# SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search

arXiv: https://arxiv.org/abs/2509.08395 · HTML: https://mlsanity.com/paper/2509.08395/

## Key facts

- Cited by 2 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 22 of its 48 references that are in the map.
- First posted on arXiv 10 Sep 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, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://mlsanity.com/paper/2404.07220/) (2024)
- [Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2501.15915/) (2025)
- [An Efficiency Study for SPLADE Models](https://mlsanity.com/paper/2207.03834/) (2022)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [On Symmetric and Asymmetric LSHs for Inner Product Search](https://mlsanity.com/paper/1410.5518/) (2014)
- [Accelerating Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15246/) (2024)
- [Faster Learned Sparse Retrieval with Block-Max Pruning](https://mlsanity.com/paper/2405.01117/) (2024)
- [Norm-Ranging LSH for Maximum Inner Product Search](https://mlsanity.com/paper/1809.08782/) (2018)
- [Effective and General Distance Computation for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2404.16322/) (2024)
- [An Approximate Algorithm for Maximum Inner Product Search over Streaming Sparse Vectors](https://mlsanity.com/paper/2301.10622/) (2023)
- [High-Ratio Compression for Machine-Generated Data](https://mlsanity.com/paper/2311.13947/) (2023)
- [VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2503.17911/) (2025)
- [Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge](https://mlsanity.com/paper/2506.22644/) (2025)
- [ProMIPS: Efficient High-Dimensional c-Approximate Maximum Inner Product Search with a Lightweight Index](https://mlsanity.com/paper/2104.04406/) (2021)
- [Dynamic Superblock Pruning for Fast Learned Sparse Retrieval](https://mlsanity.com/paper/2504.17045/) (2025)
- [EnhanceGraph: A Continuously Enhanced Graph-based Index for High-dimensional Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2506.13144/) (2025)

## Built on by (most cited first, 2 of 2)

- [FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2603.21710/) (2026)
- [MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexes](https://mlsanity.com/paper/2607.29173/) (2026)

## Abstract (arXiv)

Sparse vector Maximum Inner Product Search (MIPS) is crucial in multi-path retrieval for Retrieval-Augmented Generation (RAG). Recent inverted index-based and graph-based algorithms have achieved high search accuracy with practical efficiency. However, their performance in production environments is often limited by redundant distance computations and frequent random memory accesses. Furthermore, the compressed storage format of sparse vectors hinders the use of SIMD acceleration. In this paper, we propose the sparse inverted non-redundant distance index (SINDI), which incorporates three key optimizations: (i) Efficient Inner Product Computation: SINDI leverages SIMD acceleration and eliminates redundant identifier lookups, enabling batched inner product computation; (ii) Memory-Friendly Design: SINDI replaces random memory accesses to original vectors with sequential accesses to inverted lists, substantially reducing memory-bound latency. (iii) Vector Pruning: SINDI retains only the high-magnitude non-zero entries of vectors, improving query throughput while maintaining accuracy. We evaluate SINDI on multiple real-world datasets. Experimental results show that SINDI achieves state-of-the-art performance across datasets of varying scales, languages, and models. On the MsMarco dataset, when Recall@50 exceeds 99%, SINDI delivers single-thread query-per-second (QPS) improvements ranging from 4.2 to 26.4 times compared with SEISMIC and PyANNs. Notably, SINDI has been integrated into Ant Group's open-source vector search library, VSAG.