dorsal/arxiv
View SchemaLiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval
| Authors | Tarun Prajapati |
|---|---|
| Categories | |
| ArXiv ID | 2601.05270vv1 |
| URL | https://arxiv.org/abs/2601.05270 |
| License | http://creativecommons.org/licenses/by/4.0/ |
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]
{
"annotation_id": "cb9cc8ce-2500-449d-b02b-7330e4a33ab4",
"date_created": "2026-02-17T05:53:05.066000Z",
"date_modified": "2026-02-17T05:53:05.066000Z",
"file_hash": "84fd29a1724f6a65ac2f838b56c65733647770a8a6a38ff08539cbab8a9d0715",
"private": false,
"record": {
"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]",
"arxiv_id": "2601.05270",
"authors": [
"Tarun Prajapati"
],
"categories": [
"cs.IR",
"cs.AI",
"cs.DB"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "LiveVectorLake: A Real-Time Versioned Knowledge Base Architecture for Streaming Vector Updates and Temporal Retrieval",
"url": "https://arxiv.org/abs/2601.05270",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "f230732f-3a91-4b01-ba06-ab0457c0d7f5",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}