Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/d311891e-82b9-4a16-ab46-6af92f054f94_9a9fafc5-8b22-4d00-a724-188153f1c7b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.691, 0.024, 0.987, 0.046] in the image\nAnd my action is Action: TYPE\nValue: Matthews winery" } ]

{ "bytes": "", "path": "./images/3d76a0fc-7ba9-4a74-ac52-db0cea359553_30aa0a88-4767-45c6-8fa8-eb179e6e0cb6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced round trip flight with hotel on May 2 from Kathmandu, Nepal KTM to Shanghai, China PVG and return on May 5. Book a double room and check out with the default flights.\nPrevious actions:\n[link] Flight + Hotel -> CLICK\n[textbox] Where from? -> TYPE: KATHMANDU\n[div] Tribhuvan Intl Airport (KTM), Nepal -> CLICK\n[textbox] Where to? -> TYPE: SHANGHAI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.272, 0.363, 0.661, 0.394] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_4f65d11e-ef5e-43c6-8f29-3bb466f8c02a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] -> CLICK\n[svg] -> CLICK\n[span] Where to? -> TYPE: TOKYO\n[span] -> CLICK\n[div] Multi-city -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.669, 0.221, 0.906, 0.26] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_1c73847e-41c9-4e2b-ab4d-f9a8c2156508.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Baggage info -> CLICK\n[link] Baggage fee calculator -> CLICK\n[combobox] From -> TYPE: columbus" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.07, 0.529, 0.309, 0.561] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f9723022-04b9-4778-ad33-cf54eac3d393_a8388b0d-2e41-4cf0-ae0b-be1a72f3df55.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events starting from April 1, 2023 within 100 miles of New York and see who are going in the top listed event and follow all of them who are going.\nPrevious actions:\n[combobox] SEARCH RADIUS -> SELECT: 100 km\n[button] APPLY -> CLICK\n[button] From today -> CLICK\n[Date] FROM -> CLICK\n[Date] FROM -> TYPE: 04/01/2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.224, 0.296, 0.287, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_5da862ec-0736-4eef-82ff-2920815a68b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[link] Pool (18) -> CLICK\n[generic] Price -> CLICK\n[label] 100 - 200 USD (6) -> CLICK\n[button] APPLY -> CLICK\n[combobox] Sort by: -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.195, 0.15, 0.312, 0.162] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f57e6c0a-8f8b-4756-9f1d-1bdea7a0af5c_d1b27abe-d3b2-458b-8b80-428b838fc9eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a pack of toilet paper and a bottle of laundry detergent to your Amazon cart with the lowest total price.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: toilet paper\n[button] Go -> CLICK\n[span] Featured -> CLICK\n[option] Price: Low to High -> CLICK\n[button] Add to Cart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.008, 0.549, 0.036] in the image\nAnd my action is Action: TYPE\nValue: laundry detergent" } ]

{ "bytes": "", "path": "./images/957878ba-cb47-40d1-bf37-23039b2dff27_7d9695f9-c5ef-4fb4-908d-cbd0c1b4d423.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find a CarMax in Michigan, 49107 and book an appointment for a car repair on April 7th..\nPrevious actions:\n[link] Service & Repairs -> CLICK\n[link] FIND A SHOP NEAR YOU -> CLICK\n[link] Find a Shop -> CLICK\n[li] 43065 -> TYPE: 49107\n[textbox] Zip Code -> TYPE: 49107" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.142, 0.294, 0.164] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/95619447-fe28-4cc0-9e0a-d888e5f73d7e_27347e65-851e-4170-a7bf-64293faf81e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the toddler collection and add one pair of the cheapest socks for a 6 months to 5 years to the wishlist.\nPrevious actions:\n[option] Price: Low to high -> CLICK\n[div] See more chips. -> CLICK\n[img] Short Socks (2 Pairs) -> CLICK\n[svg] -> CLICK\n[button] Age18M-3Y(12-15cm) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.358, 0.536, 0.642, 0.579] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c55b9949-b785-4d9e-8b20-b626cb595623_7ed1aec7-f9b5-428c-ab0a-0340f1a44480.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events in Phoenix for the next 3 days.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.361, 0.027, 0.464, 0.05] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/61fa0552-66ac-4572-95f2-800537cfee7b_5b09a6bf-3ece-4b80-961a-6928f0367453.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check restaurant with delivery service available 6pm on Mar 25th in Detroit, MI.\nPrevious actions:\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: detroit\n[span] MI, USA -> CLICK\n[svg] -> CLICK\n[button] 25 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.661, 0.316, 0.855, 0.357] in the image\nAnd my action is Action: SELECT\nValue: 6 00 PM" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_4b178183-f3c3-495d-b232-53c6250c7329.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Gift Cards -> CLICK\n[div] Send a physical card through the mail. -> CLICK\n[textbox] * Amount: -> TYPE: 50\n[button] VIEW ALL -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.582, 0.234, 0.783, 0.249] in the image\nAnd my action is Action: TYPE\nValue: John" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_0c112ad5-8f20-4d35-ab34-fab5d32abbe0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[span] Paris Beauvais -> CLICK\n[generic] 26 -> CLICK\n[generic] 2 -> CLICK\n[div] -> CLICK\n[button] Apply promo code -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.063, 0.369, 0.082] in the image\nAnd my action is Action: TYPE\nValue: 1000001" } ]

