IRS Document RAG Advisor

Purpose: This project implements a RAG (Retrieval Augmented Generation) system to answer questions about IRS (Internal Revenue Service) forms and publications. It uses a Streamlit interface for user interaction, LangChain for orchestrating the RAG pipeline, ChromaDB for vector storage, BM25 for keyword-based retrieval, and an OpenAI LLM for generating answers.

Live Demo: You can try the IRS RAG Advisor live here: 2024-irs-rag-example.streamlit.app/

Source Code: The full source code is available on GitHub: charleslukowski/rag_portfolio