Vector retrieval with naive chunking and nearest neighbor search produces inaccurate answers on dense text because semantic boundaries of chunks don't align with logical units—the example shows chunking the Apple timeline causes confusion between Lisa (1983) and Macintosh (1984) dates.
causalpending
Speaker
Sam JuleneEvidence Quote
“when you chunk this text naively and you just give it to a nearest neighbor search, uh it can get confused and it thinks that it was actually in 1983 instead of 1984 because it's in the same chunk as the introduction of the Lisa”
Source
When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer— AI EngineerCreated: 8/11/2026, 5:33:11 AM
Your notes
Loading notes...