Retrieval-Augmented Search for Large-Scale Map Collections with ColPali
Jamie Mahowald, Benjamin Charles Germain Lee

TL;DR
This paper presents map-RAS, a retrieval-augmented search system for historic maps that enables multimodal querying, summarization, and inter-collection search, demonstrated on a large collection from the Library of Congress.
Contribution
Introduction of map-RAS, a novel multimodal search system for large-scale map collections with a publicly accessible demo and features for summarization and inter-collection search.
Findings
Successfully searched over 100,000 map images
Enabled multimodal queries and summarization
Facilitated inter-collection search for diverse users
Abstract
Multimodal approaches have shown great promise for searching and navigating digital collections held by libraries, archives, and museums. In this paper, we introduce map-RAS: a retrieval-augmented search system for historic maps. In addition to introducing our framework, we detail our publicly-hosted demo for searching 101,233 map images held by the Library of Congress. With our system, users can multimodally query the map collection via ColPali, summarize search results using Llama 3.2, and upload their own collections to perform inter-collection search. We articulate potential use cases for archivists, curators, and end-users, as well as future work with our system in both machine learning and the digital humanities. Our demo can be viewed at: http://www.mapras.com.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
