuitem] Venice Beach, Los Angeles, CA, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.352, 0.422, 0.648, 0.449] in the image\nAnd my action is Action: TYPE\nValue: 100" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_cebfac0b-996a-4c18-b6e8-08e9f22c8751.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[link] Footwear -> CLICK\n[menuitem] Hiking Boots -> CLICK\n[svg] -> CLICK\n[label] Brown -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.322, 0.223, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b307117b-e10c-470f-a85d-968b2e442b19_9800f6fc-8573-4f1d-bbf8-e425e6dc4fdb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coffee shop with wi-fi.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.012, 0.232, 0.019] in the image\nAnd my action is Action: TYPE\nValue: coffee shop" } ]

{ "bytes": "", "path": "./images/265cd715-0607-4ebe-8420-046b1a165239_0a054763-8af3-4199-864e-2582834bd49d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are Jerry Trainor's upcoming projects?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.187, 0.156, 0.198] in the image\nAnd my action is Action: TYPE\nValue: Jerry Trainor" } ]

{ "bytes": "", "path": "./images/11344944-81ef-4fde-82b7-7e9724fc96f1_c8d4e4d8-3926-494b-b1ae-2f1317e4cfd1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of discussion forums for games I own.\nPrevious actions:\n[link] COMMUNITY -> HOVER\n[link] DISCUSSIONS -> CLICK\n[link] Game Forums -> CLICK\n[div] Most Popular (this week) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.226, 0.278, 0.436, 0.293] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0633c328-f1ad-42bd-8aec-7a1883b5898d_b770f788-e3a6-45d2-96df-e3a62380ac46.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 luxury trip deal anywhere to go in spring\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.098, 0.49, 0.486, 0.523] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b74fa2c-3236-45ac-9b4d-ff913112db52_dffd4c05-f61c-46df-8ab9-a2c7da5b03af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking near Sofi stadium that allows to pay with phone.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: sofi stadium" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.261, 0.314, 0.326, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_1c0713cb-8c16-4984-a9d8-a39278a27255.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[listbox] hour -> SELECT: 23\n[svg] -> CLICK\n[listbox] select children -> SELECT: 2\n[listbox] select child age -> SELECT: 5-15\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.269, 0.327, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_36fb74bd-494a-45a8-9dd0-de77fd479449.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[b] Columbus -> TYPE: NEW YORK\n[span] -> CLICK\n[svg] -> CLICK\n[span] Where to? -> TYPE: TOKYO\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.233, 0.103, 0.298, 0.112] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_43dc260b-617f-4482-b487-26b210b2a179.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[button] Make -> CLICK\n[listitem] Chevrolet (101) Chevrolet (101) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Price -> CLICK\n[button] $10,000 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.015, 0.187, 0.125, 0.212] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc98662-4405-4a30-9854-9301c98fdb37_438596ce-4f48-4b91-987f-08aae356b4ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the parking options in Florida to book to enter on may 6 at 5 pm and leave the same day at 6pm?\nPrevious actions:\n[textbox] Search for parking -> TYPE: florida\n[li] Florida, USA -> CLICK\n[textbox] Start Date -> CLICK\n[svg] -> CLICK\n[gridcell] Sat May 06 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.301, 0.191, 0.338] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

{ "bytes": "", "path": "./images/ce34bc61-e3d2-40c8-b02b-b149efc4b115_3b8ad033-513a-4bff-9546-bda8e4d9c844.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a mini van at Brooklyn City from April 5th to April 8th for a 22 year old renter.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: Brooklyn" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.449, 0.83, 0.492] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_67bf019d-0b9f-412d-abd8-1b30480269c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\n[button] Our Company -> CLICK\n[link] Careers  -> CLICK\n[link] Students & Grads -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.547, 0.39, 0.844, 0.449] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d92911a-b208-4d68-ad00-46d2d67f9efa_40384767-ea26-43fd-af97-41d9f4f1070c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] Please enter City, State, or Zip Code -> TYPE: SPRING, TX\n[div] Spring, TX, US -> CLICK\n[link] Click to submit search form -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.028, 0.37, 0.147, 0.385] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_892aaf63-9463-482a-95b8-2a7e145c429f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.474, 0.277, 0.488] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8aedabbf-a7b4-4da7-8eaf-9e159a3ec99b_55d5d079-4d18-450a-8fe7-9eee0ea3d7cb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: review the dinner menu of La Bergamote restaurant in Hell's Kitchen.\nPrevious actions:\n[button] Search -> CLICK\n[heading] La Bergamote — Midtown -> CLICK\n[link] Reservation -> CLICK\n[button] Menu -> CLICK\n[tab] Dinner Menu -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.289, 0.452, 0.311] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b130a70-f03a-4f86-8f2a-44f1b44f3655_e96f5968-a7e3-4e14-90a4-c528877899fa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check my trip for Smith and booking number X899987799.\nPrevious actions:\n[link] Manage trips / Check-in -> CLICK\n[textbox] Passenger last name , required. -> TYPE: Smith" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.149, 0.365, 0.172] in the image\nAnd my action is Action: TYPE\nValue: X899987799" } ]

