Datasets:

neulab

/

Mind2Web_train_llava

like 2

{ "bytes": "", "path": "./images/1d0dcb84-da65-4830-ba60-cc2b09a52a13_e7149b0a-8004-47b5-a369-901f174947a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 plastic bathroom baskets that are gray from low to high prices near zip code 60173.\nPrevious actions:\n[textbox] Enter zip code to save preferred delivery location... -> TYPE: 60173\n[span] Update ZIP code -> CLICK\n[span] See all bathroom boxes & baskets -> CLICK\n[button] Show filter modal Color -> CLICK\n[checkbox] Gray 12 products -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.353, 0.122, 0.454, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b39c9ac-a965-4902-a7d9-ec7fb36ca096_1dd4cd76-6894-4702-8d5e-d107e0846f67.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of a flight between San Antonio, Texas, and Bellingham, Washington on April 8.\nPrevious actions:\n[link] Flight status -> CLICK\n[textbox] From , required. -> TYPE: san antonio\n[a] SAT - San Antonio International, TX -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.381, 0.32, 0.62, 0.337] in the image\nAnd my action is Action: TYPE\nValue: washington" } ]

{ "bytes": "", "path": "./images/acc13b3d-0585-4cbe-a2b1-30c6e25517fa_e5e1ae2d-f013-428c-a7ff-d3144deb008c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] Gift Cards  -> CLICK\n[link] Browse Gift Cards -> CLICK\n[button] Our Brands -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.228, 0.456, 0.316, 0.511] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_e7266152-d209-4b04-b2dc-0c07b35a3d1b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.279, 0.0, 0.354, 0.031] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6d338fef-6d40-4f08-a045-861ddbc3d9f4_46aff272-d165-4cda-bb3a-39cf087aaba3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 glamping locations in Northern California.\nPrevious actions:\n[link] WAYS TO STAY  -> CLICK\n[link] GLAMPING  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.207, 0.276, 0.324, 0.286] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e9c7496f-bdea-4651-aeae-0f4d12d59d12_4d4276de-b1f8-4b63-95a9-90730f481623.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Filter car accident lawyers in Stanford, CA, sort them by distane and find the phone number of the nearest one.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.407, 0.164, 0.586, 0.198] in the image\nAnd my action is Action: TYPE\nValue: Stanford, CA" } ]

