MotherDuck Research
Advancing the future of data + AI.
MotherDuck: DuckDB in the Cloud and in the Client
We describe and demo MotherDuck: a new service that connects DuckDB to the cloud. MotherDuck provides the concept of hybrid query processing: the ability to execute queries partly on the client and partly in the cloud.
Results on Results: Building New Results from Cached Partial Results
An intelligent recovery framework for real-time SQL previews. When composing partial cached results produces too few rows, a Data Lineage heuristic selects the cheapest upstream dependency to re-fetch — enabling fluid exploratory analysis in MotherDuck's hybrid architecture.
Cost-Based Hybrid Query Optimization in MotherDuck
This thesis tackles a core challenge in MotherDuck's hybrid execution model: deciding which parts of a query should run locally vs. in the cloud. The result is a cost-based optimizer that delivers up to 17x speedups on long-running analytical queries.
Query-Log-Informed Schema Descriptions and their Impact on Text-to-SQL
Automatically generating schema documentation from historical query logs to improve LLM-powered Text-to-SQL. Tested on both the BIRD benchmark and MotherDuck’s production data warehouse, query pattern descriptions boost SQL generation accuracy by up to 16% on real-world data.
Declarative Caching in MotherDuck
This thesis introduces Accelerated Approximate Views — a new SQL-level caching mechanism for MotherDuck’s hybrid execution model. By partially materializing query results on the client, AAVs reduce latency for interactive data exploration in both native and WebAssembly environments.
Towards Efficient Data Wrangling with LLMs using Code Generation
Instead of applying LLMs to every row, generate code once and run it on millions of rows. Up to 37-point F1 improvement on data transformations at a fraction of the cost.