公开(公告)号：US20250133037A1

公开(公告)日：2025-04-24

申请号：US18920765

申请日：2024-10-18

Applicant: Maplebear Inc.

Inventor： Jacob Jensen ,  Shubhanshu Mishra ,  Aomin Wu ,  Rajpal Paryani ,  Guanghua Shu ,  Sicheng Zhou

IPC: H04L51/02

Abstract: A system may smartly edit the context of a conversation to be input into a chatbot LLM by using a conversation compression algorithm to prune and compress redundant elements. The system evaluates the conversation context compression algorithm using both a chatbot LLM and an adversarial LLM. The system retrieves a logged conversation and generates a compressed conversation context from the logged conversation. The system generates a synthetic user response by applying the adversarial LLM and generates a test conversation by replacing a user response in the conversation with the synthetic user response. The system generates a compressed context of the test conversation. The system generates a test chatbot LLM response by prompting the chatbot LLM with the compressed context of the test conversation. The system evaluates the conversation context compression algorithm by comparing the test chatbot response with a benchmark chatbot response.

公开(公告)号：US20250165513A1

公开(公告)日：2025-05-22

申请号：US18948027

申请日：2024-11-14

Applicant: Maplebear Inc.

Inventor： Vinesh Reddy Gudla ,  Tejaswi Tenneti ,  Shubhanshu Mishra

IPC: G06F16/33 ,  G06F16/2452

Abstract: An online system uses a machine-learned language model (e.g., an LLM) to improve multilingual search capabilities. The system generates a prompt for the LLM that includes a set of search queries in a first language along with their context, as well as a request for translating these queries into a second language. This prompt is sent to a model serving system, which executes it through the LLM and returns translated queries in the second language. Additionally, the concierge system accesses a first set of features derived from the search results in the first language, and updates these features based on the newly translated search queries to create a second set of features. These translated queries and the second set of features are then used to train a search model optimized for queries in the second language.

公开(公告)号：US20250086685A1

公开(公告)日：2025-03-13

申请号：US18243600

申请日：2023-09-07

Applicant: Maplebear Inc.

Inventor： Shubhanshu Mishra ,  Gia Young ,  Jennie Morgan Burger ,  Joseph Olivier ,  Brent Luna ,  Yuanzheng Zhu ,  Mackenzie Cala ,  Armand Raquel-Santos ,  David Zandman ,  Mia Martinez Barnett ,  Callie Bleckner ,  Mohammad Abdul-Rahim

IPC: G06Q30/0601 ,  G06V20/50

Abstract: An online concierge system assists users in identifying additional information about items in an image. Image regions are identified in the image that may correspond to unknown items and an item search space is determined for detecting items in the image regions based on a context of the image, such as items in a warehouse or a list of items delivered to a customer. The identified items are used to retrieve relevant item information that is included in a prompt for a language model to extract relevant information for the item. As such, the process may automatically process the image into relevant textual information about the pictured items. Applications may be used to assist vision-impaired users in distinguishing delivered items or quickly identifying and evaluating relevant information about items.