LLM as HPC Expert: Extending RAG Architecture for HPC Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912203274190848 |
|---|---|
| author | Miyashita, Yusuke Tung, Patrick Kin Man Barthélemy, Johan |
| author_facet | Miyashita, Yusuke Tung, Patrick Kin Man Barthélemy, Johan |
| contents | High-Performance Computing (HPC) is crucial for performing advanced computational tasks, yet their complexity often challenges users, particularly those unfamiliar with HPC-specific commands and workflows. This paper introduces Hypothetical Command Embeddings (HyCE), a novel method that extends Retrieval-Augmented Generation (RAG) by integrating real-time, user-specific HPC data, enhancing accessibility to these systems. HyCE enriches large language models (LLM) with real-time, user-specific HPC information, addressing the limitations of fine-tuned models on such data. We evaluate HyCE using an automated RAG evaluation framework, where the LLM itself creates synthetic questions from the HPC data and serves as a judge, assessing the efficacy of the extended RAG with the evaluation metrics relevant for HPC tasks. Additionally, we tackle essential security concerns, including data privacy and command execution risks, associated with deploying LLMs in HPC environments. This solution provides a scalable and adaptable approach for HPC clusters to leverage LLMs as HPC expert, bridging the gap between users and the complex systems of HPC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14733 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM as HPC Expert: Extending RAG Architecture for HPC Data Miyashita, Yusuke Tung, Patrick Kin Man Barthélemy, Johan Distributed, Parallel, and Cluster Computing Artificial Intelligence High-Performance Computing (HPC) is crucial for performing advanced computational tasks, yet their complexity often challenges users, particularly those unfamiliar with HPC-specific commands and workflows. This paper introduces Hypothetical Command Embeddings (HyCE), a novel method that extends Retrieval-Augmented Generation (RAG) by integrating real-time, user-specific HPC data, enhancing accessibility to these systems. HyCE enriches large language models (LLM) with real-time, user-specific HPC information, addressing the limitations of fine-tuned models on such data. We evaluate HyCE using an automated RAG evaluation framework, where the LLM itself creates synthetic questions from the HPC data and serves as a judge, assessing the efficacy of the extended RAG with the evaluation metrics relevant for HPC tasks. Additionally, we tackle essential security concerns, including data privacy and command execution risks, associated with deploying LLMs in HPC environments. This solution provides a scalable and adaptable approach for HPC clusters to leverage LLMs as HPC expert, bridging the gap between users and the complex systems of HPC. |
| title | LLM as HPC Expert: Extending RAG Architecture for HPC Data |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2501.14733 |