Datasets:

neulab

/

Mind2Web_train_llava

like 2

Follow

NeuLab @ LTI/CMU 62

{ "bytes": "", "path": "./images/ac59be41-36c3-44c5-8e1f-ffb9461ba980_5df012f2-ae71-4ede-b641-41f8e3e454f3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for all Alternative Concerts taking place in New York City.\nPrevious actions:\n[button] Change Location -> CLICK\n[searchbox] Search by city... -> TYPE: New York\n[option] New York, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.047, 0.794, 0.264, 0.864] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/549a9805-e404-4dcf-8c72-ddf46471114b_b9fe007b-b768-4fd2-96c9-21e99e1fc443.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Compare two wireless printers that are rated above 4 stars.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.011, 0.418, 0.035] in the image\nAnd my action is Action: TYPE\nValue: wireless printer" } ]

{ "bytes": "", "path": "./images/49c60777-2500-4cea-8200-a95d3be2c9a1_cdc883f2-d336-484b-88e6-badadb5a758f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rental for an economy car in Houston from Mar 10 to Mar 13.\nPrevious actions:\n[textbox] Pick up -> TYPE: Houston\n[a] Houston, US -> CLICK\n[button] Search -> CLICK\n[button] Economy cars 5 Seats 1 Large bag 1 Small bag From ... -> CLICK\n[p] Economy -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.792, 0.389, 0.917, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a67318a4-5049-4ac5-8c6b-c14fc527483f_475e620f-02b0-4a95-ba4b-bce28ab58e23.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse used BWM cars made in 2010 and compare the four cheapest listings\nPrevious actions:\n[select] 2024 -> SELECT: 2010\n[combobox] Sort By -> SELECT: Price: Low to High\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.659, 0.308, 0.675, 0.323] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9326b908-cbe6-41f6-957f-00b84c26bfcc_aa7bf5bf-a02a-47e5-8a36-dbdb3b463d2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 recently added guitar pro non-acoustic tab intros\nPrevious actions:\n[link] Tabs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.023, 0.472, 0.153, 0.485] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_1d0e7048-7e14-408c-b0ec-c8d6a200c859.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[combobox] Year -> SELECT: 2016\n[combobox] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Camry\n[textbox] Mileage -> TYPE: 40000\n[button] Go -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.351, 0.317, 0.634, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/479bdc82-ec52-447b-a577-fa2bcdc3886f_cb270e9a-7513-44a0-992e-1db9994bb336.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers on home essentials under $20 and add the first 3 items to favorites.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.501, 0.077, 0.556, 0.104] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4272e233-3440-4572-bd86-b3a2b22a4061_ba11d9d1-a12c-4fea-99a3-b8c63f58c538.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tours and attractions in Kyoto, Japan from May 25 with free cancellation option, check availability for 2 adults and 1 infant, and book.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.451, 0.034, 0.551, 0.056] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_149a80ed-1e2c-4a63-941f-99a5fec6a11e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.391, 0.024, 0.45, 0.062] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d0eda4b-7a6e-45a4-bd8c-59fd3da58676_6fcf3fd4-8f58-4bd7-8267-d4fa5cd2b6e9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[strong] Addis Ababa -> CLICK\n[textbox] To Autocomplete selection. Enter your place. -> TYPE: accra\n[strong] Accra -> CLICK\n[option] One way -> CLICK\n[gridcell] 14 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.819, 0.585, 0.922, 0.613] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/479bdc82-ec52-447b-a577-fa2bcdc3886f_1ec386a0-9145-4cc5-ad86-8df75e74fa30.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 offers on home essentials under $20 and add the first 3 items to favorites.\nPrevious actions:\n[link] Deals -> CLICK\n[link] Home Essentials Under $20 -> CLICK\n[button] Save to favorites, KUDDARNA, Chair pad, outdoor -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.353, 0.349, 0.384, 0.379] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cdbd410d-170a-426d-b6d2-60dafaffe853_e7cce11b-e3ef-43c9-bc41-3f6db08f9d2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 best seller accessories for the Model X\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.705, 0.054, 0.753, 0.081] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a1d1f6c0-1ae9-47f0-b054-8f3f9935b7da_82693ec7-34ef-40f8-b3b7-daca962c2a76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule for the San Francisco 49ers.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.163, 0.014, 0.211, 0.022] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5b37d2e1-cbf7-4465-b28b-b63b0754895b_5c046918-7e8b-44d4-a49e-521c81e5d12b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a cheapest train ticket in upstairs deck and at least one window seat from Paris to Milan on March 26, departing after noon for 16 year old and 45 year old.