{ "bytes": "", "path": "./images/34e13beb-0235-41d4-b108-137cc7480904_3785a3c5-0358-4871-bc29-918d4d0b6fc3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] 05:30PM -> CLICK\n[span] Apr 20 -> CLICK\n[gridcell] 21 -> CLICK\n[span] 07:30PM -> CLICK\n[link] 05:30AM -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.902, 0.09, 0.959, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4c3b2a4f-4b54-4724-9d8a-0ea95ab180c5_84e6c79d-94e9-4e04-b994-04ebf807383a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find forum threads which include the name Taylor Swift in the title within last month\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.343, 0.032, 0.402, 0.041] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14f5587e-1353-419e-a381-f92d54ea2059_1429f24c-c8ac-40fb-aaea-d2c48942177c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bio information about Lebron James.\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.04, 0.405, 0.053] in the image\nAnd my action is Action: TYPE\nValue: Lebron James" } ]

{ "bytes": "", "path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_23187c57-820d-46f2-9022-ea9050f9f41d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[span] 12 -> CLICK\n[i] -> CLICK\n[i] -> CLICK\n[span] SEARCH -> CLICK\n[tab] Lowest price first -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.077, 0.291, 0.089, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_58a721bb-f7cf-4303-b880-5014865024b3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new trash can with automated lid that is under $60 and available for Buy It Now.\nPrevious actions:\n[textbox] Maximum Value in $ -> TYPE: 60\n[button] Submit price range -> CLICK\n[input] -> CLICK\n[input] -> CLICK\n[button] Sort selector. Best Match selected. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.078, 0.83, 0.091] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_d49c529a-3bf3-4aa5-a54f-0de7ededcd0c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.726, 0.216, 0.75, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50f1e384-4b63-4827-a670-cd19f5a2c710_9f7bc34f-467d-4f7f-bbea-3cf3193b675d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Schedules -> CLICK\n[searchbox] From -> TYPE: Bay Shore\n[listitem] Bay Shore -> CLICK\n[searchbox] To -> TYPE: Breakneck ridge" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.212, 0.474, 0.233] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b4362dec-6803-415a-a112-819f694b84d9_795d2e6f-3df8-4c64-a81e-fd2558515b2a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Purchase a one meal season dining pass for the Six flags great america\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Great America -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.783, 0.123, 0.843, 0.153] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b8cfdd2c-c48d-4a58-84fb-a88514baf637_83616b73-0718-430d-979e-39e05350f0a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.788, 0.69, 0.906, 0.72] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_578f1744-b335-4030-b230-ae524d9563ac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[textbox] What type of deals? -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.217, 0.284, 0.664, 0.314] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_13f39fc7-d314-4c0a-afec-4a96349324c6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[checkbox] 15 June 2023 -> CLICK\n[checkbox] 20 June 2023 -> CLICK\n[span] 2 adults -> CLICK\n[button] - -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.466, 0.263, 0.475] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_b7887659-969f-4d57-b28d-4c563523c87a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[button] Stations G–K  -> CLICK\n[link] Gloucester -> CLICK\n[link] Plan a trip from this station -> CLICK\n[combobox] To  -> TYPE: NORTH PLYMOUTH\n[em] Plymouth -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.263, 0.352, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7b05f537-af7a-4fd7-972b-123ce5a34294_d59b9cb4-58a1-43ef-885c-cbb45c1d1897.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of flight 6944 on April 6\nPrevious actions:\n[link] Flight status -> CLICK\n[span] Flight number -> CLICK\n[spinbutton] Flight number , required. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.283, 0.365, 0.297] in the image\nAnd my action is Action: TYPE\nValue: 6944" } ]

