LEDD: Large Language Model-Empowered Data Discovery in Data Lakes

TL;DR

LEDD is an end-to-end system that uses large language models to improve data discovery in data lakes by generating hierarchical catalogs and enabling semantic table search through natural language queries.

Contribution

LEDD introduces an extensible architecture leveraging LLMs for comprehensive semantic data discovery and cataloging in data lakes, addressing key challenges in data management.

Findings

Provides hierarchical global catalogs with semantic meanings

Enables semantic table search based on natural language

Facilitates downstream tasks like schema linking and model training

Abstract

Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large language models (LLMs) facilitate the processing of data semantics, challenges remain in architecting an end-to-end system that comprehensively exploits LLMs for the two semantics-related tasks. In this demo, we propose LEDD, an end-to-end system with an extensible architecture that leverages LLMs to provide hierarchical global catalogs with semantic meanings and semantic table search for data lakes. Specifically, LEDD can return semantically related tables based on natural-language specification. These features make LEDD an ideal foundation for downstream tasks such as model training and schema linking for text-to-SQL tasks. LEDD also provides a simple Python interface to facilitate the extension and the replacement of data discovery algorithms.