Education, Science, Technology, Innovation and Life
Open Access
Sign In

Application of RAG Model Based on Retrieval Enhanced Generation Technique in Complex Query Processing

Download as PDF

DOI: 10.23977/acss.2024.080608 | Downloads: 70 | Views: 1259

Author(s)

Xiangcan Li 1

Affiliation(s)

1 Bytedance Inc, San Jose, 95131, USA

Corresponding Author

Xiangcan Li

ABSTRACT

In the field of complex query processing, traditional natural language processing models are often difficult to effectively deal with the diversity and complexity of query contents. The Retrieval Augmented Generation (RAG) model demonstrates unique advantages in processing complex queries by combining the two processes of retrieval and generation. This paper provides an in-depth discussion on the working principle of the RAG model and applies it to complex query processing scenarios. By analyzing real cases and validating experimental results, we demonstrate the significant advantages of the RAG model in enhancing query processing results. Although the RAG model shows good performance in processing complex queries, its application still faces some challenges and limitations. This paper concludes with an outlook on the future development of the RAG model, exploring possible optimization directions and application prospects.

KEYWORDS

RAG model, retrieval enhancement generation, complex query processing, natural language processing, deep learning

CITE THIS PAPER

Xiangcan Li, Application of RAG Model Based on Retrieval Enhanced Generation Technique in Complex Query Processing. Advances in Computer, Signals and Systems (2024) Vol. 8: 47-53. DOI: http://dx.doi.org/10.23977/acss.2024.080608.

REFERENCES

[1] Cambazoglu B B, Aykanat C. Performance of query processing implementations in ranking-based text retrieval systems using inverted indices [J]. Information Processing & Management, 2006, 42(4):875-898. DOI: 10. 1016/j. ipm. 2005. 06. 004. 
[2] Tamine L, Chrisment C, Boughanem M. Multiple query evaluation based on an enhanced genetic algorithm [J]. Information Processing & Management, 2003, 39(2):215-231. DOI:10. 1016/S0306-4573 (02)00048-1. 
[3] Doller M, Tous R, Gruhne M, et al. The MPEG Query Format: Unifying Access to Multimedia Retrieval Systems [J]. IEEE Multimedia, 2008, 15(4):82-95. DOI:10. 1109/MMUL. 2008. 96. 
[4] Gao Y, Zheng B, Chen G, et al. Continuous visible nearest neighbor query processing in spatial databases[J]. The VLDB Journal, 2011, 20(3):p. 371-396. DOI:10. 1007/s00778-010-0200-z. 
[5] Candan K S, Li W S, Priya M L. Similarity-based ranking and query processing in multimedia databases[J]. Data & Knowledge Engineering, 2000, 35(3):259-298. DOI:10. 1016/S0169-023X (00)00025-2. 
[6] Aldous K J. A system for the automatic retrieval of information from a specialist database [J]. Information Processing & Management, 1996, 32(2):139-154. DOI:10. 1016/s0306-4573 (96)85002-3. 
[7] Wu J K, Narasimhalu A D. Fuzzy content-based retrieval in image databases [J]. Information Processing & Management, 1998, 34(5):513-534. DOI:10. 1016/S0306-4573(98)00017-X. 
[8] Komai Y, Sasaki Y, Hara T, et al. A kNN Query Processing Method in Mobile Ad Hoc Networks[J]. IEEE Transactions on Mobile Computing, 2011, 1(13):287-288. DOI: 10. 1109/MDM. 2011. 39. 
[9] Fuhr, Norbert. A decision-theoretic approach to database selection in networked IR[J]. Acm Transactions on Information Systems, 1999, 17(3):229-249. DOI:10. 1145/314516. 314517. 
[10] Mamouras K, Raghothaman M, Alur R, et al. Stream QRE: modular specification and efficient evaluation of quantitative queries over streaming data[J]. Acm Sigplan Notices, 2017, 52(6):693-708. DOI: 10. 1145/3140587. 3062369.

Downloads: 38553
Visits: 697942

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.