FRAGATA: Semantic Retrieval of HPC Support Tickets via Hybrid RAG over 20 Years of Request Tracker History
Santiago Paramés-Estévez, Nicolás Filloy-Montesino, Jorge Fernández-Fabeiro, José Carlos Mouriño-Gallego
TLDR
FRAGATA is a hybrid RAG system for semantic retrieval of HPC support tickets, significantly improving knowledge reuse over 20 years of history.
Key contributions
- Introduces FRAGATA, a hybrid RAG system for semantic retrieval of HPC support tickets.
- Enables finding relevant past incidents despite language, typos, or specific query wording.
- Deployed on CESGA's infrastructure, supporting incremental updates and supercomputer offloading.
- Demonstrates substantial qualitative improvement over the native Request Tracker search engine.
Why it matters
This paper solves the challenge of leveraging decades of support knowledge in HPC centers. FRAGATA offers a robust semantic search solution, significantly enhancing knowledge reuse, improving operational efficiency, reducing incident resolution times.
Original 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 (CESGA) this history has been managed for over twenty years with Request Tracker (RT), whose built-in search engine has significant limitations that hinder knowledge reuse by the support staff. This paper presents Fragata, a semantic ticket search system that combines modern information retrieval techniques with the full RT history. The system can find relevant past incidents regardless of language, the presence of typos, or the specific wording of the query. The architecture is deployed on CESGA's infrastructure, supports incremental updates without service interruption, and offloads the most expensive stages to the FinisTerrae III supercomputer. Preliminary results show a substantial qualitative improvement over RT's native search.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.