Intelligent NLP-Driven Query System for Seamless Interaction with Relational Databases using CHATDB

This study presents ChatDB, a system that can automatically translate Natural Language Queries (NLQ) into Structured Query Language (SQL) to allow non-technical users to easily interact with relational databases. Through the use of advanced Natural Language Processing (NLP) methods and current language models such as ChatOpenAI, along with techniques like tokenization, lemmatization, and semantic analysis, the system translates user queries and provides correct SQL commands. Results are given in a structured, user-friendly format so that the user who lacks SQL skills can easily use them. The originality of this work lies in its simplicity to integrate NLP with relational databases by applying methods like tokenization, lemmatization, and semantic analysis to optimize query processing without loss of data efficiency and integrity. The value of the system is demonstrated by its ability to respond to advanced queries and give instant feedback, hence being an appropriate utility for use in areas such as education, human resource management, and business intelligence. Its contribution is the construction of a solid platform for interactions using NLP and databases to set the grounds for future refinement. The next step can involve the utilization of infinite-dimension (n-D) cubes to further improve scalability and support even more complex queries. The study adds to the emerging area of intelligent data retrieval systems, providing a scalable and user-friendly solution for practical applications.