发表机构
KAIST; GraphAI（韩国科学技术院; GraphAI公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AkasicDB是一款支持在单一框架内协同执行向量、图、关系操作的数据库系统，可实现全模态检索增强生成（Omni RAG），演示显示其性能优于仅向量方法，且暴露了现有数据库架构的局限。
AI 中文摘要
近期的检索增强生成（RAG）系统日益将向量检索与结构化知识相结合，如图检索增强生成（Graph RAG）和过滤式向量搜索。然而，现有数据库架构难以高效支持此类复杂RAG工作流，因为它们依赖数据库外的流水线或数据库内的非原生集成，导致开销过高。本文作为演示论文，提出AkasicDB这一数据库系统，其通过在单一执行框架内协同执行向量相似度搜索、图遍历和关系过滤，原生支持此类RAG工作流。AkasicDB在我们此前的工作Chimera基础上扩展了原生向量支持，以实现此类统一执行。基于AkasicDB，我们演示了首个向量-图-关系型RAG的原生集成，即全模态检索增强生成（Omni RAG）。通过交互式聊天式演示，用户可执行并可视化Omni RAG查询，直接体验其相较于仅向量方法更优的检索与推理能力，同时观察现有数据库架构在支持Omni RAG时的实际局限。演示视频可通过此URL获取。
英文摘要
Recent Retrieval-Augmented Generation (RAG) systems increasingly combine vector retrieval with structured knowledge, such as Graph RAG and Filtered vector search. However, existing database architectures struggle to support such complex RAG workflows efficiently, as they rely on out-of-DB pipelines or in-DB non-native integration, leading to high overhead. This demo paper presents AkasicDB, a database system that natively supports such RAG workflows by jointly executing vector similarity search, graph traversal, and relational filtering within a single execution framework. AkasicDB extends our prior work, Chimera, with native vector support to enable such unified execution. Based on AkasicDB, we demonstrate the first native integration of Vector-Graph-Relational RAG, which we refer to as Omni RAG. Through an interactive chat-style demonstration, users execute and visualize Omni RAG queries, directly experiencing its superior retrieval and reasoning over vector-only approaches while observing the practical limitations of existing database architectures in supporting Omni RAG. A demonstration video is available at https://youtu.be/8d09_dtrEIM
CommentsSIGMOD 2026 demonstration
Journal refSIGMOD Companion 2026, pp. 70-73
