Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_6de1827e-c854-41bf-86ca-4ebe2a33339c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\n[span] mens black hoodie -> CLICK\n[div] Size Range -> CLICK\n[link] Big & Tall (5,552) -> CLICK\n[div] Price -> CLICK\n[link] $25 to $50 (2,237) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.132, 0.986, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aaade1d2-3a7b-4373-be01-ef98ed86288e_a18e6348-cedb-4bbb-9fb5-a4a982378a3e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Search for anything -> TYPE: trash can automatic lid" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.049, 0.643, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_76bc3358-5f1f-416e-acf7-b934c7231a1a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[div] Send a physical card through the mail. -> CLICK\n[textbox] * Amount: -> TYPE: 50\n[button] VIEW ALL -> CLICK\n[img] -> CLICK\n[textbox] To: -> TYPE: John" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.788, 0.191, 0.99, 0.203] in the image\nAnd my action is Action: TYPE\nValue: James" } ]

{ "bytes": "", "path": "./images/7c2ab1ed-54b7-4316-8b2f-d7467e01b540_85c9acad-b16f-4c31-bc8b-86e56639c5e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\n[div] Madurai, Tamil Nadu, India -> CLICK\n[path] -> CLICK\n[button] Search -> CLICK\n[svg] -> CLICK\n[label] Air India -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.251, 0.074, 0.263] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/164cf025-e767-4781-930d-5bd46ad2c4c1_e4018dc3-e21a-46c7-b1c3-4add061eb3ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Resy Staff Favorites in Seattle?\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.08, 0.026, 0.151, 0.085] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0db002f6-db7d-4382-9c0d-8f5cef2afa17_c4d4d763-c6fa-47ba-8efb-eb4fb52f41dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 detailed uses of Anuall Pass for 2023 on the USGS Online\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Passes -> CLICK\n[link] Annual Pass -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.05, 0.54, 0.95, 0.579] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/50f1e384-4b63-4827-a670-cd19f5a2c710_68e483d8-9bfd-4c8c-9327-82577a11be18.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.0, 0.445, 0.069] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a632871-a6a8-40fd-b48f-6fea49cf48da_3f3803f1-9aa7-4da7-807e-d31136723db3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the NBA score board on March 11th\nPrevious actions:\n[link] NBA -> CLICK\n[link] Scores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.698, 0.176, 0.717, 0.189] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cbfa5c92-41cb-4481-97b2-9fb41298be13_50f2d198-a0f4-4230-9b83-ed557dc56d79.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wireless bra in size xxs or s, add one brown and one purple color to the cart and view the total cart value.\nPrevious actions:\n[svg] -> CLICK\n[heading] Wireless Bra (Ultra Relax) -> CLICK\n[checkbox] BROWN -> CLICK\n[button] ADD TO CART -> CLICK\n[button] CONTINUE SHOPPING -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.815, 0.138, 0.843, 0.153] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc98662-4405-4a30-9854-9301c98fdb37_fef9b6f7-061e-4b76-b684-5505c9d7eb70.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.185, 0.304, 0.195, 0.315] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4c21e9f-fbd7-4c45-a282-de06ae3b73c5_4fc94d2c-6706-4bf3-8e0c-3c65f2f15b5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Thai restaurant and get notified when they have an open table between 5 to 7 PM\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: thai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.183, 0.102, 0.691, 0.133] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f640279-bd9d-45ae-b3fc-43338977e2c1_95f17546-5fa4-44c6-a51c-d57bf20770b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of Museums in New York City.\nPrevious actions:\n[link] CITIES -> CLICK\n[link] NEW YORK CITY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.258, 0.36, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_5de17e26-948b-45a1-8b27-0a3a8a79b72d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Departure station, London selected. -> TYPE: edinburg" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.114, 0.117, 0.326, 0.162] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_4aaa493a-ae2e-4cb4-8081-485b49488432.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[img] -> CLICK\n[link] Produce -> CLICK\n[link] Fresh Fruits -> CLICK\n[span] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.754, 0.252, 0.815, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_d20e2519-15c9-4c7d-943b-75513d98fbb4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] To -> TYPE: little caribbean\n[listitem] Little Caribbean, Brooklyn, NY, USA -> CLICK\n[button] Open Travel Preferences modal. -> CLICK\n[combobox] Minimize my -> SELECT: Walking\n[button] Done button - Press enter key to submit travel pre... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.383, 0.359, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/883fc533-d267-4eeb-8ccd-fe77bc28cd9b_3d415174-370e-47c0-bb34-e9e442c78a84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Discover Katy Perry and add bookmark to it and view all tracks.\nPrevious actions:\n[link] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.906, 0.035] in the image\nAnd my action is Action: TYPE\nValue: Katy Perry" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_7e1f4374-8e17-49c2-be93-d6bba3d0ec0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[link] Categories -> CLICK\n[link] Grocery -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.323, 0.316, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_dc06c01d-2251-4bed-b48d-e4f0c2639a7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[option] New York City area (NYC) -> CLICK\n[textbox] To -> TYPE: Aruba\n[option] Aruba (AUA) -> CLICK\n[span] 1 -> CLICK\n[button] return Friday, May 5, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.719, 0.234, 0.853, 0.256] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/694f3b5c-8ee4-45c1-bb7c-b5377c366096_3132d536-bc3a-4ad1-a326-4db8b75dc6ad.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.273, 0.691, 0.322] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d070774f-9ca2-43c0-a7d0-221697791cf0_a848bcb3-b6ff-4c1a-9a10-e66ec68c5196.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a place with a good swimming pool that charges between $200 and $300 per night.\nPrevious actions:\n[img] -> CLICK\n[span] Filters -> CLICK\n[textbox] min price $ -> TYPE: 200" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.526, 0.198, 0.739, 0.209] in the image\nAnd my action is Action: TYPE\nValue: 400" } ]