{ "bytes": "", "path": "./images/cb07d410-75ff-483a-920c-3ce2a295524f_7ba6a708-e79c-4eb7-a274-40acd111584b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 kicker with the most made field goals in the 2022-2023 NFL season.\nPrevious actions:\n[link] Stats -> CLICK\n[link] Field Goals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.068, 0.252, 0.124, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2c19d467-4e44-4c0d-b050-a13823ca545d_9c268783-bff3-4bc7-8657-d596565595c5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hard side Carry-on Luggage used for business in black color.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.032, 0.164, 0.053] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_ac6c5b85-a57e-437d-88c5-ba2902646ae3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[span] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: SHANGHAI\n[div] Shanghai, China -> CLICK\n[textbox] Where to? -> TYPE: SEOUL" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.267, 0.303, 0.656, 0.352] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10593972-6b1d-4b07-ba61-cb56ca0f06e3_ad5f42ba-311a-4ef7-9762-870220d71672.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Lenovo laptop under $800 and create a price alert for $400.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.011, 0.39, 0.034] in the image\nAnd my action is Action: TYPE\nValue: lenovo laptop" } ]

{ "bytes": "", "path": "./images/44bde32f-12bd-4c70-a1a5-37bdadfe872b_6699b58e-e6c0-46f8-8547-370f9a9e6248.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find target branded sprinkles for easter baking\nPrevious actions:\n[link] Categories -> CLICK\n[span] Grocery -> CLICK\n[span] Easter Baking -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.402, 0.178, 0.459, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/851ed4e6-51ee-47ad-a861-a28bdc61a102_077c4e0c-a79b-448b-8bfe-0973673ac73a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the page to schedule a Model X test drive.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.819, 0.054, 0.869, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61fa0552-66ac-4572-95f2-800537cfee7b_a9f12745-aa3a-4825-b3f5-06459fe37511.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurant with delivery service available 6pm on Mar 25th in Detroit, MI.\nPrevious actions:\n[combobox] Reservation type -> SELECT: Delivery\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: detroit\n[span] MI, USA -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.59, 0.271, 0.636, 0.318] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78c52592-76e4-4c45-afd5-f94cf213314e_0a182a4e-608c-4def-8a52-ea6734b8cc01.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play a star wars movie trailer.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.189, 0.008, 0.613, 0.027] in the image\nAnd my action is Action: TYPE\nValue: Star Wars" } ]

{ "bytes": "", "path": "./images/3c9442f9-5542-4395-918a-6551dbba3e3a_5ebe5f2c-a94a-441c-9a90-094aa2e89e97.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Massively Multiplayer games which can be played on VR.\nPrevious actions:\n[link] Massively Multiplayer -> CLICK\n[generic] VR -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.464, 0.392, 0.536, 0.408] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_7cbb3878-36cd-48df-96b4-d28fad34a7c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find premium car in Brooklyn for a day.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Rent A Car -> CLICK\n[button] Pick-up -> TYPE: Brooklyn\n[button] Brooklyn New York, United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.202, 0.571, 0.227] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8cb94647-b0a8-4b8c-b00a-4788ef522b79_0ddfeb2e-f66f-45bf-83fa-9e1e9b969560.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trains from New York to Washington DC leaving on april 18 for 2 adults with disability\nPrevious actions:\n[textbox] Depart Date -> CLICK\n[gridcell] Tuesday, April 18, 2023 -> CLICK\n[img] Add travelers and discounts -> CLICK\n[button] + -> CLICK\n[button] Apply Filters -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.178, 0.254, 0.192, 0.269] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_d7bb0019-1d5f-4911-ad86-8eb40fe86004.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[textbox] Enter your pick-up location or zip code -> TYPE: Manhattan\n[div] Manhattan -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 20 -> CLICK\n[link] 20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.23, 0.891, 0.264] in the image\nAnd my action is Action: SELECT\nValue: 3 00 PM" } ]

