EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Zhangchi, Kuang, Dongdong, Wang, Zhongyuan, Nie, Zhijie, Zheng, Yaowei, Zhang, Richong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917803649400832
author Feng, Zhangchi
Kuang, Dongdong
Wang, Zhongyuan
Nie, Zhijie
Zheng, Yaowei
Zhang, Richong
author_facet Feng, Zhangchi
Kuang, Dongdong
Wang, Zhongyuan
Nie, Zhijie
Zheng, Yaowei
Zhang, Richong
contents This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The first is accurate question answering. We designed a straightforward RAG scheme based on (1) a specific data processing workflow (2) dual-route sparse retrieval for coarse ranking (3) LLM Reranker for reranking (4) LLM answer generation and optimization. This approach achieved first place in the GLM4 track in the preliminary round and second place in the GLM4 track in the semifinals. The second is simple deployment. Our method primarily consists of BM25 retrieval and BGE-reranker reranking, requiring no fine-tuning of any models, occupying minimal VRAM, easy to deploy, and highly scalable; we provide a flexible code library with various search and generation strategies, facilitating custom process implementation. The last one is efficient inference. We designed an efficient inference acceleration scheme for the entire coarse ranking, reranking, and generation process that significantly reduces the inference latency of RAG while maintaining a good level of accuracy; each acceleration scheme can be plug-and-play into any component of the RAG process, consistently enhancing the efficiency of the RAG system. Our code and data are released at \url{https://github.com/BUAADreamer/EasyRAG}.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
Feng, Zhangchi
Kuang, Dongdong
Wang, Zhongyuan
Nie, Zhijie
Zheng, Yaowei
Zhang, Richong
Computation and Language
Artificial Intelligence
This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The first is accurate question answering. We designed a straightforward RAG scheme based on (1) a specific data processing workflow (2) dual-route sparse retrieval for coarse ranking (3) LLM Reranker for reranking (4) LLM answer generation and optimization. This approach achieved first place in the GLM4 track in the preliminary round and second place in the GLM4 track in the semifinals. The second is simple deployment. Our method primarily consists of BM25 retrieval and BGE-reranker reranking, requiring no fine-tuning of any models, occupying minimal VRAM, easy to deploy, and highly scalable; we provide a flexible code library with various search and generation strategies, facilitating custom process implementation. The last one is efficient inference. We designed an efficient inference acceleration scheme for the entire coarse ranking, reranking, and generation process that significantly reduces the inference latency of RAG while maintaining a good level of accuracy; each acceleration scheme can be plug-and-play into any component of the RAG process, consistently enhancing the efficiency of the RAG system. Our code and data are released at \url{https://github.com/BUAADreamer/EasyRAG}.
title EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.10315