{"ID":2837490,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.05270","arxiv_id":"2601.05270","title":"LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval","abstract":"Modern Retrieval-Augmented Generation (RAG) systems struggle with a fundamental architectural tension: vector indices are optimized for query latency but poorly handle continuous knowledge updates, while data lakes excel at versioning but introduce query latency penalties. We introduce LiveVectorLake, a dual-tier temporal knowledge base architecture that enables real-time semantic search on current knowledge while maintaining complete version history for compliance, auditability, and point-in-time retrieval. The system introduces three core architectural contributions: (1) Content-addressable chunk-level synchronization using SHA-256 hashing for deterministic change detection without external state tracking; (2) Dual-tier storage separating hot-tier vector indices (Milvus with HNSW) from cold-tier columnar versioning (Delta Lake with Parquet), optimizing query latency and storage cost independently; (3) Temporal query routing enabling point-in-time knowledge retrieval via delta-versioning with ACID consistency across tiers. Evaluation on a 100-document corpus versioned across five time points demonstrates: (i) 10-15% re-processing of content during updates compared to 100% for full re-indexing; (ii) sub-100ms retrieval latency on current knowledge; (iii) sub-2s latency for temporal queries across version history; and (iv) storage cost optimization through hot/cold tier separation (only current chunks in expensive vector indices). The approach enables production RAG deployments requiring simultaneous optimization for query performance, update efficiency, and regulatory compliance. Code and resources: [https://github.com/praj-tarun/LiveVectorLake]","short_abstract":"Modern Retrieval-Augmented Generation (RAG) systems struggle with a fundamental architectural tension: vector indices are optimized for query latency but poorly handle continuous knowledge updates, while data lakes excel at versioning but introduce query latency penalties. We introduce LiveVectorLake, a dual-tier tempo...","url_abs":"https://arxiv.org/abs/2601.05270","url_pdf":"https://arxiv.org/pdf/2601.05270v1","authors":"[\"Tarun Prajapati\"]","published":"2025-11-24T11:15:39Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.DB\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":606696,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2837490,"paper_url":"https://arxiv.org/abs/2601.05270","paper_title":"LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval","repo_url":"https://github.com/praj-tarun/LiveVectorLake","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}