{ "bytes": "", "path": "./images/4f069a59-c53b-4efe-bcfb-fc9fd864ea2e_58ba99b5-6faa-44dd-b30f-0e2896aa3265.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rare books and sort the results by auction end time.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: rare books\n[button] Search -> CLICK\n[link] Auction -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.718, 0.085, 0.792, 0.103] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/521d9006-4560-49af-b232-c713d87dd2e2_83bc3946-6fe5-400e-b95a-ba5c990b552c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a group ticket for 20 people in Six Flags Magic Mountain in Los Angeles on Apr 30, add 5 mega meal deals with it. Name the group Crew and check out as James Johnson, [email protected]. It is a family trip organized by Johnson.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK\n[link] Tickets, Passes, VIP Tours  -> CLICK\n[link] Group Tickets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.481, 0.465, 0.508] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a51b649f-15b4-4ce4-936e-0b76efa0dd2d_9e72492a-35b1-496e-9260-942c1aaf9854.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel credits for the passenger Leon Sin with the record locator jcqnhd ans ticket number 1234567\nPrevious actions:\n[searchbox] Search AA.com® -> TYPE: travel credit\n[searchbox] Search AA.com® -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.105, 0.191, 0.895, 0.249] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_397474e3-703a-42e4-b314-d556bd57c30c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[link] Shop -> CLICK\n[link] SHOP ALL CARS -> CLICK\n[div] Best match -> CLICK\n[label] Lowest mileage -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.171, 0.249, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e592a68f-567f-4d6a-a1d6-4166cd129638_d70dfa91-1ad9-4da1-acd8-cc6f2f92b944.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 truck for 10001 zip code on Sunday 11:30 am with flexible dates.\nPrevious actions:\n[button] Reservations -> CLICK\n[link] Budget Truck -> CLICK\n[textbox] US City,State or Zip Code -> TYPE: 10001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.082, 0.172, 0.352, 0.196] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_d345b944-ded9-4a4b-b8c0-e1eaf822f340.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a non-fiction children's book for ages 9-11 on the topic of history in the Hindi language, and add the top book to the cart, if not available choose notify me option and also add the book to new wishlist must buy.\nPrevious actions:\n[select] All -> SELECT: Ages 9-11 (13,217)\n[select] All -> SELECT: Hindi (59)\n[button] Refine results -> CLICK\n[link] Notify me -> CLICK\n[link] Add to wishlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.272, 0.115, 0.716, 0.148] in the image\nAnd my action is Action: TYPE\nValue: Must buy" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_843eff2d-9962-4a8b-9e30-2c0b32f05d88.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[checkbox] Return to a different location -> CLICK\n[searchbox] Return Location (ZIP, City or Airport) (required) -> TYPE: MONTGOM\n[span] Montgom -> CLICK\n[button] Selected Pick-Up Date 03/21/2023 -> CLICK\n[button] Selected Return Date 03/22/2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.271, 0.377, 0.376, 0.406] in the image\nAnd my action is Action: SELECT\nValue: 11 00 AM" } ]

{ "bytes": "", "path": "./images/47072aee-1cb7-436c-8dc6-b2a6d109a100_4f8ec5f7-cb1b-4f13-9702-36f547598319.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 black strollers within $100 to $250.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.023, 0.553, 0.042] in the image\nAnd my action is Action: TYPE\nValue: black stroller" } ]