{ "bytes": "", "path": "./images/4a4ecf18-e7a3-448a-b8cb-b337ee20048d_d0076f22-6fca-4791-b04d-2567fd6b3d69.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 3 in Los angeles for diner at 09 PM on Mar 10\nPrevious actions:\n[svg] -> CLICK\n[button] Los Angeles -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> TYPE: diner\n[heading] Spiral Diner & Bakery - Fort Worth -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.135, 0.192, 0.158] in the image\nAnd my action is Action: SELECT\nValue: 3 Guests" } ]

{ "bytes": "", "path": "./images/3eae65d9-7778-4cf2-bc3d-f666b5e43bce_390bf505-f485-4703-86b5-6894eda4e191.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Notify me about availability for 2 guests on april 17 at the High Tide restaurant\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: high tide\n[heading] High Tide -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.193, 0.26, 0.373, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/66625c9d-5bf3-42d1-b463-ab2767307201_aba5ccb1-8c17-4ae3-b311-38bbf81bd19f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Learn more about the Partner Deal that gives 25% off for Veterans.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.538, 0.026, 0.598, 0.039] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/76294719-e146-4f92-986f-42b86a9808c7_83e6f82f-518e-46a3-83e7-9512d36279d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 store in Los Angeles, California, and set Riverside as my store and add a card from that store to my favorites\nPrevious actions:\n[link] Find a store -> CLICK\n[p] 31 stores -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.204, 0.207, 0.796, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2c19d467-4e44-4c0d-b050-a13823ca545d_305706d0-b1f9-42fc-988c-a57904eb9ce7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find hard side Carry-on Luggage used for business in black color.\nPrevious actions:\n[img] -> CLICK\n[svg] -> CLICK\n[button] Color -> CLICK\n[div] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.72, 0.359, 0.988, 0.398] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8865ca64-0df2-4e3f-905d-a9e07e1eeb68_93f20444-cbc4-4f91-ae8d-26e72b80b236.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bike service charges for store at Lafayette St, 10013.\nPrevious actions:\n[button] Cycle -> CLICK\n[link] Shop Services -> CLICK\n[link] Find a bike shop near you -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.569, 0.372, 0.59] in the image\nAnd my action is Action: TYPE\nValue: 10013" } ]

