The integration of Large Language Models (LLMs) with NoSQL databases offers a novel solution for ... more The integration of Large Language Models (LLMs) with NoSQL databases offers a novel solution for managing and retrieving research and development (R&D) experiment documentation. This paper investigates the architectural design, real-world application, and ethical implications of using LLMs to access unstructured and semistructured R&D documents stored in NoSQL systems. Emphasis is placed on natural language query interfaces, semantic search capabilities, and agent-based retrieval for improving operational efficiency, reducing full-time equivalent (FTE) workload, and preserving institutional knowledge. We conclude by highlighting ethical considerations and future research directions for intelligent documentation systems in R&D environments.
International Journal of Advances in Engineering and Management (IJAEM), 2025
This article examines the transformative role of artificial intelligence in automating Enterprise... more This article examines the transformative role of artificial intelligence in automating Enterprise Resource Planning (ERP) system configuration and customization processes. The articleanalyzes current implementation challenges faced by organizations and explores how AI-driven solutions, particularly machine learning and natural language processing, can streamline ERP deployments. Through comprehensive analysis of industry data and case studies, the article investigates the impact of AI automation on implementation timelines, resource allocation, and system configuration accuracy. The findings demonstrate significant improvements in operational efficiency, cost optimization, and user adoption rates through AI integration, while also addressing technical architecture considerations and security frameworks necessary for successful implementation.
In the food and beverage industry, the ability to create innovative flavor formulations efficient... more In the food and beverage industry, the ability to create innovative flavor formulations efficiently is critical for maintaining competitive advantage. The traditional process of flavor development, while proven, faces significant challenges in meeting modern market demands due to its time-consuming nature and reliance on extensive experimentation and subjective evaluation. This paper explores how artificial intelligence is transforming flavor development through advanced data analytics, machine learning, and automated systems. By examining implementations across major food manufacturers, we demonstrate how AI-driven approaches are revolutionizing traditional methods, from initial conception to market deployment. The research highlights significant improvements in development efficiency, prediction accuracy, resource optimization, and market responsiveness, while also addressing critical implementation considerations and future implications for the industry.
Uploads
Papers by Tanmoy Biswas