Retrieval Augmented Generation (RAG) on large technical reports

This project is part of the Co-operative Education for Enterprise Development (CEED) program with academic supervisors Prof. Melinda Hodkiewicz and Dr Caitlin Woods.

The Challenge

Retrieve research data and insights in large technical reports using generative artificial intelligence (AI). Reliance on keyword search and expert interpretation leaves aspects of MRIWA’s reports content untapped. The lack of a standardised format complicates use of them by automated systems and impedes computational analysis.

The Solution

Recent advancements in Large Language Models (LLMs) have revolutionised AI’s capability to process and understand natural language, demonstrating strong ability in complex practical tasks. Often being limited to their pre-trained knowledge, LLMs falter when technical domain-specific information is required. Retrieval Augmented Generation (RAG) systems counter this issue, providing the AI with context beyond its prior training.

This project aims to develop a RAG system, leveraging the power of LLMs, to process MRIWA’s technical reports, allowing users to query this knowledge base using natural language.

Proposed Benefit to WA

Unlock the value embedded in MRIWA’s technical reports and integrate it with current information to foster new insights in the WA minerals industry.