Monitoring continuous data for meaningful signals increasingly demands long-horizon, stateful reasoning over unstructured streams. However, today's LLM frameworks remain stateless and one-shot, and traditional Complex Event Processing (CEP) systems, while capable of temporal pattern detection, assume structured, typed event streams that leave unstructured text out of reach. We demonstrate VectraFlow, a semantic streaming dataflow engine, to address both gaps. VectraFlow extends traditional relational operators with LLM-powered execution over free-text streams, offering a suite of continuous semantic operators -- filter, map, aggregate, join, group-by, and window -- each with configurable throughput-accuracy tradeoffs across LLM-based, embedding-based, and hybrid implementations. Building on this, a semantic event pattern operator lifts complex event processing to unstructured document streams, combining LLM-based event extraction with NFA-based temporal rule matching for stateful reasoning over sequences of semantic events. In this demonstration, users will interact with VectraFlow's live query interface to compose semantic pipelines over clinical document streams. Attendees will compile natural language intents into executable operator graphs, inspect intermediate stateful outputs, and observe end-to-end temporal pattern detection, from raw text to matched event cohorts.

翻译：摘要：对连续数据进行有意义信号监测的需求日益增长，这要求对非结构化流进行长期、有状态的推理。然而，当前的大语言模型框架仍保持无状态和一次性处理模式，而传统复杂事件处理系统虽具备时间模式检测能力，但仅适用于结构化、类型化的事件流，无法处理非结构化文本。我们提出VectraFlow——一种语义流式数据流引擎，以弥合这两类系统的差距。VectraFlow通过基于大语言模型（LLM）的自由文本流执行能力扩展传统关系运算符，提供一套连续语义运算符（过滤、映射、聚合、连接、分组和窗口），每种运算符均支持基于LLM、嵌入和混合实现的吞吐量-准确性可配置权衡。在此基础上，语义事件模式运算符将复杂事件处理提升至非结构化文档流，结合基于LLM的事件抽取与基于NFA的时间规则匹配，实现语义事件序列的有状态推理。在本次演示中，用户将通过VectraFlow的实时查询接口，基于临床文档流构建语义流水线。参与者可将自然语言意图编译为可执行运算符图，检查中间状态输出，并观察从原始文本到匹配事件队列的端到端时间模式检测过程。