Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_3c16c075-2c0d-4f6b-8239-27d144b4b7bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[label] 9 -> CLICK\n[label] Available in Store -> CLICK\n[label] KEEN -> CLICK\n[svg] -> CLICK\n[label] .Stars::before { -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.846, 0.274, 0.9, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/122af0dc-9e4e-4c5a-98ad-5c4d02f32284_1533426c-6f64-4fc5-aa01-7fad60360f2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 next available bus from Chicago to Ann Arbor.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Chicago\n[span] Chicago, IL -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Ann Arbor" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.366, 0.406, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/74cb088a-06d9-4a5e-9b00-61fd6b874e89_f99dcc87-41a8-46f2-9c49-357593e5e4e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 exercise events taking place in San Francisco between July 10-31.\nPrevious actions:\n[generic] next -> CLICK\n[generic] next -> CLICK\n[generic] next -> CLICK\n[button] 10 -> CLICK\n[button] 31 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.684, 0.327, 0.879, 0.425] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_50a2f5c1-64de-41e9-abd0-4451f762fcea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.146, 0.031, 0.227, 0.05] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1684f224-47d5-45ed-9a26-821b98b851cd_947b3258-9cc5-40c9-8aec-b8e6041d3782.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the highest reviewed for a 4-adults stay in Hollywood, USA, on April 19 to 23 with an option for free cancellation with a price range between 150 to 200 dollars.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: HOLLYWOOD\n[span] Hollywood -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.488, 0.447, 0.499, 0.457] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_ac23a9dc-a401-429c-a93f-dbbf04494cbb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[textbox] *Amount -> TYPE: 150\n[span] Marriott Deluxe Box -> CLICK\n[textbox] To -> TYPE: Clara\n[textbox] From -> TYPE: James\n[textbox] Message Line 1 -> TYPE: Happy Christmas" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.293, 0.714, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_1e025e9b-cd9f-43a1-83c4-088b78703733.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.052, 0.475, 0.061] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/57f72023-3633-4c97-93f6-af12fe2edf4f_326b47cd-cccd-456f-b004-592a3038e94b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\n[searchbox] Search -> TYPE: SOUTH AFRICAN HISTORY PODCAST" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.541, 0.009, 0.553, 0.017] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab139e9d-eb99-47f7-8d0b-f93479fadadf_9b8e4f5e-44c2-4d7b-822a-2f50757cdf0b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track a bus using service number 5456165184.\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.17, 0.25, 0.198] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ce76343-dafe-4cf6-9bfd-918834d0c641_6d984d16-dfbc-428c-b948-d82c0d1ca057.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated fast responding phone repair shop for data recovery in Houston.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.375, 0.038, 0.434, 0.068] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8888ebb8-c2b3-4173-9718-51d752b9e5ab_3d0769b3-8443-4f88-9b2a-25919abee6b0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[a] JFK - New York John F Kennedy Intl, NY -> CLICK\n[span] -> CLICK\n[textbox] To , required. -> CLICK\n[textbox] To , required. -> TYPE: Heathrow\n[a] LHR - London Heathrow, United Kingdom -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.509, 0.5, 0.693, 0.534] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bba6dd60-babd-4d8d-9e8b-242b0ffc08d7_df6e386e-5d3b-41fa-9e31-180a841bf8e5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guide for paying with commuter benefits.\nPrevious actions:\n[p] About -> HOVER\n[link] SpotHero for Business -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.6, 0.303, 0.737, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c82bd6d6-6f08-4f1d-aeef-351c86694bbc_bb39f777-043d-4f12-9973-afd6bef8c9b5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest movies for rent in the Redbox kiosk at any Winn Dixie in Daytona Beach.\nPrevious actions:\n[button] Navigate to Find a kiosk nearby -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.254, 0.702, 0.268] in the image\nAnd my action is Action: TYPE\nValue: Daytona" } ]

