Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/82c5913d-8392-44a2-8873-6627a281fa23_731f1c88-2e9c-40af-a9a2-5cbb8486771a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate monthly payment for car value of $50,000 and downpayment of $10,000 with interest rate of 4% for 60 months.\nPrevious actions:\n[menuitem] Finance -> HOVER\n[menuitem] Loan Calculator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.188, 0.473, 0.213] in the image\nAnd my action is Action: TYPE\nValue: 50000" } ]

{ "bytes": "", "path": "./images/fca09c13-5e6c-49d5-b3ee-b620a70b19f5_e33e7423-a005-4de8-89dc-d34c5f297820.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a hotel with lowest price in Tokyo for 2 adults and 1 child for 10 May and checkout on 12.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[option] Top destination Tokyo, Japan (City) -> CLICK\n[div] 10 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.368, 0.393, 0.377, 0.404] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3e9d6144-e92b-4fb0-b634-48bf3eb5090b_4e0c7759-42dd-49e7-b8f0-c1a71191be69.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.141, 0.285, 0.359, 0.309] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_33320628-6d12-4948-a068-aad951d8eab1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] Going to -> TYPE: Miami, FL\n[textbox] Going to -> TYPE: Miami, FL\n[button] Miami (MIA - Miami Intl.) Florida, United States -> CLICK\n[button] 1 traveler -> CLICK\n[img] Increase adults -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.65, 0.118, 0.786, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/44a12ff5-0172-444a-b979-f224162c1aa8_743b5d19-6618-4851-8d60-aff7605fc7d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cars to pick up at the laguardia airport in April 12th, 2023 midnight\n and return to same location at noon\nPrevious actions:\n[button] Locations -> CLICK\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: laguardia airport\n[span] LaGuardia Airport -> CLICK\n[button] Find a Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.121, 0.296, 0.255, 0.306] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/af97084c-5b72-4fec-be1e-dcab0980b335_bc8a6490-c12c-4d18-bed0-e0a9652265d7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all Bayern Munich goalie stats\nPrevious actions:\n[button] MORE -> CLICK\n[div] Soccer -> CLICK\n[div] Bundesliga -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.181, 0.401, 0.469, 0.465] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_d4f72df1-7bad-4682-801b-1306a7dbf865.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find two rooms in a cheapest hotel in Niagra Falls for three adults and one three year old kid from May 17 to May 20, view only available hotels within 100 to 200 dollar range with taxes and fees, and choose the cheapest hotel that offers free breakfast and a pool.\nPrevious actions:\n[option] Niagara Falls, ON, Canada -> CLICK\n[button] 1 NIGHT Sun, Apr 09 - Mon, Apr 10 -> CLICK\n[span] 17 -> CLICK\n[span] 20 -> CLICK\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.104, 0.188, 0.113] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81fb481b-a234-4e25-b494-9ed26a03e977_0d8093b0-56b9-45e6-b9c9-b8d9c0f501cc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add the second most popular horror series to my watchlist.\nPrevious actions:\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.364, 0.106, 0.628, 0.122] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_18dc8214-4872-434c-876a-f628e23fcfc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[button] Next month -> CLICK\n[button] Next month -> CLICK\n[button] Jul 1, 2023 -> CLICK\n[button] Jul 7, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.432, 0.304, 0.568, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/78c52592-76e4-4c45-afd5-f94cf213314e_3f5e842c-d368-42bb-a2c6-1407fa5b61d0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Play a star wars movie trailer.\nPrevious actions:\n[textbox] Search IMDb -> TYPE: Star Wars\n[button] Submit Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.065, 0.422, 0.653, 0.432] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fbe9f625-7b47-4e13-a2f5-6823195d7438_76121b93-9b56-4b51-86a1-c62104d6fb48.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find a cheapest direct flight From mumbai to new delhi, India, on june 1 and return travel on june 8.\nPrevious actions:\n[tab] Flights -> CLICK\n[generic] Round-trip -> CLICK\n[combobox] Flying from -> TYPE: MUMBAI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.338, 0.476, 0.351] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/11344944-81ef-4fde-82b7-7e9724fc96f1_25b10621-3099-4546-9ff0-dd74ac022908.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse the list of discussion forums for games I own.\nPrevious actions:\n[link] COMMUNITY -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.071, 0.482, 0.092] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/984f5bdb-d6d0-4b9d-ae23-bee8283a4f40_b066ef7b-a2bc-40b2-941a-8aeae8f79bf8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 2-5 day cruises to the Caribbean from Miami during August 2023.