{ "bytes": "", "path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_9b2f17c5-ddb8-49a4-87b3-1840f8f1047e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[textbox] Enter ZIP or State -> CLICK\n[textbox] Enter ZIP or State -> TYPE: 07470\n[button] set store -> CLICK\n[button] Distance & Shipping -> CLICK\n[button] Nationwide -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.544, 0.234, 0.578] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b28e6a37-6e9c-46bb-8012-18ca742a521f_714aee7c-12e9-46f2-80e7-71ba558c3f4a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Explore (current) -> CLICK\n[link] Africa 29 -> CLICK\n[div] Durban -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.102, 0.512, 0.211, 0.532] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0790c8be-6e6d-4e2a-9c13-43ac9367da4c_0c664ad1-d63c-45e2-bb2e-95f9b295e8f4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the most recent full time Accounting & Finance Job available in Richmond, Virginia.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.323, 0.007, 0.384, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ee22220c-802b-431f-abb4-0131fd8dbe5f_10fb0059-93be-4e14-875a-92fd1557bfd5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 tickets for a free pet festival in English in Portland on april 15 to april 16\nPrevious actions:\n[label] -> CLICK\n[label] -> CLICK\n[combobox] autocomplete -> TYPE: portland\n[div] Portland -> CLICK\n[span] Pick a date... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.18, 0.518, 0.209, 0.543] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35cf31d3-c88d-45fe-9959-4cf1de72bc7d_af4330bb-a695-48ff-bddb-dddf6ee09277.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse for trending women sports bras and add 3 trending black bras to Wishlist.\nPrevious actions:\n[menuitem] Women -> CLICK\n[link] Sports Bras -> CLICK\n[div] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.226, 0.07, 0.239] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/998e55fb-66d7-443f-bb73-9cb6a2bc26a8_5799d00b-7193-4441-9a23-5d2fd1c7d4f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used BMW i3 for 10001 zip code with lowest price.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.123, 0.0, 0.169, 0.04] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_61a66563-d15b-4bd5-a0e1-cca261a596de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Enter license plate -> TYPE: YAW639\n[combobox] state -> SELECT: LA\n[button] Get your offer -> CLICK\n[textbox] ZIP Code -> TYPE: 70726\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.343, 0.31, 0.383] in the image\nAnd my action is Action: TYPE\nValue: 222900" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_36e6f5fb-eb43-4278-aee1-29a470c244a3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.23, 0.042, 0.343, 0.069] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_e420dd73-9c53-48e7-b5be-51c7c081f040.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] Select -> CLICK\n[button] Continue for $ 148 . 16 -> CLICK\n[button] Continue with Value fare -> CLICK\n[button] Log in later -> CLICK\n[button] - -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.603, 0.166, 0.659] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e92cd371-0bd2-4ac3-82e4-7fdaac46b626_0551c27e-cc99-459d-b713-9a698a9eb578.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\n[img] Zyrtec 24 Hour Allergy Relief Tablets with 10 mg C... -> CLICK\n[button] Check More Stores -> CLICK\n[textbox] Enter zip code or location. Please enter a valid l... -> TYPE: 90028\n[img] -> CLICK\n[generic] 6201 Hollywood Blvd., Suite 126 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.796, 0.202, 0.87, 0.21] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b040b35d-cfd3-41b8-8b8b-851ab151a9cc_8711c91a-4523-49b7-aab6-78c85d0e8af7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the complexity rating for Frosthaven.\nPrevious actions:\n[combobox] Search -> TYPE: frosthaven" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.769, 0.048, 0.986, 0.06] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/725c38e7-7987-40b3-8f19-8450f8277f06_ad95a52e-a737-472f-89dd-9b9c096d10c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest event to attend in Athens, Greece on April 2nd\nPrevious actions:\n[div] Sort by -> CLICK\n[div] Lowest price -> CLICK\n[div] All dates -> CLICK\n[span] 2 -> CLICK\n[span] 2 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.436, 0.172, 0.781, 0.183] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/91843d71-05c3-4b17-9b8c-856f2390fe02_cf567012-e9c2-4c4d-a269-6abf5adff7d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 year that Tom Brady had the most touchdowns in a single seasson.\nPrevious actions:\n[link] Players -> CLICK\n[link] Tom Brady -> CLICK\n[link] STATS -> CLICK\n[link] CAREER -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.604, 0.282, 0.655, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e4f8a347-b288-4a00-9e6b-89cbccda42d2_d1e11c67-483f-4ef7-aac4-3740e9498349.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 parking near any airport in california starting april 20 and ending april 23\nPrevious actions:\n[link] View All Airports -> CLICK\n[link] Reserve Now -> CLICK\n[textbox] Select Start Date -> CLICK\n[gridcell] Thu Apr 20 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.407, 0.273, 0.595, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/102c50a4-23f8-44ae-8300-43822b271dbf_49fbd1f1-44e1-46b1-807a-88fa536868b9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 3 places from OMG! below $500 to Wishlist and name it \"Togo\".\nPrevious actions:\n[link] Show 684 stays -> CLICK\n[path] -> CLICK\n[textbox] Name -> TYPE: Togo\n[button] Create -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.291, 0.317, 0.709, 0.363] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eee72e78-71bd-434b-ba74-33888ea5522d_353ff760-01eb-4a28-8694-2e0dfbf72cb4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel in Le maraise neighborhood in paris with 2 room for 3 adult on March 27th to April 2nd.\nPrevious actions:\n[link] Search for hotels -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.241, 0.1, 0.478, 0.125] in the image\nAnd my action is Action: TYPE\nValue: Le maraise" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_49b0a764-2d11-408e-81a9-a1f9983a7ac5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.214, 0.046, 0.652, 0.081] in the image\nAnd my action is Action: TYPE\nValue: Nintendo Switch Console" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_05442d32-f8bd-4cac-8990-cc1c6885ba52.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\n[button] make it my store -> CLICK\n[path] -> CLICK\n[span] Easter -> CLICK\n[span] Easter Eggs -> CLICK\n[button] Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.188, 0.816, 0.202] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d4b44c7-d11a-41c1-8be7-af4ae80b7a8c_e169a421-70f0-477a-9db4-ed882245eb5c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 store near 11231 zip code.\nPrevious actions:\n[span] Columbus -> CLICK\n[searchbox] Search by ZIP code or city, state -> TYPE: 11231\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.863, 0.229, 0.981, 0.252] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3c9442f9-5542-4395-918a-6551dbba3e3a_b060e216-e69b-4bad-81a0-482a2cfd7a18.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show Massively Multiplayer games which can be played on VR.\nPrevious actions:\n[link] Massively Multiplayer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.481, 0.116, 0.497, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2089ee5c-1ccd-495e-9a80-f62e129554ed_888d6f02-95b8-4b33-8eb6-25baeaba2feb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 deals in California\nPrevious actions:\n[button] DEALS -> CLICK\n[link] DEALS & PROMOTIONS Amtrak travel deals, promotions... -> CLICK\n[label] All Regions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.201, 0.558, 0.269, 0.573] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e9d71b9-b936-41d0-b1f9-cbfc17f79f51_ba10e068-4c5c-44f8-8b25-50986ef28501.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the baggage fee for first class flight leaving Columbus CMH to New Orleans MSY on april 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Baggage info -> CLICK\n[link] Baggage fee calculator -> CLICK\n[combobox] From -> TYPE: columbus\n[button] Columbus, OH, US (CMH) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.322, 0.211, 0.562, 0.228] in the image\nAnd my action is Action: TYPE\nValue: new orleans" } ]

