Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.03291 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914444776308736 |
|---|---|
| author | Dornauer, Benedikt Racasan, Mircea-Cristian |
| author_facet | Dornauer, Benedikt Racasan, Mircea-Cristian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03291 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models Dornauer, Benedikt Racasan, Mircea-Cristian Hardware Architecture Artificial Intelligence 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. |
| title | RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03291 |