FUTURAL: A Metasearch Platform for Empowering Rural Areas with Smart Solutions

TL;DR

FUTURAL develops a metasearch platform with an LLM-powered natural language interface to access and retrieve smart solutions for rural social and environmental issues, demonstrating effective MVP implementation.

Contribution

The paper presents an open-source MVP for a metasearch platform utilizing LLMs, focusing on design, adaptation tools, and evaluation techniques for rural smart solutions.

Findings

The approach is highly effective in retrieving relevant solutions.

The MVP can be efficiently extended with additional services and datasets.

Evaluation results confirm the platform's usability and performance.

Abstract

The FUTURAL project aims to provide a comprehensive suite of digital Smart Solutions (SS) across five critical domains to address pressing social and environmental issues. Central to this initiative is a robust Metasearch platform, which will not only serve as the primary access point to FUTURAL's solutions but also facilitate the search and retrieval of SS developed by other initiatives. This paper elaborates on the MVP implementation for the MetaSearch platform. It focuses on a single, open-source data service and harnesses the generative capabilities of Large Language Models (LLMs) to create a user-friendly natural language interface. The design of the Minimum Viable Product (MVP), the tools used for adapting LLMs to our specific application, and our comprehensive set of evaluation techniques are thoroughly detailed. The results from our evaluations demonstrate that our approach is highly effective and can be efficiently implemented in future iterations of the MVP. This groundwork paves the way for extending the platform to include additional services and diverse data sets from the FUTURAL project, enhancing its capacity to address a broader array of queries and datasets.