EdgeRAG: Online-Indexed RAG for Edge Devices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seemakhupt, Korakit, Liu, Sihang, Khan, Samira
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910768583147520
author Seemakhupt, Korakit
Liu, Sihang
Khan, Samira
author_facet Seemakhupt, Korakit
Liu, Sihang
Khan, Samira
contents Deploying Retrieval Augmented Generation (RAG) on resource-constrained edge devices is challenging due to limited memory and processing power. In this work, we propose EdgeRAG which addresses the memory constraint by pruning embeddings within clusters and generating embeddings on-demand during retrieval. To avoid the latency of generating embeddings for large tail clusters, EdgeRAG pre-computes and stores embeddings for these clusters, while adaptively caching remaining embeddings to minimize redundant computations and further optimize latency. The result from BEIR suite shows that EdgeRAG offers significant latency reduction over the baseline IVF index, but with similar generation quality while allowing all of our evaluated datasets to fit into the memory.
format Preprint
id arxiv_https___arxiv_org_abs_2412_21023
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EdgeRAG: Online-Indexed RAG for Edge Devices
Seemakhupt, Korakit
Liu, Sihang
Khan, Samira
Machine Learning
Deploying Retrieval Augmented Generation (RAG) on resource-constrained edge devices is challenging due to limited memory and processing power. In this work, we propose EdgeRAG which addresses the memory constraint by pruning embeddings within clusters and generating embeddings on-demand during retrieval. To avoid the latency of generating embeddings for large tail clusters, EdgeRAG pre-computes and stores embeddings for these clusters, while adaptively caching remaining embeddings to minimize redundant computations and further optimize latency. The result from BEIR suite shows that EdgeRAG offers significant latency reduction over the baseline IVF index, but with similar generation quality while allowing all of our evaluated datasets to fit into the memory.
title EdgeRAG: Online-Indexed RAG for Edge Devices
topic Machine Learning
url https://arxiv.org/abs/2412.21023