{ "bytes": "", "path": "./images/8eef04e2-3d51-4a0e-84f2-db017a69050b_442b805f-3033-4997-a3d7-ef6375d4f79e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the Promo Code for Spring Break Savings and packages.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.281, 0.06, 0.352, 0.085] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b390b60-5c04-40ee-a5af-353def43ffbc_7dbbe8fd-aead-477a-92b2-485de3aec565.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 japanese restaurants in Fresno with online delivery.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.001, 0.417, 0.035] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_0ab87d28-e48a-4d69-abc3-8606181a83dc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[searchbox] Please type your destination -> TYPE: mexico city\n[option] Mexico City - Benito Juarez Intl, MX (MEX) Mexico -> CLICK\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Low to High\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.496, 0.331, 0.508] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/978376c1-8545-4160-81d5-722bdea60434_97e6816f-d2a6-4372-95a4-4801d088446e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Start the process to sign up for CVS ExtraCare\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.022, 0.194, 0.042] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bd32af6e-9fae-4968-b3e6-d143f148f5b8_45e135d4-8e5f-4562-bd2d-e03101466691.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 copy of the Gorillaz first studio album.\nPrevious actions:\n[combobox] Search artists, albums and more... -> TYPE: gorillaz\n[link] Gorillaz Gorillaz Artist -> CLICK\n[link] Gorillaz -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.695, 0.104, 0.832, 0.118] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00e83fae-f2f0-48ab-912c-32c03982642b_a0430d87-5a11-4409-8dc3-fff996002ea6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show computer game reviews sorted by score.\nPrevious actions:\n[button] Reviews -> CLICK\n[link] Game Reviews -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.425, 0.191, 0.55, 0.217] in the image\nAnd my action is Action: SELECT\nValue: PC" } ]

{ "bytes": "", "path": "./images/126b4604-8b04-4eb1-9027-266631c96f01_3f13fb42-633d-48a5-8d77-afcf9de93569.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 an outdoor table for 3 people at a Los Angeles restaurant for 5:00 PM on April 7th\nPrevious actions:\n[button] Los Angeles -> CLICK\n[link] La Cha Cha Cha -> CLICK\n[div] Today -> CLICK\n[button] April 7, 2023. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.199, 0.192, 0.224] in the image\nAnd my action is Action: SELECT\nValue: 3 Guests" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_b0b1bb1a-52a6-45bd-b8bc-b97ddb5f9e5b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[span] Automatic -> CLICK\n[button] Back to all categories -> CLICK\n[heading] Distance & Shipping -> CLICK\n[button] $99 Or Less -> CLICK\n[menuitem] Free to home or store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.281, 0.249, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_2a8e8987-2a95-4d21-a7b6-11eed00c07d8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[div] Thu, Apr 20 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 6:00 PM\n[combobox] Drop off time -> SELECT: 11:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.193, 0.923, 0.245] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_d8059cb9-a62c-4a11-811c-e185798ece8a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[link] Careers -> CLICK\n[link] Open Jobs -> CLICK\n[span] -> CLICK\n[button] Country -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.479, 0.218, 0.502] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2b1d94b-5309-4c9b-bcdd-8048172af7b5_e0bfc000-6c7f-49c9-bfea-873bbac85dab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 foldable over-ear headphone under 35 USD in certified refurbished condition with lowest price + shipping.\nPrevious actions:\n[button] Condition -> CLICK\n[link] Certified - Refurbished -> CLICK\n[button] Sort: Best Match -> CLICK\n[link] Price + Shipping: lowest first -> CLICK\n[button] Features -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.704, 0.451, 0.868, 0.481] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_c2cf99e0-83fb-4746-9a9d-7b151d9c60b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[LabelText] Sell My Car -> CLICK\n[textbox] Enter license plate -> TYPE: YAW639\n[combobox] state -> SELECT: LA\n[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 70726" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.224, 0.096, 0.246] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/551ab381-5bfe-4491-9602-0b0c584d1346_51d5a5f6-926f-4a16-98db-bffa5b3c9436.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Give me the IMDB recommendations of what to watch.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.008, 0.144, 0.029] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_478e1cc4-76bf-46aa-beb1-599a90f1a9b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\n[dt] Customer Ratings -> CLICK\n[i] -> CLICK\n[button] APPLY -> CLICK\n[span] Compare -> CLICK\n[span] Compare -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.906, 0.59, 0.984, 0.604] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d0d6b0ed-82e4-4ba7-9a9b-7b874dacf19c_cba371fd-cedd-44b5-bc73-f66ef9af18f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the map of Cleveland's animal shelters.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.001, 0.417, 0.033] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/73de3022-2f58-4bd4-8de6-4a201f2bbc98_f0b16e02-0be2-4f9e-9cf5-c08950f7b267.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 if there are tickets availabe for the Hamilton musical in Richmond, VA.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.226, 0.782, 0.269] in the image\nAnd my action is Action: TYPE\nValue: Hamilton" } ]

{ "bytes": "", "path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_86f0129f-5ca2-437f-ace5-ada6f8fda4ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 closest parking spot to the Orlando Magic at Brooklyn Nets event, happening in Barclays Center, to enter after 3 pm and exit after 5 pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: barclays center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK\n[p] Orlando Magic at Brooklyn Nets -> CLICK\n[select] Sort by Distance -> SELECT: Sort by Distance\n[combobox] Start Time -> SELECT: 3:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.27, 0.384, 0.307] in the image\nAnd my action is Action: SELECT\nValue: 5 00 PM" } ]

{ "bytes": "", "path": "./images/14b5885e-5454-465f-92bf-d8f7315c4a46_dfd559fc-eb25-4cda-9a91-8c60b0bbce36.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a ticket from Abbotsford to Sheboygan on March 26, 2023.\nPrevious actions:\n[button] Explore -> CLICK\n[link] Route map -> CLICK\n[textbox] Pick an origin Pick a destination -> TYPE: Abbotsford" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.297, 0.168, 0.312] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_c6851a43-51ca-4a93-b937-d560a9c4ce56.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest return tickets from Leeds to Sheffield leaving at 8:30 am on Mar 25, 2023 and returning at 23:00 pm on same day for 1 adult and 2 child.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: Leeds\n[span] Leeds -> CLICK\n[span] Sheffield -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.194, 0.194, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d87b507-14dd-4903-a131-fa089499ccb5_8321c8e6-a5b7-45a2-b38e-6d0b5fba0bf0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight From Dublin To Athens Greece for 1 Adult that leaves on April 1 and returns April 5th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.406, 0.104, 0.713, 0.115] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7b5b2188-afd4-4279-b738-c37a1b5f2142_fcec7df7-3669-4c5f-8162-19849487f0c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 list of available opportunities for a volunteer event for year 2023\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Volunteer -> CLICK\n[link] Become a VIP and Volunteer with Us Today!› -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.339, 0.178, 0.416, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_e97577ad-f25d-42c2-98a2-74fda1a588c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] Confirm email address -> TYPE: [email protected]\n[input] -> TYPE: 1111111111111111\n[textbox] Address 1 -> TYPE: the home of joe bloggs\n[textbox] City -> TYPE: new york\n[textbox] Postcode/ZIP code -> TYPE: 10001" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.588, 0.95, 0.647] in the image\nAnd my action is Action: TYPE\nValue: new york" } ]

{ "bytes": "", "path": "./images/b28e6a37-6e9c-46bb-8012-18ca742a521f_8e52b340-62a8-48f8-8d18-ce80711db210.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Explore Durban in Africa and book a flight from Doha for 2 adults and 1 infant, on May 28, book the first flight in economy comfort.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: doha\n[strong] Doha -> CLICK\n[textbox] Depart date please enter date in the format dd spa... -> CLICK\n[gridcell] 28 May 2023 -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.765, 0.188, 0.942, 0.213] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_4b90093f-4363-4c73-8a02-87ab5e4686d0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[button] Type -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Flavor -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.963, 0.013, 0.988, 0.039] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_10ce4c27-0114-485f-b18a-e5fed2af6d57.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.504, 0.656, 0.625, 0.679] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/51b75f3d-b293-495d-a5a0-8ed5cc8270a2_4208985a-6f68-4493-a1fb-3abbe9503a0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Make a reservation for 2 guests on april 21 at noon in a restaurant in Austin that is new on resy\nPrevious actions:\n[path] -> CLICK\n[button] Austin -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.601, 0.884, 0.649] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e7b05d4-7dfb-4345-af2b-3e1dcd1c2ea2_dd2bc1cb-54ad-4246-8005-f7287aa435c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a map with charging stations in London.\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/fcb50c4e-a89e-4f18-b7c0-423295e7c298_016bf36a-0f5f-4e4b-a312-232d7232cea2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 certified pre-owned front-wheel drive Jeep, Compass model car with single owner and the lowest mileage within 500 miles of zip 59316.\nPrevious actions:\n[menuitem] Buy -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.11, 0.205, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/48ca542f-5346-40b9-b586-9294a2f64519_93b28944-f841-4fa4-a303-7c39d9c73332.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Like a game mix album.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.321, 0.004, 0.561, 0.018] in the image\nAnd my action is Action: TYPE\nValue: game mix" } ]

{ "bytes": "", "path": "./images/13f1648c-9de8-497d-bed3-02096206dc5f_e62362e7-8e6f-4005-a005-b8bdb6c3d5bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add two pairs of women's Pink sweet pants in XXL size to your cart and view your cart.\nPrevious actions:\n[link] WOMEN -> CLICK\n[tab] Bottoms -> CLICK\n[link] Pants -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.265, 0.299, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_85649359-30cc-4848-9453-3f2577813005.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[link] Fishing -> CLICK\n[menuitem] View All -> CLICK\n[label] Ice Fishing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.205, 0.222, 0.215] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90a0f029-c1af-4dd7-8ccd-c4c2a74e8731_76bcc527-fafd-4e31-b315-fac7ab42f06f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 basic economy flight + hotel for an award travel from las vegas to san francisco leaving and returning on any date on april for 1 traveler and one room\nPrevious actions:\n[link] Award travel -> CLICK\n[span] Flight + hotel -> CLICK\n[label] Basic Economy -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: las vegas\n[span] Las Vegas, NV -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.762, 0.622, 0.782] in the image\nAnd my action is Action: TYPE\nValue: san francisco" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_2911643c-507a-480b-b496-9cfb4b77d8f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[textbox] Date use format: 01-Apr-23 -> CLICK\n[rect] -> CLICK\n[link] 26 -> CLICK\n[polyline] -> CLICK\n[span] Youth -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.196, 0.291, 0.223] in the image\nAnd my action is Action: SELECT\nValue: 16" } ]

{ "bytes": "", "path": "./images/60e1de47-efdb-47e8-935f-2ac38af1ead3_638420e6-97e6-466f-a168-587f17749282.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Prometheus movie to watchlist.\nPrevious actions:\n[textbox] Search IMDb -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.189, 0.007, 0.613, 0.025] in the image\nAnd my action is Action: TYPE\nValue: Prometheus" } ]

{ "bytes": "", "path": "./images/d88f70e8-9b66-4f08-9aa4-e49375b14920_23546e33-8ba3-46f1-b1b7-f8e0acf5ebc2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for places to stay in Santa Fe, New Mexico for a weekend starting on Jun 16th for 3 guests and 2 rooms.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Santa Fe\n[span] Santa Fe, New Mexico, United States -> CLICK\n[div] 16 -> CLICK\n[div] 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.904, 0.268, 0.92, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_bc008675-e4f9-468b-a15a-02d622cc6f06.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\n[link] Smart Home -> CLICK\n[link] Smart Lighting -> CLICK\n[button] Indoor Lighting (7) -> CLICK\n[checkbox] Strip Light (3) -> CLICK\n[button] Sort By: Best Match -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.795, 0.177, 0.991, 0.199] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ce76343-dafe-4cf6-9bfd-918834d0c641_07e02302-548c-4332-9e6c-188c7e6baade.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated fast responding phone repair shop for data recovery in Houston.\nPrevious actions:\n[textbox] Near -> TYPE: houston\n[span] Houston -> CLICK\n[button] Fast-responding -> CLICK\n[radio] Data recovery -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.518, 0.118, 0.612, 0.137] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_e7444f63-7c77-4462-a723-ab00e729c46d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[button] 15 -> CLICK\n[combobox] Time -> SELECT: 10:00 AM\n[combobox] Party size -> SELECT: 4 guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.872, 0.213, 0.894, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d29e8a14-ee66-4330-b282-09cb1955aad0_5600ca04-7659-49c0-b34a-7c7de417fea1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 weekly ad in List View.\nPrevious actions:\n[button] Savings & Memberships -> CLICK\n[link] Weekly Ad -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.661, 0.097, 0.714, 0.121] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/05238c0f-514f-4af2-bc4c-f7521d649825_5a806dc6-8254-4dee-a2cc-c981755d5bb3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Dota 2 game and add all DLC to cart.\nPrevious actions:\n[textbox] search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.08, 0.93, 0.095] in the image\nAnd my action is Action: TYPE\nValue: Dota 2" } ]

{ "bytes": "", "path": "./images/fca09c13-5e6c-49d5-b3ee-b620a70b19f5_e3e842b2-02c0-4a19-8fbc-05f8de17a805.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.195, 0.734, 0.829, 0.744] in the image\nAnd my action is Action: TYPE\nValue: Tokyo" } ]

