SQL-Geni: A Secure Multi-Agent Natural Language Database Querying System

SQL-Geni, a secure multi-agent system for querying databases in natural language.

SQL-Geni, a secure multi-agent system for querying databases in natural language. It is offered as a reference project: a complete, worked example of how a system like this is designed, built and evaluated, so that a developer can study it, run it and learn from it.

It suits learners who want to work with language models and text or speech: preparing text data, using or fine-tuning a model, evaluating it and building an interface around it.

The main parts are cooperating agents with defined roles and tools, security and privacy controls such as encryption and access control, text or speech data preparation, model training, fine-tuning or prompting, and evaluation with task-appropriate metrics. The reference build uses LLM APIs, Python, Hugging Face Transformers, spaCy, and PyTorch, with a clear project structure, setup instructions and sample data so that it can be run and extended.