# Curator: Efficient Indexing for Multi-Tenant Vector Databases

arXiv: https://arxiv.org/abs/2401.07119 · HTML: https://mlsanity.com/paper/2401.07119/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 13 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1405.5869/) (2014)
- [Practical and Optimal LSH for Angular Distance](https://mlsanity.com/paper/1509.02897/) (2015)
- [Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph](https://mlsanity.com/paper/1707.00143/) (2017)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search](https://mlsanity.com/paper/2105.09613/) (2021)
- [Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors](https://mlsanity.com/paper/1802.02422/) (2018)
- [On Symmetric and Asymmetric LSHs for Inner Product Search](https://mlsanity.com/paper/1410.5518/) (2014)
- [Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1410.5410/) (2014)
- [EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph](https://mlsanity.com/paper/1609.07228/) (2016)
- [Randomized partition trees for exact nearest neighbor search](https://mlsanity.com/paper/1302.1948/) (2013)
- [Learning to Index for Nearest Neighbor Search](https://mlsanity.com/paper/1807.02962/) (2018)

## Built on by (most cited first, 3 of 3)

- [HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning[Technical Report]](https://mlsanity.com/paper/2505.01538/) (2025)
- [ShardMemo: Scope-Before-Routing for Agentic Memory Retrieval](https://mlsanity.com/paper/2601.21545/) (2026)
- [Optimizing Domain-Specific Image Retrieval: A Benchmark of FAISS and Annoy with Fine-Tuned Features](https://mlsanity.com/paper/2412.01555/) (2024)

## Abstract (arXiv)

Vector databases have emerged as key enablers for bridging intelligent applications with unstructured data, providing generic search and management support for embedding vectors extracted from the raw unstructured data. As multiple data users can share the same database infrastructure, multi-tenancy support for vector databases is increasingly desirable. This hinges on an efficient filtered search operation, i.e., only querying the vectors accessible to a particular tenant. Multi-tenancy in vector databases is currently achieved by building either a single, shared index among all tenants, or a per-tenant index. The former optimizes for memory efficiency at the expense of search performance, while the latter does the opposite. Instead, this paper presents Curator, an in-memory vector index design tailored for multi-tenant queries that simultaneously achieves the two conflicting goals, low memory overhead and high performance for queries, vector insertion, and deletion. Curator indexes each tenant's vectors with a tenant-specific clustering tree and encodes these trees compactly as sub-trees of a shared clustering tree. Each tenant's clustering tree adapts dynamically to its unique vector distribution, while maintaining a low per-tenant memory footprint. Our evaluation, based on two widely used data sets, confirms that Curator delivers search performance on par with per-tenant indexing, while maintaining memory consumption at the same level as metadata filtering on a single, shared index.