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.

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.