#RAG
2 posts tagged RAG. All posts
Chunking documents for retrieval: fixed size, recursive splits and headingsFour ways to chunk documents for RAG, from fixed windows to heading-aware splits, plus a small recall test that shows which one works for your embedding model.
Retrieval-augmented generation from scratch with SQLiteBuild RAG in about 130 lines of Python: chunk Markdown, embed it locally, store vectors in SQLite, search by cosine similarity and get cited answers from Claude.
© 2026 David Li · Home · Blog · RSS ·Classic site · Built with Astro, Starlight and three.js · Logos:Font Awesome Free (CC BY 4.0)