RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909906333859840 |
|---|---|
| author | Wang, Zhengchao Hu, Yitao Ye, Jianing Chang, Zhuxuan Yu, Jiazheng Deng, Youpeng Li, Keqiu |
| author_facet | Wang, Zhengchao Hu, Yitao Ye, Jianing Chang, Zhuxuan Yu, Jiazheng Deng, Youpeng Li, Keqiu |
| contents | Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12979 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems Wang, Zhengchao Hu, Yitao Ye, Jianing Chang, Zhuxuan Yu, Jiazheng Deng, Youpeng Li, Keqiu Machine Learning Databases Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse. |
| title | RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems |
| topic | Machine Learning Databases |
| url | https://arxiv.org/abs/2511.12979 |