pipette
ENEnglish

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

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

Revista con revisión por paresAfirmaciones fuertes, leer con cuidadoUso en el mundo real

En palabras de los autores

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.

Resultado principalEl resumen no menciona limitaciones.

Apareció: lunes, 26 de octubre. Nature Communications. Revista con revisión por pares.

DOI: 10.1038/s41467-026-78509-6