Vector embeddings with chunking and nearest-neighbor search was Writer's second major retrieval approach before moving to graph-based systems.

factualpending

Speaker

Sam Julene

Evidence Quote

“we went to vector embeddings and did chunking and embeddings and put it in a database and then similarity search”

Source

When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer— AI Engineer
Created: 8/11/2026, 6:20:39 AM

Your notes

Loading notes...