\nPrevious actions:\n[link] 2-5 DAY CRUISES Get big savings! Check out 2-5 day... -> CLICK\n[button] Sail To -> CLICK\n[button] Caribbean -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.266, 0.075, 0.491, 0.129] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_1680dfb8-7555-457e-916a-b744dd50ccb5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[button] hotels -> CLICK\n[div] Destination or property -> TYPE: jakarta\n[hp-input-button] Destination or property -> TYPE: jakarta\n[div] Jakarta, Special Capital Region of Jakarta -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.151, 0.273, 0.19] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4a0bd619-4aa9-48d8-8322-89a86aef93db_0a1e66bf-415c-4c64-a0c9-7fe592135fec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed used antique Oak chair in the French style made before year 1800.\nPrevious actions:\n[link] Collectibles -> CLICK\n[button] Antiques -> CLICK\n[link] Furniture -> CLICK\n[link] Chairs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.834, 0.198, 0.923, 0.223] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4498c83b-029f-4f1e-af81-722de20160e2_94ea9c63-2eec-4898-9bd9-b1155e31d79e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a train with the shortest trip from New York, NY to Washington DC on June 1 in first class and add the ticket to the cart, preferably in the morning .\nPrevious actions:\n[button] Done -> CLICK\n[button] FIND TRAINS -> CLICK\n[span] Sort/Filter -> CLICK\n[checkbox] filter trains by Time of Day:6a-12p -> CLICK\n[mat-pseudo-checkbox] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.852, 0.551, 0.944, 0.57] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_2c586599-8f29-41ca-a0b1-87e1e3789284.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 for a flight from united airlines leaving Belo Horizonte to Buenos Aires on April 9\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK\n[link] Flight status -> CLICK\n[generic] Apr 7, 2023 -> CLICK\n[option] Apr 9, 2023 -> CLICK\n[combobox] Airline. Enter to change collapsed list. Selected ... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.187, 0.637, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/360eeaa8-0077-42f4-8200-1e3cf6414cda_b4e902e0-1823-4a2d-82d1-e4cb17411a3a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a message to Joe Bloggs who has the username 'boredcelt'.\nPrevious actions:\n[button] Community -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.052, 0.615, 0.065] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_84c56bf6-9bbd-44d5-bcd2-ec8a1a549af6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.638, 0.107, 0.691, 0.118] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dc636898-246e-4b08-9978-6a6dc1b20320_476b5f29-c0de-40d0-8f3d-2ce384cd591c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 mattresses available with Amazon Basics and Follow the store.\nPrevious actions:\n[link] Amazon Basics -> CLICK\n[link] BEDROOM -> CLICK\n[link] Mattress & Mattress Toppers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.096, 0.278, 0.168, 0.297] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/013faefc-26df-4eeb-be59-5638c5f9dc72_ec1bbbbe-ce3c-4e80-8b4a-5549ce2cb133.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a room at the Marriott Bonvoy resort in the Caribbean for a 10-day stay starting on May 5th.\nPrevious actions:\n[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: Carribbean\n[button] 1 NIGHT Wed, Apr 19 - Thu, Apr 20 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.846, 0.224, 0.88, 0.253] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_df0d8978-9049-4cb9-968c-6df0e0da3812.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Mileage -> TYPE: 155000\n[button] Next -> CLICK\n[span] Black -> CLICK\n[button] Next -> CLICK\n[button] None -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.367, 0.286, 0.386] in the image\nAnd my action is Action: SELECT\nValue: Good" } ]

{ "bytes": "", "path": "./images/998d121b-c858-485d-9dd3-4609575d144b_3105db36-2d46-422c-990a-31de39ab0a29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular song this week by the no. 1 weekly charts ranked artist\nPrevious actions:\n[link] Charts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.097, 0.181, 0.145, 0.195] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f7b93dc1-2f19-419e-a6e0-a701008c17fa_fcf8a62d-5909-423d-b5d8-241e0adb4dac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the booking with ticket 123456 under the name James Buck.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.437, 0.306, 0.623, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b59dd33-7f6a-48df-aa1e-9cc67177287f_9164d8b5-1f9c-401b-ac02-e2235a798755.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 spot near Dallas Love Field Airport.\nPrevious actions:\n[tab] Airport -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.06, 0.784, 0.076] in the image\nAnd my action is Action: TYPE\nValue: Dallas Love Field" } ]

{ "bytes": "", "path": "./images/b1eb6602-3aa7-40ee-8968-69d83e7ef21c_09ad252d-0aa9-4500-9c76-a6f428acfcae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[combobox] Select Maximum Year -> SELECT: 2023\n[combobox] select-filter -> SELECT: 50 mi\n[span] Silver -> CLICK\n[p] Black -> CLICK\n[p] Lexus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.032, 0.35, 0.226, 0.361] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b627cbc-a45e-4f7e-9d02-bfca1a41070a_8db68fdb-b4d0-4883-ba65-f2ecbb8ac59b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View details for a Times Square parking lot that is wheelchair accessible.\nPrevious actions:\n[textbox] Search for parking -> TYPE: Times Square\n[li] Times Square, New York, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.319, 0.36, 0.384, 0.39] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_4b43afb6-5cfb-4405-95c9-4fefabda58be.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK\n[button] 03/29/2023 -> CLICK\n[combobox] Return Time Selector -> SELECT: 1:00 PM\n[button] Browse Vehicles -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.037, 0.625, 0.059, 0.649] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_bff2b2ce-8a02-4c9e-8262-f76461b7f237.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Hotel in Boston zip code 02199 and make a pick-up reservation in a suv with gps for 2 people on March 27 11 am and return on March 29, 1 pm.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.025, 0.499, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e035a36-1c77-4014-98ec-4d48ee41d904_f34ec95c-8c93-4e9a-8b49-69c0eaee86e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 the fare types to book a 1-adult ticket from Springfiels, IL to Austin, TX for April 29th 2023\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: SPRINGFIELD\n[button] Springfield, IL, US (SPI) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: AUSTIN" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.258, 0.582, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_a40a0d44-e057-46e9-98bc-cf21b715bbb6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] TIRE_CONDITION -> SELECT: Good To Go\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK\n[button] No -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.165, 0.476, 0.284, 0.513] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/632bb279-036c-48e5-b40a-962b2e90d6d1_1aefcac7-5379-4ce3-b57c-ee32805a47e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 winter coats featured in the weekly ad and is at least 15% off.\nPrevious actions:\n[searchbox] Search: suggestions appear below -> TYPE: winter coat\n[button] go -> CLICK\n[button] Deals -> CLICK\n[div] -> CLICK\n[button] Update -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.619, 0.112, 0.692, 0.13] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a698566-2a8f-4d9d-9da9-17288b66917f_2eacf5f3-80a5-491f-9d67-5d5793a8d030.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hotels in Tokyo for two adults and one child, with a budget of $500 per night for 2 nights starting on May 5th.\nPrevious actions:\n[combobox] Enter a destination or property -> TYPE: Tokyo\n[generic] Japan -> CLICK\n[div] 5 -> CLICK\n[div] 7 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.382, 0.303, 0.393, 0.309] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4770e887-f523-4609-a989-ded8c8abad19_ac59711d-fcaa-4057-92af-1038cdc97b7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round trip economy flight from Pune to New York in June and select the fully refundable.\nPrevious actions:\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: Pune\n[button] Pune, IN (PNQ) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: New York\n[button] New York, NY, US (NYC - All Airports) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.284, 0.202, 0.478, 0.229] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8308d10f-3904-473a-a186-c6b8f939f018_05079796-ff63-4353-b6f4-58469eeb7be8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] Where to? -> TYPE: India" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.173, 0.729, 0.206] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1860601a-faef-4dba-8cbb-807ea8434dca_a6a47a5f-af4c-4828-877e-98c2bec76ac6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Travel Planning Center -> CLICK\n[button] Find Your Destination -> CLICK\n[link] Explore Destinations & Travel Requirements -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.068, 0.472, 0.207, 0.51] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_7457cb3f-1727-46f9-ba3c-c6fa1f567265.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flight ticket from Addis Ababa to Accra on April 14 and book the cheaper economy ticket.\nPrevious actions:\n[textbox] From Autocomplete selection. Enter your place. -> TYPE: addis ababa\n[strong] Addis Ababa -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: accra" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.326, 0.72, 0.358] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_6283deae-3b1b-4134-a5c2-b272074c2708.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my parking space in Houston. Name: James Smith, Email: [email protected], phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[textbox] First Name * -> TYPE: James\n[textbox] Last Name * -> TYPE: Smith\n[textbox] Email * -> TYPE: [email protected]\n[textbox] Phone * -> TYPE: 8888888888\n[combobox] Market: * -> SELECT: Chicago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.212, 0.22, 0.787, 0.299] in the image\nAnd my action is Action: TYPE\nValue: 123rd st" } ]

