Abstract: An online system receives a user request from a client device through the interface, identifies one or more featured products based on the query, and generates a prompt for input to a machine-learned generative language model. The prompt specifies both the user's request and a request to suggest the featured products in association with a response to the user request. This prompt is fed into a machine-learned language model via a model serving system for execution. The online system receives a response generated by the model, generates a query response based on the response generated by the model, and transmits instructions to the client device to display the query response. The online system collects data on user interactions with the uses the collected data to fine-tune the machine-learned generative language model.

Abstract: An online system performs an atypical replacement recommendation task in conjunction with a model serving system or the interface system to make recommendations to a user for replacing a target item with an atypical replacement item. The online system receives a search query from a user and identifies a target item based on the search query. The online system identifies a set of candidate items for replacing the target item. The online system may select one or more atypical replacement items in the set of candidate items, and generate an explanation for each atypical replacement item. The explanation provides a reason for using the atypical replacement item to replace the target item. The online system provides the atypical replacement items and the corresponding explanations as a response to the search query.

Abstract: An online system presents a sponsored content page to a user in conjunction with a model serving system. The online system accesses a content page for a food item and identifies one or more sponsorship opportunities at the content page. The online system identifies one or more candidate sponsors for each sponsorship opportunity. The online system selects a bidding sponsor for the sponsorship opportunity from the one or more candidate sponsors and a candidate item associated with the bidding sponsor as a sponsored item. The online system provides a content page, a description of the sponsored item, and a request to generate a sponsored content page for the sponsorship opportunity to a model serving system. The online system receives a sponsored content page generated by a machine-learning language model at the model serving system and presents the sponsored content page to a user.

Abstract: An online system performs a task in conjunction with the model serving system or the interface system. The system generates a first prompt for input to a machine-learned language model, which specifies contextual information and a first request to generate a theme. The system provides the first prompt to a model serving system for execution by the machine-learned language model, receives a first response, and generates a second prompt. The second prompt specifies the theme and a second request to generate a third prompt for input to an image generation model that includes a third request to generate one or more images of one or more items associated with the theme. The system receives the third prompt by executing the model on the second prompt, provides the third prompt to the image generation model, and receives one or more images for presentation.

Abstract: Embodiments relate to automatically generating a basket of items to be recommended to a user of an online system. The online system communicates a basket opportunity to a group of retailers, wherein the basket opportunity defines a plurality of item categories each associated with a respective item to be included in a basket. The online system receives, from each retailer in response to the basket opportunity, a respective bid of a plurality of bids for the basket opportunity. The online system applies a computer model to each bid to determine a score for each bid and selects a winning bid for the user based on determined scores for the bids. For each item category, the online system populates the basket with a respective item from a catalog of a retailer that is associated with the winning bid. The online system then presents the basket with items to the user.

Abstract: An online system performs inference in conjunction with a machine-learned language model to determine one or more key items in an order. The system generates a prompt for input to a machine-learned language model. The prompt may specify at least the list of ordered items in the order and a request to infer one or more key items in the order. The system provides the prompt to a model serving system for execution by the machine-learned language model for execution. The system parses the response from the model serving system to extract a subset of items as the one or more key items of the order. The system generates an interface presenting the order of the list of items and one or more indications on the interface that indicate the subset of items are key items of the order.

Abstract: An online concierge system may receive, from a customer, a selection of an item that is associated with a first brand. The online concierge system may extract features associated with the customer and features associated with the item. The online concierge system may input the extracted features to a machine learning model that is trained to predict a degree of association between the customer and the first brand associated with the item. The online concierge system may identify candidate alternatives for replacing the item. The candidate alternatives may include a first alternative that is associated with the first brand and a second alternative that is associated with a second brand different from the first brand. The online concierge system may select, based on the degree of association between the customer and the first brand, one or more candidate alternatives to be presented to the customer to replace the item.

Abstract: An online concierge system generates a graph connecting items with attributes of the items and other items. Hence, the graph includes nodes corresponding to attributes and nodes corresponding to items, with an item connected to attributes of the item in the graph. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and compares different combinations of terms to the graph to determine connections between different combinations of terms in the graph. Based on measures of connectedness between combinations of terms and connections in the graph, items are identified from one or more combinations of terms. Information about the identified items is presented to the customer.

Abstract: An online concierge system generates a graph connecting items with attributes of the items and other items. Hence, the graph includes nodes corresponding to attributes and nodes corresponding to items, with an item connected to attributes of the item in the graph. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and compares different combinations of terms to the graph to determine connections between different combinations of terms in the graph. Based on measures of connectedness between combinations of terms and connections in the graph, items are identified from one or more combinations of terms. Information about the identified items is presented to the customer.

