RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models

Benedikt Dornauer; Mircea-Cristian Racasan

cs.ARMar 27, 2026

RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models

Authors: Benedikt Dornauer, Mircea-Cristian Racasan

Organizations: University of Innsbruck Innsbruck, Austria · c.c.com Moser GmbH Teslastraße 4, 8074 Grambach, Austria

Abstract

This paper introduces RAGnaroX, a resource-efficient ChatOps assistant that operates entirely on commodity hardware. Unlike existing solutions that often rely on external providers such as Azure or OpenAI, RAGnaroX offers a fully auditable, on-premise stack implemented in Rust. Its architecture integrates modular data ingestion, hybrid retrieval, and function calling, enabling flexible yet secure deployment. Our evaluation focuses on the RAG pipeline, with benchmarks conducted on the SQuAD (single-hop QA), MultiHopRAG (multi-hop QA), and MLQA (cross-lingual QA) datasets. Results show that RAGnaroX achieves competitive accuracy while maintaining strong resource efficiency, for example, reaching 0.90 context precision on single-hop questions with an average response time of 2.5 seconds per request. A replication package containing the tool, the demonstration video (https://www.youtube.com/watch? v=cDxfuEbcoM4), and all supporting materials are available at https://github.com/genius-itea/RAGnaroX.git.

Figures & tables

Fig. 1: Conceptual overview of the RAGnaroX data integration and retrieval–generation pipeline for ChatOps.

Fig. 2: Performance Metrics in RAGnaroX, with changed generation models

Model	Single-hop QA		Multi-hop QA
Model	Faith.	AnsRel.	Faith.	AnsRel.
Qwen3 (14B)	0.8327	0.7846	0.7039	0.6407
Qwen3 (8B)	0.8364	0.7865	0.6874	0.6328
Mistral (7B)	0.7963	0.7705	0.4654	0.6568
Gemma-3n-E2B	0.7183	0.7722	0.4067	0.5056
Qwen3 (4B)	0.8588	0.8168	0.6341	0.6790

TABLE I: Faithfulness and answer relevancy comparison

Corpus– Question	Ctx. P.	Ctx. R.	Faith.		AnsRel.
Corpus– Question	Ctx. P.	Ctx. R.	14B	4B	14B	4B
en–en	0.86	0.91	0.83	0.81	0.73	0.75
de–de	0.74	0.77	0.77	0.73	0.41	0.44
es–es	0.82	0.87	0.77	0.80	0.53	0.58
en–de	0.59	0.70	0.74	0.70	0.41	0.43
de–en	0.64	0.73	0.73	0.71	0.71	0.65

TABLE II: RAG system performance of Qwen3 14B and 4B

Retrieval-Augmented Generation

Retrieval-augmented generation connects language models to external knowledge so answers can use current, domain-specific evidence.

See all 792 papers

An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
Apr 23, 2026Mykola Trokhymovych, Yana Oliinyk, Nazarii NyzhnykRetrieval-Augmented Generation Hybrid Retrieval
Pompeu Fabra University · Independent Researcher
RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
Jul 21, 2026Dan MusetoiuRetrieval-Augmented Generation Fine-Tuning
IT Department, Agency for Financing Rural Investments (AFIR), Romania
Little Brains, Big Feats: Exploring Compact Language Models
Jun 29, 2026Dari Baturova, Elena Bruches, Ivan Chernov +3Retrieval-Augmented Generation On-Device Language Model Inference
Siberian Neuronets LLC, Novosibirsk, Russia

Apr 23, 2026J/K move · Enter open · S save

An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation

Mykola Trokhymovych, Yana Oliinyk, Nazarii Nyzhnyk

Pompeu Fabra University · Independent Researcher

Retrieval-Augmented Generation Hybrid Retrieval Efficient Language Model Inference

Open paper AskPDF arXiv

This paper presents a highly efficient Retrieval-Augmented Generation (RAG) system built specifically for Ukrainian document question answering, which achieved 2nd place in the UNLP 2026 Shared Task. Our solution features a custom two-stage search pipeline that retrieves relevant document pages, paired with a specialized Ukrainian language model fine-tuned on synthetic data to generate accurate, grounded answers. Finally, we compress the model for lightweight deployment. Evaluated under strict computational limits, our architecture demonstrates that high-quality, verifiable AI question answering can be achieved locally on resource-constrained hardware without sacrificing accuracy.

Abstract

Retrieval-Augmented Generation

Explore similar work

An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation

RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency

Little Brains, Big Feats: Exploring Compact Language Models