COPILOT IMPLEMENTATION: RECURSIVE ITERATION OF RETRIEVAL AUGMENTED GENERATION (RAG)

Abstract: apparatus and methods are disclosed for implementing a copilot as a network of microservices including specialized large language models (llms) or other trained machine learning (ml) tools. this architecture supports flexible, customizable, or dynamically determinable dataflow. compared to much larger competing llms, comparable or superior performance is achieved, while significantly reducing computation time and hardware requirements, even to a single compute node with a single gpu. examples incorporate a retrieval microservice, as least one data producer, and a core microservice. based on client input, the retrieval microservice can perform multiple iterations of retrieval augmented generation (rag). at each iteration, output (based on any preceding iterations' results or the client input) is transmitted to a data producer, and results received therefrom. eventually, based on these results, an output is transmitted toward the core microservice for generation of a response to the client input. variations and additional techniques are disclosed.

Inventor(s): Elaine Kelsey, Elliot Nicholas Robson, Sazzad Mahmud Nasir, Jeffrey Thomas Yarbro, Robert Oscar Robson, Lauren Elizabeth Egerton, Spencer Thomas Ward, Brendan Michael Kelly

CPC Classification: G06F16/3329 ({Natural language query formulation or dialogue systems})

Search for rejections for patent application number 20250231973