System and method for personalizing large language models in query systems
A system and method are provided for personalizing large language models in query systems.
1 . A computing system comprising:
a processor; and
a non-transitory computer-readable storage device storing computer-executable instructions, the instructions operable to cause the processor to perform operations comprising:
receiving a user query from a user device;
generating a response to the user query;
feeding the query and the response to a large language model (LLM);
generating a summarized response to the user query via the LLM;
causing the summarized response to be displayed on the user device;
determining a persona of a user associated with the user query, the persona comprising knowledge characteristics of the user;
determining one or more reformatting options based on the persona of the user; and
causing the one or more reformatting options to be displayed on the user device.
2 . The computing system of claim 1 , wherein generating the response to the user query comprises analyzing a knowledge base of information stored in a storage device in communication with the processor.
3 . The computing system of claim 2 , wherein analyzing the knowledge base of information comprises executing a semantic or hybrid vector search within the knowledge base.
4 . The computing system of claim 1 , wherein generating the response to the user query comprises identifying one or more documents relevant to the user query.
5 . The computing system of claim 1 , wherein causing the one or more reformatting options to be displayed on the user device comprises causes an option to present a natural language summary of a code snippet.
6 . The computing system of claim 1 , wherein causing the one or more reformatting options to be displayed on the user device comprises causes an option to convert a code snippet to a different programming language.
7 . The computing system of claim 1 , wherein the operations further comprise:
receiving a user input from the user device selecting one of the one or more reformatting options;
processing the selected reformatting option; and
performing reformatting of the summarized response based on the selected reformatting option.
8 . The computing system of claim 7 , wherein processing the selected reformatting option comprises analyzing a conversation history to identify a message to be reformatted.
9 . The computing system of claim 7 , wherein performing the reformatting of the summarized response based on the selected reformatting option comprises reformatting the summarized response via the LLM.
10 . A computer-implemented method, performed by at least one processor, comprising:
receiving a user query from a user device;
generating a response to the user query;
feeding the query and the response to a large language model (LLM);
generating a summarized response to the user query via the LLM;
causing the summarized response to be displayed on the user device;
determining a persona of a user associated with the user query, the persona comprising knowledge characteristics of the user;
determining one or more reformatting options based on the persona of the user; and
causing the one or more reformatting options to be displayed on the user device.
11 . The computer-implemented method of claim 10 , wherein generating the response to the user query comprises analyzing a knowledge base of information stored in a storage device in communication with the processor.
12 . The computer-implemented method of claim 11 , wherein analyzing the knowledge base of information comprises executing a semantic or hybrid vector search within the knowledge base.
13 . The computer-implemented method of claim 10 , wherein generating the response to the user query comprises identifying one or more documents relevant to the user query.
14 . The computer-implemented method of claim 10 , wherein causing the one or more reformatting options to be displayed on the user device comprises causes an option to present a natural language summary of a code snippet.
15 . The computer-implemented method of claim 10 , wherein causing the one or more reformatting options to be displayed on the user device comprises causes an option to convert a code snippet to a different programming language.
16 . The computer-implemented method of claim 10 comprising:
receiving a user input from the user device selecting one of the one or more reformatting options;
processing the selected reformatting option; and
performing reformatting of the summarized response based on the selected reformatting option.
17 . The computer-implemented method of claim 16 , wherein processing the selected reformatting option comprises analyzing a conversation history to identify a message to be reformatted.
18 . The computer-implemented method of claim 16 , wherein performing the reformatting of the summarized response based on the selected reformatting option comprises reformatting the summarized response via the LLM.