一个可扩展的多模态文档处理系统，让大模型高效理解各类文件。
MMORE: Massive Multimodal Open RAG & Extraction
- 模块化分布式架构，支持文本、图像、音视频等15种文件格式
- 比单机基线快3.8倍，扫描PDF识别准确率比Docling高40%
- 适合需要处理真实世界多源数据的医疗、金融等领域应用
我们提出MMORE，一个开源的海量多模态开放检索增强生成与信息提取管道，用于大规模摄入、转换和检索异构文档格式的知识。该系统支持超过十五种文件类型，包括文本、表格、图像、邮件、音频和视频，并将其统一处理为下游大模型可用的格式。其模块化分布式架构支持跨CPU与GPU的并行扩展。在处理基准测试中，相较于单节点基线，性能提升3.8倍；在扫描版PDF上，准确率比Docling高出40%。系统集成混合密集-稀疏检索机制，支持交互式API与批量RAG端点。在PubMedQA上的评估显示，增强后的医学大模型随检索深度增加，问答准确率持续提升。MMORE为部署任务无关的RAG系统提供了稳健且可扩展的基础，适用于多样化的现实世界多模态数据。代码已开源：https://github.com/swiss-ai/mmore。
原文摘要 · Abstract (English)
We introduce MMORE, an open-source pipeline for Massive Multimodal Open RetrievalAugmented Generation and Extraction, designed to ingest, transform, and retrieve knowledge from heterogeneous document formats at scale. MMORE supports more than fifteen file types, including text, tables, images, emails, audio, and video, and processes them into a unified format to enable downstream applications for LLMs. The architecture offers modular, distributed processing, enabling scalable parallelization across CPUs and GPUs. On processing benchmarks, MMORE demonstrates a 3.8-fold speedup over single-node baselines and 40% higher accuracy than Docling on scanned PDFs. The pipeline integrates hybrid dense-sparse retrieval and supports both interactive APIs and batch RAG endpoints. Evaluated on PubMedQA, MMORE-augmented medical LLMs improve biomedical QA accuracy with increasing retrieval depth. MMORE provides a robust, extensible foundation for deploying task-agnostic RAG systems on diverse, real-world multimodal data. The codebase is available at https://github.com/swiss-ai/mmore.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。