{ "bytes": "", "path": "./images/df73be67-e81a-444f-82cc-e69d54a72734_090caaac-cb79-4e25-b11f-dafd929b8871.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gift shops available at a park in New York\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.51, 0.846, 0.555] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f84075a2-9d97-4964-9c80-70f5bee8a418_7d12b26e-cea6-48a9-84bb-31a71783af9e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 my trip with ticket number 3329456534543 along with my name John Green\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[combobox] Find Your Trip By -> CLICK\n[option] Ticket Number -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.366, 0.098, 0.562, 0.132] in the image\nAnd my action is Action: TYPE\nValue: 3329456534543" } ]

{ "bytes": "", "path": "./images/555dd7af-72ce-4455-b4d1-dd9b20ae7c5e_2c84e548-890b-4c83-bb17-731112429425.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two 100-pound digital gift cards with a birthday card and message of Happy Birthday Love from Stewart Bloom, send to Denise Bloom on email id [email protected] and Debbie Wolowitz on email id [email protected].\nPrevious actions:\n[input] -> TYPE: Denise\n[input] -> TYPE: Bloom\n[input] -> TYPE: [email protected]\n[input] -> TYPE: Debbi\n[input] -> TYPE: Wolowitz" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.661, 0.674, 0.916, 0.709] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/1282a011-194c-40c4-8f76-875e502cdd53_15edde36-09a1-4143-8fd1-1aa23e4c17fb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[searchbox] Search Site -> TYPE: laptop\n[button]  -> CLICK\n[textbox] price to -> TYPE: 700" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.793, 0.192, 0.818] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9653dc0d-96d9-414f-a711-3af94bd7cf5b_5dbffc54-e517-4b9b-a93d-8731878ee4e4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: sell playstation controller for cash credit on GameStop in 43240.\nPrevious actions:\n[img] -> CLICK\n[link] Sony DUALSHOCK 4 Wireless Controller for PlayStati... -> CLICK\n[div] Find a Store -> CLICK\n[link] FIND A STORE -> CLICK\n[textbox] SEARCH BY CITY, STATE, OR ZIP CODE -> TYPE: 43240" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.843, 0.199, 0.991, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ad381d87-53a0-4aa1-a1e5-d6d172a905cd_5f626ce1-8f6c-41da-a606-191bbaf298a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all the women cropped tops with lowest price first.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.136, 0.005, 0.204, 0.034] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/de1045f4-14ce-4de9-9aa8-601315b73b0e_e63bd0c5-1f40-461f-a792-dfe15f095b29.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the most popular documentary tv series sorted by IMDB rating, see the details of the top result.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.075, 0.022] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dc2aa3f8-eda0-455b-98dc-adc56089259a_1f10d654-9925-42b4-80dc-1c85e4fc7e9d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get route information for flights from Ohio and New York airports that have already arrived.\nPrevious actions:\n[div] Ohio -> CLICK\n[textbox] Destination -> TYPE: New York\n[div] New York -> CLICK\n[img] Submit Search -> CLICK\n[group]  Status -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.368, 0.076, 0.377] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e0feee24-dfed-454a-aa40-eda244f1d044_d7a061ca-bdc0-46b6-9f53-d3a7eb20cd89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the balance sheet and cash flow statement for the fiscal year 2021 of Six Flags.\nPrevious actions:\n[link] Investors -> CLICK\n[link] Financial Info -> CLICK\n[heading] Balance Sheet -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.273, 0.637, 0.384, 0.675] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1860601a-faef-4dba-8cbb-807ea8434dca_6530ec2d-af29-4aa3-87d9-1459e0e0aab5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check for travel requirements when travelling from New York to Tokyo as US citizen.\nPrevious actions:\n[tab] Travel Info -> CLICK\n[link] Travel Planning Center -> CLICK\n[button] Find Your Destination -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.067, 0.288, 0.309, 0.301] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9a5ab90-517c-4323-a343-6e10e6b9632f_39ddc5fa-ac0b-46c4-97f1-7fda5d38e1d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 gift registry of Carla Cahill, when asked for password use Michael Cahill as name and [email protected] as email.\nPrevious actions:\n[link] Gift Registry -> CLICK\n[span] Find a Registry -> CLICK\n[textbox] First Name -> TYPE: Carla" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.393, 0.233, 0.534, 0.257] in the image\nAnd my action is Action: TYPE\nValue: Cahill" } ]

