Digital Products Based on Large Language Models for the Exploration of Graph-Databases in Materials Science and Manufacturing

Semantic technologies are gaining traction in materials science and manufacturing. Specifically, the integration of graph databases with ontologies facilitates the harmonization of typically heterogeneous materials and process data, as well as the representation of complex workflows in the field (e.g., processing experimental and simulation data or transferring and tracking data along process chains). This approach enables previously inaccessible data for scientists and engineers to be made available in a FAIR (findable, accessible, interoperable, reusable) manner. On this basis, both science and industry, anticipate a significant boost in materials and process innovation, leading to a more resilient and sustainable production. Nevertheless, one of the main challenges in making semantic technologies usable for engineers is enabling navigation and exploration of the typically complex and flexible graph-based data structures. This work presents two approaches for data exploration in graph-databases using large language models (LLMs), namely LLM-CypherGen and SPARQL-Agent, and their application in two digital products developed within the EU research project DiMAT demonstrated across different use cases in materials science and manufacturing.