Databases are the most critical assets for enterprises, and yet they remain largely inaccessible to people who make the most important decisions. In this paper, we describe the Tursio search platform that builds an abstraction layer, aka semantic knowledge graph, over the underlying databases to make them searchable in natural language. Tursio infuses large language models (LLMs) into every part of the query processing stack, including data modeling, query compilation, query planning, and result reasoning. This allows Tursio to process natural language queries systematically using techniques from traditional query planning and rewriting, rather than black-box memorization. We describe the architecture of Tursio in detail and present a comprehensive evaluation on production workloads, and synthetic and realistic benchmarks. Our results show that Tursio achieves high accuracy while being efficient and scalable, making databases truly searchable for non-expert users.
@article{arxiv.2602.08320,
title = {Making Databases Searchable with Deep Context},
author = {Alekh Jindal and Shi Qiao and Shivani Tripathi and Niloy Debnath and Kunal Singh and Pushpanjali Nema and Sharath Prakash and Aditya Halder and Ronith PR and Sadiq Mohammed and Abdul Hameed and Karan Hanswadkar and Ayush Kshitij and Sarthak Bhatt and Rony Chatterjee and Jyoti Pandey and Christina Pavlopoulou and Ravi Shetye},
journal= {arXiv preprint arXiv:2602.08320},
year = {2026}
}