Document Chat answered questions about one file. This project generalizes that into a real RAG pipeline: embedding a folder of documents into a persistent FAISS index, retrieving semantically relevant chunks with score-threshold filtering, and — critically — an A/B mode that puts RAG and no-RAG answers side by side so you can see exactly what retrieval is buying you, not just assume it’s working.
RAG is the single most-asked-about AI Engineer skill in job descriptions today — this is the project that lets you speak to it with specifics, not buzzwords.