{ "bytes": "", "path": "./images/58badcfc-343a-47c1-8aec-f609925eb4ed_332e2265-61e7-4ed9-b753-4fe9255dc1e0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ricky Kej track to listen and share which has been added in the last year and is between 2 to 10 minutes.\nPrevious actions:\n[searchbox] Search -> TYPE: Ricky Kej\n[link] Search for “Ricky Kej” -> CLICK\n[link] Tracks -> CLICK\n[link] Added any time -> CLICK\n[link] Past year -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.039, 0.44, 0.212, 0.46] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f75897b-8df4-4f4c-88c3-72d440f6a4ee_a5d96eea-9933-4c28-aba9-b0b7b95ea8a4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me all the destinations in Armenia, Austria, Belgium and Bulgaria in Alphabetical order\nPrevious actions:\n[button] Plan -> CLICK\n[link] Try Somewhere New -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.035, 0.047, 0.128, 0.093] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7cee0c0-b67d-46b8-bbd1-9f042fe810f5_7c7f0a13-b479-4828-9bd3-dbbb8bafdace.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Retrieve booking for 123456 last name Smith.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.252, 0.273, 0.479, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/130b1cd5-3e2f-4676-aea4-24ba9706171b_dd3a385f-430e-44de-adb5-e2318ec80c1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 on demand sales section and rent a film in HD format.\nPrevious actions:\n[link] Visit the On Demand page -> HOVER\n[link] On Sale Now -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.217, 0.122, 0.395, 0.328] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ecb649da-0ca7-4707-8ebb-8707296e28b7_8735b62b-f80c-4908-8d6f-bb314454a8b7.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flights available from Calgary (CYYC) to New York (ZNY).\nPrevious actions:\n[textbox] Origin -> TYPE: Calgary" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.339, 0.22, 0.632, 0.228] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14b72eb6-48c6-4408-9044-94c3003dccfc_ff659553-9a17-46b7-8ba2-3b166e41eb8e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[checkbox] 10 May 2023 -> CLICK\n[checkbox] 12 May 2023 -> CLICK\n[button] Search -> CLICK\n[button] Choose your room -> CLICK\n[link] Choose Another Hotel -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.842, 0.268, 0.968, 0.29] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/36f2e415-356b-4e44-9ab1-6c3054d4de1f_3072f153-fda1-40dc-a266-ae38ada19df4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check if cars are available for tomorrow at Elevated Escape in North Carolina.\nPrevious actions:\n[div] Elevated Escape -> CLICK\n[div] Tue, Mar 28 -> CLICK\n[checkbox] 24 March 2023 -> CLICK\n[div] Sat, Mar 25 -> CLICK\n[checkbox] 25 March 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.853, 0.088, 0.923, 0.115] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9b03e9a1-39bb-48d5-a33a-a2b05a6eb379_9761249d-77f4-4009-a2f7-051f0a77a81a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 upcoming MLB games taking place on Sunday, 3/19.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.36, 0.1, 0.384, 0.115] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/31a74ae0-4b8a-407b-8f3d-a094a6966254_3c77beb9-4242-4ebe-8ec6-d5599cf39cd9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 books of Dr Seuss with price range of $20 to $40 and add 2 to basket.\nPrevious actions:\n[link] Dr. Seuss -> CLICK\n[select] All -> SELECT: US$20 to US$40\n[button] Refine results -> CLICK\n[button] Add to basket -> CLICK\n[button] Close -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.374, 0.327, 0.517, 0.36] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cd92cea9-a60f-4e09-90d7-32384ccdd61c_b75cd0fb-f7e4-4a75-a5aa-58ce641b02be.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 most played games based on daily players.\nPrevious actions:\n[link] New & Noteworthy -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.313, 0.204, 0.369, 0.225] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c02c193-2aef-4817-92b4-56722edc6b57_944f9f58-f6e0-4143-a86a-a3ee31f8e955.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\n[textbox] Search by keyword or web id -> TYPE: skirt\n[textbox] Search by keyword or web id -> ENTER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.279, 0.048, 0.288] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/009cc066-87b2-4ebb-ad8f-41eeb3d94be6_abd904e6-4b53-4414-95db-52a328c92bb3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.476, 0.091, 0.523, 0.107] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c5d1ecbe-f7a6-4d27-9e03-08dcfdcb524f_c72c6551-816f-4f68-a498-19516269cc9f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a flight + cruise for two flying from Atlanta in October for vacation starting on October 8 for 6 nights with Miami as the departure port, choose the cheapest flight, hotel, and room in the cruise for booking.