{ "bytes": "", "path": "./images/d1942a73-745f-44c5-ba30-0d0c7925f5d2_385a6a91-88f4-4837-83e1-2f3c5b92b626.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 comedy movie streaming on Netflix and add to watchlist.\nPrevious actions:\n[link] Netflix streaming -> CLICK\n[svg] -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK\n[img] Chris Rock: Selective Outrage -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.34, 0.374, 0.5, 0.39] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2fc63250-ac9a-4cd4-a29d-6460f0652fa3_481aabef-7831-4470-967a-8926d70118fa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a wireless keyboard and mouse combo under $100.\nPrevious actions:\n[searchbox] Search Site -> TYPE: wireless keyboard mouse\n[button]  -> CLICK\n[textbox] price to -> TYPE: 100" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.445, 0.192, 0.468] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e8603513-2740-485e-adf9-86361dd015f4_f149f408-6377-466c-8b6a-f552605df2f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare FlightAware subscriptions and signup for Enterprise plan.\nPrevious actions:\n[span] Products -> CLICK\n[span] Premium Subscriptions -> CLICK\n[button] Compare Subscriptions -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.511, 0.505, 0.583, 0.524] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/18a581b9-5021-40aa-835d-3c8110402df3_a544e04d-4b21-40f0-beb2-5da432e73791.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 adventure movies coming to theaters.\nPrevious actions:\n[link] MOVIES -> HOVER\n[link] Coming soon to theaters -> CLICK\n[span] Genre -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.361, 0.43, 0.381] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d9c6a43-eeb3-40ec-8617-d09a68fb0fb3_8365081d-8726-4dad-9a47-25429f6fb4c8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 routes from NYP to WAS on May 15th.\nPrevious actions:\n[textbox] From -> CLICK\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK\n[textbox] To -> TYPE: was\n[option] Washington, DC - Union Station (WAS) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.604, 0.11, 0.712, 0.135] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6a7eaba3-f6ec-4eba-9e04-ff974b228ef4_46c14367-c9aa-4663-aef8-8d3ebac75daa.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select an event from the 2019 UFC schedule and show me the full profile from one of the athletes\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.356, 0.054, 0.39, 0.089] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_9945456e-05f3-4c9e-8ce8-65ca56ec133c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[link] Parking -> CLICK\n[link] Find Parking Lots -> CLICK\n[button] Stations G–K  -> CLICK\n[link] Gloucester -> CLICK\n[link] Plan a trip from this station -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.157, 0.22, 0.335, 0.239] in the image\nAnd my action is Action: TYPE\nValue: NORTH PLYMOUTH" } ]

{ "bytes": "", "path": "./images/eee72e78-71bd-434b-ba74-33888ea5522d_95b4682d-c31a-4bcc-877d-e861c8f213ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Search -> CLICK\n[button] Number of rooms and guests -> CLICK\n[button] Increment -> CLICK\n[button] Increment -> CLICK\n[div] Update -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.654, 0.064, 0.754, 0.078] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_694f27c3-ec85-4bb5-a08c-7650fcbbbaf9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[textbox] Start Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK\n[combobox] Start Time -> SELECT: 9:00 AM\n[combobox] End Time -> SELECT: 6:00 PM\n[button] Update Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.419, 0.397, 0.432] in the image\nAnd my action is Action: SELECT\nValue: Sort by Distance" } ]

{ "bytes": "", "path": "./images/9a5aa299-e77d-44ca-ab0f-f6fd83e3fde1_af09a4fc-7fe3-430f-9aad-50d6c1d8ce02.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest and highest-rated hotel in the Navi Mumbai area of Mumbai, India, on April 12 for just one day.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: mumbai\n[span] Mumbai -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.573, 0.292, 0.583, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/619ba95b-5a27-4c53-841c-edc281aacf7a_3b9dcd1e-9bb4-4599-b812-5fda7a1bf251.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dome tent to my shopping cart.\nPrevious actions:\n[link] Camping -> CLICK\n[menuitem] View All -> CLICK\n[div] Type -> CLICK\n[label] Dome -> CLICK\n[link] Bass Pro Shops Eclipse 2-Person 5x7 Dome Tent -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.691, 0.704, 0.976, 0.736] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_11b8428e-580a-427b-945b-e9964306d187.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[button] Search -> CLICK\n[textbox] Maximum Value in $ -> TYPE: 400\n[button] Submit price range -> CLICK\n[input] -> CLICK\n[input] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.718, 0.246, 0.792, 0.271] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e9d6144-e92b-4fb0-b634-48bf3eb5090b_88070251-f05f-4d48-8365-9ae69c638083.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.196, 0.359, 0.215] in the image\nAnd my action is Action: TYPE\nValue: Oyster Bay" } ]

