Ask the Canon: Semantic Search Without a Vector Database

I built out askthecanon.com this weekend, a semantic search over 100 public-domain books (from the Gutenberg project). You ask a question in plain language and get the passages that mean that, cited by author, title, and chapter. I wanted a local, no-generative-AI solution: a retrieval engine using Hugging Face embeddings and NumPy that returns original passages, no full vector database (yet), no API calls at query time.