On an Approach to Developing Information and Reference Systems Based on Large Language Models

Abstract

The aim of this study is to develop a corporate context-aware question-answering system in the form of a chatbot to support territorial management by providing fast and accurate access to relevant information. The system is built upon large language models leveraging the Retrieval-Augmented Generation (RAG) approach, combined with modern data processing and retrieval techniques. The knowledge base of the system incorporates textual and tabular data extracted from official reports on environmental conditions. A PostgreSQL database with the pgvector extension was employed to store and retrieve large volumes of vectorized data efficiently. Advanced Bi- and Cross-encoder architectures were integrated to enhance the accuracy of context interpretation and the relevance of retrieved answers. The system’s backend was implemented using the Text Generation Interface platform, while the frontend relies on ReactJS and a Telegram bot, ensuring an intuitive user interface for diverse audiences. Additional features, such as query classification filters and temporal interval normalization, were introduced to refine the system’s response precision and user experience. The results demonstrate the effectiveness of combining state-of-the-art artificial intelligence technologies with robust data management solutions. The developed system not only improves response accuracy and retrieval efficiency but also offers scalability and adaptability for application in various domains. This research highlights the potential of AI-driven solutions in addressing complex challenges in territorial management and beyond.