VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Shi, Tang, Chaoyue, Xu, Bokai, Cui, Junbo, Ran, Junhao, Yan, Yukun, Liu, Zhenghao, Wang, Shuo, Han, Xu, Liu, Zhiyuan, Sun, Maosong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912254409048064
author Yu, Shi
Tang, Chaoyue
Xu, Bokai
Cui, Junbo
Ran, Junhao
Yan, Yukun
Liu, Zhenghao
Wang, Shuo
Han, Xu
Liu, Zhiyuan
Sun, Maosong
author_facet Yu, Shi
Tang, Chaoyue
Xu, Bokai
Cui, Junbo
Ran, Junhao
Yan, Yukun
Liu, Zhenghao
Wang, Shuo
Han, Xu
Liu, Zhiyuan
Sun, Maosong
contents Retrieval-augmented generation (RAG) is an effective technique that enables large language models (LLMs) to utilize external knowledge sources for generation. However, current RAG systems are solely based on text, rendering it impossible to utilize vision information like layout and images that play crucial roles in real-world multi-modality documents. In this paper, we introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline. In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM. Compared to traditional text-based RAG, VisRAG maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process. We collect both open-source and synthetic data to train the retriever in VisRAG and explore a variety of generation methods. Experiments demonstrate that VisRAG outperforms traditional RAG in both the retrieval and generation stages, achieving a 20--40% end-to-end performance gain over traditional text-based RAG pipeline. Further analysis reveals that VisRAG is efficient in utilizing training data and demonstrates strong generalization capability, positioning it as a promising solution for RAG on multi-modality documents. Our code and data are available at https://github.com/openbmb/visrag.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10594
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Yu, Shi
Tang, Chaoyue
Xu, Bokai
Cui, Junbo
Ran, Junhao
Yan, Yukun
Liu, Zhenghao
Wang, Shuo
Han, Xu
Liu, Zhiyuan
Sun, Maosong
Information Retrieval
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Retrieval-augmented generation (RAG) is an effective technique that enables large language models (LLMs) to utilize external knowledge sources for generation. However, current RAG systems are solely based on text, rendering it impossible to utilize vision information like layout and images that play crucial roles in real-world multi-modality documents. In this paper, we introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline. In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM. Compared to traditional text-based RAG, VisRAG maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process. We collect both open-source and synthetic data to train the retriever in VisRAG and explore a variety of generation methods. Experiments demonstrate that VisRAG outperforms traditional RAG in both the retrieval and generation stages, achieving a 20--40% end-to-end performance gain over traditional text-based RAG pipeline. Further analysis reveals that VisRAG is efficient in utilizing training data and demonstrates strong generalization capability, positioning it as a promising solution for RAG on multi-modality documents. Our code and data are available at https://github.com/openbmb/visrag.
title VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
topic Information Retrieval
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.10594