AkasicDB: Demonstrating Omni RAG with a Unified Vector-Graph-Relational DBMS

2026-08-10

AI Summary

Existing databases struggle to efficiently support complex RAG workflows that integrate vector retrieval, graph traversal, and relational filtering, often relying on external pipelines that incur substantial overhead. This work proposes AkasicDB, the first system to natively unify vector similarity search, graph traversal, and relational querying within a single execution framework, thereby realizing an Omni RAG paradigm that seamlessly combines vectors, graphs, and relations. Built upon an extended Chimera architecture with native vector support, AkasicDB deeply integrates vector indexing, graph processing, and relational query engines. Experimental results demonstrate that Omni RAG significantly outperforms pure vector-based approaches in both retrieval accuracy and reasoning capability, while also exposing fundamental architectural limitations of conventional databases in handling such multimodal workflows.

Abstract

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

Problem

• Retrieval-Augmented Generation
• Vector-Graph-Relational DBMS
• Omni RAG
• Database Architecture
• Structured Knowledge Integration

Innovation

• Omni RAG
• Vector-Graph-Relational DBMS
• Native Integration
• Unified Execution Framework
• Chimera Extension