{ "bytes": "", "path": "./images/b467797c-5fab-4ee6-9b1f-ac6dc50c05cf_32f50fb0-29e4-45af-ac3a-e2c5e30fd5c1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[link]  Computer Peripherals  -> CLICK\n[link] Printer Ink & Toner  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.449, 0.568, 0.458] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_27cebec5-d92c-4883-b6f0-9514162b357b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[link] Fares & Tolls -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.516, 0.324, 0.66, 0.335] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5a15ea92-571d-4a45-ad18-5b4eddbc70a6_c8d98ede-94ff-4686-80c4-d63369045443.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the lowest priced plus size one piece active swimsuit in color black.\nPrevious actions:\n[link] Shop by Category -> CLICK\n[link] Women -> HOVER\n[link] Swimwear -> CLICK\n[link] Women's Plus -> CLICK\n[div] Color -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.014, 0.319, 0.106, 0.334] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14f5587e-1353-419e-a381-f92d54ea2059_33996c48-9ef9-42e0-9ae2-d73a23df1bee.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find bio information about Lebron James.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.049, 0.169, 0.057, 0.173] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f118238f-ef8f-4b63-9159-a81e981ef46e_4df4d08c-48cb-452b-bd28-c31f36f0c7f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add decorative LED Candles to the cart.\nPrevious actions:\n[link] Products -> CLICK\n[button] Lighting -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.355, 0.142, 0.605, 0.159] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3d7f4f43-cff8-45fa-8249-97a8369c2d1f_287372aa-eea9-4451-9ea6-628052669c61.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Send a 50-dollar home sweet home gift to my friend John with the message Congrats on your new home, and add this card to your cart and checkout.\nPrevious actions:\n[img] -> CLICK\n[textbox] To: -> TYPE: John\n[textbox] From: -> TYPE: James\n[textbox] Message: 200 characters remaining -> TYPE: Congrats on your new home.\n[button] ADD TO CART -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.754, 0.187, 0.992, 0.205] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e721b00-f406-449b-9885-0267b47ecfdb_65871880-9edf-4376-ba5a-724665a1454b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 used Jaguar XFs with no black exterior color and save the search as Jaguar to get a notification daily.\nPrevious actions:\n[button] Advanced Search -> CLICK\n[textbox] Ex. Black exterior -> TYPE: black\n[button] Black (Exterior Color) -> CLICK\n[button] SAVE SEARCH -> CLICK\n[textbox] Custom name your search -> TYPE: Jaguar" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.604, 0.588, 0.648] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0fb36232-0d2a-4115-9012-99dbaad25a5e_08a1e24a-5539-4b20-a56a-a6201abec410.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one-way flights from New York to Toronto.\nPrevious actions:\n[span] -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: New York" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.076, 0.266, 0.359, 0.29] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/754c8c29-92b6-4af1-9594-f9d3da37b951_1ca75cb6-4ad0-4233-bba6-b07ccfdec468.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 3-star rated hostel with balcony and free cancellation option in Udipi, Karnataka for one person under 50 dollars from June 15 to 20, free wifi is compulsory.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[button] Show all 25 -> CLICK\n[span] -> CLICK\n[button] Sort by:Top picks for solo travellers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.288, 0.163, 0.473, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7f94386a-d032-43cf-9dbe-2b64430c9c28_56c6ec61-144d-4320-836a-4aaa0573ed66.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: locate the store in IL\nPrevious actions:\n[link] Store Locator -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.821, 0.264, 0.959, 0.303] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c73b1674-9c61-46a3-84dd-8fad3622a035_2010968d-7952-46a7-b08a-1b281434fdac.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight from New York to Miami from Mar 27 to Mar 31 that has the lowest core price in points.\nPrevious actions:\n[span] Search flights -> CLICK\n[button] Continue to flight results -> CLICK\n[link] Sort & Filter -> CLICK\n[svg] -> CLICK\n[label] Points -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.336, 0.223, 0.355] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/daec5481-187d-4e2f-9dae-a11892cdadf2_6940b55b-a01a-4773-a195-09ade3dfa191.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a journey with return option on same day from Edinburg to Manchester on April 2nd and book the best possible option available.\nPrevious actions:\n[combobox] Departure station, London selected. -> TYPE: edinburg\n[span] Edinburgh (Waverley) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.096, 0.327, 0.119] in the image\nAnd my action is Action: TYPE\nValue: manchester" } ]

