This Jupyter Notebook demonstrates a Retrieval-Augmented Generation (RAG) system designed to answer questions about the Star Wars universe. The system combines a retriever that fetches relevant documents from a knowledge base with a language model that generates answers based on these documents. The core components include embeddings for vector representations, a FAISS vector store for efficient retrieval, and a conversational retrieval chain.
This project has been developed as a class project for the course Natural Language Processing, taught by Dr. Giorgio Satta, at the University of Padua, in June 2024. The contributors are Shabnam Zareshahraki and Joseph Fiume.
The project is maintained as a Jupyter Notebook, thus, run the notebook from the beginning to the end to see the results. The whole notebook is commented and self-contained.