Vector Databases for Retrieval-Augmented Generation

This review examines vector databases for retrieval-augmented generation. The organizing question is which indexing, update, filtering, provenance, and consistency choices preserve retrieval quality at operational scale. Ten related scholarly sources are synthesized through a decision-centered framework spanning problem definition, mechanism, measurement, evaluation, implementation, and governance. The review does not invent experiments, pooled estimates, or unreported quantitative results. It instead evaluates the strength and transferability of the available evidence, with particular attention to evaluating answer quality without isolating retrieval, freshness, and citation failures. The resulting framework links technical or empirical performance to explicit use conditions and identifies tests that should precede wider adoption in knowledge-intensive generative systems.

1. Gysel, C. V., Rijke, M. D., & Kanoulas, E. (2018). Neural Vector Spaces for Unsupervised Information Retrieval. ACM Transactions on Information Systems, 36(4), 1-25. https://doi.org/10.1145/3196826 DOI
2. Kiran, S. (2025). Hybrid Retrieval-Augmented Generation (RAG) Systems with Embedding Vector Databases. International Journal of Scientific Research in Computer Science Engineering and Information Technology, 11(2), 2694-2702. https://doi.org/10.32628/cseit25112702 DOI
3. Kittichai, V., Sompong, W., Kaewthamasorn, M., Sasisaowapak, T., Naing, K. M., Tongloy, T., Chuwongin, S., Thanee, S., & Boonsang, S. (2024). A novel approach for identification of zoonotic trypanosome utilizing deep metric learning and vector database-based image retrieval system. Heliyon, 10(9), e30643. https://doi.org/10.1016/j.heliyon.2024.e30643 DOI
4. Nowaková, J., Prílepok, M., & Snášel, V. (2016). Medical Image Retrieval Using Vector Quantization and Fuzzy S-tree. Journal of Medical Systems, 41(2), 18. https://doi.org/10.1007/s10916-016-0659-2 DOI
5. Pan, J. J., Wang, J., & Li, G. (2024). Survey of vector database management systems. The VLDB Journal, 33(5), 1591-1615. https://doi.org/10.1007/s00778-024-00864-x DOI
6. Pujiono, I., Agtyaputra, I. M., & Ruldeviyani, Y. (2024). IMPLEMENTING RETRIEVAL-AUGMENTED GENERATION AND VECTOR DATABASES FOR CHATBOTS IN PUBLIC SERVICES AGENCIES CONTEXT. JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), 10(1), 216-223. https://doi.org/10.33480/jitk.v10i1.5572 DOI
7. Sarwar, A., Mehmood, Z., Saba, T., Qazi, K. A., Adnan, A., & Jamal, H. (2018). A novel method for content-based image retrieval to improve the effectiveness of the bag-of-words model using a support vector machine. Journal of Information Science, 45(1), 117-135. https://doi.org/10.1177/0165551518782825 DOI
8. Shuo, L., Affendey, L. S., & Sidi, F. (2024). Content-Based Image Retrieval Using Transfer Learning and Vector Database. International Journal of Advanced Computer Science and Applications, 15(9). https://doi.org/10.14569/ijacsa.2024.0150985 DOI
9. Taipalus, T. (2024). Vector database management systems: Fundamental concepts, use-cases, and current challenges. Cognitive Systems Research, 85, 101216. https://doi.org/10.1016/j.cogsys.2024.101216 DOI
10. Zhao, D. (2024). FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.13272 DOI