{ "bytes": "", "path": "./images/000c2828-e8ce-4b18-bfe0-89ed333add06_80ff8fd1-64c6-4df9-91bd-7478a1730329.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a $25 digital gift card for Tim Stebee, whose email address is [email protected]. Fill in sender name Jeerimiah Waton\nPrevious actions:\n[img] -> CLICK\n[img] GameStop Digital Gift Cards -> CLICK\n[textbox] Recipient Name -> TYPE: Tim Stebee" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.24, 0.975, 0.288] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/8f6374b0-36f1-478e-a282-a61849c8174f_c3667e3c-b19b-44bc-a90e-e55c3a194518.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add eleven produce items from Aldi, including 1 pack of blueberry, 6 bananas, 1 grape tomato, 1 roma tomato, 1 cilantro, to my cart and have it delivered tomorrow between 10am and 1pm to the default address.\nPrevious actions:\n[img] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.441, 0.066, 0.45] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/34e13beb-0235-41d4-b108-137cc7480904_ef48f3d8-f9e6-40d1-931c-334e477f5a28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] CITIES -> CLICK\n[span] Find your state -> CLICK\n[link] New York -> CLICK\n[link] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.25, 0.179, 0.592, 0.207] in the image\nAnd my action is Action: TYPE\nValue: 66 perry st" } ]

{ "bytes": "", "path": "./images/1538e37b-9c33-48b0-b10e-662e192ad53a_3be9ae7f-a70b-4318-8fb6-4ad2c22b8f3f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 stops in Alanson, MI\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.398, 0.01, 0.481, 0.049] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5e5f14-c875-4cfd-a517-175619491b90_c8ccfecb-f35d-47be-a43b-48928934fcd3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 NFL Scoreboard from the superbowl 2015\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[use] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.502, 0.292, 0.514, 0.316] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1a16a98f-4e8f-4ff9-9fa2-b97d2d403cc3_5a7f29fc-db45-4eee-8795-c0ab17f04f05.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 set of sonoma bath towels to the cart and apply a coupon code for free shipping.\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: bath towels\n[span] bath towels -> CLICK\n[img] Sonoma Goods For Life® Ultimate Bath Towel with Hy... -> CLICK\n[link] BATH TOWEL -> CLICK\n[button] Add to Cart -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.506, 0.276, 0.72, 0.298] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a2959cdb-fbc4-435f-ba89-85d50d22298c_19738f5d-7377-4d14-9f1e-8589bd2c655c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.067, 0.784, 0.085] in the image\nAnd my action is Action: TYPE\nValue: jfk" } ]

{ "bytes": "", "path": "./images/e92cd371-0bd2-4ac3-82e4-7fdaac46b626_d5b4d8ea-73a9-4e11-8496-13694222c79b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add zyrtec to the cart for pickup at the nearest CVS to zip code 90028\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.013, 0.804, 0.031] in the image\nAnd my action is Action: TYPE\nValue: zyrtec" } ]

{ "bytes": "", "path": "./images/c82bd6d6-6f08-4f1d-aeef-351c86694bbc_d0bc46ae-42b7-4510-949b-2c0c747f8ac3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] City or ZIP Code -> TYPE: Daytona\n[button] select to search for a kiosk using city or zipcode -> CLICK\n[button] select to browse a kiosk -> CLICK\n[button] Show Filters -> CLICK\n[button] Filter by rent -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.27, 0.141, 0.284] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3110612f-63fe-4a7a-98d0-29c806d6a34f_cf550759-5d20-4109-8c9a-469f64f2f1e6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Trains in Spain guide that will help you learn about Renfe fare types\nPrevious actions:\n[img] header.burgerMenu.title -> CLICK\n[menuitem] European trains -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.607, 0.124, 0.966, 0.141] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f355cfcf-a3f7-47e4-b0be-b1c595e0954e_d0f6e4c4-1e10-4b80-808a-2e0d70eb0ce0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 current deals for California.\nPrevious actions:\n[button] DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.105, 0.266, 0.213] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/41cd71cb-cae5-41c8-abe8-67e42fabd4a5_77b1d0a6-ec27-41a0-905a-1fd4d43e01ec.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 details of Grand National Parks tour.