Democratizing reliable knowledge-seeking with MyGPT: a privacy-first, open-source retrieval-augmented generation platform

Abstract Large language models (LLMs) have transformed knowledge discovery, but their use in sensitive domains is limited by privacy concerns and risks of data leakage. Moreover, LLMs may hallucinate when queried about information outside their training data, undermining their reliability for scientific, clinical, or policy-related tasks. We present MyGPT, a fully open-source, privacy-preserving retrieval-augmented-generation (RAG) platform that uses open-source LLMs and operates locally or within secure institutional environments. MyGPT empowers users to query user-defined libraries such as biomedical literature, confidential clinical documents, and multilingual global health policies, while ensuring that sensitive data never leaves the secure environment. We introduce confidence metrics, including “relevance scores” and “hallucination index,” and provide explicit source citation from the library within a single interface to assess contextual support for generated answers. MyGPT offers a cost-effective, modular, open-source alternative to commercial LLM services and democratizes knowledge-seeking across multiple domains, including use at remote facilities without internet access.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-10-24
DOI
https://doi.org/10.1038/s41467-026-78509-6
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Democratizing reliable knowledge-seeking with MyGPT: a privacy-first, open-source retrieval-augmented generation platform

Catherine G. Lam, Jaimin N Patel, Beth Moorefield, Dinesh Keerthi et al.
Nature Communications
Topic Modeling
article

Democratizing reliable knowledge-seeking with MyGPT: a privacy-first, open-source retrieval-augmented generation platform

Catherine G. Lam, Jaimin N Patel, Beth Moorefield, Dinesh Keerthi, Inês Chen, Dan Alford, Charalampos G. Kalodimos, Duccio Malinverni, Vikas D. Trivedi, Carlos Rodríguez‐Galindo, Bálint Mészáros, Stephen M Gottschalk, Katalin Paréj, Anthony Woodard, Steve Mathew, Renato Umeton, Cai Li, M. Madan Babu, Shahinur Alam, Thika You, Jude Downing, Hugh Ferguson, Sagar Pathak, Desiree Becerra Armada, Cindy Morris, Mukundan Ragavan, Madison Sluter
article en

Abstract

Abstract Large language models (LLMs) have transformed knowledge discovery, but their use in sensitive domains is limited by privacy concerns and risks of data leakage. Moreover, LLMs may hallucinate when queried about information outside their training data, undermining their reliability for scientific, clinical, or policy-related tasks. We present MyGPT, a fully open-source, privacy-preserving retrieval-augmented-generation (RAG) platform that uses open-source LLMs and operates locally or within secure institutional environments. MyGPT empowers users to query user-defined libraries such as biomedical literature, confidential clinical documents, and multilingual global health policies, while ensuring that sensitive data never leaves the secure environment. We introduce confidence metrics, including “relevance scores” and “hallucination index,” and provide explicit source citation from the library within a single interface to assess contextual support for generated answers. MyGPT offers a cost-effective, modular, open-source alternative to commercial LLM services and democratizes knowledge-seeking across multiple domains, including use at remote facilities without internet access.

Nature Communications
St. Jude Children's Research Hospital (US), University of Tennessee Health Science Center (US)
Openalex Percentile: Top 13%
Topic Modeling
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon