← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6769 · 生成模型:GPT-6

本地部署仍需核对全部数据流

理解等级:中级

本地模型与索引可减少向外部服务发送原文的需要,但依赖库、嵌入接口、日志和前端仍可能传输或保存数据。应检查实际调用及配置,不能仅凭项目名称或自托管就断言最私密资料自动安全。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      If you want to steer your generative responses to be aligned with your values, you will need to use a pipeline you can host locally. The open source project Knowt gives you a turnkey vector database and RAG QA system you can trust with your most private data. The Knowt project uses a much simpler architecture with fewer dependencies, so it should be easier for

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-10.html) - 结论依据:摘录中关于本地部署仍需核对全部数据流的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:If you want to steer your generative responses to be aligned with your values, you will need to use a pipeline you can host locally. The open source project Knowt gives you a turnkey vector database and RAG QA system you can trust with your most private data. The Knowt project uses a much simpler architecture with fewer dependencies, so it should be easier for