Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB
Summary: FlockMTL embeds LLMs/RAG in DuckDB via PROMPT/MODEL DDLs, exposing LLM-backed scalar/aggregate functions for chained tuple predictions and hybrid search. Relational optimizations (batching, meta-prompting) and resource-independent abstractions reduce data movement and orchestration. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Anas Dorbani (Polytechnique Montréal)
- 2. Sunny Yasser (Polytechnique Montréal)
- 3. Jimmy Lin (University of Waterloo)
- 4. Amine Mhedhbi (Polytechnique Montréal)
BibTeX Citation
@article{dorbani_vldb25,
title = {{Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB}},
author = {Dorbani, Anas and Yasser, Sunny and Lin, Jimmy and Mhedhbi, Amine},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {5415--5418},
doi = {10.14778/3750601.3750685},
url = {https://doi.org/10.14778/3750601.3750685},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,868 | SemBench: A Benchmark for Semantic Query Processing Engines | 2026 | VLDB | 5.3546848e-05 |
| 10,184 | 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis] | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 103 | DuckDB: an Embeddable Analytical Database | 2019 | SIGMOD | 0.00034161428 |
| 1,245 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 0.00011507415 |
| 2,809 | Text2SQL is Not Enough: Unifying AI and Databases with TAG | 2025 | CIDR | 8.0994951e-05 |
| 4,045 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD | 6.9394654e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,401 | SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer | 2026 | SIGMOD |
| 2 | 10,200 | Automating Database-Native Function Code Synthesis with LLMs | 2026 | SIGMOD |
| 3 | 4,045 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 4 | 10,499 | SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL | 2026 | SIGMOD |
| 5 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 6 | 4,944 | Hybrid Querying Over Relational Databases and Large Language Models | 2025 | CIDR |
| 7 | 4,886 | Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs | 2024 | VLDB |
| 8 | 6,439 | DuckPGQ: Bringing SQL/PGQ to DuckDB | 2023 | VLDB |
| 9 | 6,999 | DuckPGQ: Efficient Property Graph Queries in an analytical RDBMS | 2023 | CIDR |
| 10 | 9,542 | Database as Runtime: Compiling LLMs to SQL for In-database Model Serving | 2025 | SIGMOD |