{ "bytes": "", "path": "./images/3bb1c925-71ef-4713-a139-a3be65f8a7a5_416ca3da-f479-4b9d-b5f5-29b8c251f0f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show reviews for Fallout 4 and mark the first one as helpful.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.055, 0.93, 0.065] in the image\nAnd my action is Action: TYPE\nValue: Fallout 4" } ]

{ "bytes": "", "path": "./images/8dc49f67-4803-416a-8d05-d6e891e3efc0_6cd768bb-689b-45f4-aa5e-d0e6532efd84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the hotel with highest review score having free internet and free cancelation in Chennai for 20/03/23\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: Chennai\n[option] Chennai, Tamil Nadu, India -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.213, 0.215, 0.246, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1c6bfd10-4dcb-4a5c-bb2d-922ff9f20087_05e33d5a-8cac-4627-a403-d66707fd9217.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an English language book on roman empire history in the Kindle store released in the last 90 days, it should be displayed according to its latest publication date, and add the top result to the shopping list.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Kindle E-readers & Books -> CLICK\n[link] Kindle Books -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.008, 0.651, 0.034] in the image\nAnd my action is Action: TYPE\nValue: roman empire history" } ]

{ "bytes": "", "path": "./images/db53ba89-9cff-441a-a703-053e89e32961_dbc01bfc-47d2-48f9-b43a-8b8e74b33d08.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 superhero sci-fi movies based on comic books rated 7 to 9, and add the three movies with the most votes to my watchlist.\nPrevious actions:\n[path] -> CLICK\n[span] Browse Movies by Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.494, 0.752, 0.541, 0.761] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56cac423-4be9-4f74-9031-7cef1fe60ef9_0f4a4727-3b2d-4295-b8fd-52f2e3c17124.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[combobox] Year -> SELECT: 2005\n[combobox] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Corolla" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.625, 0.203, 0.71, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f208b8b-6d5c-4d3f-8df0-cab24d29edda_405e3a16-3fd4-405a-8e06-74ca8e5fe25b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Last of Us series and add it to my watch list.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.175, 0.156, 0.187] in the image\nAnd my action is Action: TYPE\nValue: The Last of Us" } ]

