Work

ENVRI Knowledge Base - An Intelligent System for Discoverability and Collaboration

Year: 2025

Type: article

Abstract: ENVRI-Hub NEXT Use Case - ENVRI Knowledge Base The ENVRI-Hub Knowledge Base provides searching capabilities to locate environmental content, including data, metadata, or notebooks, in three different ways. It offers a free text search system powered by a Large Language Model (LLM), which provides users with a summarised response followed by a list of contents categorised into four classes: i) Web Content, ii) Metadata, iii) APIs, and iv) Jupyter Notebooks. Furthermore, it also offers a dialogue-based search agent, which complements the free text search with a natural language chatbot, allowing users to discuss and analyse content with follow-ups. Finally, it provides an interface to external virtual research environments to test the notebooks, which are found by the search system, to explore the datasets, metadata, and APIs. To consolidate all the services, a federated authentication system is provided to enable Research Infrastructures (RIs) to customize indexing policies and control the content in the Knowledge base. Test the Search Test the AI Environmental Expert

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17725483

Authors: Islam, Nafis Tanveer, Zhao, Zhiming, Dobler, Delphine, Drago, Federico, Ozolina, Karlina

Institutions: University of Amsterdam, LifeWatch ERIC, Euro-Argo ERIC, EGI, Integrated Carbon Observation System

Language: English

Topic: Research Data Management Practices

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Award: ENVironmental Research Infrastructures delivering an open access Hub and NEXT-level interdisciplinary research framework providing services for advancing science and society