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

2026-04-15 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Cloud Computing & IT Infrastructure · Depth: Advanced, quick

Summary

The Galician Supercomputing Center (CESGA) has developed Fragata, a semantic ticket search system designed to improve knowledge reuse from over two decades of Request Tracker (RT) support ticket history. Fragata addresses the significant limitations of RT's native search engine by employing modern information retrieval techniques. This system enables support staff to locate relevant past incidents irrespective of language barriers, typographical errors, or specific query phrasing. Its architecture is deployed on CESGA's infrastructure, supports incremental updates without service interruption, and utilizes the FinisTerrae III supercomputer for computationally intensive stages. Preliminary evaluations indicate a substantial qualitative enhancement compared to RT's built-in search capabilities.

Key takeaway

For research scientists managing large volumes of historical support data, you should consider implementing a semantic retrieval system like Fragata. This approach can significantly improve knowledge reuse by overcoming limitations of native search engines, allowing for more efficient incident resolution and better support staff productivity.

Key insights

Fragata enhances HPC support ticket retrieval using hybrid RAG over two decades of historical data.

Principles

• Semantic search improves knowledge reuse.
• Hybrid RAG overcomes native search limitations.

Method

Fragata combines modern information retrieval with full RT history, supporting incremental updates and offloading expensive stages to a supercomputer for semantic ticket search.

In practice

• Implement semantic search for legacy systems.
• Utilize supercomputing for retrieval tasks.

Topics

• FRAGATA
• Semantic Retrieval
• HPC Support Tickets
• Hybrid RAG
• Request Tracker

Best for: Research Scientist, AI Scientist, AI Engineer, IT Professional

Related on AIssential

• FRAGATA: Semantic Retrieval of HPC Support Tickets via Hybrid RAG over 20 Years of Request Tracker History — Hybrid RAG systems can effectively transform decades of unstructured support ticket data into a semantically searchable knowledge base.
• Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs — PDF parsing for RAG should produce a relational set of linked tables, not flat text, to preserve document structure.
• HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG — HKVM-RAG uses hypergraph keys to organize multi-hop evidence, improving RAG performance by complementing dense retrievers.
• RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora — RARE framework improves RAG evaluation by accounting for document redundancy in high-similarity real-world corpora.
• Your RAG System Isn’t Retrieving. It’s Guessing. — Current Retrieval Augmented Generation (RAG) systems largely rely on vector databases and the assumption that semantic similarity equates to relevance, a principle powering billions in infrastructure.
• The retrieval rebuild: Why hybrid retrieval intent tripled as enterprise RAG programs hit the scale wall — Enterprise RAG is shifting from simple vector search to complex hybrid retrieval for production agentic AI.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.