Paper Title
Sequelizer - A No Code SQL Model Generator, Visualizer and Query Generation from Natural Language
Abstract
The modern world relies on an extensive data driven network. The data is managed and stored in the form of
RDBMS. With huge amounts of data, using the right commands and approach has become a major show stopper in reducing
costs and increasing performance. The majority of RDBMS is built based on Structured Query Language (SQL). This has led
to the requirement of profound knowledge in SQL for efficient usage. The advancements in Natural Language processing
can be used for bridging the knowledge gap in such scenarios. Natural language based querying eases the creation of
complex queries. This, when integrated with a No code tool can aid in seamless creation and visualization of SQL tables and
queries. In this paper, we propose a Natural language based querying of SQL tables along with a no code tool for visualizing
the tables. When the visualizer is integrated with query generation, the queries generated can be highly accurate with reduced
errors due to a schema aware query generation. This method also aids in effortless joins among tables and generates the most
optimized queries.
Keywords - SQL, Natural language processing, No code tool, Query generation, Large language model, Visualization