Real-time Spatial Retrieval Augmented Generation for Urban Environments
David Nazareno Campo, Javier Conde, \'Alvaro Alonso, Gabriel Huecas,, Joaqu\'in Salvach\'ua, Pedro Reviriego

TL;DR
This paper introduces a real-time spatial Retrieval Augmented Generation architecture tailored for urban environments, enabling dynamic, context-aware AI applications in cities by leveraging linked data and FIWARE components.
Contribution
It presents a novel spatial RAG architecture that integrates temporal and spatial filtering for urban AI applications, demonstrated through a Madrid tourism assistant use case.
Findings
Successful implementation using FIWARE components
Effective integration of Foundation Models with spatial data
Validated architecture through a practical city use case
Abstract
The proliferation of Generative Artificial Ingelligence (AI), especially Large Language Models, presents transformative opportunities for urban applications through Urban Foundation Models. However, base models face limitations, as they only contain the knowledge available at the time of training, and updating them is both time-consuming and costly. Retrieval Augmented Generation (RAG) has emerged in the literature as the preferred approach for injecting contextual information into Foundation Models. It prevails over techniques such as fine-tuning, which are less effective in dynamic, real-time scenarios like those found in urban environments. However, traditional RAG architectures, based on semantic databases, knowledge graphs, structured data, or AI-powered web searches, do not fully meet the demands of urban contexts. Urban environments are complex systems characterized by large…
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.
Taxonomy
TopicsGeographic Information Systems Studies · 3D Modeling in Geospatial Applications · Context-Aware Activity Recognition Systems
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Linear Warmup With Linear Decay · Dropout · Layer Normalization · Byte Pair Encoding · Attention Dropout · Softmax · Residual Connection · WordPiece