{ "bytes": "", "path": "./images/3e9d6144-e92b-4fb0-b634-48bf3eb5090b_e11321fa-806c-4878-b2b8-656dd9b9c735.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan a trip from Greenport to Oyster Bay Branch, starting with train and ending via bus with less than 1/2 mile walk.\nPrevious actions:\n[searchbox] From -> TYPE: Greenport\n[listitem] Greenport, NY, USA -> CLICK\n[searchbox] To -> TYPE: Oyster Bay\n[listitem] Oyster Bay, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.201, 0.359, 0.227] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_55dbe23a-9887-4aca-9658-46b687dac5af.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for Castles in Europe for a week next month and price below $1000 per night.\nPrevious actions:\n[button] Location Anywhere -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.739, 0.302, 0.777, 0.337] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549452ab-637a-4997-bce1-5898541bb288_3a060beb-0619-4c77-8131-7ffe4c62debf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all NFL tickets\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.205, 0.026, 0.28, 0.047] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/562d8516-e1fa-464b-9bb1-542fe818c721_a8fc3743-1bc9-4364-8cf4-243301d9ad7a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] King of Tokyo -> CLICK\n[button] Sort: Recently Added -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.264, 0.136, 0.383, 0.153] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_5081e4ab-c126-42d1-a018-1794aa0466d0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\n[div] Size -> CLICK\n[link] S -> CLICK\n[div] Filter -> CLICK\n[RootWebArea] Women's Sports Bras | Under Armour -> CLICK\n[button] Show more -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.572, 0.233, 0.609] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_7f7174c9-88dc-4df0-8fac-54a0603bbbac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[textbox] Leaving from -> TYPE: jfk\n[button] New York (JFK - John F. Kennedy Intl.) New York, U... -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: heathrow\n[button] London (LHR - Heathrow) United Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.129, 0.568, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccd8d9f9-65f1-42ac-a699-5db7e380c760_16b24021-bfdb-41dd-a733-ca9415863d65.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Washington airports to New York airports and only show those with scheduled status.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.512, 0.072, 0.594, 0.104] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/401c4e6f-6b0b-47b4-8157-92d7ca468bbc_7473d4f5-d147-4c64-912c-620553698746.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: rent a car in Brooklyn - Central, NY on from April 9 to April 15.\nPrevious actions:\n[combobox] Enter pick up city, airport name, or airport code. -> TYPE: Brooklyn Central\n[div] Brooklyn - Central (New York), US -> CLICK\n[textbox] Pickup -> CLICK\n[button] Sunday, April 9, 2023 -> CLICK\n[button] Saturday, April 15, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.29, 0.376, 0.484, 0.403] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_5d6ff011-4cfd-4d8b-abdc-39e927e234bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.501, 0.064, 0.556, 0.086] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_4da58b5c-bb8e-4c17-be85-757cbff832c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.093, 0.646, 0.126] in the image\nAnd my action is Action: TYPE\nValue: resident evil" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_fe2547fa-bebe-490d-95b9-22a6f8cd70f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.083, 0.67, 0.103] in the image\nAnd my action is Action: TYPE\nValue: Smithsonian" } ]

{ "bytes": "", "path": "./images/9b6316ee-4cfb-490e-bf52-9ee6cdded08b_110a1d40-5b06-4c86-821d-a085f20b70f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 ideas and recommendation for things to do in Cancun.\nPrevious actions:\n[textbox] Where to? -> TYPE: cancun\n[circle] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.411, 0.073, 0.498, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c02c193-2aef-4817-92b4-56722edc6b57_0df26719-4457-4f0d-a480-07531eaae3b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: skirt\n[textbox] Search by keyword or web id -> ENTER\n[span] Gender -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.133, 0.086, 0.144] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_b37e82ef-4b52-4746-8b5e-68663a04a73d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Transmission -> CLICK\n[span] Automatic -> CLICK\n[button] Back to all categories -> CLICK\n[heading] Distance & Shipping -> CLICK\n[button] $99 Or Less -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.413, 0.237, 0.435] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7685e8ad-3989-4316-85dd-746fac2956be_c1977bd0-8644-4263-937b-c5b4d681d54b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a recently posted part-time Job in Gamestop stores in Fresno, California, and apply.\nPrevious actions:\n[link] Careers -> CLICK\n[link] View Jobs Stores -> CLICK\n[button] State / Province -> CLICK\n[span] -> CLICK\n[button] City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.439, 0.307, 0.459] in the image\nAnd my action is Action: TYPE\nValue: fre" } ]

{ "bytes": "", "path": "./images/05238c0f-514f-4af2-bc4c-f7521d649825_86b75914-108e-4670-923c-28f40115d397.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.083, 0.93, 0.098] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ff82e848-f29e-477b-a286-c807cbd0d8fa_6e9ddb40-c8c9-49c8-b24d-23de6338158b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a job in customer services in Qatar Airways, find any job available in India, view the details and save the job.\nPrevious actions:\n[link] Careers This link will take you away from the Qata... -> CLICK\n[span] 64 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.128, 0.603, 0.15] in the image\nAnd my action is Action: TYPE\nValue: india" } ]

{ "bytes": "", "path": "./images/4a4ecf18-e7a3-448a-b8cb-b337ee20048d_1cb32c35-d655-487b-ad30-fc234522bfe5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a table for 3 in Los angeles for diner at 09 PM on Mar 10\nPrevious actions:\n[svg] -> CLICK\n[button] Los Angeles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.171, 0.028, 0.441, 0.062] in the image\nAnd my action is Action: TYPE\nValue: diner" } ]

{ "bytes": "", "path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_2c1ac090-674a-426e-9cab-3857abef2dfe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Search by keyword or web id -> TYPE: mens black hoodie\n[span] mens black hoodie -> CLICK\n[div] Size Range -> CLICK\n[link] Big & Tall (5,552) -> CLICK\n[div] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.235, 0.123, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3786bf-56a4-4b4a-a94e-a4c1620cd0b2_062beced-fb6a-435e-9e47-a52f8ff8db4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 videos from the Oscar 2023.\nPrevious actions:\n[button] Open Navigation Drawer -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.122, 1.0, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ebae9339-93bf-4f5a-9396-ce30bcec7b49_caf5665b-735a-4dbc-b204-6b82136c31db.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 price of Boys' INFANT UA SURGE 3 RUNNING SHOES. black color and 9K size\nPrevious actions:\n[menuitem] Kids -> CLICK\n[div] Product Category -> CLICK\n[link] Shoes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.517, 0.233, 0.549] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e0feee24-dfed-454a-aa40-eda244f1d044_72517ff4-d1db-49a4-a416-9539c0b06e84.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 balance sheet and cash flow statement for the fiscal year 2021 of Six Flags.\nPrevious actions:\n[link] Investors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.08, 0.412, 0.15] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5f2c3149-1820-4632-bfdb-3cf4615de2cc_cc132005-2d40-4e1f-8699-bf828e06b700.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dog food for puppies that is rated at least 4 stars and sort the results by price from low to high.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: dog food\n[button] dog food -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.438, 0.032, 0.446] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_31a14711-3dfc-40e7-82e0-7c877e622c01.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.084, 0.327, 0.111] in the image\nAnd my action is Action: TYPE\nValue: edinburg" } ]

{ "bytes": "", "path": "./images/95936f53-1e60-4bad-9cd2-65831e309768_e7584865-130e-41bc-8b05-9c8a0376a1e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 restaurants, open 24 hours, and sorted by rating.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.257, 0.348, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_e72a4cee-1a25-4609-a4a9-09587f670585.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[menuitem] First class -> CLICK\n[button] Departing April 5, 2023 -> CLICK\n[button] May 27, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Leaving from -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.128, 0.362, 0.161] in the image\nAnd my action is Action: TYPE\nValue: jfk" } ]

