LMI-Capstone

Data + Resources for the Multimodal RAG in Education Capstone Project

Contents:

This repository contains content pulled from weeks 7-9 of DS3001. The content from other weeks will need to be pulled from Canvas and the course repo. The documents incldued are the raw documents and will need to be reformatted to be chunked and vectorized.

pdf_books folder:

.pdf files of textbooks we have found to be relevant and high quality resources

lecture_transcripts folder:

.txt files of the automatically generated transcripts from Professor Wright's weekly lecture videos

lectures folder:

.pdf/.ppt files of lecture slides

RAG resources:

• LangChain videos A good overview to get an idea of the big picture & different parts of RAG

• RAG paper The original publication

• HuggingFace Another good walkthrough of a RAG architecture with examples and plainly written commentary

• RAG with LangChain tutorial book Another great tutorial with code + explanations for implementing RAG

• RAG vs Fine tuning A nice comparison between RAG and fine-tuning, helpful to understand why RAG may be a better solution than fine-tuning for some applications.