Perplexity-inspired metasearch-based alternatives to FAIR GPT: Open-source AI consultants for research data management

Schmidt, Thomas ; Shigapov, Renat ; Kamlah, Jan ; Schumm, Irene

Preview

PDF
heiBOOKS-1652-978-3-911056-51-9-CH30-2.pdf - Published
Download (268kB)

DOI:	https://doi.org/10.11588/heibooks.1652.c23938
URL:	https://books.ub.uni-heidelberg.de//heibooks/catal...
URN:	urn:nbn:de:bsz:180-madoc-711460
Document Type:	Conference or workshop publication
Year of publication:	2025
Book title:	E-Science-Tage 2025 : Research Data Management : Challenges in a Changing World
Page range:	402-408
Conference title:	E-Science-Tage: Research Data Management: Challenges in a Changing World
Location of the conference venue:	Heidelberg, Germany
Date of the conference:	12.-14.03.2025
Publisher:	Heuveline, Vincent ; Kling, Philipp ; Heuschkel, Florian ; Habinger, Sophie G. ; Krömer, Cora F.
Place of publication:	Heidelberg
Publishing house:	heiBOOKS
ISBN:	978-3-911056-52-6 , 978-3-911056-51-9
Related URLs:	https://books.ub.uni-heidelberg.de//heib...
Publication language:	English
Institution:	Zentrale Einrichtungen > University Library
Pre-existing license:	Creative Commons Attribution, Share Alike 4.0 International (CC BY-SA 4.0)
Subject:	004 Computer science, internet
Individual keywords (German):	Forschungsdatenmanagement , LLM , Chatbot , FDM Assistent , FAIR
Keywords (English):	research data management , LLMs , chatbot , RDM assistants , FAIR data
Abstract:	Chatbots and virtual assistants are becoming increasingly popular for user questions and support. With FAIR GPT, the Mannheim University Library released a virtual assistant for research data management (RDM) in 2024, designed to help researchers and institutions in making their data FAIR (Findable, Accessible, Interoperable, Reusable). FAIR GPT provides various RDM services, e.g. metadata enhancement, repository selection and FAIR assessment. However, FAIR GPT has numerous disadvantages: As a ‘Custom GPT’ of OpenAI, it is proprietary software that only outputs sources for the generated answers if it uses its internal web search tool (which cannot be controlled by the user) and therefore lacks transparency. Reliance on external cloud-based services leads to privacy concerns when dealing with sensitive (meta)data and the chatbot is still prone to hallucinations, thus reducing its trustworthiness. These issues led us to explore alternative open-source solutions. We searched for opensource alternatives to Perplexity.ai, a system known for its ability to provide citations for the information it retrieves through web searches. We identified three candidates available on GitHub: Perplexica, sensei, and farfalle. These tools use local instances of the metasearch engine SearXNG to perform internet searches, using the results as input for Large Language Models (LLMs). We modified these tools to focus specifically on RDM tasks, releasing the new versions on GitHub openly under the names FAIRplexica, FAIR-sensei and FAIR-farfalle.

	Dieser Eintrag ist Teil der Universitätsbibliographie.
	Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Search Authors in

BASE: Schmidt, Thomas ; Shigapov, Renat ; Kamlah, Jan ; Schumm, Irene

Google Scholar: Schmidt, Thomas ; Shigapov, Renat ; Kamlah, Jan ; Schumm, Irene

ORCID: Schmidt, Thomas