Making Databases Searchable with Deep Context

2026-02-09

AI Summary

This work addresses the challenge of limited accessibility to enterprise databases for non-technical users, primarily due to the absence of effective natural language querying capabilities. The authors propose a novel query system that integrates large language models (LLMs) with semantic knowledge graphs, embedding LLMs deeply into the entire query processing pipeline—including parsing, planning, rewriting, and result reasoning—rather than treating them as black-box generators. By leveraging structured semantic abstractions, the approach enhances both the interpretability and accuracy of natural language queries. Experimental results demonstrate that the system achieves high accuracy, efficiency, and strong scalability in both real-world production environments and standard benchmarks, significantly lowering the barrier for non-expert users to interact with complex databases.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• database searchability
• natural language querying
• semantic knowledge graph
• non-expert users
• enterprise databases

Innovation

• semantic knowledge graph
• large language models
• natural language query
• query planning
• database searchability