From Commands to Prompts: LLM-based Semantic File System for AIOS
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909541638078464 |
|---|---|
| author | Shi, Zeru Mei, Kai Jin, Mingyu Su, Yongye Zuo, Chaoji Hua, Wenyue Xu, Wujiang Ren, Yujie Liu, Zirui Du, Mengnan Deng, Dong Zhang, Yongfeng |
| author_facet | Shi, Zeru Mei, Kai Jin, Mingyu Su, Yongye Zuo, Chaoji Hua, Wenyue Xu, Wujiang Ren, Yujie Liu, Zirui Du, Mengnan Deng, Dong Zhang, Yongfeng |
| contents | Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems (AIOS). However, when these applications and systems interact with the underlying file system, the file system still remains the traditional paradigm: reliant on manual navigation through precise commands. This paradigm poses a bottleneck to the usability of these systems as users are required to navigate complex folder hierarchies and remember cryptic file names. To address this limitation, we propose an LLM-based semantic file system ( LSFS ) for prompt-driven file management. Unlike conventional approaches, LSFS incorporates LLMs to enable users or agents to interact with files through natural language prompts, facilitating semantic file management. At the macro-level, we develop a comprehensive API set to achieve semantic file management functionalities, such as semantic file retrieval, file update monitoring and summarization, and semantic file rollback). At the micro-level, we store files by constructing semantic indexes for them, design and implement syscalls of different semantic operations (e.g., CRUD, group by, join) powered by vector database. Our experiments show that LSFS offers significant improvements over traditional file systems in terms of user convenience, the diversity of supported functions, and the accuracy and efficiency of file operations. Additionally, with the integration of LLM, our system enables more intelligent file management tasks, such as content summarization and version comparison, further enhancing its capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11843 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Commands to Prompts: LLM-based Semantic File System for AIOS Shi, Zeru Mei, Kai Jin, Mingyu Su, Yongye Zuo, Chaoji Hua, Wenyue Xu, Wujiang Ren, Yujie Liu, Zirui Du, Mengnan Deng, Dong Zhang, Yongfeng Human-Computer Interaction Artificial Intelligence Databases Machine Learning Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems (AIOS). However, when these applications and systems interact with the underlying file system, the file system still remains the traditional paradigm: reliant on manual navigation through precise commands. This paradigm poses a bottleneck to the usability of these systems as users are required to navigate complex folder hierarchies and remember cryptic file names. To address this limitation, we propose an LLM-based semantic file system ( LSFS ) for prompt-driven file management. Unlike conventional approaches, LSFS incorporates LLMs to enable users or agents to interact with files through natural language prompts, facilitating semantic file management. At the macro-level, we develop a comprehensive API set to achieve semantic file management functionalities, such as semantic file retrieval, file update monitoring and summarization, and semantic file rollback). At the micro-level, we store files by constructing semantic indexes for them, design and implement syscalls of different semantic operations (e.g., CRUD, group by, join) powered by vector database. Our experiments show that LSFS offers significant improvements over traditional file systems in terms of user convenience, the diversity of supported functions, and the accuracy and efficiency of file operations. Additionally, with the integration of LLM, our system enables more intelligent file management tasks, such as content summarization and version comparison, further enhancing its capabilities. |
| title | From Commands to Prompts: LLM-based Semantic File System for AIOS |
| topic | Human-Computer Interaction Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2410.11843 |