{ "bytes": "", "path": "./images/cdd64586-2f2e-4000-89fa-200feefcd97d_088d7365-0d88-422a-b819-ff3660ebdf1c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find newly arrived Batting Gloves for women\nPrevious actions:\n[link] New flame Icon -> CLICK\n[link] Womens -> CLICK\n[div] Product Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.435, 0.194, 0.443] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/563ec938-b259-45b7-b0d3-6360b74e601d_cf9e9473-f15a-4e35-a52d-fc2f8f6a9d9d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2 of WrestleMania single day Parking Passes on April 1st in California near LA.\nPrevious actions:\n[div] Sports -> HOVER\n[link] WWE -> HOVER\n[link] Wrestlemania -> CLICK\n[link] Parking -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.456, 0.374, 0.553, 0.396] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/57f72023-3633-4c97-93f6-af12fe2edf4f_720c5c98-aa5c-4e3a-b84b-4edf4fc74ac7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 south african history podcast with length between 10 to 30 minutes and filter it by audiobook tag.\nPrevious actions:\n[searchbox] Search -> TYPE: SOUTH AFRICAN HISTORY PODCAST\n[button] Search -> CLICK\n[link] Tracks -> CLICK\n[link] Any length -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.059, 0.201, 0.212, 0.21] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_75331416-79a1-49ba-9151-cb36c58c21e1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find comedy tv shows on netflix sorted by audience score.\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[img] netflix -> CLICK\n[span] Genre -> CLICK\n[div] -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.124, 0.238, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_cc84e6d9-c116-476e-8c9e-7bc04f3fe1ab.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[link] Search for packages -> CLICK\n[link] Hawaii Vacations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.175, 0.267, 0.286, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/39937001-8af2-4727-bb2a-6997981cf50d_4e4e4193-b03a-48de-a041-da1ba92837d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a list of tours available at the Coliseum with free cancellation.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.025, 0.131, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8308d10f-3904-473a-a186-c6b8f939f018_0fb30cdf-7ea1-47af-ad9a-010175cc1fb3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 longest private sightseeing trip of India in the month of June\nPrevious actions:\n[gridcell] Thu Jun 01 2023 -> CLICK\n[gridcell] Fri Jun 30 2023 -> CLICK\n[button] Apply -> CLICK\n[circle] -> CLICK\n[button] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.582, 0.125, 0.597] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/973bf55c-d1a0-41c7-9ec8-9f59b3dbfb58_531e7d43-cdb2-42b0-ad84-8f482edced43.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Repost on my feed a rock playlist.\nPrevious actions:\n[searchbox] Search -> TYPE: rock\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.154, 0.199, 0.17] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_98673272-fde8-4585-bcb4-8fb21d9ef497.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Choose departure date -> CLICK\n[checkbox] 5 June 2023 -> CLICK\n[button] Search -> CLICK\n[span] -> CLICK\n[tab] Fastest -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.742, 0.306, 0.916, 0.327] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_a2229723-f483-4aad-a049-63b0de313d31.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[span] Special events -> CLICK\n[DisclosureTriangle] All locations -> CLICK\n[li] NYC -> CLICK\n[DisclosureTriangle] All Categories -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.179, 0.184, 0.318, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9572e7bd-0365-4339-899d-1d1dc8504543_9cb7b962-2d18-47fb-926a-597470068e61.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[span] Birmingham -> CLICK\n[checkbox] Return to a different location -> CLICK\n[searchbox] Return Location (ZIP, City or Airport) (required) -> TYPE: MONTGOM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.293, 0.298, 0.505, 0.342] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_0eb19e0d-99bd-405c-ba39-76125661d09e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[img] Add -> CLICK\n[combobox] Age of Child 1(Child's age (years)) -> SELECT: 3\n[img] Add -> CLICK\n[combobox] Age of Child 2(Child's age (years)) -> SELECT: 5\n[img] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.343, 0.245, 0.389, 0.261] in the image\nAnd my action is Action: SELECT\nValue: 8" } ]

