US 12,405,985 B1Granted

Retrieval-augmented generation processing using dynamically selected number of document chunks

AssigneeDell Products L.P.

InventorsRamakanth Kanagovi, Gaurav Bhattacharjee, Ravi Shukla

Life of this patent

Estimating the term…

Loading patent…

Abstract

An apparatus comprises at least one processing device configured to obtain a query comprising search text and a context identifying documents to be searched using the search text, to generate document chunks by parsing the documents, to determine a degree of specificity of the search text, and to determine a number of the document chunks to select for retrieval-augmented generation processing based on the determined degree of specificity. The at least one processing device is also configured to select a subset of the document chunks based on similarity between the document chunks and the search text, the subset including the determined number of document chunks. The at least one processing device is further configured to generate and apply a prompt including the selected subset of the document chunks to a machine learning system to generate an output, and to provide an answer to the query based on the output.

Claims20

Dependent claims

An apparatus comprising:

at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain a query, the query comprising search text and a context, the context identifying one or more documents to be searched using the search text;
to generate a plurality of document chunks by parsing the one or more documents, each of the plurality of document chunks comprising a portion of content of one of the one or more documents;
to determine a degree of specificity of the search text in the query;
to determine, based at least in part on the determined degree of specificity of the search text, a number of the plurality of document chunks to select for retrieval-augmented generation processing;
to select a subset of the plurality of document chunks based at least in part on determining a similarity between content of the plurality of document chunks and the search text, the subset including the determined number of the plurality of document chunks;
to generate, based at least in part on the query, a prompt for input to a machine learning system, the prompt comprising the selected subset of the plurality of document chunks;
to apply the prompt to the machine learning system to generate an output;
and
to provide an answer to the query based at least in part on the output of the machine learning system.

8 more elements

A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:

to obtain a query, the query comprising search text and a context, the context identifying one or more documents to be searched using the search text;
to generate a plurality of document chunks by parsing the one or more documents, each of the plurality of document chunks comprising a portion of content of one of the one or more documents;
to determine a degree of specificity of the search text in the query;
to determine, based at least in part on the determined degree of specificity of the search text, a number of the plurality of document chunks to select for retrieval-augmented generation processing;
to select a subset of the plurality of document chunks based at least in part on determining a similarity between content of the plurality of document chunks and the search text, the subset including the determined number of the plurality of document chunks;
to generate, based at least in part on the query, a prompt for input to a machine learning system, the prompt comprising the selected subset of the plurality of document chunks;
to apply the prompt to the machine learning system to generate an output;
and
to provide an answer to the query based at least in part on the output of the machine learning system.

6 more elements

A method comprising:

obtaining a query, the query comprising search text and a context, the context identifying one or more documents to be searched using the search text;
generating a plurality of document chunks by parsing the one or more documents, each of the plurality of document chunks comprising a portion of content of one of the one or more documents;
determining a degree of specificity of the search text in the query;
determining, based at least in part on the determined degree of specificity of the search text, a number of the plurality of document chunks to select for retrieval-augmented generation processing;
selecting a subset of the plurality of document chunks based at least in part on determining a similarity between content of the plurality of document chunks and the search text, the subset including the determined number of the plurality of document chunks;
generating, based at least in part on the query, a prompt for input to a machine learning system, the prompt comprising the selected subset of the plurality of document chunks;
applying the prompt to the machine learning system to generate an output;
and
providing an answer to the query based at least in part on the output of the machine learning system;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

7 more elements

Dependencies are inferred from the claim text.