Feedback driven vector data storage-based query management system

A system, comprising:

• a processing system;
• and
• memory coupled to the processing system, the memory comprising computer executable instructions that, when executed by the processing system, causes the system to perform operations comprising:
• receiving, from a requesting device, a first request for information regarding a first issue associated with a first network service that is provisioned, by a service provider, at a premises location;
• generating a first prompt for a large language model ("LLM") to query a vector data storage device for the information regarding the first issue from a set of databases;
• sending the first prompt to the LLM;
• receiving an output from the LLM;
• determining a content of the output from the LLM;
• based on a determination that the output from the LLM includes a first output including data associated with the first issue, presenting the first output to the requesting device;
• and
• based on a determination that the output from the LLM includes a first message indicating that the vector data storage device was unable to find data associated with the first issue within the set of databases, performing the following:
• generating a first incident report that initiates a first investigation into the first issue in response to receiving the first message;
• and
• generating and presenting a second message to the requesting device, the second message indicating that the first issue is being investigated.

A method, comprising:

• concurrent with or prior to receiving a first input from a requesting device via a first user interface ("UI"), predicting, by a computing system, one or more topics of interest to a first end-user associated with a premises location at which a first network service is being provisioned;
• presenting, by the computing system, the one or more topics of interest to the requesting device via the first UI;
• generating, by the computing system, one or more prompts for a large language model ("LLM") to query a vector data storage device, based on the one or more topics;
• receiving, by the computing system and from the requesting device via the first UI, a selection of a first topic of interest among the one or more topics of interest;
• sending, by the computing system, a first prompt among the one or more prompts to the LLM, the first prompt corresponding to the first topic of interest;
• receiving, by the computing system, an output from the LLM;
• determining, by the computing system, a content of the output from the LLM;
• based on a determination that the output from the LLM includes a first output including data associated with the first topic of interest, presenting, by the computing system, the first output to the requesting device;
• and
• based on a determination that the output from the LLM includes a first message indicating that the vector data storage device was unable to find data associated with the first topic of interest within the set of databases, performing the following:
• generating, by the computing system, a first incident report that initiates a first investigation into the first topic of interest in response to receiving the first message;
• and
• generating and presenting, by the computing system, a second message to the requesting device, the second message indicating that the first topic of interest is being investigated.