{ "bytes": "", "path": "./images/6f4e562e-91f9-401d-8730-af947985b821_bb5ecc35-cad8-4934-8fd3-8db479c6b832.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most rated to watch tv shows or movies on Amazon Prime to watchlist.\nPrevious actions:\n[button] Filter -> CLICK\n[button] Highest Rated -> CLICK\n[button] View Results -> CLICK\n[span] Watchlist -> CLICK\n[span] Watchlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.682, 0.373, 0.788, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d4d4a01e-47d0-4e54-8bd5-3d85acebb6dd_812eb1e7-0b27-48a2-b770-544d5bccbd76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the latest action tv shows which are rated fresh by both the audience and the rotten tomatoes\nPrevious actions:\n[link] TV SHOWS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.255, 0.238, 0.273] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a747bed0-0f45-413a-8f48-2c45795e4e3d_5ecad292-0fb1-4d8e-8963-715a5e924186.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Give a like to the #1 track of the Real Time Top Chart\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.806, 0.004, 0.838, 0.021] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3b7cead3-475d-41a4-a018-db89c7ace632_363d6ca6-36b4-40cd-8116-3c77b4246f5a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 is the purchase price for powerwalls to install in a 200sqr feet 2 story house in the address 7528 East Mechanic Ave.Fargo, ND 58102\nPrevious actions:\n[link] Powerwall -> CLICK\n[link] Order Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.722, 0.243, 0.919, 0.261] in the image\nAnd my action is Action: TYPE\nValue: 7528 East Mechanic Ave. Fargo, ND 58102" } ]

{ "bytes": "", "path": "./images/39fd14c2-3bdd-4ca6-8a3a-1a6e7374c8e6_2a99e22d-6bc8-48c6-b38b-d358a070a01a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 woman t-shirt in xl size from merchandise section, add 2 pieces to the cart and check out.\nPrevious actions:\n[link] Merchandise -> CLICK\n[span] Women's Last.fm Spiral Hex Tee -> CLICK\n[select] S -> SELECT: XL" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.58, 0.332, 0.591, 0.343] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eab97f0c-38b3-4421-bff6-697b3267f23c_9d6b03f7-af9e-4339-9c0e-9b57b36796e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 carnival cruise options that include Alaska.\nPrevious actions:\n[button] SAIL TO -> CLICK\n[button] Alaska -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.741, 0.428, 0.871, 0.482] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_c73b04b6-058a-4c28-9cb2-ca6eb698b205.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[span] Special events -> CLICK\n[DisclosureTriangle] All locations -> CLICK\n[li] NYC -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.179, 0.137, 0.318, 0.157] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_9f40df58-a7fa-4181-b1a9-f08a0f0bd2eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.692, 0.06, 0.705, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/09660a8d-b01d-4e93-9dd2-0b4af256bc80_828eeb3d-81d9-49a8-a848-523adbcf487e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Change the language to UK English and the currency to Euros\nPrevious actions:\n[svg] -> CLICK\n[combobox] Language -> SELECT: 🇬🇧 English (UK)" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.551, 0.062, 0.565, 0.076] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_4c49fa1f-80b9-49fd-b1df-515931e10c8d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[tab] Flights -> CLICK\n[tab] One-way -> CLICK\n[button] 1 traveler -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.809, 0.297, 0.828, 0.311] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_89a66828-0f63-4b8f-9090-933d55e222a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] $ -> TYPE: 5\n[textbox] $$$ -> TYPE: 10\n[button] close -> CLICK\n[button] Color -> CLICK\n[div] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.963, 0.008, 0.988, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b56d5b8-1f41-43ca-9f21-369d849f1aa0_9404fc4c-c485-4e47-af68-762a4e97965f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the season pass prices for Hurricane HarborLos Angeles.