{"ID":2888396,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05662","arxiv_id":"2508.05662","title":"From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Base","abstract":"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 \u003c 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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.05662","url_pdf":"https://arxiv.org/pdf/2508.05662v1","authors":"[\"Yuzhou Zhu\"]","published":"2025-07-31T14:03:19Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[]","has_code":false}