{ "bytes": "", "path": "./images/e638beb6-059f-40ea-8653-929221e997db_e478223e-6ef8-445f-9130-d6f6645f4f9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a comprehensive health screening for women in 10003.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.131, 0.41, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_b442079b-5565-4361-b7f3-666110df8ba4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights multiple cities -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.408, 0.29, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/277bdab6-e924-45dd-ba26-d659d864d671_b7d8a0ab-d6fb-4d63-aef6-6a71b72079ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 different flavor dog treats and one dog food with lowest price to cart from Safeway.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.225, 0.011, 0.776, 0.063] in the image\nAnd my action is Action: TYPE\nValue: dog treats" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_2d3970c4-2b0a-43cd-bd19-103d5bcb4dd3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[span] Enter an Address or Venue to find parking -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.228, 0.592, 0.25] in the image\nAnd my action is Action: TYPE\nValue: stewart hotel" } ]

{ "bytes": "", "path": "./images/8e1a344d-a27b-4613-8863-7afad0829b23_39d3c8ab-ef00-491e-87fa-2c87e399e835.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest washable blue rug under 2'x3' size.\nPrevious actions:\n[link] Shop by Category -> CLICK\n[link] For the Home -> HOVER\n[link] Rugs -> CLICK\n[link] Washable Rugs Washable Rugs -> CLICK\n[span] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.34, 0.113, 0.35] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_f4d5366b-3609-465c-a8e6-285b40935b03.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 if 5pm is available to book a indoor reservation on 31st of March in Matthews Winery for 5 people\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Matthews winery\n[span] Matthews Winery -> CLICK\n[link] Book now Indoor Reservation, Two-hour indoor seati... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.434, 0.508, 0.464, 0.54] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b627cbc-a45e-4f7e-9d02-bfca1a41070a_e60b21c2-3627-44e4-9b13-975c218d9d1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details for a Times Square parking lot that is wheelchair accessible.\nPrevious actions:\n[textbox] Search for parking -> TYPE: Times Square\n[li] Times Square, New York, NY, USA -> CLICK\n[button] Filter -> CLICK\n[checkbox] Wheelchair Accessible (12) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.503, 0.458, 0.554] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c3e841d5-4624-44cb-a8b5-897b9aa3ef9b_b08451d0-5987-4e39-a51a-6ff6fb83cf22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a single day pass to Six Flags, Magic Mountain.\nPrevious actions:\n[button] Go! -> CLICK\n[link] Tickets, Passes, VIP Tours  -> CLICK\n[link] Tickets & Passes -> CLICK\n[span] Buy Now > -> CLICK\n[button] Buy Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.589, 0.215, 0.777, 0.229] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_bebe4a89-a653-4ad1-8562-d2d151c0fa90.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] Columbus Easton -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.67, 0.265, 0.847, 0.295] in the image\nAnd my action is Action: TYPE\nValue: 08817" } ]

