Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB

arXiv:2504.01157 · cs.DB, cs.AI, cs.IR · Submitted 2025-04-01 · Read on arXiv

cs.DB, cs.AI, cs.IR

Submitted: 2025-04-01

Updated: 2025-04-01

Journal ref: Proceedings of the VLDB Endowment, 18(12): 5415-5418, 2025

DOI: 10.14778/3750601.3750685

Code: https://github.com/dsg-polymtl/flockmtl

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 6× in this paper · explained in 3 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes

Sources

• Gorilla: Large Language Model Connected with Massive APIs
• Zero-Shot Listwise Document Reranking with a Large Language Model

Related papers

• Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
• Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
• Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation
• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
• MaDI-Bench: An End-to-End Data Integration Benchmark
• Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning