M(M)ORE : Massive Multimodal Open RAG & Extraction

Alexandre Sallinen, Stefan Krsteski, Paul Teiletche, Allard Marc-Antoine, Baptiste Lecoeur, Michael Zhang, Fabrice Nemo, David Kalajdzic, Matthias Meyer, Mary-Anne Hartley

Keywords: Data, Software, Processing, ML, AI

TL;DR: We introduce MMORE, an open-source pipeline for Massive Multimodal Open Retrieval- Augmented Generation and Extraction, designed to ingest, transform, and retrieve knowledge from heterogeneous document formats at scale

Abstract:

We introduce MMORE, an open-source
pipeline for Massive Multimodal Open Retrieval-
Augmented 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 paral-
lelization 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

Submission Number: 25