Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG

June 03, 2024 · Entered Twilight · 🏛 International Conference on Content-Based Multimedia Indexing

Repo contents: .env_demo, .gitattributes, .gitignore, Dockerfile, LICENSE, README.md, app.py, chainlit.md, data, main.py, main_cli.py, media, requirements.txt, setup.py, src

Authors Aleksander Theo Strand, Sushant Gautam, Cise Midoglu, Pål Halvorsen arXiv ID 2406.01280 Category cs.IR: Information Retrieval Cross-listed cs.MM Citations 1 Venue International Conference on Content-Based Multimedia Indexing Repository https://github.com/simula/soccer-rag ⭐ 9 Last Checked 1 month ago

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.