\nPrevious actions:\n[span] Flights + Cruise -> CLICK\n[button] Search flights + cruise External Link should open ... -> CLICK\n[combobox] Departing from -> TYPE: ATLANTA" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.704, 0.163, 0.96, 0.182] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/be5bae8d-bebc-4474-9d28-1cc633be8d8d_2431a829-5471-430a-b02a-c30e63a9c5c4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest hotel in New Delhi for 3 days starting from April 24 and add 3 to list.\nPrevious actions:\n[button] Check-out April 25, 2023 -> CLICK\n[button] Apr 26, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK\n[combobox] Sort by -> SELECT: Price: low to high" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.403, 0.247, 0.422, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_8516581e-6b9e-469b-8862-803974da5ef9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[button] San Francisco California, United States -> CLICK\n[button] Pick-up date April 2, 2023 -> CLICK\n[button] Apr 8, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.033, 0.142, 0.047, 0.151] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/a513befc-46c3-4bb6-87c0-8f219107c756_cc647dd5-2319-4fd2-a79e-b64dc529275b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a NBA basketball game for the PS5 to the shoping cart\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.097, 0.646, 0.131] in the image\nAnd my action is Action: TYPE\nValue: nba2k23" } ]

{ "bytes": "", "path": "./images/f9e88baa-a109-454b-839f-1ab0746a5f13_7ef7d650-69ff-4cbf-a538-30a540a0be22.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all watch options of Avatar: The Way of Water and where it's available.\nPrevious actions:\n[textbox] Search TV Shows and Movies... -> TYPE: Avatar The Way of Water" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.062, 0.192, 0.594, 0.203] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/24de7f7d-f3f0-41a6-a578-e35b513b46e5_7c000882-e591-4c81-85ea-ed2ff428e75c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[checkbox] 7.4 cubic foot (6) -> CLICK\n[span] Price -> CLICK\n[img] expand -> CLICK\n[spinbutton] Enter Minimum Price -> TYPE: 0\n[spinbutton] Enter Maximum Price -> TYPE: 1000" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.816, 0.169, 0.84] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/04d45cb8-136b-419a-a324-dfbc5e93b7a2_d44b31d5-4480-44c8-b773-49adca6d7e9c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 activities in Miami with lowest price and minimum 4 star rated.\nPrevious actions:\n[generic] United States -> CLICK\n[button] SEARCH -> CLICK\n[span] Sort and filter -> CLICK\n[div] -> CLICK\n[checkbox] 4 stars rating -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.222, 0.074, 0.237, 0.083] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/fdcac1e8-1dd0-4846-b2cf-16d916ea9e17_2f28c65c-d95f-4e34-b76b-db3a412b8fc4.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 tickets for los angeles kings this weekend\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: los angeles kings\n[option] Los Angeles Kings -> CLICK\n[button] All dates -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.724, 0.518, 0.881, 0.541] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b7e501a4-5dee-406e-b6ba-00eed783df0c_861c9513-4fed-487b-8eea-fd35543e0599.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 KOA campground in California that has RV sites.\nPrevious actions:\n[link] Filters -> CLICK\n[checkbox] RV Site -> CLICK\n[textbox] WHERE DO YOU WANT TO GO? -> TYPE: California" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.227, 0.367, 0.316, 0.388] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/ab23e83a-e3bd-4648-9d68-989f5c158d8f_2f8df0c4-d081-4b95-a0d3-3d80f872ac6a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Request a refund for the traveler Ian Lo and, his document number is 12345678912345 and email [email protected]\nPrevious actions:\n[tab] MY TRIPS -> CLICK\n[link] Request a refund -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.083, 0.537, 0.197, 0.567] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e12f51f6-c8c5-4a68-9586-d77927bca79c_4713b2b4-b558-441a-8635-75ad2fa8a3a5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add a Tesla Shop Gift Card for April May with the email [email protected] to my cart\nPrevious actions:\n[link] Shop -> CLICK\n[menuitem] Lifestyle -> CLICK\n[img] Tesla Shop Gift Card -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.688, 0.26, 0.929, 0.277] in the image\nAnd my action is Action: TYPE\nValue: April May" } ]

