公开(公告)号：US20250094787A1

公开(公告)日：2025-03-20

申请号：US18808300

申请日：2024-08-19

Applicant: Oracle International Corporation

Inventor： Karoon Rashedi Nia ,  Anatoly Yakovlev ,  Sandeep R. Agrawal ,  Ridha Chahed ,  Sanjay Jinturkar ,  Nipun Agarwal

IPC: G06N3/0475 ,  G06F21/62 ,  G06N3/092

Abstract: Disclosed herein are various approaches for sharing knowledge within and between organizations while protecting sensitive data. A machine learning model may be trained using training prompts querying a vector store to prevent unauthorized user disclosure of data derived from the vector store. A prompt may be received and a response to the prompt may be generated using the machine learning model based at least in part on the vector store.

公开(公告)号：US20250094777A1

公开(公告)日：2025-03-20

申请号：US18821539

申请日：2024-08-30

Applicant: Oracle International Corporation

Inventor： Anatoly Yakovlev ,  Sandeep R. Agrawal ,  Karoon Rashedi Nia ,  Ridha Chahed ,  Sanjay Jinturkar ,  Nipun Agarwal

IPC: G06N3/0455

Abstract: The present disclosure relates to LLM orchestration with vector store generation. An embeddings model may be selected to generate an embedding for a digital artifact. Metadata for the digital artifact may also be generated and stored in a vector store in association with the embedding. A user query may be received and categorized. One of a plurality of machine learning models may be selected based on the categorization of the user query. A prompt may be generated based at least in part on the user query, and the selected machine learning model may generate a response to the user query based at least in part on the prompt.