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.
Nowadays, there are billions interconnected devices forming Cyber-Physical Systems, Internet of Things (IoT) and Industrial Internet of Things (IIoT) ecosystems. With an increasing number of devices and systems in use, amount and the value of data, the risks of security breaches increase. One of these risks is posed by open data sources, by which are meant databases, which are not properly protected. These poorly protected databases are accessible to external actors, which poses a serious risk to the data holder and the results of data-related activities such as analysis, forecasting, monitori…
Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting
Department of Computing and Mathematics University of Sao Paulo（计算机与数学系 乌拉圭圣保罗大学）；Department of Information Systems University of Münster（信息系统系 梅茵斯特大学）
TU Darmstadt（达姆施塔特工业大学）；Bilkent University（比尔肯特大学）
The ability to extract insights from new data sets is critical for decision making. Visual interactive tools play an important role in data exploration since they provide non-technical users with an effective way to visually compose queries and comprehend the results. Natural language has recently gained traction as an alternative query interface to databases with the potential to enable non-expert users to formulate complex questions and information needs efficiently and effectively. However, understanding natural language questions and translating them accurately to SQL is a challenging task…
The well-known benefits of cloud computing have spurred the popularity of database service outsourcing, where one can resort to the cloud to conveniently store and query databases. Coming with such popular trend is the threat to data privacy, as the cloud gains access to the databases and queries which may contain sensitive information, like medical or financial data. A large body of work has been presented for querying encrypted databases, which has been mostly focused on secure keyword search. In this paper, we instead focus on the support for secure skyline query processing over encrypted o…
Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things
Department of Intelligent Systems & Robotics - The University of West Florida（威斯弗拉明戈大学智能系统与机器人系）；Florida Institute for Human and Machine Cognition（佛罗里达人类与机器认知研究所）；US Army DEVCOM Army Research Laboratory（美国陆军 DEVCOM 军事研究实验室）