\nPrevious actions:\n[button] DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.05, 0.735, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0b16b42c-dea7-4079-a2a8-79eb23447193_2d7f9a07-3428-4891-8d3b-24e22be9e7b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[tab] DEALS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.114, 0.39, 0.124] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ccb7c231-8655-4613-a28f-beb8074c523e_b61e0bec-bcd8-4a74-896a-1014bbf71f7e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\n[menuitem] Men -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.075, 0.177, 0.141, 0.185] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/56d210ec-22eb-4b3f-ba76-ee531403701a_b1259dba-320f-42b0-97a0-41dc930a594a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.028, 0.817, 0.04] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b332a3c6-c4f5-423c-a207-b1bcb28db6c3_60c544de-dc61-44c3-b0f2-0bb17011e3bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Drop D guitar tab from the 1990s.\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Drop D 39,730 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.585, 0.153, 0.609] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d4d4a01e-47d0-4e54-8bd5-3d85acebb6dd_c5203087-62da-4044-9189-5a59dd38004b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.614, 0.248, 0.668, 0.261] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0a2623c8-ce74-4572-9eb6-89d0b216d0cf_fc6195f2-3260-40a9-a000-5a0d2faf4e98.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow Taylor Swift and add a playlist to next up.\nPrevious actions:\n[searchbox] Search -> TYPE: Taylor Swift\n[button] Search -> CLICK\n[link] Taylor Swift -> CLICK\n[button] Follow -> CLICK\n[link] Playlists -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.402, 0.338, 0.489, 0.348] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1337eca1-4ca6-4102-964e-e7f6ecebcd0b_af385238-0c5d-4ce4-bf14-c3ece21aa30c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 things to do in Singapore on April 2 that are family friendly and offer free cancellation\nPrevious actions:\n[textbox] Things to do in -> TYPE: singapore\n[button] Singapore Singapore -> CLICK\n[button] From April 5, 2023 -> CLICK\n[button] Apr 2, 2023 -> CLICK\n[button] Apr 2, 2023 selected, current check in date. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.929, 0.336, 0.984, 0.353] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/42f64db7-c573-4ba8-9cab-a390e2f5e535_d6772d62-36d8-4118-a2d4-d899094404a8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a flight from Mumbai to New York City on 21st April, 2023.\nPrevious actions:\n[link] From Departure Airport or City Your Origin -> TYPE: Mumbai" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.109, 0.124, 0.362, 0.129] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87b23bf1-3c23-45a6-82bf-5a535c7cdc2f_875c751f-e7b4-444c-b6ba-c3516398869c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\n[link] Long-Term Car Rental -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: orlando" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.133, 0.215, 0.235, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_ffe3ba82-c9d1-4d63-a501-1525cbd12380.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.467, 0.241, 0.504] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b310ebc-d9f4-4eb9-b348-30b329207a36_37ad3e47-c309-4efe-ace6-3208fe05fdb8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dry cleaning shop with the highest rating and virtual consultation option for Ironing and stain treatment for a pair of suits and a few delicates in New York City.\nPrevious actions:\n[link] More -> HOVER\n[span] Dry Cleaning -> CLICK\n[textbox] Near -> TYPE: new york city\n[span] New York, NY -> CLICK\n[button] Virtual Consultations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.533, 0.111, 0.63, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/66d12284-5525-42d2-a66f-fe5c460b7764_bf7c3146-d7ce-4c7e-83ca-1e3ff7b12175.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order popcorn at AMC Grove City 14\nPrevious actions:\n[link] Visit the Food & Drinks page -> HOVER\n[link] Order Food & Drinks -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.346, 0.231, 0.63, 0.242] in the image\nAnd my action is Action: SELECT\nValue: AMC Grove City 14" } ]

{ "bytes": "", "path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_e0c7be7c-eb3c-4ce7-b04d-d385aea37cbc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[button] Locations -> HOVER\n[link] Find a Location -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.144, 0.657, 0.171] in the image\nAnd my action is Action: TYPE\nValue: washington" } ]

{ "bytes": "", "path": "./images/013faefc-26df-4eeb-be59-5638c5f9dc72_374ff5ac-f7ac-41b8-9db1-62af14e7b4a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a room at the Marriott Bonvoy resort in the Caribbean for a 10-day stay starting on May 5th.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.086, 0.103, 0.325, 0.118] in the image\nAnd my action is Action: TYPE\nValue: Carribbean" } ]

