Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191860,
        author = {Arya Nagar and Abhimanyu Singh Nagar and Sahaj Sharma and Mrs. Pooja Kumawat},
        title = {LARRY: THE RAG-POWERED SPORTS & NUTRITION GUIDE},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {8041-8043},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191860},
        abstract = {The growing reliance on digital platforms for health, nutrition, and sports guidance has introduced challenges related to accuracy, privacy, and transparency of information. Most existing solutions depend on cloud-hosted large language models (LLMs) or static rule-based systems, often producing generalized or unverifiable recommendations while retaining user data on external servers. This paper presents Larry, a Retrieval-Augmented Generation (RAG) powered sports and nutrition guidance system designed to operate entirely on a local machine. Larry leverages a curated knowledge base of authoritative books in nutrition, sports science, and general health to generate context-aware, user-specific recommendations. By combining agentic reasoning with vector-based retrieval, the system ensures responses are grounded in verified literature while preserving user privacy. A comparative study is conducted between Larry, a generic LLM without retrieval augmentation, and manual book-based consultation. Evaluation based on accuracy alignment, response consistency, and user satisfaction demonstrates that Larry significantly reduces hallucinated outputs and improves decision support. The results indicate that RAG-based, localhost-deployed systems can serve as effective, privacy-preserving alternatives to cloud-centric health guidance platforms.},
        keywords = {Retrieval-Augmented Generation, Sports Nutrition, Agentic AI, Privacy-Preserving Systems, Localhost AI, Decision Support},
        month = {January},
        }