# Cloud-Native Vector Search: A Comprehensive Performance Analysis

arXiv: https://arxiv.org/abs/2511.14748 · HTML: https://mlsanity.com/paper/2511.14748/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Vector search and ANN indexes, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 78 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Placed in

- Retrieval-augmented generation / [Vector search and ANN indexes](https://mlsanity.com/rag/vector-search-and-ann-indexes/)

## Builds on (most cited first, 12 of 12)

- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph](https://mlsanity.com/paper/1707.00143/) (2017)
- [SPFresh: Incremental In-Place Update for Billion-Scale Vector Search](https://mlsanity.com/paper/2410.14452/) (2024)
- [Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations](https://mlsanity.com/paper/2310.19126/) (2023)
- [High-Throughput Vector Similarity Search in Knowledge Graphs](https://mlsanity.com/paper/2304.01926/) (2023)
- [The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform](https://mlsanity.com/paper/1908.07389/) (2019)
- [boldsymbolSteiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes](https://mlsanity.com/paper/2408.13899/) (2024)
- [IDEBench: A Benchmark for Interactive Data Exploration](https://mlsanity.com/paper/1804.02593/) (2018)
- [TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning](https://mlsanity.com/paper/2508.17828/) (2025)
- [Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph](https://mlsanity.com/paper/2509.25487/) (2025)
- [CaGR-RAG: Context-aware Query Grouping for Disk-based Vector Search in RAG Systems](https://mlsanity.com/paper/2505.01164/) (2025)
- [GoVector: An I/O-Efficient Caching Strategy for High-Dimensional Vector Nearest Neighbor Search](https://mlsanity.com/paper/2508.15694/) (2025)

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

- [A Super Fast K-means for Indexing Vector Embeddings](https://mlsanity.com/paper/2603.20009/) (2026)
- [Efficient Iterative Retrieval with Heterogeneous Batching](https://mlsanity.com/paper/2609.25405/) (2026)
- [Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings](https://mlsanity.com/paper/2608.14648/) (2026)

## Abstract (arXiv)

Vector search has been widely employed in recommender system and retrieval-augmented-generation pipelines, commonly performed with vector indexes to efficiently find similar items in large datasets. Recent growths in both data and task complexity have motivated placing vector indexes onto remote storage -- cloud-native vector search, which cloud providers have recently introduced services for. Yet, despite varying workload characteristics and various available vector index forms, providers default to using cluster-based indexes, which on paper do adapt well to differences between disk and cloud-based environment: their fetch granularities and lack of notable intra-query dependencies aligns with the large optimal fetch sizes and minimizes costly round-trips (i.e., as opposed to graph-based indexes) to remote storage, respectively. This paper systematically studies cloud-native vector search: What and how should indexes be built and used for on-cloud vector search? We analyze bottlenecks of two common index classes, cluster and graph indexes, on remote storage, and show that despite current standardized adoption of cluster indexes on the cloud, graph indexes are favored in workloads requiring high concurrency and recall, or operating on high-dimensional data or large datatypes. We further find that on-cloud search demands significantly different indexing and search parameterizations versus on-disk search for optimal performance. Finally, we incorporate existing cloud-based caching setups into vector search and find that certain index optimizations work against caching, and study how this can be mitigated to maximize gains under various available cache sizes.