{ "bytes": "", "path": "./images/1cc13b4e-d3d3-480f-a2fe-f18e83159d93_7c668a7b-1de9-4df9-b75b-69ac45fc6d15.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: with a $200 budget check available in central parkto check in on 24th to 27th march for 2 adult and a toddler less than a year old.\nPrevious actions:\n[combobox]  -> SELECT: 1 Child\n[select] Age -> SELECT: 0\n[link] Search Hotels -> CLICK\n[radio] $100 to $200 -> CLICK\n[radio] New York (and vicinity) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.523, 0.123, 0.529] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e3c7ad0-f138-490e-918e-42bcce9f55a9_9fb8c08d-560d-454e-8098-08de434ef903.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a harry potter book to my wishlist.\nPrevious actions:\n[textbox] Search for books by keyword / title / author / ISB... -> TYPE: Harry Potter\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.335, 0.341, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1fefdb27-882b-481b-97e2-720f4d2338a3_2008bd87-e75d-4056-ab8d-218ec362bbb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 activities in Phuket, Thailand.\nPrevious actions:\n[path] -> CLICK\n[combobox] Search by city or activity -> TYPE: Phuket" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.216, 0.218, 0.795, 0.226] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8eef04e2-3d51-4a0e-84f2-db017a69050b_703f0030-4a9b-4879-a9ec-f17fff4b2859.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Special Offers -> CLICK\n[link] Deals -> CLICK\n[heading] Spring Break Savings & Packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.698, 0.666, 0.781, 0.678] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a9a2e52-24b4-46c3-9e52-0f79c15ae3d0_3ace967f-2791-4a0e-87d1-c514a29195a5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 full-time job in Budget USA in finance in any location, and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK\n[link] Openings -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.474, 0.32, 0.488] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/020bc054-a829-4af5-8f0a-6efce012c7ac_104a87a5-25a2-48c5-add0-206e46511d03.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the number 4 ranked board game on the geekmarket.\nPrevious actions:\n[button] Browse -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.124, 0.034, 0.231, 0.05] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/607cea69-abb5-4055-aa09-117650cb7cc9_eb8b8087-d063-4855-90c0-f238e4752bdd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request information for tickets for a group of 100 people at a park in california\nPrevious actions:\n[button] Browse the Parks Below -> CLICK\n[span] Six Flags Magic Mountain -> CLICK\n[button] Go! -> CLICK\n[link] Groups  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.918, 0.829, 0.938, 0.881] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_54802f88-fafb-4740-bd79-f5e3717f2733.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[span] 7 -> CLICK\n[span] 14 -> CLICK\n[button] Done -> CLICK\n[button] Lowest Regular Rate -> CLICK\n[label] Senior Discount -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.699, 0.145, 0.914, 0.193] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddee9314-5a29-4258-b11b-b6432ec719f1_70e082cb-31c1-4468-a16b-10fe67cce0bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all free virtual business start-up events happening tomorrow in Las Vegas and follow the organizer with most followers.\nPrevious actions:\n[svg] -> CLICK\n[div] Tomorrow -> CLICK\n[p] Startups & Small Business -> CLICK\n[div] #virtual -> CLICK\n[label] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.228, 0.478, 0.478, 0.519] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81fb481b-a234-4e25-b494-9ed26a03e977_eaf85801-dbb0-4f5f-bc2f-75832d6dcfb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the second most popular horror series to my watchlist.\nPrevious actions:\n[path] -> CLICK\n[span] Most Popular TV Shows -> CLICK\n[link] Horror -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.577, 0.231, 0.601, 0.244] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d56df06a-8234-4f31-8737-e74fe9d5fa04_5d55fb91-fc5c-44ae-b62e-0fc07d2d5bdc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest return tickets from Leeds to Sheffield leaving at 8:30 am on Mar 25, 2023 and returning at 23:00 pm on same day for 1 adult and 2 child.\nPrevious actions:\n[listbox] hour -> SELECT: 08\n[group] RETURN -> CLICK\n[link] 25 -> CLICK\n[listbox] hour -> SELECT: 23\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.088, 0.221, 0.233, 0.256] in the image\nAnd my action is Action: SELECT\nValue: 2" } ]

{ "bytes": "", "path": "./images/93d0190f-ff39-4b69-82fc-58cddac42006_f1d139be-16d6-448e-836d-4a5043a316d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 safety rating for 2012 Honda Civic\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, 0.245, 0.12, 0.271] in the image\nAnd my action is Action: SELECT\nValue: 2012" } ]

