# From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Base

arXiv: https://arxiv.org/abs/2508.05662 · HTML: https://mlsanity.com/paper/2508.05662/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 5 of 5)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Streaming Algorithms with Few State Changes](https://mlsanity.com/paper/2406.06821/) (2024)

## Built on by (most cited first, 2 of 2)

- [LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval](https://mlsanity.com/paper/2601.05270/) (2025)
- [RADAR: Defending RAG Dynamically against Retrieval Corruption](https://mlsanity.com/paper/2605.22041/) (2026)

## Abstract (arXiv)

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(Kt)] ≥ R^* - L Delta 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.