\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: PARIS\n[span] Paris -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: MILAN\n[span] Milano (Milan) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.167, 0.194, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1b82bda7-a360-49c4-b54a-adaa1ae388cb_5e729cf2-659d-4934-bd09-364bcb174861.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 birth place of Ali Wong.\nPrevious actions:\n[textbox] Search TV Shows and Movies... -> TYPE: Ali Wong" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.314, 0.595, 0.332] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f385156c-4f2e-410f-bc73-7ec6d0f44448_8d193167-cec0-4e41-b471-99c194209723.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 all membership tier benefits.\nPrevious actions:\n[rect] -> CLICK\n[textbox] e.g.: New York -> TYPE: Membership tier\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.113, 0.376, 0.295, 0.386] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/632bb279-036c-48e5-b40a-962b2e90d6d1_7dec7f53-f08b-4658-993a-b6121c95d246.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] go -> CLICK\n[button] Deals -> CLICK\n[div] -> CLICK\n[button] Update -> CLICK\n[button] Discount -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.079, 0.834, 0.089] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a3fc5023-1198-4c17-8c1f-45780ab7f3bd_bf438b4c-9dbc-4369-82fb-005f6e63e14c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the latest deluxe digital copy of the Xbox Series X Resident Evil game for pre-order and add it to the cart.\nPrevious actions:\n[generic] Refine by Category: Video Games -> CLICK\n[generic] Refine by Category: Xbox Series X|S -> CLICK\n[link] Shop Pre-Orders -> CLICK\n[button] Franchise -> CLICK\n[checkbox] Resident Evil Resident Evil -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.048, 0.378, 0.083] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_2c9414e4-66fa-4d75-befd-bfffdfcb6497.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.081, 0.574, 0.263, 0.585] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/86afd67c-1bff-455c-baa7-e18dcb64b0f3_66327fbb-2be0-43d0-9f9e-d4776f150711.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find comedy tv shows on netflix sorted by audience score.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.614, 0.236, 0.668, 0.248] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_db324c07-d4c8-4133-bf12-0b1be073d6e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] Military & Veterans -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: nevada city\n[span] Nevada City -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.145, 0.268, 0.23, 0.279] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6e565708-43e2-492b-9f1d-25d51387dcf7_2a577542-e4e4-4c33-b14b-3f01975609da.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Size -> SELECT: 10 guests\n[button] Update search -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Pizza -> CLICK\n[button] Submit -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.534, 0.095, 0.666, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a45ede7-6449-40b2-b032-149ddbe205a9_aed97d15-86ae-44d5-b329-3b10758f50bb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\n[combobox] autocomplete -> TYPE: New Orleans\n[div] LA, USA -> CLICK\n[button] Food & Drink -> CLICK\n[div] -> CLICK\n[button] Contact -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.306, 0.298, 0.48, 0.319] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00cef5a2-4d07-4dd9-837d-5b85ac3a63d8_b9c1f781-bdec-4323-a3d6-2930774d05bc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Chicago Bulls team schedule for the month of April.\nPrevious actions:\n[button] Search -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> CLICK\n[searchbox] Leagues, teams, players, shows, personalities... -> TYPE: Chicago Bulls\n[div] Chicago Bulls -> CLICK\n[heading] SCHEDULE -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.669, 0.101, 0.715, 0.123] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4af615be-4472-4357-8737-5286b06b385d_4bf5478b-1450-424b-80a6-b2acb4798bd3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 listings for a used 2006 Honda Civic.\nPrevious actions:\n[link] Price New/Used -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.034, 0.419, 0.12, 0.45] in the image\nAnd my action is Action: SELECT\nValue: 2006" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_7404da48-043c-4f90-99cf-3a2e99a7bf80.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[svg] -> CLICK\n[path] -> CLICK\n[checkbox] 10 May 2023 -> CLICK\n[checkbox] 12 May 2023 -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.842, 0.197, 0.968, 0.213] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_dd54cc31-18ee-44a1-92e7-fdef1940d932.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[button] Select My Car -> CLICK\n[generic] Close -> CLICK\n[button] Select My Car -> CLICK\n[generic] Close -> CLICK\n[button] Reservations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.417, 0.049, 0.628, 0.072] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_b933a80f-1cc1-4d21-86dd-2e4e50ddaa91.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 car rentals in San Francisco for a weekend trip and filter the results by the rental company Avis and car type Economy.\nPrevious actions:\n[tab] Cars -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.148, 0.495, 0.186] in the image\nAnd my action is Action: TYPE\nValue: San Francisco" } ]

{ "bytes": "", "path": "./images/779cec8e-eef5-4de8-a42e-b449363664df_d5585212-4b78-49b6-8185-eae5dec350f5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 theatre near 10001\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.021, 0.443, 0.049] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_e73d92f8-b366-4344-9c6a-f8e671a75728.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight for two adults from Shanghai to Seoul on May 10, and return on May 12 also book a hotel with it, with maximum bundled savings and if top hotel not available book the next one.\nPrevious actions:\n[div] Shanghai, China -> CLICK\n[textbox] Where to? -> TYPE: SEOUL\n[div] Seoul, Republic Of Korea -> CLICK\n[svg] -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.77, 0.319, 0.799, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aa1a4414-f141-42b8-9e8b-28d5bd1eeef2_a885209f-e3dc-4d1b-a292-b3631c292916.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 near Venice Beach that allows mobile coupons.\nPrevious actions:\n[combobox]   Enter an Address or Venue to find parking -> TYPE: Venice Beach" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.41, 0.748, 0.434] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_b93b8c53-e686-471d-bcf7-ed74fe2190a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[combobox] Sort by: -> CLICK\n[option] Price -> CLICK\n[link] VIEW RATES -> CLICK\n[button] Member Rate Prepay Non-refundable -> CLICK\n[label] I have read the rate details and accept the cancel... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.501, 0.647, 0.563] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e9d7935-0c16-46e6-9e5c-3ea9124a6bf7_b82f1731-57ab-4129-9d15-c006e6895af7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top 50 hip hop chart and play the top track, then add this track to a newly created private playlist named Top Hip Hop.\nPrevious actions:\n[button] Add to playlist -> CLICK\n[a] Create a playlist -> CLICK\n[textbox] Playlist title * -> TYPE: Top Hip Hop\n[div] -> CLICK\n[button] Save -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.696, 0.066, 0.712, 0.083] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a632871-a6a8-40fd-b48f-6fea49cf48da_888fcb67-1235-4bb3-9cdc-b96d07a8dc10.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the NBA score board on March 11th\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.148, 0.033, 0.178, 0.054] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/49372757-4c58-4cb5-bdb4-eed0c3e83199_c4146be9-5d24-4618-975d-5ebfba34bf9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an electrician that serves the 94115 zip code and is considered Fast Responding\nPrevious actions:\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: 94115\n[textbox] Find -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.131, 0.017, 0.335, 0.027] in the image\nAnd my action is Action: TYPE\nValue: electrician" } ]

{ "bytes": "", "path": "./images/8e200503-9b49-48aa-aaf6-3d6692b5cb50_658d1d45-7bab-4d3a-8ece-e898e819cc5f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for locksmiths near Texas City, Texas that provide virtual consultations and are open now.\nPrevious actions:\n[link] Home Services -> CLICK\n[textbox] Near -> TYPE: Texas City, Texas\n[button] Search -> CLICK\n[button] Open Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.505, 0.162, 0.621, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_c269bd1c-a1bb-485b-9fc9-5eaca199ab2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[link] Search for hotels -> CLICK\n[textbox] Enter a city, hotel, airport, address or landmark -> TYPE: kashi vishwanath temple" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.223, 0.12, 0.573, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/618dbd1f-16e6-442e-ba3b-364c6dbda810_73d19c95-32f0-4eed-ac23-4de4484fa210.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to limited-time offers and choose the cheapest outdoor dining table, add to the cart, and checkout as a guest and select Ikea West Chester store for pick-up.\nPrevious actions:\n[button] Show filter modal Category -> CLICK\n[button] Furniture 356 -> CLICK\n[button] + 11 more -> CLICK\n[button] Furniture sets 138 -> CLICK\n[button] Outdoor dining sets 46 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.09, 0.318, 0.121, 0.341] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf469f30-6628-4017-b963-672645d7feab_c280a5bd-f3af-43ab-a64b-29e6984be6b8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 dog collar under 10 dollar.\nPrevious actions:\n[link] Shop by Category -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.643, 0.159, 0.654] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_6860793b-b094-4e1f-88c6-07680327486c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[textbox] From -> TYPE: TEL AVIV\n[span] Tel Aviv -> CLICK\n[textbox] To -> TYPE: VENICE\n[span] Venice Treviso -> CLICK\n[div] May -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.104, 0.253, 0.131, 0.27] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_c27e0edb-166a-4fca-afd7-de2a8823e3dd.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 with EV charging for month with lowest price in Chicago.\nPrevious actions:\n[textbox] Search for parking -> TYPE: Chicago\n[li] Chicago, IL, USA -> CLICK\n[button] Filter -> CLICK\n[checkbox] EV Charging (10) -> CLICK\n[button] Show 10 Results -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.28, 0.396, 0.397, 0.409] in the image\nAnd my action is Action: SELECT\nValue: Sort by Price" } ]

