US 12,321,794 B2
Hybrid language model architecture for API orchestration including chain of thought
Giovanni Faonte, Jersey City, NJ (US); Shreya Chandrashekar Srinarasi, Jersey City, NJ (US); Mithun Azhagappan, New York, NY (US); Dinesh Gupta, Princeton Junction, NJ (US); Christopher M. Churchman, New York, NY (US); and Cheska Adrianne Mauban, Queens, NY (US)
Assigned to Goldman Sachs & Co. LLC, New York, NY (US)
Filed by Goldman Sachs & Co. LLC, New York, NY (US)
Filed on Jan. 9, 2025, as Appl. No. 19/015,513.
Application 19/015,513 is a continuation of application No. 18/929,480, filed on Oct. 28, 2024.
Claims priority of provisional application 63/593,502, filed on Oct. 26, 2023.
Prior Publication US 2025/0147820 A1, May 8, 2025
Int. Cl. G06F 3/00 (2006.01); G06F 9/54 (2006.01)
CPC G06F 9/54 (2013.01) 17 Claims
OG exemplary drawing
 
1. A method for generating a payload response for a requested functionality in a system environment, the method comprising:
receiving, at a network system, a payload request from a client device, the payload request comprising a natural language request for the requested functionality;
applying, at the network system, a small language model to the payload request to determine a set of candidate APIs from a catalog based on embeddings generated by the small language model that map the natural language in the payload request to the functionality of the APIs in the catalog, wherein determining the set of candidate APIs comprises:
determining, for each API of a plurality of APIs in the catalog, a score quantifying a likelihood the API is semantically or syntactically relevant to language in the payload request; and
selecting the APIs having scores above a threshold score as candidate APIs in the set of candidate APIs;
applying, at the network system, a large language model to the payload request and the candidate APIs to determine a selected API that performs the requested functionality, the large language model interpreting context and intent of the payload request to select a candidate API from the set of candidate APIs as the selected API based on the context and intent; and
providing the payload response to the client device, the providing comprising:
providing a location of the selected API to the client device;
executing, using a system hosting the API at the location, the selected API to generate a payload response including the requested functionality; and
transmitting, from the system to the client device, the generated payload response.