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{181081,
        author = {Yadamreddy Navaneeth and Yuva T and Taneesha S M and Shushrut R Nayak},
        title = {LogLLM: Real-Time Windows Log Analysis System Using Vector Embeddings and LLMs},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3768-3772},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181081},
        abstract = {We present LogLLM, an advanced real-time system that synergistically combines Windows log ingestion, semantic vector embeddings, and large language models (LLMs) for intelligent log analysis. LogLLM transcends traditional log analysis approaches by enabling natural language querying, sophisticated semantic search, and highly interpretable results through our novel integration of streaming log collection, vector database technology (ChromaDB), and LLM-based retrieval-augmented generation (RAG). Our architecture is informed by recent advances in LLM-based log analysis [3], embedding-driven anomaly detection [2], and domain-adaptive LLMs [4]. Extensive experiments demonstrate that LogLLM achieves exceptional accuracy and responsiveness for operational log analysis tasks, outperforming existing solutions by a significant margin in both precision and query response time.},
        keywords = {Windows Logs, Large Language Models, Vector Embeddings, Semantic Search, Real-Time Analysis, Anomaly Detection, ChromaDB, Retrieval-Augmented Generation.},
        month = {June},
        }