AI Retrieval-Augmented Generation (RAG) System with Engineering Document Information Extraction for Employee Development

This paper explores the implementation of AI large language model (LLM) support systems that utilize retrieval-augmented generation (RAG) to enhance employee effectiveness in trouble-shooting on a manufacturing production line. The RAG-augmented LLM tool is designed to ex-tract relevant data from proprietary engineering documents, including engineering specifications, product engineering documents, troubleshooting tool manuals, and manufacturing logging data, and convey this information in a comprehensible format for troubleshooting purposes. The antici-pated effects of training with the tool include improvements in employee technical communica-tion, product and process technical literacy, and the timeliness and accuracy of investigations. Increasing the performance of technical employees helps businesses meet customer deadlines and quality expectations and decreases the need for expert support. The advantage of this system over a collection of documents and data is that anyone can use it without extensive familiarity with the engineering documents, allowing a wider range of employees to learn to navigate them and raise alarms about potential systemic issues.

Name thesis:degree_name

Master of Science

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Engineering

Grantor

Texas State University

Year dc:date.issued

2025

Author dc:creator

• Perry, Robert

Advisor dc:contributor.advisor

• Aslan, Semih

Committee members dc:contributor.committeemember

• Valles, Damian
• Dutta, Anandi K.

• AI
• RAG
• documents
• artificial intelligence
• retrieval augmented generation
• documentation
• employees

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10877/23417

OAI identifier oai:identifier

oai:digital.library.txst.edu:10877/23417