Extracting actionable insights from structured databases in regulated industries, such as credit unions, is often hindered by complex schemas, legacy systems, and stringent data governance requirements. We present Tursio, a secure, on-premises, context-aware database search platform that enables business users to query enterprise databases using natural language. Tursio automatically infers a semantic knowledge graph from existing schemas, contextualizes user intent, and systematically generates accurate and compliant query plans by integrating Large Language Models (LLMs) throughout the query processing stack. We demonstrate Tursio's capabilities through realistic scenarios in the credit union domain, highlighting its effectiveness in bridging the gap between complex data structures and user intent.

翻译：在信用合作社等受监管行业中，从结构化数据库中提取可操作的洞察常因复杂的数据模式、遗留系统和严格的数据治理要求而受阻。本文提出Tursio——一个安全、本地部署、具备上下文感知能力的数据库搜索平台，使业务用户能够使用自然语言查询企业数据库。Tursio能够从现有数据模式中自动推断语义知识图谱，通过上下文理解用户意图，并通过在查询处理全栈集成大语言模型（LLMs）来系统生成准确且合规的查询方案。我们通过信用合作社领域的实际应用场景展示Tursio的功能，重点阐明其在弥合复杂数据结构与用户意图之间鸿沟方面的有效性。