Entity · product
DuckDB
productactive
duckdb-a7b639f8·5 events·first seen Aliases: DuckDB
Co-occurring entities
More like this (12)
Recent events (5)
WorkSurface-Bench: New benchmark for enterprise agent knowledge surface routing across documents, tables, and graphs
WorkSurface-Bench is a new benchmark of 1,151 tasks evaluating whether enterprise agents correctly select among heterogeneous knowledge sources (documents, tables, dependency graphs) before answering—a capability the authors term 'surface routing.' Evaluating four model backbones across six agent settings, the benchmark reveals a critical gap: agents achieve near-perfect route selection (98.7–99.8% Route F1) under gold-constrained tool access but only 56.1–75.3% answer accuracy, demonstrating that correct surface selection is necessary but insufficient for task completion. The dataset, pipeline, scoring code, and agent harness are released publicly.
Jailbreak: LLM-assisted code synthesis bypasses database drivers for 27x analytical speedup
Researchers present Jailbreak, a system that uses LLMs to synthesize storage readers that bypass database drivers (JDBC/ODBC) entirely by reading PostgreSQL and MySQL storage files directly and materializing data as Apache Arrow columnar buffers. The approach leverages LLMs to ingest database source code and documentation and regenerate format-specific parsing logic without human engineering. Evaluated against TPC-H benchmarks, the generated readers achieve up to 27x speedup over driver-based baselines and produce output consumable by DuckDB, Apache Spark, cuDF, and Spark RAPIDS. The paper argues this methodology generalizes to any database system whose file format is documented or open-source.
MLSkip: Data skipping for ML filter predicates using Parquet metadata and neural network verification
MLSkip introduces data skipping techniques for ML-based filter predicates in databases, a problem not addressed by traditional min-max pruning methods. The approach leverages Parquet's existing min-max metadata combined with neural network verification techniques to prune non-qualifying row groups. On TPC-H and TPC-DS benchmarks with ReLU architectures, the method achieves 27.4% average pruning effectiveness for low-selectivity filters, improving to 38.31% with a proposed 2D convex hull metadata structure, yielding a 1.07× end-to-end speedup in DuckDB over PyTorch.
DuckDB Integration for Analyzing 50,000+ Datasets on Hugging Face Hub
Hugging Face announced a DuckDB integration enabling direct SQL-based analysis of over 50,000 datasets hosted on the Hub without downloading them. The integration allows users to query dataset metadata, statistics, and contents using DuckDB's in-process analytical engine. This lowers the barrier to dataset discovery and exploration at scale across the Hugging Face ecosystem.
Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B
This Hugging Face blog post demonstrates a Text-to-SQL pipeline combining the Hugging Face Dataset Viewer API with MotherDuck's DuckDB-NSQL-7B model, a 7-billion parameter model fine-tuned for natural language to SQL translation. The post walks through using the model to query datasets stored on Hugging Face via DuckDB. It represents a practical integration of a domain-specialized open-weights model with a data infrastructure tool.