{ "bytes": "", "path": "./images/d0ce3db1-720b-4333-a487-2bdc8fd74a80_6928e47d-af7a-4f49-89b0-1b72a2516909.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 episodes of Alien Worlds and check where to watch Episode 4 of Season 1.\nPrevious actions:\n[textbox] Search TV Shows and Movies... -> TYPE: Alien Worlds\n[div] Alien Worlds -> CLICK\n[link] Seasons & Episodes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.038, 0.592, 0.129, 0.603] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3f62b47b-876b-487e-8681-63e80555938d_e7771434-c972-4fb1-9915-82fd77e5ec6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and view the details of 32-inch medium-light fishing rod for ice fishing available in stock under 100 dollars with an average rating of 4 and above.\nPrevious actions:\n[link] Fishing -> CLICK\n[menuitem] View All -> CLICK\n[label] Ice Fishing -> CLICK\n[svg] -> CLICK\n[label] Medium Light -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.273, 0.222, 0.289] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6b831239-435b-494e-9aa8-a49e8605d0b3_97df459e-9422-40ca-88fc-0a6f15b4fbfe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What is trending now on AMC on-demand?\nPrevious actions:\n[link] Visit the On Demand page -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.525, 0.079, 0.729, 0.101] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/90bd64ec-d48e-4796-a4e2-c46b866093c2_1e69c4c2-c2a1-4bb3-b5ad-3a4c6b19dd76.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 newest girls' training leggings in size yxl and save the top three results.\nPrevious actions:\n[div] Size -> CLICK\n[div] Sports -> CLICK\n[div] Fit -> CLICK\n[link] Fitted -> CLICK\n[div] Size -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.836, 0.072, 0.925, 0.09] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_d68603fa-5c88-4cc0-a276-31fbc5052bd6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[button] NO, THANKS -> CLICK\n[button] Close -> CLICK\n[searchbox] Search Site -> TYPE: 8GB Ram\n[button]  -> CLICK\n[img] 8GB (1x8GB) DDR3L 1600 (PC3L-12800) Desktop Memory... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.807, 0.206, 0.963, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dc636898-246e-4b08-9978-6a6dc1b20320_87f3b880-2540-4b64-b688-f10fca9ea957.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.203, 0.027, 0.292, 0.039] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/67648411-9d11-4254-8973-7d8dfbca58e8_6d69a62b-9667-42ef-bc20-3c552c0e2e2d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 four door SUVs from Avis while traveling from New Orleans, L, to New York that isn't more than $1000 in total price from Mar 25th to Apr 1st, pickup at 2PM.\nPrevious actions:\n[div] -> CLICK\n[checkbox] SUV -> CLICK\n[svg] -> CLICK\n[div] -> CLICK\n[checkbox] Avis -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.089, 0.631, 0.241, 0.662] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_ac795b03-c8fc-4cdb-9ed7-600429a37873.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.275, 0.108, 0.339, 0.118] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b6eed27-39b4-4dbc-97d3-eeec13a8817d_3ab94658-7eb5-4f3f-9a47-d87421d1a4d5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 roundtrip on July 1 from Mumbai to London and vice versa on July 5 for two adults and a 12-year-old in premium economy and if a flight is not available, search through the calendar for available flights.\nPrevious actions:\n[button] London, GB (LON - All Airports) -> CLICK\n[textbox] Depart -> CLICK\n[button] Saturday, July 1, 2023 -> CLICK\n[button] Wednesday, July 5, 2023 -> CLICK\n[button] 1 Adult -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.464, 0.343, 0.481, 0.362] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_d694c8b7-923e-4d3b-97ec-3a475e4463f0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[link] SHOP HOTELS -> CLICK\n[button] Going to -> CLICK\n[textbox] Going to -> TYPE: Ohio\n[button] Ohio United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.429, 0.113, 0.571, 0.132] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/63e3020c-bf52-4950-9e26-50f98a59b5e3_046e8cef-b409-41ce-a840-3daf9c4f05a7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 fast responding highest-rated electrician, who is currently open for replacement of some light fixtures in Westminster, and request a quote.\nPrevious actions:\n[link] Home Services -> HOVER\n[span] Electricians -> CLICK\n[textbox] Near -> TYPE: WESTMINSTER\n[span] Westminster -> CLICK\n[button] Recommended -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.588, 0.136, 0.682, 0.156] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5871c3f-27c3-48d8-bdf9-8b49382a2719_b66287f6-86b3-4e91-97b5-be53a7338c72.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add 3 movies from At the Kiosk which are new to Wishlist.\nPrevious actions:\n[link] Navigate to at-the kiosk -> CLICK\n[link] Navigate to New Releases At The Kiosk See More -> CLICK\n[img] Plane (2023) -> CLICK\n[button] Click to add title to wishlist. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.031, 0.139, 0.127, 0.186] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/604c4377-e24c-4900-a72f-346d8999d443_f55421a2-42c3-4ceb-934b-620dae199c4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a deal which is highly rated in Fiji location.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.508, 0.123, 0.902, 0.176] in the image\nAnd my action is Action: TYPE\nValue: Fiji" } ]

