DBScholar

Back to papers

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

Summary: Integrates DiskANN directly into Azure Cosmos DB’s partitioned index trees, maintaining vector indexes with operational data. Delivers <20ms search on 10M vectors, billion-scale autoscaling, stable recall, and 12–43× lower cost than serverless vector DBs. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
h7694ebc27da34202
Venue
VLDB
Year
2025
Pagerank
5.2340466e-05
Overall Rank
9,031 | 39.29%
DOI
10.14778/3750601.3750635

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{upreti_vldb25,
        title = {{Cost-Effective, Low Latency Vector Search with Azure Cosmos DB}},
        author = {Upreti, Nitish and Simhadri, Harsha Vardhan and Sundar, Hari Sudan and Sundaram, Krishnan and Boshra, Samer and Perumalswamy, Balachandar and Atri, Shivam and Chisholm, Martin and Singh, Revti Raman and Yang, Greg and Hass, Tamara and Dudhey, Nitesh and Pattipaka, Subramanyam and Hildebrand, Mark and Manohar, Magdalen and Moffitt, Jack and Xu, Haiyang and Datha, Naren and Gupta, Suryansh and Krishnaswamy, Ravishankar and Gupta, Prashant and Sahu, Abhishek and Varada, Hemeswari and Barthwal, Sudhanshu and Mor, Ritika and Codella, James and Cooper, Shaun and Pilch, Kevin and Moreno, Simon and Kataria, Aayush and Kulkarni, Santosh and Deshpande, Neil and Sagare, Amar and Billa, Dinesh and Fu, Zishan and Vishal, Vipul},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {5166--5183},
        doi = {10.14778/3750601.3750635},
        url = {https://doi.org/10.14778/3750601.3750635},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,409 An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments & Analysis] 2026 SIGMOD 4.9793485e-05
10,697 SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search 2026 VLDB 4.9793485e-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.

Rank Cited Paper Year Venue Pagerank
74 Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph 2019 VLDB 0.00037091678
341 AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data 2020 VLDB 0.00020539791
2,085 SingleStore-V: An Integrated Vector Database System in SingleStore 2024 VLDB 9.0709364e-05
2,265 ELPIS: Graph-Based Similarity Search for Scalable Data Science 2023 VLDB 8.7238222e-05
3,468 Schema-Agnostic Indexing with Azure DocumentDB 2015 VLDB 7.2774468e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 1,516 Automatically Indexing Millions of Databases in Microsoft Azure SQL Database 2019 SIGMOD
2 10,948 Nova: A Multi-Purpose Vector Engine for Low-Latency, Multi-Tenant, and Cross-Table Hybrid Retrieval 2026 VLDB
3 7,953 Fast Vector Search in PostgreSQL: A Decoupled Approach 2026 CIDR
4 10,409 An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments & Analysis] 2026 SIGMOD
5 10,929 SQL-Native Vector Search at Billion Scale in Presto 2026 VLDB
6 9,649 GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications 2025 VLDB
7 10,551 Building Stateless Serverless Vector DBs via Block-based Data Partitioning 2026 SIGMOD
8 3,468 Schema-Agnostic Indexing with Azure DocumentDB 2015 VLDB
9 10,443 Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search 2026 SIGMOD
10 9,955 Turbocharging Vector Databases using Modern SSDs 2025 VLDB