动态知识流下实时更新检索增强，兼顾速度与精度。
From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Base
- 用多向量筛选+聚类+计数器过滤，压缩知识库体积
- 召回率最高提升3点，延迟低于15毫秒，每秒处理超900文档
- 适合需要实时知识更新的问答与摘要场景
新闻、社交媒体、传感器网络和金融市场的动态数据流对静态RAG框架构成挑战。全量索引内存开销大；周期性重建引入延迟，影响数据新鲜度；简单采样则损失语义覆盖。我们提出Streaming RAG，一个统一管道，结合多向量余弦筛选、小批量聚类和基于计数器的热点过滤，维护紧凑的原型集合。我们进一步证明了近似界 $E[R(K_t)] \ge R^* - L \Delta$，将检索质量与聚类方差关联。增量索引更新机制可在不中断查询的情况下刷新原型。在八个真实数据流上的实验显示，召回率@10最高提升3点（p < 0.01），端到端延迟低于15毫秒，吞吐量超过900文档/秒，内存占用控制在150 MB以内。超参数敏感性分析验证了默认设置的有效性。在GPT-3.5 Turbo上进行开放域问答，SQuAD上精确匹配提升3.2点，F1提升2.8点；抽象摘要任务中ROUGE-L也取得提升。Streaming RAG建立了检索增强的新帕累托前沿。
原文摘要 · Abstract (English)
Dynamic streams from news feeds, social media, sensor networks, and financial markets challenge static RAG frameworks. Full-scale indices incur high memory costs; periodic rebuilds introduce latency that undermines data freshness; naive sampling sacrifices semantic coverage. We present Streaming RAG, a unified pipeline that combines multi-vector cosine screening, mini-batch clustering, and a counter-based heavy-hitter filter to maintain a compact prototype set. We further prove an approximation bound \$E\[R(K\_t)] \ge R^\* - L Δ\$ linking retrieval quality to clustering variance. An incremental index upsert mechanism refreshes prototypes without interrupting queries. Experiments on eight real-time streams show statistically significant gains in Recall\@10 (up to 3 points, p < 0.01), end-to-end latency below 15 ms, and throughput above 900 documents per second under a 150 MB budget. Hyperparameter sensitivity analysis over cluster count, admission probability, relevance threshold, and counter capacity validates default settings. In open-domain question answering with GPT-3.5 Turbo, we record 3.2-point gain in Exact Match and 2.8-point gain in F1 on SQuAD; abstractive summarization yields ROUGE-L improvements. Streaming RAG establishes a new Pareto frontier for retrieval augmentation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。