{ "bytes": "", "path": "./images/ccee2694-0d3e-4d81-8d52-5cdf82a9b81f_a1884569-f749-4e3d-96b6-2808db697b6f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 nearest apple store to zip code 60540 and check its opening time tomorrow.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.153, 0.0, 0.191, 0.025] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_fa7ae12a-1f5d-4463-820e-4ff9e9211281.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[link] Search for packages -> CLICK\n[textbox] From -> TYPE: Birmingham\n[span] Birmingham, England, United Kingdom -> CLICK\n[textbox] Enter destination or airport -> TYPE: Paris" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.41, 0.191, 0.76, 0.24] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_a18c0387-6182-447c-99ba-74444b28d91b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.662, 0.322, 0.688, 0.339] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/aeace1e7-0460-4f4e-99fb-2a8c867b97ef_15214483-2534-48e2-bb40-d84e4daf3540.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the highest rated Last-Minute Flights & Car Rentals\nPrevious actions:\n[link] Last-Minute Deals -> CLICK\n[heading] Last-Minute Flights & Car Rentals -> CLICK\n[button] Filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.335, 0.218, 0.442, 0.248] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2705de3e-4461-4668-8573-8f10c1eb6641_0a333e24-0a4d-4c6c-a466-3a1807f60957.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a low-priced refurbished Microsoft Xbox one console in white color and available in stock.\nPrevious actions:\n[checkbox] Microsoft Microsoft -> CLICK\n[button] Color -> CLICK\n[link] White -> CLICK\n[div] Condition -> CLICK\n[checkbox] Refurbished Refurbished -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.642, 0.375, 0.688] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_dae9e143-9012-43de-aa95-496ce9cabb17.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Locations -> CLICK\n[link] United States Car Rental Locations -> CLICK\n[searchbox] Location (required) * Required Field -> TYPE: 02199\n[span] 02199 -> CLICK\n[button] Continue -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.02, 0.158, 0.287, 0.176] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dadb0251-a77c-45d7-aacb-0bb2e70e2b56_725df4d5-bb6a-418d-a6d5-1dc6fd8cc328.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 food delivery services of American cuision in New York for 4 people on March 20, 8 pm.\nPrevious actions:\n[span] Delivery -> CLICK\n[button] Change location -> CLICK\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: NEW YORK\n[span] New York -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.256, 0.095, 0.47, 0.136] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdd4fc92-3b4d-48a6-9cfe-f66ffed422e6_adcc697d-c4b8-4329-8efb-83af89c3ad55.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an entire home with a rating above 5 for two in Manila, Philippines from June 1 to 8 with self-catering, double bed, free wifi, and walk-in shower, check the availability, and reserve.\nPrevious actions:\n[searchbox] Please type your destination -> TYPE: MANILA\n[option] Manila Luzon, Philippines -> CLICK\n[svg] -> CLICK\n[gridcell] 1 June 2023 -> CLICK\n[gridcell] 8 June 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.831, 0.371, 0.93, 0.412] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_9981ef68-97b3-4388-906b-0b285e5b74f2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[searchbox] Search Site -> CLICK\n[searchbox] Search Site -> TYPE: Western Digital internal SSD 1 TB" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.496, 0.009, 0.546, 0.028] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_ade61336-8901-48d1-9c8a-f14332ed9aa2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[listitem] Gas (45) Gas (45) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK\n[button] 2010 -> CLICK\n[menuitem] 2018 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.35, 0.234, 0.38] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_0bc62f29-131d-4a0f-a05b-5bb6471dd1b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[button] No -> CLICK\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, 0.667, 0.284, 0.692] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/577ac962-aefc-46c5-9050-a6069bf2a8fb_10249103-9f3d-4098-9ea7-b80db7f8af9d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find spare parts with part number 105307 and add 2 of them to cart.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Customer Service -> CLICK\n[div] Need an extra part? -> CLICK\n[link] Read more -> CLICK\n[span] Order spare parts -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.091, 0.246, 0.714, 0.278] in the image\nAnd my action is Action: TYPE\nValue: 105307" } ]