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.365, 0.846, 0.412] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_9fe8d58a-4c1f-4bbb-8bc9-2c1e157f291a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 155000\n[button] Next -> CLICK\n[span] Black -> CLICK\n[button] Next -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.193, 0.502, 0.284, 0.532] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_2e1e2b82-41a6-4bb9-af07-28fc1b8604d9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[button] Search flights + cruise -> CLICK\n[label] October 08, 2023 -> CLICK\n[span] Nights -> CLICK\n[label] Miami -> CLICK\n[button] View details -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.815, 0.732, 0.952, 0.766] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1203a016-d541-4914-9cdb-f042ad0abcf5_2fed1405-e307-4548-b8db-160e3d6a3342.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Anime TV shows and sorty by Newest\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.614, 0.18, 0.668, 0.189] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_f0282d1a-fb09-404d-88ce-5a583a75a055.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[searchbox] Search games, consoles & more -> TYPE: resident evil\n[span] resident evil -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Video Games -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.337, 0.375, 0.366] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1282a011-194c-40c4-8f76-875e502cdd53_c534f502-bbd7-495e-b75e-fa1d5e851def.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 laptops with at least 16gb of ram and under $700.\nPrevious actions:\n[textbox] price to -> TYPE: 700\n[button] APPLY -> CLICK\n[dt] Memory -> CLICK\n[span] Show -> CLICK\n[span] 16GB -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.705, 0.192, 0.719] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_f46e2703-87c4-4986-b7be-4975b7288aef.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a new list and add four items from the personal care category at Walgreens.\nPrevious actions:\n[path] -> CLICK\n[path] -> CLICK\n[svg] -> CLICK\n[img] -> CLICK\n[span] Add to list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.217, 0.309, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/77be98ff-e4db-4745-9b87-6ce69754c4c2_15c9b3ca-89b6-401b-9d4c-beb382884a11.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 wheelchair accessible parking for the Pittsburgh Pirates at St. Louis Cardinals event in Busch Stadium on Apr 13.\nPrevious actions:\n[textbox] Search for parking -> TYPE: busch stadium\n[li] Busch Stadium, Clark Avenue, St. Louis, MO, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.337, 0.379, 0.594, 0.399] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f1f4e4f7-3fb0-4aeb-8123-4882a1f39cb2_d8c4b3b3-80ff-4b99-b6c1-2591f2525750.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the new arrival of kids graphic t-shirt for 13 years old boy\nPrevious actions:\n[link] KIDS -> CLICK\n[tab] Tops -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.111, 0.378, 0.12] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_31f7682f-dbf9-40fa-8368-f25c2670dabe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[path] -> CLICK\n[button] sub 1 -> CLICK\n[div] open -> CLICK\n[option] 6 -> CLICK\n[button] Update -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.78, 0.176, 0.858, 0.201] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1d9c6a43-eeb3-40ec-8617-d09a68fb0fb3_398a1cab-4bfc-42ae-b8df-5bb1fabdb9cf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 routes from NYP to WAS on May 15th.\nPrevious actions:\n[textbox] From -> CLICK\n[option] New York, NY - Moynihan Train Hall (NYP) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.168, 0.554, 0.188] in the image\nAnd my action is Action: TYPE\nValue: was" } ]