{ "bytes": "", "path": "./images/f122e4c9-7634-4193-94f9-8623cd75d1f1_fce397d8-aece-4a06-8c4f-1a90b6b1a8bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Manchester Piccadilly to any station in London on April 8, leaving nearest 10 AM for 1 adult\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> TYPE: Manchester\n[span] Manchester Piccadilly -> CLICK\n[span] London -> CLICK\n[textbox] Date use format: 16-Mar-23 -> CLICK\n[link] 8 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.259, 0.133, 0.282] in the image\nAnd my action is Action: SELECT\nValue: 10" } ]

{ "bytes": "", "path": "./images/747429fa-7dac-4ab0-b604-13cb9bf787fe_65d6ae1d-4269-4ca6-9e02-0aabb1af9aca.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest unused wireless Logitech Keyboard under $70.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.282, 0.016, 0.39, 0.051] in the image\nAnd my action is Action: TYPE\nValue: wireless keyboard" } ]

{ "bytes": "", "path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_dd98ebcc-12fe-476a-aa79-7c94bde9eabf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.5, 0.0, 0.597, 0.044] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87b23bf1-3c23-45a6-82bf-5a535c7cdc2f_95da4d8d-e01b-4bdc-9f1c-01ab6235c3ed.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest long-term car rental with a fuel plan, GPS, and satellite radio from June 29 to July 28, pick up at 9 am at Orlando airport and dropping off at the same location.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.072, 0.479, 0.19, 0.525] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/26d3a803-b0aa-4a2c-bd31-3fe97a63388c_99a22a2c-d4bc-42e8-922b-7e29faba46d8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 vacation packages to Hawaii.\nPrevious actions:\n[link] Search for packages -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.742, 0.416, 0.83, 0.429] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/6ca55141-9ba6-4ed7-8c07-77df6c24029d_963377e9-ccf5-42ae-90ad-74516b1a38a6.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced gray-colored round-shaped mirror in stock in Atlanta, Georgia, with a maximum price of 20 dollars.\nPrevious actions:\n[button] Shape -> CLICK\n[span] -> CLICK\n[button] Shape -> CLICK\n[span] -> CLICK\n[button] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.656, 0.415, 0.966, 0.448] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/f754d919-2191-464e-a407-0f3da9409081_efd43e42-a268-4260-9e20-0333d7e55f50.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: See today's deals on video games and find the best deal on the lowest-priced mouse.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.009, 0.029, 0.054, 0.048] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_954678cc-e3c6-4ded-85b6-8032ea329f5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Alinea\n[span] Chicago, IL - Lincoln Park -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.87, 0.275, 0.908, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_d91dd847-e852-4522-8725-3ddd418c8f7c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[searchbox] Search by ZIP code or city, state -> TYPE: san diego\n[button] Submit -> CLICK\n[span] Select store -> CLICK\n[link] Flatware -> CLICK\n[button] Show more filters modal -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.95, 0.091, 0.969, 0.105] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/837989e0-7476-496a-be02-e4c69f1f989b_0c0f9528-0f31-46b0-b7c4-78507a1facc1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest one way flight from Mumbai to Dubai on 24 May.\nPrevious actions:\n[button] Remove -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.244, 0.091, 0.376, 0.112] in the image\nAnd my action is Action: TYPE\nValue: Mumbai" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_6c672ebf-8e99-41ab-843c-8fac574b2092.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[button] Water -> HOVER\n[link] Paddle Boards -> CLICK\n[img] TAHE Beach SUP-Yak Tandem Inflatable Stand Up Padd... -> CLICK\n[button] Add to cart—$799.95 -> CLICK\n[link] Cart & Checkout -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.671, 0.25, 0.956, 0.268] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5ad0f114-6cea-4f61-af3d-f9f4d4096d6c_e644a94d-62bd-43a0-8279-1ea74b67e337.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Uncharted: Legacy of Thieves Collection to my guide and find the Queen's bracelet information.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.019, 0.153, 0.196, 0.175] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5c52af02-ccc7-491a-bea7-05de278bf7da_870c171f-328a-46b1-8d81-e111a3d7a5f1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest flight from any New York airport to Aruba for 1 person using TrueBlue points which leaves on May 1 and returns on May 5\nPrevious actions:\n[textbox] To -> TYPE: Aruba\n[option] Aruba (AUA) -> CLICK\n[span] 1 -> CLICK\n[button] return Friday, May 5, 2023 -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.752, 0.219, 0.853, 0.257] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/164cf025-e767-4781-930d-5bd46ad2c4c1_aa4ff294-fa00-493f-8625-e483115057f9.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: What are the Resy Staff Favorites in Seattle?\nPrevious actions:\n[button] Location Atlanta -> CLICK\n[button] Seattle -> CLICK\n[textbox] Search restaurants, cuisines, etc. -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.489, 0.119, 0.576, 0.139] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/34e13beb-0235-41d4-b108-137cc7480904_b3dd079c-2531-400a-92c1-7555485e132e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] CITIES -> CLICK\n[span] Find your state -> CLICK\n[link] New York -> CLICK\n[link] New York -> CLICK\n[span] Enter an Address or Venue to find parking -> TYPE: 66 perry st" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.261, 0.2, 0.272, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_383cc11d-8136-408f-bb05-a3222ccfdfc0.