{ "bytes": "", "path": "./images/cf8b2846-ac33-46aa-887c-174de6184057_ddc83651-4e21-47b3-8ccc-50fc0d5e4783.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 status of my order with order number X123456789 and email [email protected]\nPrevious actions:\n[link] 🚚Order Status -> CLICK\n[textbox] Order number * -> TYPE: X123456789" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.341, 0.766, 0.372] in the image\nAnd my action is Action: TYPE\nValue: [email protected]" } ]

{ "bytes": "", "path": "./images/fd2e9403-3201-4bb7-a19d-f475960cf5be_be3a6710-98f4-4b0c-8508-ef55b5dca3d3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Thai restaurants that offer delivery and have vegan options available.\nPrevious actions:\n[textbox] Find -> TYPE: thai restaurants\n[span] Thai Restaurants -> CLICK\n[button] Offers Delivery -> CLICK\n[span] 1 -> CLICK\n[button] See all -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.316, 0.296, 0.332, 0.314] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_40470783-4757-4eac-a28c-fa1bfa9a8517.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[textbox] Enter your pick-up location or zip code -> TYPE: Harry Reid Intl Airport, LAS\n[span] , United States -> CLICK\n[link] click here -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: Ohare, Chicago\n[span] , United States -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.477, 0.193, 0.524, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8e133f6c-155d-4ba4-89f5-16f569d6e918_f14aee92-2270-4ef1-a4f2-6f3c03627989.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find cheapest food tour in Paris which offers free cancellation\nPrevious actions:\n[circle] -> CLICK\n[button] -> CLICK\n[div] Food Tours -> CLICK\n[label] Free Cancellation -> CLICK\n[span] Featured -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.82, 0.254, 0.926, 0.264] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_9e12befd-5920-4a3a-a8c7-6f47a1a13b4f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[textbox] Where are you going? -> TYPE: GOA\n[div] Goa -> CLICK\n[checkbox] 25 April 2023 -> CLICK\n[checkbox] 29 April 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.84, 0.287, 0.927, 0.333] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_ae57d1a1-a97c-4a44-aec7-1f1d6bd7c8d4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for a Four Points by Sheraton gift card of value 150 dollars with Marriott deluxe box and add it to the cart in the name of Clara from James with a happy Christmas message and checkout.\nPrevious actions:\n[button] For Guests -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.656, 0.308, 0.672] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d5054276-2223-44f3-b2ed-4944bae4d2b1_ff1cb425-d1e1-4bf8-8ac2-2e6ef4dbf5d6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Locations -> CLICK\n[link] United States Car Rental Locations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.084, 0.288, 0.666, 0.323] in the image\nAnd my action is Action: TYPE\nValue: 02199" } ]

{ "bytes": "", "path": "./images/ef23fbf3-f05e-41e2-b847-a27028f42470_145d33f0-a819-4a3b-b6d3-3ae7980c8dda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 “pizza” restaurants near Atlanta\nPrevious actions:\n[svg] -> CLICK\n[button] Atlanta -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.151, 0.038, 0.424, 0.085] in the image\nAnd my action is Action: TYPE\nValue: pizza" } ]

{ "bytes": "", "path": "./images/bdc1f69a-da73-4e51-9dd8-83494d4983c2_60166de7-b684-4fd1-a01e-814cabfb53ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 check-in flight for John Smith having ticket no. 123456780\nPrevious actions:\n[link] Check In -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.177, 0.26, 0.35, 0.294] in the image\nAnd my action is Action: TYPE\nValue: John" } ]