{ "bytes": "", "path": "./images/a2959cdb-fbc4-435f-ba89-85d50d22298c_393218a4-be87-41c9-880d-9dff65eb1a23.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces in JFK airport between April 18-20 that have lowest shuttle times\nPrevious actions:\n[tab] Airport -> CLICK\n[searchbox] Airport Name, Code or City -> TYPE: jfk\n[li] John F. Kennedy International Airport (JFK) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.044, 0.059, 0.233, 0.077] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e200503-9b49-48aa-aaf6-3d6692b5cb50_9a258ed2-27f1-43d8-96f2-b7dd1562bcea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 locksmiths near Texas City, Texas that provide virtual consultations and are open now.\nPrevious actions:\n[link] Home Services -> CLICK\n[textbox] Near -> TYPE: Texas City, Texas\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.152, 0.279, 0.172] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/40cd58cd-6c9a-47b9-a927-92243970d87a_27418770-0fb2-4572-8950-c111ca546d72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 monthly daytime only parking nearest to Madison Square Garden starting from April 22\nPrevious actions:\n[tab] Monthly -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.132, 0.785, 0.165] in the image\nAnd my action is Action: TYPE\nValue: madison square garden" } ]

{ "bytes": "", "path": "./images/c8990751-0aab-440c-bf6d-a32ac1216344_d73fbe6d-8222-4166-9484-330d448e6b15.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 guided vacations in Europe for more than 10 nights in the month of July\nPrevious actions:\n[li] July -> CLICK\n[button] SEARCH DEALS -> CLICK\n[button] Filter -> CLICK\n[button] 10+ Night Trips -> CLICK\n[button] Guided Trips -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.708, 0.438, 0.772, 0.473] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_8ec95e8f-a20b-4ab2-be5b-78333b5b16fd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[link] Plan a trip from this station -> CLICK\n[combobox] To  -> TYPE: NORTH PLYMOUTH\n[em] Plymouth -> CLICK\n[button] Depart at 8:20 AM, 4/10/23  -> CLICK\n[LabelText] Monday, April 10, 2023, click or press the enter o... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.296, 0.358, 0.323, 0.376] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0f63c624-6097-473e-ad19-59bc139836d1_12c4f752-1759-4fe1-b011-6efe7006dcda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 developer jobs in Dallas, Texas, and review details of the latest job then create an 8-day alert after signing in.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.478, 0.431, 0.504] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4e44e7b6-3d2a-4ca2-870a-edc9e9751d5d_59b106a8-1c6b-4d63-bf92-a82e063fc15a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 last minute cruise deal\nPrevious actions:\n[link] Last-Minute Deals -> CLICK\n[heading] Last-Minute Cruise Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.277, 0.079, 0.292] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_131ab6e4-1cda-403e-892f-48975f9de2b6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[heading] Category -> CLICK\n[input] -> CLICK\n[option] Tops -> CLICK\n[heading] Size -> CLICK\n[label] L -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.435, 0.397, 0.445] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14a4e19d-d82d-45dd-b4f0-6b60ed87d085_cc1747c1-6897-475a-a414-30da991bc3fd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearest Sprouts Farmers Market and add two fruits and one sauce from the deals.\nPrevious actions:\n[img] -> CLICK\n[link] Deals -> CLICK\n[div] Add -> CLICK\n[span] Add -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.898, 0.762, 0.969, 0.771] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/593830ff-fd2c-4479-abf8-8fddee2cdaea_decbda01-c8ad-439a-a719-9fae758733b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 brochure of Loss Damage Waiver Protection.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.602, 0.021, 0.74, 0.031] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_0711a396-35a4-4cc4-b1a1-0264829f7b8b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\n[gridcell] 24 June 2023 -> CLICK\n[textbox] Passengers / Class -> CLICK\n[button] Decrease number of infant passengers -> CLICK\n[button] Increase number of child passengers -> CLICK\n[span] (Business/First) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.655, 0.402, 0.927, 0.424] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/895f32c1-7d6f-4474-b5b1-50daf5cb2a40_c2522b37-de29-4b8e-8f85-8cbe56475733.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 jobs available in Texas for American Airlines.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.307, 0.522, 0.431, 0.546] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3cb44998-5a0c-44c5-84b7-ffb729a356d8_c2e9086d-05ae-454c-a286-99169b97287a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 schedule between New York and Washington DC sorted by shortest trip.\nPrevious actions:\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK\n[textbox] To -> TYPE: Washington\n[option] Washington, DC - Union Station (WAS) -> CLICK\n[textbox] Depart Date -> CLICK\n[gridcell] Monday, April 17, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.824, 0.105, 0.957, 0.13] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/93f3a9a1-2fd8-4457-b689-d70b3249b99b_3f9a5ae5-bcb9-4dda-aec6-2e5d2e3a0499.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight status with flight number 2819 on 18th of March.\nPrevious actions:\n[tab] FLIGHT STATUS -> CLICK\n[button]  Search by date required selected as 15 March 202... -> CLICK\n[link] 18 March 2023, Saturday -> CLICK\n[button] done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.127, 0.562, 0.173] in the image\nAnd my action is Action: TYPE\nValue: 2819" } ]

{ "bytes": "", "path": "./images/2e2cb6d9-560c-4258-baed-82e0ed5b5dbc_3b61150e-f073-4093-b655-8b362b023c5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bus stop information at Abbotsford, WI.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.339, 0.012, 0.422, 0.059] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_7eca4c5a-2094-4510-8f7c-b18976791000.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[link] Browse Gift Cards -> CLICK\n[button] Our Brands -> CLICK\n[img] Travel Reinvented. -> CLICK\n[textbox] *Amount -> TYPE: 150\n[span] Marriott Deluxe Box -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.665, 0.45, 0.873, 0.467] in the image\nAnd my action is Action: TYPE\nValue: Clara" } ]

{ "bytes": "", "path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_4c168a73-6f51-4f60-8121-76e76caa359d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.134, 0.785, 0.167] in the image\nAnd my action is Action: TYPE\nValue: barclays center" } ]

{ "bytes": "", "path": "./images/2d92911a-b208-4d68-ad00-46d2d67f9efa_107e8ce0-5be5-4b2f-8966-35de535030bd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store in spring, Texas.\nPrevious actions:\n[link] Store Locator -> CLICK\n[textbox] Please enter City, State, or Zip Code -> TYPE: SPRING, TX" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.013, 0.177, 0.517, 0.194] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_32423741-d475-4401-bb90-37b5783f2819.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[span] -> CLICK\n[button] Shape -> CLICK\n[span] -> CLICK\n[button] Price -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.956, 0.014, 0.988, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b70e49b-2759-4276-ad4f-471e405544b9_91233398-b0ea-424a-9cd5-2b60b4283b6b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all conductor trainee job openings in Amtrak New York and apply to the latest job.\nPrevious actions:\n[link] Careers -> CLICK\n[textbox] Search by Keyword -> TYPE: Conductor\n[textbox] Search by Location -> TYPE: New Yok\n[button] To make this website accessible to screen reader, ... -> CLICK\n[button] To make this website accessible to screen reader, ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.116, 0.603, 0.305, 0.641] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f4dcbd09-45f3-47b5-a49d-36658d5b50ca_0d7efda5-9240-4c57-9a5c-5446e9c2d83c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for Pizza making class in New York next month.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.248, 0.292, 0.28] in the image\nAnd my action is Action: SELECT\nValue: Events" } ]

{ "bytes": "", "path": "./images/95499427-980a-4115-b1aa-6b252b4fb2c3_bc4dbb7f-e800-41f5-9fb1-edeecfa090b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cough medicine that is rated 4 stars and above and is $15-$20.\nPrevious actions:\n[combobox] Search products and services -> TYPE: cough medicine\n[button] Search for cough medicine -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.385, 0.143, 0.407] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bcc2b6df-c012-4513-9fc1-ab149e93001f_56260a12-8133-43af-ba62-a8526f0e5aee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 12-inch available moving truck with a complete protection package for approx 250 miles, pick it up at 4:00 pm, and drop it off at the same location on June 20 at 4:30 pm from zip 07718.\nPrevious actions:\n[input] -> TYPE: 250\n[button] Continue to Location -> CLICK\n[select] Select a Pick-up Time -> SELECT: 04:00 PM\n[select] 04:30 PM -> SELECT: 04:30 PM\n[button] Select Pick-up Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.157, 0.428, 0.255, 0.462] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a31de393-c6e0-4175-858b-03cdc435d585_edb2c211-bef6-4991-a828-73831abc411d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 events happening at Madison Square Garden.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: Madison Square Garden" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.113, 0.748, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e133f6c-155d-4ba4-89f5-16f569d6e918_00e19130-721a-425b-aa74-57bcbb23ded3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest food tour in Paris which offers free cancellation\nPrevious actions:\n[button] Paris France -> CLICK\n[circle] -> CLICK\n[button] -> CLICK\n[div] Food Tours -> CLICK\n[label] Free Cancellation -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.919, 0.263, 0.963, 0.276] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06309af8-9ca0-41c4-8acc-1e4e5db2f344_59276a5b-5c7e-49bc-ba3e-07e7219dfcd1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the most popular Women's Athletic Shoes.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.018, 0.092, 0.137, 0.128] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aeace1e7-0460-4f4e-99fb-2a8c867b97ef_da04e845-1f80-4464-80df-2a89df6c5d9b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the highest rated Last-Minute Flights & Car Rentals\nPrevious actions:\n[link] Last-Minute Deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.344, 0.363, 0.656, 0.511] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_b87d39de-e0c4-41ce-9ed7-37de94e8fe7b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.612, 0.699, 0.642] in the image\nAnd my action is Action: TYPE\nValue: Doja Cat" } ]

