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

arXiv: https://arxiv.org/abs/2504.01157 · HTML: https://mlsanity.com/paper/2504.01157/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [Text2SQL is Not Enough: Unifying AI and Databases with TAG](https://mlsanity.com/paper/2408.14717/) (2024)

## Built on by (most cited first, 15 of 15)

- [SemBench: A Benchmark for Semantic Query Processing Engines](https://mlsanity.com/paper/2511.01716/) (2025)
- [100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models](https://mlsanity.com/paper/2603.15970/) (2026)
- [Research Challenges in Relational Database Management Systems for LLM Queries](https://mlsanity.com/paper/2508.20912/) (2025)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026)
- [Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm](https://mlsanity.com/paper/2603.04799/) (2026)
- [Large Databases Need Small, Open-Weight Language Models](https://mlsanity.com/paper/2606.31808/) (2026)
- [Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs](https://mlsanity.com/paper/2509.20208/) (2025)
- [Towards Effective Orchestration of AI x DB Workloads](https://mlsanity.com/paper/2603.03772/) (2026)
- [LLM+Graph@VLDB'2025 Workshop Summary](https://mlsanity.com/paper/2604.02861/) (2026)
- [MLSkip: Data Skipping for ML Filters via Lightweight Metadata](https://mlsanity.com/paper/2606.03946/) (2026)
- [SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL](https://mlsanity.com/paper/2608.20630/) (2026)
- [Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries](https://mlsanity.com/paper/2610.12768/) (2026)
- [Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing](https://mlsanity.com/paper/2610.13823/) (2026)
- [Accelerating Cross-Model LLM Inference via Attention Map Reuse](https://mlsanity.com/paper/2610.14688/) (2026)

## Abstract (arXiv)

Knowledge-intensive analytical applications retrieve context from both structured tabular data and unstructured, text-free documents for effective decision-making. Large language models (LLMs) have made it significantly easier to prototype such retrieval and reasoning data pipelines. However, implementing these pipelines efficiently still demands significant effort and has several challenges. This often involves orchestrating heterogeneous data systems, managing data movement, and handling low-level implementation details, e.g., LLM context management. To address these challenges, we introduce FlockMTL: an extension for DBMSs that deeply integrates LLM capabilities and retrieval-augmented generation (RAG). FlockMTL includes model-driven scalar and aggregate functions, enabling chained predictions through tuple-level mappings and reductions. Drawing inspiration from the relational model, FlockMTL incorporates: (i) cost-based optimizations, which seamlessly apply techniques such as batching and caching; and (ii) resource independence, enabled through novel SQL DDL abstractions: PROMPT and MODEL, introduced as first-class schema objects alongside TABLE. FlockMTL streamlines the development of knowledge-intensive analytical applications, and its optimizations ease the implementation burden.