Jul 2026
TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization
TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training is studied, which achieves 11ms median query latency at 100K vectors versus 707ms for warehouse brute-force scan.
Navnit Shukla, Kamal Pandey, Omsankar Tiwari
· arXiv.org · 1 citation