DGAI decouples vector storage from graph topology in on-disk ANN indexes and adds similarity-aware dynamic layout plus hierarchical PQ two-stage querying to achieve 8x faster insertions/deletions and 67% lower peak query latency under mixed workloads.
GPT semantic cache: Reducing LLM costs and latency via semantic embedding caching.CoRR, abs/2411.05276
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries
DGAI decouples vector storage from graph topology in on-disk ANN indexes and adds similarity-aware dynamic layout plus hierarchical PQ two-stage querying to achieve 8x faster insertions/deletions and 67% lower peak query latency under mixed workloads.