Writer's next approach used vector embeddings with chunking and stored results in a database for similarity search, then passed results to the LLM, but this caused two major problems: inaccurate answers from chunking artifacts and failure on concentrated data.
factualpending
Speaker
Sam JuleneEvidence Quote
“we went to vector embeddings and did chunking and embeddings and put it in a database and then similarity search... we ran into two major problems with this”
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...