StreamingRAG: Real-time Contextual Retrieval and Generation Framework

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sankaradas, Murugan, Rajendran, Ravi K., Chakradhar, Srimat T.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912202506633216
author Sankaradas, Murugan
Rajendran, Ravi K.
Chakradhar, Srimat T.
author_facet Sankaradas, Murugan
Rajendran, Ravi K.
Chakradhar, Srimat T.
contents Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs) on these data streams. Traditional Retrieval-Augmented Generation (RAG) systems address knowledge limitations of these models, but suffer from slow preprocessing, making them unsuitable for real-time analysis. We propose StreamingRAG, a novel RAG framework designed for streaming data. StreamingRAG constructs evolving knowledge graphs capturing scene-object-entity relationships in real-time. The knowledge graph achieves temporal-aware scene representations using MM-LLMs and enables timely responses for specific events or user queries. StreamingRAG addresses limitations in existing methods, achieving significant improvements in real-time analysis (5-6x faster throughput), contextual accuracy (through a temporal knowledge graph), and reduced resource consumption (using lightweight models by 2-3x).
format Preprint
id arxiv_https___arxiv_org_abs_2501_14101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StreamingRAG: Real-time Contextual Retrieval and Generation Framework
Sankaradas, Murugan
Rajendran, Ravi K.
Chakradhar, Srimat T.
Computer Vision and Pattern Recognition
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs) on these data streams. Traditional Retrieval-Augmented Generation (RAG) systems address knowledge limitations of these models, but suffer from slow preprocessing, making them unsuitable for real-time analysis. We propose StreamingRAG, a novel RAG framework designed for streaming data. StreamingRAG constructs evolving knowledge graphs capturing scene-object-entity relationships in real-time. The knowledge graph achieves temporal-aware scene representations using MM-LLMs and enables timely responses for specific events or user queries. StreamingRAG addresses limitations in existing methods, achieving significant improvements in real-time analysis (5-6x faster throughput), contextual accuracy (through a temporal knowledge graph), and reduced resource consumption (using lightweight models by 2-3x).
title StreamingRAG: Real-time Contextual Retrieval and Generation Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.14101