Embodiments relate to utilizing an optical character recognition extraction and a large language model (LLM) to automatically populate a shopping cart of a user of an online system with items from a physical recipe. The online system receives an image capturing the physical recipe and extracts a raw text from the received image. The online system generates a prompt for input into the LLM, the prompt including a task request for the LLM to generate a list of ingredients using the raw text. The online system inputs the prompt into the LLM to generate the list of ingredients. The online system maps the list of ingredients to a list of items available by one or more retailers associated with the online system. The online system causes a device of the user to display a user interface with the list of items.

Methods are described herein for implementing multi-location switching in an online marketplace. A system may receive, via a communication interface, a first request to access a user account that may be associated with one or more sub-accounts. The system may validate the first request and generate a first user interface based on the user account. The first user interface may include visual representations of data dependent on the user account. The system may present, via the communication interface, the first user interface. The system may receive a second request to access a first sub-account of the one or more sub-accounts. In response, the system may update the first user interface based on the first sub-account to yield a second user interface. The second user interface may include updated visual representations of data dependent on the first sub-account. The system may present the second user interface.

Information on one or more products is obtained from a third-party information source. The one or more products can comprise a product, a service, a coupon, or a membership. A video about the one or more products is rendered by a video user interface to a user. The video user interface and the third-party information source are interfaced between each other based on a user interaction with the video user interface. Product information is fetched from a server based on the interfacing between the video user interface and the third-party information source. The video is augmented with further information based on the fetching.

Embodiments relate to utilizing an optical character recognition extraction and a large language model (LLM) to automatically populate a shopping cart of a user of an online system with items from a physical recipe. The online system receives an image capturing the physical recipe and extracts a raw text from the received image. The online system generates a prompt for input into the LLM, the prompt including a task request for the LLM to generate a list of ingredients using the raw text. The online system inputs the prompt into the LLM to generate the list of ingredients. The online system maps the list of ingredients to a list of items available by one or more retailers associated with the online system. The online system causes a device of the user to display a user interface with the list of items.

In one embodiment, a method by a processing system includes receiving information associated with a first processing request for a first interaction, sending instructions for generating customized embedded fields within a graphical user interface displayed on a computing device associated with the user, where the customized embedded fields are configured to receive as input data associated with a digital instrument, and where a subset of the customized embedded fields is configured to analyze the data associated with the digital instrument to determine whether the data associated with the digital instrument is accurate and valid, receiving the data associated with the digital instrument, receiving a confirmation for the first interaction and an indication that the user has provided authorization to create a user profile with the processing system, facilitating an authorization for the first interaction, and creating the user profile in a database.

A unified shopping and checkout system and method for a multiple merchant e-commerce platform which allows a buyer on a multiple merchant e-commerce platform to simultaneously complete a wide variety of types of transactions through a combined shopping interface, a cart building engine, and a unified checkout interface. The combined shopping interface includes both products and live bookings from many different merchants and allows them to be browsed, compared, and selected. The cart building engine allows for the aggregation of both products and live bookings into a single transaction by, in part, providing for the provision of the information needed to prior to allowing for the purchase of all selected products and/or bookings in a single transaction, and then provides for the use the information and funds provided during the transaction to complete corresponding transactions for the products and booking selected by the user, with the selected merchants.