{ "bytes": "", "path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_ae649734-cc80-41d9-a091-a527d4701cf0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[span] Venice Treviso -> CLICK\n[div] May -> CLICK\n[generic] 9 -> CLICK\n[generic] 16 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.862, 0.405, 0.922, 0.442] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/70b3ef5b-d900-44cf-9b62-9ecece97954c_1387e66f-88ee-4ac8-8cc8-363de89dd7bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find climbing gear and sort the results by price high to low.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.128, 0.079, 0.181, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dc0190c-57cc-4c0f-b939-c0617102166e_7c115bfc-020b-4e0e-a063-b947e23e0649.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add to favorites a cruise from San Francisco to the Panama Canal departing Oct 2024\nPrevious actions:\n[span] Sail To -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.72, 0.47, 0.863, 0.502] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f118238f-ef8f-4b63-9159-a81e981ef46e_aa2386b0-24c1-4193-add3-fb6646cfc330.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 decorative LED Candles to the cart.\nPrevious actions:\n[link] Products -> CLICK\n[button] Lighting -> CLICK\n[link] Decorative lighting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.314, 0.229, 0.41, 0.274] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36f2e415-356b-4e44-9ab1-6c3054d4de1f_6fea70db-8ef9-4ac9-b662-4ee385b4af59.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 if cars are available for tomorrow at Elevated Escape in North Carolina.\nPrevious actions:\n[textbox] Pick-up location -> TYPE: Elevated Escape\n[div] Elevated Escape -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.447, 0.132, 0.553, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1f4e4f7-3fb0-4aeb-8123-4882a1f39cb2_8a5133cf-2c25-469b-97f9-4451368b96a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the new arrival of kids graphic t-shirt for 13 years old boy\nPrevious actions:\n[link] KIDS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.075, 0.257, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_cd172bd3-2207-4a53-99df-1609f3cf87a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[button] Get cheapest tickets -> CLICK\n[span] Continue -> CLICK\n[listbox] Direction -> SELECT: Forward facing\n[listbox] Position -> SELECT: Window\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.747, 0.185, 0.925, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/747429fa-7dac-4ab0-b604-13cb9bf787fe_74c03d0b-0836-477c-ad20-05abb250cd56.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest unused wireless Logitech Keyboard under $70.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless keyboard\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.7, 0.158, 0.71] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_88c687c0-458c-43e5-b265-561b2efdf331.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[select] Alabama -> SELECT: New York\n[textbox] Zip Code -> TYPE: 10001\n[textbox] (###) ###-#### -> TYPE: 888888888\n[textbox] Email Address -> TYPE: [email protected]\n[textbox] Email Address -> TYPE: [email protected]" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.268, 0.685, 0.313] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_8ca47df3-bfb0-474d-bb4c-705ed1bbf199.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless printer" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.542, 0.017, 0.592, 0.053] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_d61748b4-b9f8-457e-bc90-a8a516c8e12a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[link] Homes -> CLICK\n[searchbox] Please type your destination -> TYPE: MANILA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.087, 0.405, 0.112] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6fc427d-c2fd-4f1b-8f7d-8bb8647e63e9_09bfdb44-76c7-465e-ba08-dab8c6dc2e1b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find deals in New York.\nPrevious actions:\n[a] City Pages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.571, 0.176, 0.712, 0.191] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61d28a34-cc8e-46a9-b41d-c95933de2214_8f549f9d-9187-4482-bc70-2a244ffd8c8f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all time popular drop c rock tab of beginner difficulty\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Beginner 554,088 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.283, 0.153, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/562d8516-e1fa-464b-9bb1-542fe818c721_205dfea0-1032-44c3-8c8d-3b2e3c7d1daf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest copy of King of Tokyo on GeekMarket that ships to Canada.\nPrevious actions:\n[button] Shopping -> CLICK\n[link] GeekMarket -> CLICK\n[combobox] Search Board Games... -> TYPE: king of tokyo" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.201, 0.034, 0.485, 0.056] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_f8c7c15b-6d3a-4e6c-b1af-f569d552ca2b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[div] -> CLICK\n[div] -> CLICK\n[span] 36 -> CLICK\n[button] 34 -> CLICK\n[button] Confirm Seats -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.693, 0.295, 0.926, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5d47068-b773-4061-b7ba-17bd25e88e06_e28c2d70-46de-45d6-b3ed-20ea099217a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Save two deals and offers for US.\nPrevious actions:\n[button] Deals -> HOVER\n[button] Deals -> CLICK\n[link] US Deals -> CLICK\n[button] Save Now -> CLICK\n[button] Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.061, 0.749, 0.088] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dc2aa3f8-eda0-455b-98dc-adc56089259a_89f2b1aa-4e07-4d42-858c-a415206f1d5a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.545, 0.619, 0.572] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/f4555944-010b-48d2-a4cb-b7103c686bac_b5539183-9fb0-420f-a745-564979f75b5f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the movie which won the jury prize in Cannes 2022, add the director of the movie to the new list named director and add \"to watch\" in the description of that list.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.075, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2130e7-1108-4281-8772-25c8671fb88e_049acc7d-e917-45d0-99ed-6c273ee77075.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] History -> CLICK\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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.745, 0.24, 0.973, 0.266] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_01cf52dc-6cba-4c51-a75d-5f2a7730b67c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[span] -> CLICK\n[select] 1992 -> SELECT: 2010\n[button] Close dialog -> CLICK\n[select] 2024 -> SELECT: 2010\n[combobox] Sort By -> SELECT: Price: Low to High" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.899, 0.172, 0.969, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/85706225-aa42-43c1-8cfa-8696118698a2_39c6496a-5532-4d83-8d37-d129f42d5ea2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of flights from Los Angeles area to Boston area tomorrow\nPrevious actions:\n[button] Travel Info -> CLICK\n[link] Flight Tracker -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.197, 0.202, 0.397, 0.247] in the image\nAnd my action is Action: TYPE\nValue: Los Angeles" } ]

