BDI-Kit Demo: A Toolkit for Programmable and Conversational Data Harmonization

TL;DR

BDI-Kit is an extensible toolkit that facilitates data harmonization through programmable APIs and AI-assisted natural language interfaces, addressing heterogeneity challenges in data schemas and representations.

Contribution

It introduces a dual-interface toolkit combining programmatic and conversational methods for flexible, iterative data harmonization.

Findings

Demonstrates effective use of BDI-Kit in real-world scenarios.

Shows how AI-assisted dialogue improves data harmonization process.

Highlights the toolkit's extensibility and user interaction capabilities.

Abstract

Data harmonization remains a major bottleneck for integrative analysis due to heterogeneity in schemas, value representations, and domain-specific conventions. BDI-Kit provides an extensible toolkit for schema and value matching. It exposes two complementary interfaces tailored to different user needs: a Python API enabling developers to construct harmonization pipelines programmatically, and an AI-assisted chat interface allowing domain experts to harmonize data through natural language dialogue. This demonstration showcases how users interact with BDI-Kit to iteratively explore, validate, and refine schema and value matches through a combination of automated matching, AI-assisted reasoning, and user-driven refinement. We present two scenarios: (i) using the Python API to programmatically compose primitives, examine intermediate outputs, and reuse transformations; and (ii) conversing with the AI assistant in natural language to access BDI-Kit's capabilities and iteratively refine outputs based on the assistant's suggestions.