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.06, 0.105, 0.374, 0.116] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/3cb44998-5a0c-44c5-84b7-ffb729a356d8_1959a470-8e5c-4c0f-826c-a690ded653ae.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the schedule between New York and Washington DC sorted by shortest trip.\nPrevious actions:\n[textbox] From -> TYPE: New York\n[option] New York, NY - Moynihan Train Hall at Penn Sta. (N... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.333, 0.163, 0.554, 0.182] in the image\nAnd my action is Action: TYPE\nValue: Washington" } ]

{ "bytes": "", "path": "./images/3c098275-ff82-48b1-bd00-6313b4caf215_fe9e507b-6b68-4939-b7eb-2cd4132794b2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] Pick-up -> TYPE: San Francisco\n[button] San Francisco California, United States -> CLICK\n[button] Pick-up date April 2, 2023 -> CLICK\n[button] Apr 8, 2023 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.608, 0.306, 0.664, 0.32] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b770af80-75f0-470c-8797-1466d90c35ce_04efa8bd-69ee-4f5a-97a9-0a70d2e5de36.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest last-minute pet-friendly road trip hotel deal in May for a single person with a pet and book.\nPrevious actions:\n[button] Road Trips -> CLICK\n[button] Last-Minute -> CLICK\n[button] $ Price: Low to High -> CLICK\n[button] DONE -> CLICK\n[heading] $139 Vermont: Cozy Kimpton in the heart of Manches... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.728, 0.242, 0.845, 0.26] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_009a6173-dd0d-4afc-89c3-25931c746449.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\n[button] close -> CLICK\n[button] Flavor -> CLICK\n[div] -> CLICK\n[button] close -> CLICK\n[button] Pizza Crust Type -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.723, 0.28, 0.802, 0.295] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/e48f848d-62b8-441e-aafb-c76aeb2c4f84_662fb87c-70e4-4f70-bf85-337aa79a8d75.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an internship role for a university graduated in the in Germany, and apply to the job posted in last 7 days.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.055, 0.457, 0.945, 0.563] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/06a6d90b-071d-4644-8372-b928e99ae970_63b445da-7103-4ceb-b2b2-afc1395d10c2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[textbox] DESTINATION WHERE CAN WE TAKE YOU?SEARCH FROM CUR... -> TYPE: NIAGRA FALLS\n[option] Niagara Falls, ON, Canada -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.358, 0.108, 0.661, 0.184] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/24de7f7d-f3f0-41a6-a578-e35b513b46e5_0a38b7ed-8182-4324-bbae-469672aa4c1d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[textbox] Search by SKU, Model # or Keyword -> TYPE: Magtag electric dryer\n[button] Maytag in Electric Dryers -> CLICK\n[checkbox] 7.3 cubic foot (5) -> CLICK\n[checkbox] 7.4 cubic foot (6) -> CLICK\n[span] Price -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.144, 0.28, 0.156, 0.311] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ed913ba-62a3-4214-a947-217b74c4b8f7_178bcb43-7ba1-429d-a973-088ef383426e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List upcoming animation and anime movies in theaters\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.39, 0.313, 0.658, 0.345] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_7591b059-f011-44df-9bc3-cf3399a62179.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[tab] Flights -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.192, 0.09, 0.266, 0.106] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8ab1c90f-52e0-4c07-9d41-d44c75c25c5e_3371a7e6-bf53-469a-941f-47a7f6038b5d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for an automatic grey sports car with the lowest price, gas fuel and free shipping manufactured between 2018 to 2022, compare the top two results and compare photos.\nPrevious actions:\n[button] Fuel Type -> CLICK\n[listitem] Gas (45) Gas (45) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Year -> CLICK\n[button] 2010 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.01, 0.389, 0.238, 0.41] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/973bf55c-d1a0-41c7-9ec8-9f59b3dbfb58_c8aaa308-dddf-4bc7-9835-e30a48203407.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Repost on my feed a rock playlist.\nPrevious actions:\n[searchbox] Search -> TYPE: rock\n[button] Search -> CLICK\n[link] Playlists -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.426, 0.251, 0.47, 0.262] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_c3092161-3b70-4ae0-833a-2ec69d613c38.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[input] -> TYPE: beauty salons\n[link] Beauty Salons -> CLICK\n[input] -> TYPE: Seattle, WA\n[link] Seattle, WA -> CLICK\n[link] Seattle, WA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.789, 0.005, 0.867, 0.023] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edb8e817-e9d7-45eb-9706-01967e3a0fe8_f7935528-8d53-49ae-9235-70b6c1304d79.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get offer to sell car with AZ XA1234 number plate from Arizona state.\nPrevious actions:\n[LabelText] Sell My Car -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.255, 0.19, 0.5, 0.209] in the image\nAnd my action is Action: TYPE\nValue: XA1234" } ]

