Saved in:
Bibliographic Details
Main Authors: Nguyen, Duy A., Do, Hai H., Doan, Minh, Do, Minh N.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.12938
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915675295973376
author Nguyen, Duy A.
Do, Hai H.
Doan, Minh
Do, Minh N.
author_facet Nguyen, Duy A.
Do, Hai H.
Doan, Minh
Do, Minh N.
contents The ability to extract value from historical data is essential for enterprise decision-making. However, much of this information remains inaccessible within large legacy file systems that lack structured organization and semantic indexing, making retrieval and analysis inefficient and error-prone. We introduce SPAR (Session-based Pipeline for Adaptive Retrieval), a conceptual framework that integrates Large Language Models (LLMs) into a Retrieval-Augmented Generation (RAG) architecture specifically designed for legacy enterprise environments. Unlike conventional RAG pipelines, which require costly construction and maintenance of full-scale vector databases that mirror the entire file system, SPAR employs a lightweight two-stage process: a semantic Metadata Index is first created, after which session-specific vector databases are dynamically generated on demand. This design reduces computational overhead while improving transparency, controllability, and relevance in retrieval. We provide a theoretical complexity analysis comparing SPAR with standard LLM-based RAG pipelines, demonstrating its computational advantages. To validate the framework, we apply SPAR to a synthesized enterprise-scale file system containing a large corpus of biomedical literature, showing improvements in both retrieval effectiveness and downstream model accuracy. Finally, we discuss design trade-offs and outline open challenges for deploying SPAR across diverse enterprise settings.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems
Nguyen, Duy A.
Do, Hai H.
Doan, Minh
Do, Minh N.
Information Retrieval
The ability to extract value from historical data is essential for enterprise decision-making. However, much of this information remains inaccessible within large legacy file systems that lack structured organization and semantic indexing, making retrieval and analysis inefficient and error-prone. We introduce SPAR (Session-based Pipeline for Adaptive Retrieval), a conceptual framework that integrates Large Language Models (LLMs) into a Retrieval-Augmented Generation (RAG) architecture specifically designed for legacy enterprise environments. Unlike conventional RAG pipelines, which require costly construction and maintenance of full-scale vector databases that mirror the entire file system, SPAR employs a lightweight two-stage process: a semantic Metadata Index is first created, after which session-specific vector databases are dynamically generated on demand. This design reduces computational overhead while improving transparency, controllability, and relevance in retrieval. We provide a theoretical complexity analysis comparing SPAR with standard LLM-based RAG pipelines, demonstrating its computational advantages. To validate the framework, we apply SPAR to a synthesized enterprise-scale file system containing a large corpus of biomedical literature, showing improvements in both retrieval effectiveness and downstream model accuracy. Finally, we discuss design trade-offs and outline open challenges for deploying SPAR across diverse enterprise settings.
title SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systems
topic Information Retrieval
url https://arxiv.org/abs/2512.12938