Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Fragata, a hybrid retrieval-augmented generation (RAG) system for semantic search of 20 years of HPC support tickets stored in Request Tracker. Fragata combines dense retrieval using sentence transformers with keyword-based search to overcome limitations of RT's built-in search, handling multilingual queries and typos. Preliminary results demonstrate improved retrieval quality compared to RT's native search, with the system deployed on CESGA's infrastructure and leveraging the FinisTerrae III supercomputer for computationally intensive tasks.
Unlock decades of supercomputing support knowledge: Fragata's hybrid RAG system makes 20 years of HPC support tickets searchable with semantic understanding, even across languages and typos.
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.