公开(公告)号：US11496444B1

公开(公告)日：2022-11-08

申请号：US16450658

申请日：2019-06-24

Applicant: Amazon Technologies, Inc.

Inventor： Yong Yuan ,  Saurabh Kumar Singh ,  Sachin Bangalore Raj

IPC: H04L9/40

Abstract: Technologies are disclosed for enforcing access control to resources of an indexing system using resource paths. Before performing a search for resources, access control is performed. By determining the resource paths that the user is authorized and/or unauthorized to access before performing the search, the search engine returns resources that the user is authorized to access instead of returning resources that the user may not be authorized to access. Before submitting a search query to a search engine an augmented search query is generated. The augmented search query includes one or more filter rules (which may be referred to herein as “filters”) that specify the resource paths to include or exclude from the search. The augmented search query limits the search to resources that the user is authorized to access.

公开(公告)号：US20250111091A1

公开(公告)日：2025-04-03

申请号：US18478766

申请日：2023-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Karthik Saligrama Shreeram ,  Varun Sembium Varadarajan ,  Sanjukta Ghosh ,  Nidish Rajendran Nair ,  Surya Ram ,  Ashwin Shukla ,  Sachin Bangalore Raj ,  Ishaan Berry ,  Ji Hoon Kim ,  Kartik Mittal ,  Pankhuri Gupta ,  Tiejun Zhao

IPC: G06F21/62

Abstract: Intent classification is performed for executing a retrieval augmented generation pipeline for natural language tasks using a generative machine learning model. A natural language generative application with associated data repositories may submit a natural language task. A classification machine learning model is used to determine an intent for the natural language request. A number of iterations of a retrieval pipeline may be determined to perform the natural language task based on the intent. The natural language request may be processed through a retrieval pipeline according to the determined number of iterations before returning a result to the request.

公开(公告)号：US20250110979A1

公开(公告)日：2025-04-03

申请号：US18478647

申请日：2023-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Karthik Saligrama Shreeram ,  Varun Sembium Varadarajan ,  Sanjukta Ghosh ,  Nidish Rajendran Nair ,  Sachin Bangalore Raj ,  En Lin ,  Jeff Gregory Registre ,  Jaydeep Ramani ,  Inan Tainwala ,  Kartik Mittal ,  Pankhuri Gupta ,  Tiejun Zhao

IPC: G06F16/33 ,  G06F16/332

Abstract: Distributed orchestration of data retrieval for generative machine learning model may be performed. When a natural language request to perform a natural language task is received that is associated with a generative application, one or more data retrievers may be selected to access associated data repositories according to a previously specified retrieval configuration for the generative natural language application. The data may then be obtained by the selected data retrievers and used to generate a prompt to a generative machine learning model. A result of the generative machine learning model may then be used to provide a response to the natural language request to perform the natural language task.