{ "bytes": "", "path": "./images/7bda9645-0b5f-470a-8dd7-6af0bff4da68_60794dd3-fdc5-4c9a-9b1f-c84d44ea1544.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[combobox] Reservation type -> SELECT: Pickup\n[svg] -> CLICK\n[searchbox] Find a location -> TYPE: Boston\n[span] Boston -> CLICK\n[svg] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.594, 0.404, 0.64, 0.425] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/112dba49-3ea4-49ce-9a7b-b47d82d3f81b_dce74858-cfe5-48b1-92a4-6ed0b917dc77.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 top-rated outdoor activity events in Spain, that is happening on May 1 and book the tickets for two adults in morning group with an English guide.\nPrevious actions:\n[div] Events & Activities -> CLICK\n[input] -> CLICK\n[button] Spain -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.616, 0.206, 0.681, 0.221] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f8089c50-e80c-4532-82a1-96009f485c57_276f37d7-195e-4140-8216-7cd9f629c82d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] WOMEN -> CLICK\n[tab] Tops -> CLICK\n[link] T-Shirts -> CLICK\n[gridcell] Price -> CLICK\n[label] $40-$60 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.445, 0.473, 0.463, 0.495] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/10b2af14-f708-4abe-94fc-00163d11cb56_7745dc56-1d07-4d83-b0b6-b196f26a0413.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] Next -> CLICK\n[link] Personal Care -> CLICK\n[svg] -> CLICK\n[img] -> CLICK\n[span] Add to list -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.309, 0.314, 0.309, 0.325] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_f4fb861e-2b80-49a8-9c84-909518e0e7c0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[button] Move forward to switch to the next month. -> CLICK\n[button] Wednesday, August 2, 2023 -> CLICK\n[button] Monday, August 7, 2023 -> CLICK\n[button] 1 Adult -> CLICK\n[button] Substract one Adult -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.298, 0.143, 0.481, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/84d8a4df-0bba-45f9-b4c8-f5d455de451c_59cfb94c-6b8b-4897-a5b9-a0ec07c8afda.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 one baby one piece to cart.\nPrevious actions:\n[link] BABY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.294, 0.139, 0.351, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/749dfeeb-8293-4c25-9cad-84f1a93f165d_13d2a2b2-7b05-4bd4-9a33-659aa7490405.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find EV charging supported parking closest to Smithsonian museum on Apr 9 between 9am to 6pm\nPrevious actions:\n[checkbox] EV Charging (1) -> CLICK\n[button] Show 1 Results -> CLICK\n[textbox] Start Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK\n[combobox] Start Time -> SELECT: 9:00 AM" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.209, 0.301, 0.384, 0.338] in the image\nAnd my action is Action: SELECT\nValue: 6 00 PM" } ]

{ "bytes": "", "path": "./images/54d60a7c-f52d-4d79-b879-34698507e22c_d3001f53-d5a7-4ef6-b3f3-30fd3b8fdd2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 round-trip from Albany to New York leaving Mar 18 and returning Mar 19 for 3 people\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: albany\n[span] Albany, NY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.329, 0.166, 0.566, 0.188] in the image\nAnd my action is Action: TYPE\nValue: New York" } ]

{ "bytes": "", "path": "./images/0790c8be-6e6d-4e2a-9c13-43ac9367da4c_d183a68c-3454-480a-9d79-b2d033f7853d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: search the most recent full time Accounting & Finance Job available in Richmond, Virginia.\nPrevious actions:\n[button] Open helpful links menu -> CLICK\n[link] Search jobs at CarMax -> CLICK\n[textbox] Search for Job title -> TYPE: Accounting\n[link] Accounting & Finance 7 jobs -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.201, 0.331, 0.23] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4bce534f-3057-40ca-aecd-ffb07b3c9fcb_70ab65e1-8095-4743-b42b-90879639ae57.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search the actor who won the Oscars for best actor in a suuporing role ine 1990, and add his upcoming movies to my watchlist.\nPrevious actions:\n[span] Oscars -> CLICK\n[link] 1990 -> CLICK\n[link] Denzel Washington -> CLICK\n[button] Expand Upcoming -> CLICK\n[button] add to watchlist -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.04, 0.245, 0.059, 0.258] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8368b990-c6ca-4cfe-a7ab-c2a88697639d_51b4faa6-0136-4f49-baad-9bd1bc178051.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Build a PC with Intel i9 Raptor Lake 24 cores, Asus ROG strix Z790 motherboard, Asus TUF Rtx 4090 and remaining all compatible products with SSD.\nPrevious actions:\n[link]  CPU -> CLICK\n[button] START A NEW BUILD -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK\n[button]  SELECT -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.453, 0.274, 0.512, 0.285] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc174cb2-520d-49c3-93da-f93a1c485c03_9fd3a843-608c-4ab6-9bd2-3adee3a14559.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Calculate the fare options to go from the south station to the north station\nPrevious actions:\n[button] Fares  -> CLICK\n[link] Fares Overview -> CLICK\n[combobox] Enter a location -> TYPE: south station" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.682, 0.204, 0.695, 0.211] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/883fc533-d267-4eeb-8ccd-fe77bc28cd9b_0b780e87-4aa8-4eaf-a19b-cb3457052141.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Discover Katy Perry and add bookmark to it and view all tracks.\nPrevious actions:\n[link] Search -> CLICK\n[textbox] Search -> TYPE: Katy Perry\n[button] Search -> CLICK\n[a] -> CLICK\n[button] BOOKMARK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.469, 0.457, 0.531, 0.485] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2d18cb36-5628-49e8-a336-c25c153c5527_94da50d6-e71f-4997-abeb-db862c325ecc.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 John Atas's trip with the confirmation number 1000001\nPrevious actions:\n[tab] MY TRIPS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.056, 0.362, 0.17, 0.377] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0ff1648e-28bb-4014-9b8a-3c050c25e334_c14edccf-de52-47b8-928c-f87f13139747.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 women's hiking boots section and filter the results to show only those that are waterproof and have a rating of at least 4 stars and size 6.\nPrevious actions:\n[button] Camp & Hike -> HOVER\n[link] Women's -> CLICK\n[link] add filter: 6(220) -> CLICK\n[link] add filter: Waterproof(171) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.053, 0.431, 0.204, 0.441] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/dfa415d9-efb2-4477-bc33-672f02d3399d_89654b34-bfdf-4514-b1a1-1aa91462bf85.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a low-priced small air-conditioned car on rent in Mexico City Airport for under 100 dollars and book without insurance for next day.\nPrevious actions:\n[span] Car rentals -> CLICK\n[searchbox] Please type your destination -> TYPE: mexico city\n[option] Mexico City - Benito Juarez Intl, MX (MEX) Mexico -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.82, 0.204, 0.93, 0.227] in the image\nAnd my action is Action: SELECT\nValue: Low to High" } ]

