Towards Data Science July 25, 2026 By Oleg Tereshin

How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes

Read the original on Towards Data Science →

Architecting cost-effective infrastructure by navigating the latency and storage trade-offs of HNSW, SPANN, and DiskANN The post How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes appeared first on Towards Data Science .

Summary generated by The Flow from the publisher's feed. The full article lives at Towards Data Science.

arXiv AI

Jun 2

Evaluation of Baseline Methods for IDD-based SSD External Memory Search

arXiv:2606. 01840v1 Announce Type: new Abstract: Many difficult search problems cannot be solved by algorithms such as A* using only RAM.

By Yuki Suzuki, Alex Fukunaga

Towards Data Science

Jul 1

What Can We Do When Memory Becomes the New Bottleneck in Data Engineering?

How Pandas chunking, Dask, and Polars help process millions of records when adding more compute isn't an option. The post What Can We Do When Memory Becomes the New Bottleneck in Data Engineering?

By Jiayan Yin

rag data-engineering

arXiv Machine Learning

Jun 9

Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors

arXiv:2606. 08813v1 Announce Type: cross Abstract: We present HNTL (Hierarchical No-pointer Tangent-Local), the core vector indexing and candidate generation framework of the Aperon vector memory system.

By Yong Fu

arXiv AI

1d ago

Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings

arXiv:2608. 14648v1 Announce Type: cross Abstract: In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality reduction, quantization, and dimension pruning.

By Leonardo Kuffo, Peter Boncz

rag efficiency

arXiv Machine Learning

Jul 14

FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval

arXiv:2607. 10044v1 Announce Type: new Abstract: Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs.

By Dakshitha Anandakumar, Anurag Mukkara, Wenxiang Hu, Jiusheng Chen, M Akash Kumar, Ting Ye, Qiang Lou, Jian Jiao

agents efficiency

arXiv AI

Jul 21

When to Use Which? Benchmarking Optimisers for Configurable Systems under Varying Budgets

arXiv:2607. 16476v1 Announce Type: cross Abstract: Software configuration tuning is crucial for optimising system performance, and various optimisers have emerged over the last decade.

By Chao Jiang, Yulong Ye, Tao Chen, Miqing Li

benchmarks

Related stories

Evaluation of Baseline Methods for IDD-based SSD External Memory Search

What Can We Do When Memory Becomes the New Bottleneck in Data Engineering?

Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors

Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings

FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval

When to Use Which? Benchmarking Optimisers for Configurable Systems under Varying Budgets