图数据库在LLM智能体中的记忆成本：跨图数据库引擎的查询、摄取与更新性能比较评估

中文摘要 AI 辅助

图数据库常被定位为连接数据工作负载的绝对必要组件，然而它们实际差异所在的系统维度——查询规划、索引和数据就绪成本——很少与供应商宣传相分离。我们构建了一个合成但具有生物医学形态的属性图（102万个节点，总计534万个节点和边行），以及一个包含二十个查询的工作负载，涵盖邻域查找、有界路径、集合交集、反连接、分组聚合、Top-k排序、时间过滤、全表扫描和关系连接。我们将Corvic AI——一个专为Corvic本体管理层（“记忆”）设计的列式查询引擎——与七个专用或图扩展数据库系统（LoraDB、Ladybug、DuckPGQ、Memgraph、Neo4j、HugeGraph和FalkorDB）在跨越三个数量级的三个图规模上进行了基准测试。我们报告了每个系统的查询延迟几何平均值、批量摄取吞吐量、点更新延迟和答案正确性，并推导了一个简单的总拥有成本模型，该模型将摄取/查询权衡表示为查询量的函数。我们的核心发现是，该样本中没有系统是绝对最快的：原生图引擎（Ladybug）在狭窄、有界的邻域形状上优于Corvic AI，而Corvic AI在扫描或连接图的大部分形状上更快，而通过SQL/PGQ实现图查询语法的系统（DuckPGQ）仅因查询计划选择而明显较慢。我们数据中的主要成本差异不是查询延迟，而是使数据可查询的成本：批量摄取吞吐量在引擎间变化达三个数量级（5.0k-4.3M行/秒），一个简单的交叉点计算表明，对于每次数据刷新少于约10^5次查询的任何工作负载，这一差距主导了总成本。

英文摘要

Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually differ - query planning, indexing, and data-readiness cost - is rarely isolated from vendor framing. We construct a synthetic, biomedical-shaped property graph (1.02 million nodes, 5.34 million total node and edge rows) and a twenty-query workload spanning neighborhood lookups, bounded paths, set intersections, anti-joins, grouped aggregation, top-k ranking, temporal filters, full scans, and relational joins. We benchmark Corvic AI - a purpose-built columnar query engine underlying Corvic's ontology management layer ("memories")- against seven purpose-built or graph-extension database systems (LoraDB, Ladybug, DuckPGQ, Memgraph, Neo4j, HugeGraph, and FalkorDB) at three graph scales spanning three orders of magnitude. We report query latency geomeans, bulk-ingest throughput, point-update latency, and answer correctness for each system, and we derive a simple total-cost-of-ownership model that expresses the ingest/query trade-off as a function of query volume. Our central finding is that no system in this sample is categorically fastest: a native graph engine (Ladybug) outperforms Corvic AI on narrow, bounded-neighborhood shapes, while Corvic AI is faster on shapes that scan or join a large fraction of the graph, and a system implementing graph query syntax via SQL/PGQ (DuckPGQ) is measurably slower purely due to query-plan choice. The dominant cost differential in our data is not query latency but the cost of making data queryable at all: bulk-ingest throughput varies by three orders of magnitude across engines (5.0k-4.3M rows/s), a gap that a simple crossover-point calculation shows dominates total cost for any workload with fewer than roughly 105 queries per data refresh.

发表机构

• Corvic AI Research（Corvic人工智能研究院）
• UT Austin（德克萨斯大学奥斯汀分校）

机构由 AI 辅助整理，请以论文原文为准。