MMORE: Massive Multimodal Open RAG & Extraction
This provides a scalable foundation for deploying RAG systems on real-world multimodal data, though it appears incremental as an integration of existing techniques.
The authors tackled the problem of processing and retrieving knowledge from diverse multimodal document formats at scale, introducing MMORE, an open-source pipeline that achieved a 3.8-fold speedup over single-node baselines and 40% higher accuracy than Docling on scanned PDFs.
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.