{ "bytes": "", "path": "./images/5f09e15c-c987-4bdb-ab6e-5db39b18317d_692ed3d3-325b-412e-bc50-f2c834c7c4c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 3 tickets for a Special Event or Experience in Miami on may 4\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> CLICK\n[button] View all Miami Restaurants › -> CLICK\n[path] -> CLICK\n[link] Thursday, May 4th | American Express Presents CARB... -> CLICK\n[combobox] 2 tickets for Thursday, May 4th | American Express... -> SELECT: 3 Tickets" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.071, 0.328, 0.162, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_4d36a13d-82ba-46ee-8587-497ec99d0638.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] Sat 13 May -> CLICK\n[checkbox] 1 June 2023 -> CLICK\n[span] Where from? -> TYPE: TOKYO\n[span] TYO -> CLICK\n[span] Where to? -> TYPE: NEW DELHI" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.392, 0.308, 0.648, 0.346] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8089c50-e80c-4532-82a1-96009f485c57_ef25943f-68a6-4969-91d1-956e78f70336.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Women's t-shirt for $40-$60 and add it to Wishlist, stop at the Login screen.\nPrevious actions:\n[link] T-Shirts -> CLICK\n[gridcell] Price -> CLICK\n[label] $40-$60 -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.31, 0.491, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4775a0e3-3dad-46f2-b719-b1c0dae9e147_a008a7f6-6480-487f-abda-be44b38c3d47.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tortillas bread in grocery stock near zip 59901 and add 5 pieces of 12 pcs pack in the cart and view the cart.\nPrevious actions:\n[textbox] Zip Code -> TYPE: 59901\n[button] Search By Zip Code -> CLICK\n[button] MAKE MY STORE -> CLICK\n[button] Departments -> HOVER\n[button] Grocery & Home -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.187, 0.177, 0.368, 0.192] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/62806bef-eeeb-4892-b4d5-6a8d2005c58d_8a105984-8971-4dbe-8929-a49933e300de.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trending searches in Columbus.\nPrevious actions:\n[link] CITY PAGES -> CLICK\n[link] Columbus -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.412, 0.343, 0.588, 0.379] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4008118a-68a1-4a9f-968c-8b92a979dff7_42238faf-5676-4bfc-8fb1-4c18741ce175.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 breakfast options on the Carnival Breeze ship.\nPrevious actions:\n[button] Explore -> HOVER\n[link] Dining -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.3, 0.969, 0.598] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_0a3ab473-d734-47eb-9710-22e03410d4f6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.138, 0.406, 0.167] in the image\nAnd my action is Action: TYPE\nValue: beauty salons" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_d838fd6f-80b5-45fc-8388-4038eb8363ca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[link] Shopping bag, 1 items -> CLICK\n[span] Continue to checkout -> CLICK\n[span] Guest checkout -> CLICK\n[span] Select a store -> CLICK\n[span] IKEA West Chester -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.956, 0.015, 0.988, 0.053] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_48bf6e5e-9a49-4d59-a377-26dcf4a830f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pizza serving restaurants for pick up in Chicago, sufficient for 10 people on March 30, 8:15 PM from a joint which also offers dining package.\nPrevious actions:\n[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: CHICAGO\n[span] Chicago -> CLICK\n[span] Mar 18 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.409, 0.438, 0.448, 0.482] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04b8b406-a031-48a3-a002-b1791d872e16_6ed1aa8a-c227-4ee2-8dfb-d04fe3d3fdb8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $100 Google Play Gift Card to cart and recipient email address as [email protected]\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Google Play\n[button] google play gift card -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.219, 0.128, 0.393, 0.275] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdb6b70d-6083-49b5-908c-a6c0f711c175_24d287e5-d848-4bd8-bacd-eb06b15a0036.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.376, 0.266, 0.486, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf159a0f-e6d7-46fa-beea-c231934fa7a9_9bbb8418-648f-4efb-a31e-9cb314c075be.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 travel agents in Grand Junction, Colorado\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search the site -> TYPE: travel agent\n[button] Find -> CLICK\n[link] Find A Travel Agent | Carnival Cruise Line -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.359, 0.503, 0.494, 0.545] in the image\nAnd my action is Action: TYPE\nValue: Grand Junction" } ]

{ "bytes": "", "path": "./images/0f63c624-6097-473e-ad19-59bc139836d1_7b459c84-10b1-4039-8d5e-815757741f7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\n[link] We're hiring! Join our team , Opens another site i... -> CLICK\n[button] Careers -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.529, 0.341, 0.65, 0.361] in the image\nAnd my action is Action: CLICK" } ]