{ "bytes": "", "path": "./images/122178b3-b5d4-41f0-be38-150ca0e2f5ed_c87db43b-1abd-4fd3-83a9-fe2edd7bfa4e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a black blazer for men with L size and add to wishlist.\nPrevious actions:\n[span] blazer -> CLICK\n[heading] Gender > Category -> CLICK\n[input] -> CLICK\n[option] MEN -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.192, 0.461, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_b10d981a-f02e-4c54-b95c-df1ac0369cdc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[button] Furniture 356 -> CLICK\n[button] + 11 more -> CLICK\n[button] Furniture sets 138 -> CLICK\n[button] Outdoor dining sets 46 -> CLICK\n[button] Add to bag, TÄRNÖ, Table+2 chairs, outdoor -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.945, 0.056, 0.977, 0.091] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4b2bb9e4-8e28-490b-895f-80da5e7e2815_c8d056c9-ef8e-4e07-9631-352f60776776.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get email alerts for a flight from BHZ to EWN leaving on april 30 on the email [email protected]\nPrevious actions:\n[a] BHZ - Belo Horizonte, Brazil -> CLICK\n[textbox] To , required. -> TYPE: ewn\n[a] EWN - Coastal Carolina Regional, NC -> CLICK\n[button] 􎀺 View Calendar: To navigate the calendar, use the... -> CLICK\n[link] 30 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.368, 0.29, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a065d3cb-e588-437b-b2e5-38359e770014_cff4214f-6139-4db1-9095-650cfe5bbd79.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.394, 0.568, 0.412] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_b900e955-2f87-44cd-aff7-61b5ec066da7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find The Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[button] Meetings & Events -> CLICK\n[link] Group Travel -> CLICK\n[link] Group Travel for Students -> CLICK\n[textbox] Destination -> TYPE: washington\n[menuitem] Washington D.C., DC, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.326, 0.48, 0.342] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c731e6d1-7194-4d16-a6a8-f5fc9be56a55_898acdb2-6360-4662-92d3-040ee591da52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a pop rock album CD from the United Kingdom that was released in 2016, is between £15 and £20 and in perfect condition.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.465, 0.0, 0.557, 0.03] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/15a0ffe5-8462-4a8e-8938-91b05a40756f_c8c86f76-7509-46a1-bb49-dc9b4b8a0664.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a new address to the account. The address is 2983 Marietta Street, APT 2. Business name is Buck.\nPrevious actions:\n[span] 171 2nd street -> CLICK\n[textbox] Add a new address -> TYPE: 2983 Marietta Street" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.301, 0.442, 0.337] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_654b35b4-a888-4328-a473-69f63632a8e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[button] Add Age -> CLICK\n[button] Add Less than 1 -> CLICK\n[button] Add 1 -> CLICK\n[button] Add 2 -> CLICK\n[button] Find Hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.59, 0.214, 0.601, 0.221] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/298c854d-2987-498b-b43e-6a6452fb11c7_5a234296-fb23-449c-877a-cbc770096ab7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[button] London England -> CLICK\n[circle] -> CLICK\n[link] Unique Experiences -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.026, 0.371, 0.107, 0.382] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/401c4e6f-6b0b-47b4-8157-92d7ca468bbc_e0fd3f28-3f04-455d-8bde-a480f0ec1b0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[heading] CAR -> CLICK\n[combobox] Enter pick up city, airport name, or airport code. -> TYPE: Brooklyn Central\n[div] Brooklyn - Central (New York), US -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.181, 0.158, 0.209] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fd0e4520-b47b-4a24-9b21-d10e68c42472_e92228fd-d6ce-45f2-9dfd-42fc9c17c776.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK\n[gridcell] Friday, April 14, 2023 -> CLICK\n[combobox] Hour -> TYPE: 12\n[combobox] Minute -> TYPE: 00\n[combobox] AM or PM -> SELECT: PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.135, 0.169, 0.353, 0.2] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c44cfc8c-abea-4eef-838a-ba3a2716f8fa_70b1e9a6-c1b1-42d3-8b25-a284ee385e10.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK\n[input] -> TYPE: 25000\n[input] -> TYPE: 5000\n[input] -> TYPE: 12" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.16, 0.363, 0.265, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/059327ab-e26e-4af6-9063-f58c50ecd2d2_b567c00f-f405-4acf-999c-13b2ccdc84f4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the schedule and maps for the orange line\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.24, 0.397, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_7ace8414-2b72-436a-84f4-f81ce2d5ecc0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Sports Bras -> CLICK\n[div] Size -> CLICK\n[link] S -> CLICK\n[div] Filter -> CLICK\n[RootWebArea] Women's Sports Bras | Under Armour -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.643, 0.102, 0.655] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78e346d2-3c80-4243-b921-ed35c4c4d923_ca9851d3-60f2-424e-9945-db5862f53d2c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track an order using the order number of 456481897 and phone number of 8984486417.\nPrevious actions:\n[link] Order Tracker -> CLICK\n[textbox] Order number EXAMPLES: ECEA12345, 01234567 -> TYPE: 456481897" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.241, 0.908, 0.27] in the image\nAnd my action is Action: TYPE\nValue: 898-448-6474" } ]

{ "bytes": "", "path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_4e3a9490-e833-4e4c-957f-e0556fb8e96c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find The Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[link] Group Travel for Students -> CLICK\n[textbox] Destination -> TYPE: washington\n[menuitem] Washington D.C., DC, USA -> CLICK\n[textbox] Start Date -> CLICK\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.164, 0.478, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_20a9bb0e-d885-42ee-bfb2-0a0ab6c13706.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[div] Goa -> CLICK\n[checkbox] 25 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.444, 0.263, 0.453] in the image\nAnd my action is Action: CLICK" } ]