US 12,216,694 B1
Systems and methods for using prompt dissection for large language models
Vineeth Chinmaya Murthy, Bengaluru (IN); and Rafal Powalski, Warsaw (PL)
Assigned to Instabase, Inc., Dover, DE (US)
Filed by Instabase, Inc., Dover, DE (US)
Filed on Jul. 25, 2023, as Appl. No. 18/358,780.
Int. Cl. G06F 17/30 (2006.01); G06F 16/33 (2019.01); G06F 40/30 (2020.01)
CPC G06F 16/3347 (2019.01) [G06F 40/30 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system configured to use prompt dissection to prompt one or more machine learning models for a set of one or more documents, the system comprising:
electronic storage configured to electronically store information, wherein the stored information includes a set of document segments, wherein individual document segments are included in the set of one or more documents, wherein the stored information further includes a set of semantic vectors, wherein individual semantic vectors are associated with individual document segments; and
one or more hardware processors configured by machine-readable instructions to:
effectuate a presentation of a user interface, the user interface being configured to obtain a compound query from a user, wherein the compound query includes two or more subqueries including a first subquery and a second subquery;
create, using the one or more machine learning models, for individual ones of the two or more subqueries, subquery vectors that semantically represent the two or more subqueries, wherein the subquery vectors include a first subquery vector representing the first subquery and a second subquery vector representing the second subquery;
determine a subset of the set of semantic vectors, wherein the determination is based on comparisons, wherein the comparisons include a first comparison using the first subquery vector and a second comparison using the second subquery vector;
create a combination of the individual document segments that are associated with the subset of the set of semantic vectors as determined;
provide one or more prompts to the one or more machine learning models, using the created combination of the individual document segments as context, wherein the one or more prompts are based on the compound query; and
present to the user, through the user interface, one or more replies obtained from the one or more machine learning models in reply to the one or more prompts.