Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG

TL;DR

SoccerRAG is a novel framework that combines Retrieval Augmented Generation and Large Language Models to enable natural language querying of multimodal soccer datasets, improving accessibility and user interaction.

Contribution

The paper introduces SoccerRAG, a new system integrating RAG and LLMs with a multimodal dataset and an interactive UI for soccer information retrieval via natural queries.

Findings

Supports dynamic querying of soccer data

Enables automatic data validation

Provides a chatbot-like interactive interface

Abstract

The rapid evolution of digital sports media necessitates sophisticated information retrieval systems that can efficiently parse extensive multimodal datasets. This paper demonstrates SoccerRAG, an innovative framework designed to harness the power of Retrieval Augmented Generation (RAG) and Large Language Models (LLMs) to extract soccer-related information through natural language queries. By leveraging a multimodal dataset, SoccerRAG supports dynamic querying and automatic data validation, enhancing user interaction and accessibility to sports archives. We present a novel interactive user interface (UI) based on the Chainlit framework which wraps around the core functionality, and enable users to interact with the SoccerRAG framework in a chatbot-like visual manner.