Abstract: An online concierge system generates a graph connecting items with attributes of the items and other items. Hence, the graph includes nodes corresponding to attributes and nodes corresponding to items, with an item connected to attributes of the item in the graph. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and compares different combinations of terms to the graph to determine connections between different combinations of terms in the graph. Based on measures of connectedness between combinations of terms and connections in the graph, items are identified from one or more combinations of terms. Information about the identified items is presented to the customer.

Abstract: Systems and methods for continuous processing of unstructured data streams are provided. Information may be stored in memory regarding a query, including associated search results and statistics derived at an identified time. After the identified time, unstructured data may be received from a plurality of streams over a communication network. A full-text search may be conducted on the received unstructured data based on the query to yield one or more matches. The stored statistics associated with the query may be retrieved from memory and updated based on the search results of the unstructured data received at the subsequent time. The updated statistics may then be stored in memory for retrieval at a subsequent time.

Abstract: In an online concierge system, a customer adds items to an online shopping cart. The online concierge system determines key ingredients from the items in the online shopping cart by mapping the items to generic items and removing non-ingredient items and staple items. The online concierge system retrieves recipes including at least one of the key ingredients. The online concierge system determines complementary ingredients based on the other ingredients in the recipes and calculates co-occurrence scores for the complementary ingredients. Using the co-occurrence scores, the online concierge system ranks the complementary ingredients and sends for display a subset of the complementary ingredients as recommended items.

Abstract: In an online concierge system, a customer adds items to an online shopping cart. The online concierge system determines key ingredients from the items in the online shopping cart by mapping the items to generic items and removing non-ingredient items and staple items. The online concierge system retrieves recipes including at least one of the key ingredients. The online concierge system determines complementary ingredients based on the other ingredients in the recipes and calculates co-occurrence scores for the complementary ingredients. Using the co-occurrence scores, the online concierge system ranks the complementary ingredients and sends for display a subset of the complementary ingredients as recommended items.

Abstract: A method for maintaining an index in multi-tier data structure includes providing a plurality of a storage devices forming the multi-tier data structure, caching an index of key-value pairs across the multi-tier data structure, wherein each of the key-value pairs includes a key, and one of a data value and a data pointer, the key-value pairs stored in the multi-tier data structure, providing a journal for interfacing with the multi-tier data structure, providing a plurality of zone allocators recording which zones of the multi-tier data structure are in used, and providing a plurality of zone managers for controlling access to cache lines of the multi-tier data structure through the journal and zone allocators, wherein each zone manager maintains a header object pointing to data to be stored in an allocated zone.

Abstract: A method for maintaining an index in multi-tier data structure includes providing a plurality of a storage devices forming the multi-tier data structure, caching an index of key-value pairs across the multi-tier data structure, wherein each of the key-value pairs includes a key, and one of a data value and a data pointer, the key-value pairs stored in the multi-tier data structure, providing a journal for interfacing with the multi-tier data structure, providing a plurality of zone allocators recording which zones of the multi-tier data structure are in used, and providing a plurality of zone managers for controlling access to cache lines of the multi-tier data structure through the journal and zone allocators, wherein each zone manager maintains a header object pointing to data to be stored in an allocated zone.

Abstract: A method for maintaining an index in multi-tier data structure includes providing a plurality of a storage devices forming the multi-tier data structure, caching an index of key-value pairs across the multi-tier data structure, wherein each of the key-value pairs includes a key, and one of a data value and a data pointer, the key-value pairs stored in the multi-tier data structure, providing a journal for interfacing with the multi-tier data structure, providing a plurality of zone allocators recording which zones of the multi-tier data structure are in used, and providing a plurality of zone managers for controlling access to cache lines of the multi-tier data structure through the journal and zone allocators, wherein each zone manager maintains a header object pointing to data to be stored in an allocated zone.

Abstract: Systems and methods for continuous processing of unstructured data streams are provided. Information may be stored in memory regarding a query, including associated search results and statistics derived at an identified time. After the identified time, unstructured data may be received from a plurality of streams over a communication network. A full-text search may be conducted on the received unstructured data based on the query to yield one or more matches. The stored statistics associated with the query may be retrieved from memory and updated based on the search results of the unstructured data received at the subsequent time. The updated statistics may then be stored in memory for retrieval at a subsequent time.

Abstract: A method for maintaining an index in multi-tier data structure includes providing a plurality of a storage devices forming the multi-tier data structure, caching an index of key-value pairs across the multi-tier data structure, wherein each of the key-value pairs includes a key, and one of a data value and a data pointer, the key-value pairs stored in the multi-tier data structure, providing a journal for interfacing with the multi-tier data structure, providing a plurality of zone allocators recording which zones of the multi-tier data structure are in used, and providing a plurality of zone managers for controlling access to cache lines of the multi-tier data structure through the journal and zone allocators, wherein each zone manager maintains a header object pointing to data to be stored in an allocated zone.