We present SocialGenPod, a decentralised and privacy-friendly way of deploying generative AI Web applications. Unlike centralised Web and data architectures that keep user data tied to application and service providers, we show how one can use Solid -- a decentralised Web specification -- to decouple user data from generative AI applications. We demonstrate SocialGenPod using a prototype that allows users to converse with different Large Language Models, optionally leveraging Retrieval Augmented Generation to generate answers grounded in private documents stored in any Solid Pod that the user is allowed to access, directly or indirectly. SocialGenPod makes use of Solid access control mechanisms to give users full control of determining who has access to data stored in their Pods. SocialGenPod keeps all user data (chat history, app configuration, personal documents, etc) securely in the user's personal Pod; separate from specific model or application providers. Besides better privacy controls, this approach also enables portability across different services and applications. Finally, we discuss challenges, posed by the large compute requirements of state-of-the-art models, that future research in this area should address. Our prototype is open-source and available at: https://github.com/Vidminas/socialgenpod/.

翻译：我们提出SocialGenPod，一种去中心化且隐私友好的生成式AI网络应用部署方案。与将用户数据绑定至应用和服务提供商的中心化网络与数据架构不同，我们展示了如何利用Solid（一种去中心化网络规范）将用户数据与生成式AI应用解耦。我们通过原型系统演示了SocialGenPod：用户可与不同大语言模型对话，并可选地利用检索增强生成技术，基于存储在用户授权访问（直接或间接）的任意Solid Pod中的私密文档生成答案。SocialGenPod采用Solid的访问控制机制，使用户能完全掌控其Pod中数据的访问权限。所有用户数据（聊天记录、应用配置、个人文档等）均安全存储在用户的个人Pod中，与特定模型或应用提供商相隔离。除提供更优的隐私控制外，该方案还支持跨不同服务与应用的数据可移植性。最后，我们探讨了当前先进模型对大规模算力的需求所带来的挑战，这些挑战正是该领域未来研究亟待解决的方向。我们的原型系统为开源项目，可通过https://github.com/Vidminas/socialgenpod/ 获取。