Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huerga-Pérez, Naamán, Álvarez, Rubén, Ferrero-Guillén, Rubén, Martínez-Gutiérrez, Alberto, Díez-González, Javier
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916715685740544
author Huerga-Pérez, Naamán
Álvarez, Rubén
Ferrero-Guillén, Rubén
Martínez-Gutiérrez, Alberto
Díez-González, Javier
author_facet Huerga-Pérez, Naamán
Álvarez, Rubén
Ferrero-Guillén, Rubén
Martínez-Gutiérrez, Alberto
Díez-González, Javier
contents Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings at scale presents significant memory challenges. To address this issue, we systematically investigate on MTEB benchmark two complementary optimization strategies: quantization, evaluating standard formats (float16, int8, binary) and low-bit floating-point types (float8), and dimensionality reduction, assessing methods like PCA, Kernel PCA, UMAP, Random Projections and Autoencoders. Our results show that float8 quantization achieves a 4x storage reduction with minimal performance degradation (<0.3%), significantly outperforming int8 quantization at the same compression level, being simpler to implement. PCA emerges as the most effective dimensionality reduction technique. Crucially, combining moderate PCA (e.g., retaining 50% dimensions) with float8 quantization offers an excellent trade-off, achieving 8x total compression with less performance impact than using int8 alone (which provides only 4x compression). To facilitate practical application, we propose a methodology based on visualizing the performance-storage trade-off space to identify the optimal configuration that maximizes performance within their specific memory constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques
Huerga-Pérez, Naamán
Álvarez, Rubén
Ferrero-Guillén, Rubén
Martínez-Gutiérrez, Alberto
Díez-González, Javier
Information Retrieval
Computation and Language
Databases
Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings at scale presents significant memory challenges. To address this issue, we systematically investigate on MTEB benchmark two complementary optimization strategies: quantization, evaluating standard formats (float16, int8, binary) and low-bit floating-point types (float8), and dimensionality reduction, assessing methods like PCA, Kernel PCA, UMAP, Random Projections and Autoencoders. Our results show that float8 quantization achieves a 4x storage reduction with minimal performance degradation (<0.3%), significantly outperforming int8 quantization at the same compression level, being simpler to implement. PCA emerges as the most effective dimensionality reduction technique. Crucially, combining moderate PCA (e.g., retaining 50% dimensions) with float8 quantization offers an excellent trade-off, achieving 8x total compression with less performance impact than using int8 alone (which provides only 4x compression). To facilitate practical application, we propose a methodology based on visualizing the performance-storage trade-off space to identify the optimal configuration that maximizes performance within their specific memory constraints.
title Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques
topic Information Retrieval
Computation and Language
Databases
url https://arxiv.org/abs/2505.00105