Retrieval-Augmented Search for Large-Scale Map Collections with ColPali
By: Jamie Mahowald, Benjamin Charles Germain Lee
Potential Business Impact:
Find old maps easily with smart search.
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.
Similar Papers
SARCH: Multimodal Search for Archaeological Archives
Information Retrieval
Finds old book pictures and words faster.
Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering
Digital Libraries
Helps computers answer questions from old, messy papers.
A Survey on Retrieval And Structuring Augmented Generation with Large Language Models
Computation and Language
Helps AI tell true facts, not made-up ones.