Database Paper Browser

Back to papers

Cost-Effective, Low Latency Vector Search with Azure Cosmos DB

Summary: Embed DiskANN in Cosmos DB: one per-partition vector index in existing index trees, <20ms queries on 10M vectors, stable recall under updates. Shows ~43x/12x lower query cost vs Pinecone/Zilliz and automatic partitioning to scale to billions—argues for DB-integrated vectors. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
14116
Venue
VLDB
Year
2025
Pagerank
4.3341665e-05
Overall Rank
9,480 | 34.05%
DOI
10.14778/3750601.3750635

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
10,224 SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search 2026 VLDB 4.1945683e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers