Log Classification System Using Deepseek R1 LLM, NLP, Regex, BERT
Date:
Developed a hybrid log classification system combining Regex rules, Sentence Transformers with Logistic Regression, and LLMs to handle logs of varying complexity.
Built and deployed a FastAPI-based RESTful service for real-time log processing and seamless system integration.
Achieved a 40% improvement in log classification accuracy compared to traditional rule-based approaches.
Reduced operational costs by 30% by automating log analysis and minimizing manual intervention.
Implemented an end-to-end NLP pipeline from preprocessing to model inference and deployment. Technologies: Python, FastAPI, Sentence Transformers, scikit-learn, LLMs