{ "bytes": "", "path": "./images/0b16b42c-dea7-4079-a2a8-79eb23447193_80087b51-ce0f-4a04-b7ef-512f6c67dfc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[link] Fly to Miami (MIA) -> CLICK\n[button] New York/Newark (EWR) Miami (MIA) Roundtrip|Econom... -> CLICK\n[textbox] Departure -> CLICK\n[gridcell] Saturday, May 13, 2023 -> CLICK\n[gridcell] Thursday, May 18, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.301, 0.486, 0.699, 0.517] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6c28458c-ba2a-41a5-b5c2-948f2954c25b_a20c534d-630c-4fa9-94d6-ef298b8e67ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest travel time flight for 1 traveler from JFK, NYC to Heathrow, London on April 19, then from Heathrow, London to CDG, Paris on April 21 and then from CDG, Paris to JFK, NYC on April 23\nPrevious actions:\n[button] PLAN TRAVEL -> CLICK\n[link] Flights -> CLICK\n[link] Search flights multiple cities -> CLICK\n[textbox] From , required. -> CLICK\n[textbox] From , required. -> TYPE: JFK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.101, 0.381, 0.393, 0.402] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_4326dff5-bcbc-46fd-a64f-37c77bc38404.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[div] Pacific Coast Highway Road Trip -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: LOS ANGELES\n[span] Los Angeles Intl Airport -> CLICK\n[textbox] mm/dd/yyyy -> CLICK\n[select] April 2023 -> SELECT: July 2023" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.639, 0.305, 0.666, 0.328] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c91b907-39db-49c3-af73-5eb5c2390a93_a2f646a1-bb6e-4bef-8e80-9f65de82161c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a store in Modesto California and set is as my store.\nPrevious actions:\n[link] Find a store -> CLICK\n[searchbox] Search carmax locations. -> TYPE: california" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.326, 0.11, 0.34, 0.119] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/03ac581c-ef95-4435-9d35-435e198b82de_ca7b5174-50e8-410c-882e-d33568d72b38.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View the Emergency Sickness Plan policy certificates for Connecticut.\nPrevious actions:\n[button] Cars & Services -> CLICK\n[link] Protections & Coverages -> CLICK\n[heading] Emergency Sickness Plan (ESP) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.699, 0.396, 0.748, 0.414] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/caafd610-202e-49d2-85d1-3f167f3ab443_5f017f7d-93a9-4835-b53f-c1af4eccc6e8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the map of a Six flags park in mexico\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.514, 0.242, 0.783, 0.281] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b3fbf029-aa63-4dd1-879f-47d8abbae4d4_61dd1ff8-f57e-465b-8b8f-90340bb4c4d1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an attorney for divorce in Union City, NJ.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.615, 0.163, 0.675, 0.174] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8d9e09e1-c31a-420b-ace8-079204db551a_6ed5c79c-dd28-42e1-af23-8a7962616627.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Select a ticket for an event similar to professional boxing\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: professional boxing\n[option] Professional Boxing -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.063, 0.126, 0.251, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/27724810-0bc8-446a-a2f4-b53a87e190df_36b4afb0-08a0-487e-9118-53846861391d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 location and operating hours of the nearest CVS pharmacy to zip code 90028\nPrevious actions:\n[button] change store -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.363, 0.151, 0.593, 0.169] in the image\nAnd my action is Action: TYPE\nValue: 90028" } ]