Salvato in:
Dettagli Bibliografici
Autori principali: Weber, Ingo, Linka, Hendrik, Mertens, Daniel, Muryshkin, Tamara, Opgenoorth, Heinrich, Langer, Stefan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.00039
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917601194541056
author Weber, Ingo
Linka, Hendrik
Mertens, Daniel
Muryshkin, Tamara
Opgenoorth, Heinrich
Langer, Stefan
author_facet Weber, Ingo
Linka, Hendrik
Mertens, Daniel
Muryshkin, Tamara
Opgenoorth, Heinrich
Langer, Stefan
contents Since OpenAI's release of ChatGPT, generative AI has received significant attention across various domains. These AI-based chat systems have the potential to enhance the productivity of knowledge workers in diverse tasks. However, the use of free public services poses a risk of data leakage, as service providers may exploit user input for additional training and optimization without clear boundaries. Even subscription-based alternatives sometimes lack transparency in handling user data. To address these concerns and enable Fraunhofer staff to leverage this technology while ensuring confidentiality, we have designed and developed a customized chat AI called FhGenie (genie being a reference to a helpful spirit). Within few days of its release, thousands of Fraunhofer employees started using this service. As pioneers in implementing such a system, many other organizations have followed suit. Our solution builds upon commercial large language models (LLMs), which we have carefully integrated into our system to meet our specific requirements and compliance constraints, including confidentiality and GDPR. In this paper, we share detailed insights into the architectural considerations, design, implementation, and subsequent updates of FhGenie. Additionally, we discuss challenges, observations, and the core lessons learned from its productive usage.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00039
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FhGenie: A Custom, Confidentiality-preserving Chat AI for Corporate and Scientific Use
Weber, Ingo
Linka, Hendrik
Mertens, Daniel
Muryshkin, Tamara
Opgenoorth, Heinrich
Langer, Stefan
Software Engineering
Artificial Intelligence
Human-Computer Interaction
Since OpenAI's release of ChatGPT, generative AI has received significant attention across various domains. These AI-based chat systems have the potential to enhance the productivity of knowledge workers in diverse tasks. However, the use of free public services poses a risk of data leakage, as service providers may exploit user input for additional training and optimization without clear boundaries. Even subscription-based alternatives sometimes lack transparency in handling user data. To address these concerns and enable Fraunhofer staff to leverage this technology while ensuring confidentiality, we have designed and developed a customized chat AI called FhGenie (genie being a reference to a helpful spirit). Within few days of its release, thousands of Fraunhofer employees started using this service. As pioneers in implementing such a system, many other organizations have followed suit. Our solution builds upon commercial large language models (LLMs), which we have carefully integrated into our system to meet our specific requirements and compliance constraints, including confidentiality and GDPR. In this paper, we share detailed insights into the architectural considerations, design, implementation, and subsequent updates of FhGenie. Additionally, we discuss challenges, observations, and the core lessons learned from its productive usage.
title FhGenie: A Custom, Confidentiality-preserving Chat AI for Corporate and Scientific Use
topic Software Engineering
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2403.00039