PulseAugur
LIVE 14:49:23
research · [1 source] ·
0
research

Fragata system uses hybrid RAG to semantically search 20 years of HPC support tickets

Researchers have developed Fragata, a new system designed to semantically search through two decades of high-performance computing (HPC) support tickets. This system utilizes a hybrid Retrieval-Augmented Generation (RAG) approach to overcome the limitations of traditional search engines, enabling more effective knowledge reuse for support staff. Fragata can identify relevant past incidents despite variations in language, typos, or specific phrasing, and has demonstrated significant qualitative improvements over existing search functionalities. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances knowledge retrieval for technical support teams by enabling semantic search over extensive historical data.

RANK_REASON This is a research paper detailing a new system for semantic search of historical support tickets.

Read on arXiv cs.AI →

COVERAGE [1]

  1. arXiv cs.AI TIER_1 · Santiago Param\'es-Est\'evez, Nicol\'as Filloy-Montesino, Jorge Fern\'andez-Fabeiro, Jos\'e Carlos Mouri\~no-Gallego ·

    FRAGATA: Semantic Retrieval of HPC Support Tickets via Hybrid RAG over 20 Years of Request Tracker History

    arXiv:2604.13721v2 Announce Type: replace-cross Abstract: The technical support team of a supercomputing centre accumulates, over the course of decades, a large volume of resolved incidents that constitute critical operational knowledge. At the Galician Supercomputing Center (CES…