{ "bytes": "", "path": "./images/690eedad-706c-4c48-a803-45b4f1c069bb_ca11435d-ef30-4f9f-8a60-fdc777a44ab9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bestsellers under $20 and available in hardback.\nPrevious actions:\n[link] Bestsellers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.027, 0.249, 0.196, 0.273] in the image\nAnd my action is Action: SELECT\nValue: Under US$20" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_fa2e4ec5-e583-4ee6-9768-6bc6f7d43822.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[button] Consoles & Hardware chevron_right -> CLICK\n[button] Xbox One -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles -> CLICK\n[checkbox] Microsoft Microsoft -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.356, 0.375, 0.387] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_2f60a0c7-f38b-45e6-ab39-8b984c0ecd9b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Men's Shoes -> CLICK\n[link] Nike -> CLICK\n[button] US Shoe Size -> CLICK\n[link] 9 -> CLICK\n[button] Condition -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.791, 0.094, 0.932, 0.108] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_a091ad8f-b00e-4d24-838b-439f2c89e0c3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Edit cuisine type filter -> CLICK\n[checkbox] Mediterranean -> CLICK\n[button] Submit -> CLICK\n[button] Open additional search filters -> CLICK\n[checkbox] Outdoors -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.287, 0.532, 0.306, 0.554] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_36a9d86c-7e16-4e62-8351-5bf4f50e8b2d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve a lowest priced car for pickup from Birmingham Airport, Alabama, at 11 am on March 22, 2023, and the return location is Montogomery Airport, Alabama, at 5 pm on March 25, 2023.\nPrevious actions:\n[searchbox] Pick-up & Return Location (ZIP, City or Airport) (... -> TYPE: BIRMINGHAM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.216, 0.553, 0.237] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_9f67bc8f-0bad-45c4-b2f4-b3ebbbe9aef6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[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\n[combobox] End Time -> SELECT: 5:00 PM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.1, 0.322, 0.3, 0.359] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4777d638-204d-4e44-b81c-2fb43c471fb2_b7a670b5-20f0-4800-b4b3-ffd095b8acd6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most reviewed cocktail bar with outdoor seating for reservation in San Francisco.\nPrevious actions:\n[textbox] Near -> TYPE: SAN FRANCISCO\n[span] San Francisco -> CLICK\n[checkbox] Cocktail Bars -> CLICK\n[checkbox] Outdoor Seating -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.524, 0.122, 0.617, 0.138] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_79ecf264-bcba-4974-af90-74b67ca769aa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] CONDITION -> SELECT: Good\n[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.719, 0.284, 0.752] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ba150cb-3b4a-4f0a-bff0-b448c78608ae_a0318c58-8752-4304-9f6b-235154d272b0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotel deals in Las Vegas for four adults starting on May 17 and ending on May 20, and if deal is not available, set an alert for the same.\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Hotels -> CLICK\n[textbox] Where? -> TYPE: las vegas\n[div] Las Vegas, NV -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.119, 0.697, 0.169] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b390b60-5c04-40ee-a5af-353def43ffbc_68bbcc87-382f-446f-b611-bf58f39479cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] CITY PAGES -> CLICK\n[link] Fresno -> CLICK\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.13, 0.137, 0.215, 0.148] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_f13cc2d8-4952-40bf-a4fb-54be342dfa9d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fare for JFK, NY to Heathrow, London and nearby airports for 1 adult on April 22, one way\nPrevious actions:\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK\n[textbox] Depart , required. -> CLICK\n[textbox] Depart , required. -> TYPE: 04/22/2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.106, 0.401, 0.29, 0.434] in the image\nAnd my action is Action: SELECT\nValue: 1" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_404e24fc-6086-4570-a4aa-a1f1530104a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\n[button] $10,000 -> CLICK\n[menuitem] $20,000 -> CLICK\n[button] $56,000 + -> CLICK\n[menuitem] $30,000 -> CLICK\n[button] Back to all categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.276, 0.165, 0.36, 0.188] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fc98662-4405-4a30-9854-9301c98fdb37_9ce52b41-222b-432a-93fc-3a3050e800b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the parking options in Florida to book to enter on may 6 at 5 pm and leave the same day at 6pm?\nPrevious actions:\n[textbox] Search for parking -> TYPE: florida\n[li] Florida, USA -> CLICK\n[textbox] Start Date -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.198, 0.376, 0.228, 0.411] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_a725013c-1fb2-44f4-b17c-66f001302852.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\n[button] Make -> CLICK\n[span] (954) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Series -> CLICK\n[listitem] 1-SERIES (8) 1-SERIES (8) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.317, 0.253, 0.343] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_e23e2c2a-cf6c-45ff-8920-f0444ffee944.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Alaska -> CLICK\n[button] SAIL FROM -> CLICK\n[button] Seattle, WA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.452, 0.341, 0.591, 0.384] in the image\nAnd my action is Action: CLICK" } ]