Preprint · 2026 · Open access
A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library
Research Square · Published 30 September 2026 · DOI 10.21203/rs.3.rs-11169373/v1
In brief
“A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library” is a 2026 preprint by Dukhik Hovsepyan, published in Research Square. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.
- Citations
- 0
- Authors
- 1
Abstract
Efficient similarity search in high-dimensional vector spaces is increasingly important for applications such as semantic retrieval, recommendation systems, and retrieval-augmented generation. As vector collections grow, the performance of vector-search systems depends on the interaction between indexing methods, system architecture, and execution environment. This study experimentally compares a specialized vector-search library and a vector database using FAISS and Qdrant under a common benchmarking procedure. FAISS was evaluated using the IndexFlatL2 configuration, while Qdrant was evaluated using an HNSW-based configuration in Local Mode. Both configurations were tested with the same synthetic workload consisting of 20,000 vectors with 128 dimensions and 500 search queries, with the 10 nearest vectors requested for each query. Under the tested single-core execution environment, FAISS achieved a mean query latency of 0.3961 ms and a throughput of 2,524.32 queries per second, whereas Qdrant Local Mode achieved 9.8535 ms and 101.49 queries per second, respectively. Thus, the evaluated FAISS configuration exhibited approximately 24.9 times lower mean latency and 24.9 times higher throughput. These results characterize the performance of the specific configurations and deployment conditions used in the experiment rather than providing a universal comparison of the two technologies. The study provides an empirical baseline for examining the performance characteristics and practical trade-offs between specialized vector-search libraries and database-oriented vector retrieval systems.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hovsepyan, D. (2026). A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library. Research Square. https://doi.org/10.21203/rs.3.rs-11169373/v1
MLA 9
Hovsepyan, Dukhik. “A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-11169373/v1.
Chicago
Hovsepyan, Dukhik. 2026. “A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library.” Research Square. https://doi.org/10.21203/rs.3.rs-11169373/v1.
Harvard
Hovsepyan, D. (2026) ‘A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library’, Research Square. doi:10.21203/rs.3.rs-11169373/v1.
IEEE
D. Hovsepyan, “A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library,” Research Square, 2026, doi: 10.21203/rs.3.rs-11169373/v1.
BibTeX
@misc{hovsepyan2026comparative,
title = {{A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library}},
author = {Hovsepyan, Dukhik},
howpublished = {Research Square},
year = {2026},
doi = {10.21203/rs.3.rs-11169373/v1},
url = {https://doi.org/10.21203/rs.3.rs-11169373/v1}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- similarity search
- vector databases
- Qdrant
- FAISS
- HNSW index
- query response time
- throughput
- benchmarking
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Hovsepyan, D. (2026). A Comparative Analysis of Efficient Similarity Search in Qdrant as a Vector Database and FAISS as a Vector Search Library. Research Square. https://doi.org/10.21203/rs.3.rs-11169373/v1
How many times has this paper been cited?
0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Research Square: sign in and open the PDF from this page.
Who wrote this paper?
Dukhik Hovsepyan.
What is the DOI of this paper?
10.21203/rs.3.rs-11169373/v1, permanently at https://doi.org/10.21203/rs.3.rs-11169373/v1. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.