Hybrid Retrieval-Augmented Generation (RAG) Systems with Embedding Vector Databases
DOI:
https://doi.org/10.32628/CSEIT25112702Keywords:
Vector Databases, Retrieval-augmented Generation, Embedding Representations, Hybrid Retrieval Strategies, Domain-Specific OptimizationAbstract
This article explores the integration of embedding vector databases into Retrieval-Augmented Generation (RAG) systems to enhance the capabilities of large language models. The article explores how hybrid retrieval strategies combining dense vector search with traditional keyword-based methods can address the limitations of standalone LLMs, particularly regarding knowledge cutoff, hallucinations, and access to domain-specific information. The article presents a comprehensive framework covering theoretical foundations, methodological approaches, implementation considerations, and experimental results across multiple domains. By leveraging vector embeddings for semantic search alongside traditional retrieval techniques, the proposed system demonstrates significant improvements in accuracy, relevance, and factual correctness while maintaining reasonable query response times. The article provides valuable insights for enterprise-scale deployments of RAG systems across various application domains including healthcare, legal, technical support, and financial services.
Downloads
References
Alexandra Francis, "Retrieval augmented generation: Keeping LLMs relevant and current," Stack Overflow Blog, Oct. 18, 2023. https://stackoverflow.blog/2023/10/18/retrieval-augmented-generation-keeping-llms-relevant-and-current/
Long Ouyang et al., "Training language models to follow instructions with human feedback,", 2022. https://arxiv.org/abs/2203.02155
Vlad Rișcuția, "Embeddings and Vector Databases," Medium, May 15, 2024. https://medium.com/@vladris/embeddings-and-vector-databases-732f9927b377
Haoyu Zhang et al., "Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search," ResearchGate, 2023. https://www.researchgate.net/publication/385317111_Efficient_and_Effective_Retrieval_of_Dense-Sparse_Hybrid_Vectors_using_Graph-based_Approximate_Nearest_Neighbor_Search
Zhongquan Jian, "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," arXiv:2005.11401 [cs.CL], 2021. https://arxiv.org/abs/2005.11401
kirouane Ayoub et al., "Hybrid retrieval for RAG: Combining lexical and semantic search in LLM-based question answering systems," 2024. https://blog.gopenai.com/hybrid-search-in-retrieval-augmented-generation-e50b7eaa1a7a
Adrien Payong and Shaoni Mukherjee, "How To Choose the Right Vector Database," 2024. https://www.digitalocean.com/community/conceptual-articles/how-to-choose-the-right-vector-database
Nexla, "Retrieval-Augmented Generation (RAG) Tutorial & Best Practices," https://nexla.com/ai-infrastructure/retrieval-augmented-generation/
ORKG, "Retrieval Augmented Generation-LLM Comparison ," 2024. https://orkg.org/comparison/R716040
Ryan Calvin Barron et al., "Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization," ResearchGate, 2024. https://www.researchgate.net/publication/384630678_Domain-Specific_Retrieval-Augmented_Generation_Using_Vector_Stores_Knowledge_Graphs_and_Tensor_Factorization
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology

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