{ "bytes": "", "path": "./images/2eaf60d5-d2af-4f50-a3ad-5cc9132a770a_53d2d9a2-528f-4a9a-b182-b80a0795a6a2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[link] Used Gear -> CLICK\n[menuitem] Women's -> CLICK\n[menuitem] Running Shoes -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.021, 0.213, 0.218, 0.224] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/126b4604-8b04-4eb1-9027-266631c96f01_00403920-e25f-4c7e-877c-e8e119cda4e5.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book an outdoor table for 3 people at a Los Angeles restaurant for 5:00 PM on April 7th\nPrevious actions:\n[button] Los Angeles -> CLICK\n[link] La Cha Cha Cha -> CLICK\n[div] Today -> CLICK\n[button] April 7, 2023. -> CLICK\n[combobox] Guests -> SELECT: 3 Guests" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.127, 0.721, 0.235, 0.754] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d516b2f7-b180-422f-9e24-6fb778cb4b55_51e09831-d247-402b-9853-bfaeb5d4399b.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Ed Sheeran Chords & Tabs\nPrevious actions:\n[textbox] Enter artist name or song title -> TYPE: Ed Sheeran" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.531, 0.081, 0.897, 0.11] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ed913ba-62a3-4214-a947-217b74c4b8f7_f3eb8779-cf1a-4688-a021-2a5257bba89d.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: List upcoming animation and anime movies in theaters\nPrevious actions:\n[link] MOVIES -> CLICK\n[button] IN THEATERS -> CLICK\n[link] COMING SOON -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.156, 0.17, 0.226, 0.187] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/8f567f79-e197-4d7e-9a49-877daae6dde5_4b20b395-938e-4a1a-8f71-bdf4dfb419e2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Blue iPhone 12 Pro 128gb and add to cart.\nPrevious actions:\n[combobox] Search for anything -> TYPE: iPhone 12 Pro\n[button] Search -> CLICK\n[link] 128 GB - apply Storage Capacity filter -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.387, 0.265, 0.837, 0.277] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/9e3d2edb-6535-4180-9050-ade88dbf798e_21b2e6cd-1e81-4e05-b5f0-37feba1bafe2.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Chevrolet with lowest mileage in zip 08817 with shipping charges of 99 dollars or less, with a price between 20k to 30k.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.74, 0.009, 0.891, 0.027] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/5307bed6-1664-4cf7-9e60-0f563f9fa4fe_4abeefc8-cbb3-4f6b-9059-6c379d4e2e26.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 room for one traveler on April 3-6 that is closest to National University of Singapore and costs less than $500\nPrevious actions:\n[button] National University of Singapore Singapore, Singap... -> CLICK\n[button] Check-in April 5, 2023 -> CLICK\n[button] Apr 3, 2023 -> CLICK\n[button] Apr 6, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.826, 0.143, 0.931, 0.171] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/14be9a2b-5559-423b-8362-4dccf306992e_07461677-526b-43c3-96a0-f92b0e69a3b1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rail for Oyster Bay, Provincetown.\nPrevious actions:\n[link] commuter rail Commuter Rail -> CLICK\n[combobox] Search for a line -> TYPE: Oyster Bay\n[span] Oyster -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.006, 0.272, 0.344, 0.299] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/13d78369-994a-4202-a9ed-8361e1fdea9d_c01ffea2-9354-448e-8ff9-2f3083925381.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 bluetooth headphones with active noise-cancellation.\nPrevious actions:\n[searchbox] Search Site -> TYPE: headphones\n[button]  -> CLICK\n[span] Active -> CLICK\n[button] APPLY -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.025, 0.752, 0.158, 0.762] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/edf748d4-07cd-4f0b-aad3-01baebbd557b_56fe6cc9-a3e9-4b7c-990c-803cd8a94f2f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest available hotel for a three night stay from 1st June in Jakarta. The guest is named Joe Bloggs with the email address of [email protected] and phone number of 11111111111. Billing address is in New York, zip code 10001\n.\nPrevious actions:\n[textbox] Address 1 -> TYPE: the home of joe bloggs\n[textbox] City -> TYPE: new york\n[textbox] Postcode/ZIP code -> TYPE: 10001\n[combobox] State -> TYPE: new york\n[textbox] Card number -> TYPE: 1234" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.634, 0.369, 0.95, 0.403] in the image\nAnd my action is Action: SELECT\nValue: MasterCard" } ]

