QuackIR: Retrieval in DuckDB and Other Relational Database Management Systems
Authors’ abstract
Enterprises today are increasingly compelled to adopt dedicated vector databases for retrieval- augmented generation (RAG) in applications based on large language models (LLMs). As a potential alternative for these vector databases, we propose that organizations leverage exist- ing relational databases for retrieval, which many have already deployed in their enterprise data lakes, thus minimizing additional complex- ity in their software stacks. To demonstrate the simplicity and feasibility of this approach, we present QuackIR, an information retrieval (IR) toolkit built on relational database man- agement systems (RDBMSes), with integra- tions in DuckDB, SQLite, and PostgreSQL. Using QuackIR, we benchmark the sparse and dense retrieval capabilities of these popular RDBMSes and demonstrate that their effec- tiveness is comparable to baselines from es- tablished IR toolkits. Our results highlight the potential of relational databases as a simple op- tion for RAG scenarios due to their established widespread usage and the easy integration of retrieval abilities. Our implementation is avail- able at quackir.io. 1
Paper
- Authors
- Y. Ge, Z. Chen, J. Lin
- Publication date
- 2025
Transcript
A transcript has not been published for this episode yet.
Licensing
- Recording license
- CC-BY-4.0
The authors and publisher do not sponsor or endorse this recording.