{ "bytes": "", "path": "./images/181e8206-2d04-47ea-bcaf-f701b8c5525a_b491c36c-59cd-45e3-853d-c107a16e3373.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.69, 0.109, 0.787, 0.166] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ce76343-dafe-4cf6-9bfd-918834d0c641_414ca573-101c-43e1-9a61-dea8ac4d6a54.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated fast responding phone repair shop for data recovery in Houston.\nPrevious actions:\n[span] Phone Repair -> CLICK\n[textbox] Near -> TYPE: houston\n[span] Houston -> CLICK\n[button] Fast-responding -> CLICK\n[radio] Data recovery -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.148, 0.63, 0.165] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1c6bfd10-4dcb-4a5c-bb2d-922ff9f20087_ec68d5c3-9dd6-47e0-ae07-61673d79709f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Search Amazon -> TYPE: roman empire history\n[button] Go -> CLICK\n[link] Kindle eBooks -> CLICK\n[link] English -> CLICK\n[link] Last 90 days -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.934, 0.061, 0.968, 0.066] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_9feb1093-8b40-4fa5-81f4-548ad83d5940.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[generic] Close -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[link] 31 -> CLICK\n[link] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.433, 0.295, 0.567, 0.329] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_8d380612-6d85-4cf3-9691-a9ba0257e423.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[link] SSD Storage -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.269, 0.445, 0.358] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdb6b70d-6083-49b5-908c-a6c0f711c175_d602e0d8-9092-45a7-99e7-c0d26107ca55.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find parking spaces near Warner Theatre in Washington DC.\nPrevious actions:\n[link] CITIES -> CLICK\n[heading] WASHINGTON DC -> CLICK\n[link] Theaters -> CLICK\n[link] Warner Theatre Theaters -> CLICK\n[link] SEE OPTIONS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.246, 0.336, 0.378] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_bc897867-f54d-4a70-aeda-56cdfe8b25e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.119, 0.325, 0.136] in the image\nAnd my action is Action: TYPE\nValue: Los Angeles" } ]

{ "bytes": "", "path": "./images/f4dcbd09-45f3-47b5-a49d-36658d5b50ca_7648c204-6107-469b-915d-6b24608d0e96.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for Pizza making class in New York next month.\nPrevious actions:\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK\n[combobox] Reservation type -> SELECT: Events\n[combobox] Event date -> SELECT: Next month\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.362, 0.095, 0.452, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5418beec-bc06-4e11-9664-4038fbdeefe9_575c9828-b577-4fd4-bc2c-656a78fe0d83.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List Batman collectible figures priced under 10 dollars and a customer rating above 4 with a same-day delivery option.\nPrevious actions:\n[searchbox] Search games, consoles & more -> TYPE: BATMAN\n[span] BATMAN -> CLICK\n[link] Filter -> CLICK\n[checkbox] Same Day Delivery Same Day Delivery -> CLICK\n[generic] Refine by Category: Collectibles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.139, 0.375, 0.155] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b73503a7-e4e1-43f7-bfc0-866e7003615f_0c6371f1-0488-46a8-9683-b6d73833cee9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 taxi from O'hare Airport to 123 Main St, West Chicago, IL on Mar 29, 2023 at 12 noon for 2 adults.\nPrevious actions:\n[heading] 123 Main St -> CLICK\n[button] pickup date input field -> CLICK\n[button] 29, March 2023 -> CLICK\n[button] pickup time input field -> CLICK\n[button] Confirm -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.733, 0.207, 0.82, 0.239] in the image\nAnd my action is Action: SELECT\nValue: 2" } ]

{ "bytes": "", "path": "./images/14f0e837-af77-44b9-9cad-a8911aab30c6_451803f9-762c-48e4-a1a6-71d06f5d9431.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of flight from Columbus, number 1234 on April 5th, 2023.\nPrevious actions:\n[heading] Flight status -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.335, 0.272, 0.37] in the image\nAnd my action is Action: TYPE\nValue: 1234" } ]

{ "bytes": "", "path": "./images/e6bdb364-4327-44f0-a6d8-94eb00b36ca7_4ed5a644-3e8b-4966-8913-bb0e0c5b63ce.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the page with help in choosing a solar energy product for homes.\nPrevious actions:\n[link] Solar Panels -> CLICK\n[link] Order Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.774, 0.582, 0.901, 0.595] in the image\nAnd my action is Action: CLICK" } ]