{ "bytes": "", "path": "./images/17fffbee-e41b-46e4-ab75-675b263ca7b7_2a48ee3e-f492-498c-bdad-de1107d2da4c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest power supply unit with at least 600W power output.\nPrevious actions:\n[searchbox] Search Site -> TYPE: 600w power supply\n[button]  -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.766, 0.385, 0.823, 0.4] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/63529dc2-7b13-493e-9a0c-b1ce50256a16_d8569323-5315-47fb-9b08-d9b48ce92b2e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 flight status for the flight 12345678 leaving on april 7\nPrevious actions:\n[link] Flight status -> CLICK\n[span] Flight number -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.126, 0.346, 0.365, 0.364] in the image\nAnd my action is Action: TYPE\nValue: 12345678" } ]

{ "bytes": "", "path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_30f0a458-bb0c-49e4-b940-6b82a6d7b082.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[textbox] From -> CLICK\n[button] Ireland -> CLICK\n[span] Dublin -> CLICK\n[button] France -> CLICK\n[span] Paris Beauvais -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.134, 0.225, 0.161, 0.251] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_7005bf98-3214-4bfb-8133-79cfab48306e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[span] Stays -> CLICK\n[button] Unlock deals External Link should open in a new wi... -> CLICK\n[div] Search location -> TYPE: TEXAS CITY" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.142, 0.206, 0.374, 0.227] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7a40f4c8-7aa6-4be4-abbe-24a0b511dc0e_28f01eb6-f60d-4efe-82b9-6bab5fb6765c.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 hiking boots and filter the results to show only those with a waterproof rating of at least 3 stars.\nPrevious actions:\n[button] Camp & Hike -> CLICK\n[link] Hiking Footwear -> CLICK\n[link] add filter: Waterproof(456) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.053, 0.773, 0.208, 0.787] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4ee7d5e1-50be-49d2-8af1-83b3da0519ad_c67ea018-cdc3-44b1-aec9-1dd781811f05.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show the details for a monthly parking option in Ney York City near Street Taco to start on may 6 that i can self park\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: street taco\n[li] Street Taco, Broadway, New York, NY, USA -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.016, 0.256, 0.384, 0.294] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/49372757-4c58-4cb5-bdb4-eed0c3e83199_5fa29f1e-7753-4629-b276-e8466bef50a1.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[textbox] Find -> TYPE: electrician\n[span] Electrician -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.164, 0.214, 0.257, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/4f069a59-c53b-4efe-bcfb-fc9fd864ea2e_cf70ebee-773d-4ad7-b6b1-a2d55fdca152.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rare books and sort the results by auction end time.\nPrevious actions:\n[combobox] Search for anything -> CLICK\n[combobox] Search for anything -> TYPE: rare books\n[button] Search -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.346, 0.128, 0.39, 0.152] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/97e3f951-891d-4626-8dbb-ab6e39261d05_f566954c-0762-4dcf-a758-b847ef11f301.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find first class flight for May 27 from JFK, New York to Heathrow, London for 2 adults, one 4 year old child and one infant under 1 year old who will sit on a lap.\nPrevious actions:\n[button] Departing April 5, 2023 -> CLICK\n[button] May 27, 2023 -> CLICK\n[button] Done : (Save changes and close the date picker.) -> CLICK\n[button] Leaving from -> CLICK\n[textbox] Leaving from -> TYPE: jfk" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.069, 0.28, 0.362, 0.326] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/00deddc4-8991-47b5-92f1-f9eb88011b16_9fd0d975-1788-4b24-ae73-d661fc03b8ea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find all outdoor events this month in NYC\nPrevious actions:\n[span] Special events -> CLICK\n[DisclosureTriangle] All locations -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.332, 0.192, 0.471, 0.208] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/80e12375-19ad-400f-9e35-2a3853173bed_1a61760b-4d3e-459f-9940-00033fd2555e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Shop for the same-day delivery of thin crust frozen pepperoni pizza and add 2 packets to the cart.\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.066, 0.031, 0.164, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/bf94a193-a30b-45b7-a93e-4733ea6a7ed4_158410d4-4bff-4a9d-bd03-39997c0c9a89.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Alaska Cruises from Seattle in September 2023 with a duration of 8 days for 4 people on a ship Carnival Luminosa.\nPrevious actions:\n[button] 6 - 9 Days -> CLICK\n[button] SEARCH CRUISES -> CLICK\n[button] Number of Guests -> CLICK\n[path] -> CLICK\n[path] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.345, 0.083, 0.416, 0.1] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7ec95f61-b8f4-4431-84d2-55d9f7cdd594_5335dfb4-618b-4282-951a-e9066ef63841.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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[option] United Airlines (UA) -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: belo horizonte\n[button] Belo Horizonte, MG, BR (CNF - Tancredo Neves) -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: buenos aires\n[button] Buenos Aires, AR (EZE - Ministro Pistarini) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.087, 0.366, 0.246, 0.392] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/53b4ca73-c05b-4609-98c8-a0a62072bdb5_25e25bd8-d8c8-4a09-a158-eccbd9e38296.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 cheapest vitamin C and D to cart.\nPrevious actions:\n[button] load Vitamins Menu -> CLICK\n[button] load Vitamins A-Z Menu -> CLICK\n[link] Vitamin C -> CLICK\n[div] Relevance -> CLICK\n[div] Price Low to High -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.416, 0.316, 0.574, 0.442] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c9740663-a6aa-4aee-919a-330a9f2b3091_603d8a45-cc7a-4dc0-a899-c74f8c86e870.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find highest rated room for one adult in Los Angeles, CA between May 7 to May 14 which offers senior discount, free breakfast, is pet friendly and has a pool\nPrevious actions:\n[span] , CA, USA -> CLICK\n[button] 1 NIGHT Sat, Apr 08 - Sun, Apr 09 -> CLICK\n[span] 7 -> CLICK\n[span] 14 -> CLICK\n[button] Done -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.232, 0.118, 0.353, 0.128] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/2a831fb6-3110-4ffb-8687-1d2acab09873_2cdca21b-352f-4f82-84fa-16b60dde7c28.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a park that has a campground and is located in the state of Colorado.\nPrevious actions:\n[link] FIND A PARK -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.44, 0.194, 0.56, 0.204] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/df3b7cd4-526e-453b-9114-c0db1b3ed5ea_08a0952a-311d-46f3-bcfd-f183dc5cf434.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Dining Room Sets under furniture and filter the results to show only items availble under the Buy It Now format.\nPrevious actions:\n[link] Home & Garden -> CLICK\n[button] Furniture -> CLICK\n[link] Dining Sets -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.83, 0.661, 0.933, 0.686] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/55631305-2957-4343-b4f7-73aa68acba47_64eb802f-8390-4ffb-8a72-1f10211fffbe.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy two tickets for the Boston Red Sox vs. New York Yankees game on August 18th, with a total cost of no more than $200.\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: red sox vs yankees\n[button] Search -> CLICK\n[link] TICKETS -> CLICK\n[span] -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.771, 0.256, 0.799, 0.287] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_1a2a11b4-132e-4f75-a8fb-ab3ede13cd0f.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[path] -> CLICK\n[textbox] From -> TYPE: faro\n[span] Faro -> CLICK\n[textbox] To -> TYPE: bournemouth\n[span] Bournemouth -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.367, 0.309, 0.394, 0.326] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/254a67f6-3e37-4f12-838d-2d9fb0cedbf0_eaf260c8-e239-4e96-b387-970c8a48e56e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 stats of the Athletic Club from spanish Laliga\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.341, 0.036, 0.356, 0.051] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/c4538b84-ca81-413a-8f3d-7ce87e42b4f6_4dd1dfca-450b-40d4-a55b-c20df696ad63.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 Saturday park hours for Six Flags, Magic Mountain.\nPrevious actions:\n[button] Browse the Parks Below -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.527, 0.583, 0.846, 0.614] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/cc174cb2-520d-49c3-93da-f93a1c485c03_9d6b2e4b-880a-40d0-ac9d-3f9fdcb3e7eb.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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\n[link] T red line silver line commuter rail Zone 1A Sout... -> CLICK\n[combobox] Enter a location -> TYPE: north station" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.732, 0.296, 0.745, 0.305] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/0c02c193-2aef-4817-92b4-56722edc6b57_1945d47d-5810-42ee-bc36-5f0a90c7c1f8.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see the best seller gender neutral skirts\nPrevious actions:\nNone" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.194, 0.046, 0.553, 0.083] in the image\nAnd my action is Action: TYPE\nValue: skirt" } ]

{ "bytes": "", "path": "./images/54e0d420-ec89-456a-b179-67c6b4b4babc_44b87654-0fc1-443f-88c2-f8898601f2bf.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order one TAHE inflatable stand up paddle board using my default account/shipping info.\nPrevious actions:\n[button] Water -> HOVER\n[link] Paddle Boards -> CLICK\n[img] TAHE Beach SUP-Yak Tandem Inflatable Stand Up Padd... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.591, 0.22, 0.956, 0.243] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_ae470708-5a6a-454a-a56e-1bacceda7eea.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the closest parking spot to the Orlando Magic at Brooklyn Nets event, happening in Barclays Center, to enter after 3 pm and exit after 5 pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: barclays center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.337, 0.379, 0.545, 0.399] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/81835704-aebc-4600-abd4-02102509fda5_be0a740c-1b47-4b45-b879-8a45d32f7c0a.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 premium 4-door car with automatic transmission and unlimited mileage at Heathrow Airport for pickup, on date April 26, 2 pm, and drop off at the same Airport on April 30, 1 pm, book a range rover if available with full protection.\nPrevious actions:\n[label] Pick-up location -> TYPE: Heathrow\n[div] London Heathrow Airport (LHR) -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.444, 0.129, 0.552, 0.168] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_f25623fb-9589-4fb2-984c-2da6871e9a33.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[link] VACATIONS & RAIL TOURS Train vacation packages thr... -> CLICK\n[img] -> CLICK\n[link] Close -> CLICK\n[button] Instant Quote -> CLICK\n[textbox] What city would you like to depart from? -> TYPE: Chicago" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.289, 0.416, 0.316, 0.431] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/35646414-520b-4de0-90e0-5dfeafd850a3_383ffaec-42ae-4770-9ef6-305c581ca89e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a lowest priced ticket from Bristal airport to London Paddington on April 8 after 2 pm, seating must be forward facing window side with power socket.\nPrevious actions:\n[span] Bristol Airport (By Bus) -> CLICK\n[combobox] Arrival station, none selected. Select a station. -> TYPE: LONDON\n[span] London Paddington -> CLICK\n[textbox] Date use format: 25-Mar-23 -> CLICK\n[link] 8 -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.074, 0.209, 0.133, 0.227] in the image\nAnd my action is Action: SELECT\nValue: 14" } ]

{ "bytes": "", "path": "./images/e224beac-a998-41e4-abd1-5370196ce9df_1f6d99a6-6430-48ff-a6a9-8c7881d4a609.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for the cheapest led smart home indoor strip lighting, add it to the cart, and schedule the delivery.\nPrevious actions:\n[button] Departments -> HOVER" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.171, 0.122, 0.177, 0.127] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/920f240d-77a9-476b-a1d4-dcc88d199bfa_83416428-3787-4952-875d-dcfbb6e4cdc3.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 rock music events in Canada, happening this weekend and save top three popular events for my record.\nPrevious actions:\n[link] Music -> CLICK\n[svg] -> CLICK\n[div] Canada -> CLICK\n[svg] -> CLICK\n[div] This weekend -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.245, 0.526, 0.343, 0.667] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/12324b80-88bd-4d48-962c-ae80203e5058_ebbb7fed-de37-4ce8-ad48-6bf6573f5708.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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 $1 movie night film and rent blockers\nPrevious actions:\n[link] Navigate to deals -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.889, 0.531, 0.948, 0.54] in the image\nAnd my action is Action: CLICK" } ]

{ "bytes": "", "path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_5c1467a5-8401-44d3-a4d2-2beb7cfeb39e.png" }

[ { "from": "human", "value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within 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] Make -> SELECT: Toyota\n[combobox] Model -> SELECT: Camry\n[textbox] Mileage -> TYPE: 40000\n[button] Go -> CLICK\n[div] XLE Sedan 4D -> CLICK" }, { "from": "gpt", "value": "For my next step, the target element of my action is bounded by the box [0.548, 0.436, 0.634, 0.464] in the image\nAnd my action is Action: CLICK" } ]