{ "bytes": "", "path": "./images/50c13c64-4c9b-4f55-84f6-65ae443848a2_a360bd43-6df1-447e-a026-95d0a8b1cac9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated romantic summer vacations in Spain\nPrevious actions:\n[textbox] When? -> CLICK\n[li] Summer -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.658, 0.452, 0.718, 0.474] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_6c38c5ba-28c2-45c8-bc24-96c1388d7b6e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Customer Service -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.475, 0.887, 0.491] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_b28fa573-26af-4855-b623-b308ad84fd80.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the most popular Women's Athletic Shoes.\nPrevious actions:\n[span] Shop by Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.149, 0.159, 0.158] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cac423-4be9-4f74-9031-7cef1fe60ef9_acffa63c-d008-44bd-9e78-eb0247cd85cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fuel economy for a 2005 Toyota Corolla\nPrevious actions:\n[link] Price New/Used -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.443, 0.12, 0.49] in the image\nAnd my action is Action: SELECT\nValue: 2005" } ]

{ "bytes": "", "path": "./images/14d4edf5-e5ca-40e8-8e5d-77068a22c32c_52743c90-fd78-45d7-bfbe-99eb4ee84c1b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the scores of the premiership on 19th of March.\nPrevious actions:\n[span] Scores -> CLICK\n[heading] SOCCER -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.188, 0.065, 0.267, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8df744ef-83ee-4472-9fb0-25bd9cf9dcd9_4fc61431-330e-4811-a880-f1d5e77c1642.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ten-ride ticket from Washington to New york starting from April 5\nPrevious actions:\n[tab] Rail Passes -> CLICK\n[link] EXPLORE MULTI-RIDE PASSES -> CLICK\n[textbox] From -> TYPE: WASHINGTON\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] To -> TYPE: NEW YORK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.327, 0.169, 0.559, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5cb859d-8460-4b27-b6c9-d6fea6de9889_07da8bf9-a101-42cb-865c-597a7150f981.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 kids 13Y size t shirts and add 3 to cart.\nPrevious actions:\n[link] KIDS -> CLICK\n[link] T-Shirts -> CLICK\n[gridcell] Size -> CLICK\n[label] 13Y(160) -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.041, 0.267, 0.256, 0.473] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4baa4918-3312-4b9b-9506-333057d6856b_71adc0ae-641d-4097-929f-2698381759d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 coupons and deals in New York.\nPrevious actions:\n[link] Coupons -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.493, 0.01, 0.789, 0.042] in the image\nAnd my action is Action: TYPE\nValue: new york" } ]

{ "bytes": "", "path": "./images/58f811fd-0f17-430b-befc-885605e13e41_94d5fd23-1ec9-4921-8aeb-0f577f753252.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Cancel an order with order number X123456 of Harry Potter Box Set as not available at address.\nPrevious actions:\n[input] -> TYPE: James Smith\n[textbox] Email address used to place your order * -> TYPE: [email protected]\n[textbox] Order number * -> TYPE: X123456\n[textbox] Date you received your order (DD/MM/YY) * -> TYPE: 08/04/23\n[textbox] Please cancel my order for the following products ... -> TYPE: Harry Potter Box Set" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.235, 0.549, 0.759, 0.577] in the image\nAnd my action is Action: TYPE\nValue: Not available at address" } ]