C 编译器。 在 macOS 上，你可以通过运行以下命令获得 C 语言编译器： $ xcode-select --install Linux 用户通常需要根据发行版（distribution）文档安装 GCC 或 Clang。比如，如果你使用 Ubuntu，可以安装 build-essential 包。 12/562Rust 程序设计语言 简体中文版 在 Windows 上安装 rustup 简体中文版 $ rustup self uninstall 本地文档 安装程序也自带一份文档的本地拷贝，可以离线阅读。运行 rustup doc 在浏览器中查看本地 文档。 任何时候，如果你拿不准标准库中的类型或函数的用途和用法，请查阅应用程序接口 （application programming interface，API）文档！ 文本编辑器和集成开发环境（Integrated Development 对于你的编辑器、工具，以及代码位 于何处并没有特定的要求，如果你更倾向于使用集成开发环境（IDE），而不是命令 行，请尽管使用你喜欢的 IDE。目前很多 IDE 都在一定程度上支持 Rust；查看 IDE 文档以了解更多细节。Rust 团队一直致力于借助 rust-analyzer 提供强大的 IDE 支 持。详见附录 D。 创建项目目录 首先创建一个存放 Rust 代码的目录。Rust 并不关心代码的存放位置，不过对于本书的练习和

专业模型训练） 业务流程自动化（ A g e n t框架） 组织协同（ 工作流） 人机交互 赋能个人和 企业员工 生产力提升 多模态 能力 3 图片理解和处理 视频理解和处理 音频理解和处理 非结构化文档处理 47政企、创业者必读 DeepSeek能力很强大 个人使用绰绰有余 但要在政府、企业应用需要和场景结合  大模型要藏在产品后面  客户要的不是电动机，是「刮胡刀」「吹风机」  知识库打造是DeepSeek更懂企业的基础 知识自动汇集，不流失 多模态数据处理和理解 非结构化文档处理和理解 搜索，辅助内部办公和外部客户服务 为业务大模型RAG做准备 内部知识管理 • 把企业内部的碎片化知识， 把专 家头脑中的经验转化为显性知识 管理起来， 如员工邮件、 文档文 件、 聊天记录、 工作记录等 工作流知识管理 1 外部情报分析 • 抓取外部情报， 例如行业报告、

way it thinks best. (This might even be a graphical display in something like a Jupyter or Pluto notebook.) By default (e.g. in scripts or in the text REPL), it calls show(io, "text/plain", x), or equivalently loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

way it thinks best. (This might even be a graphical display in something like a Jupyter or Pluto notebook.) By default (e.g. in scripts or in the text REPL), it calls show(io, "text/plain", x), or equivalently loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

way it thinks best. (This might even be a graphical display in something like a Jupyter or Pluto notebook.) By default (e.g. in scripts or in the text REPL), it calls show(io, "text/plain", x), or equivalently loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

way it thinks best. (This might even be a graphical display in something like a Jupyter or Pluto notebook.) By default (e.g. in scripts or in the text REPL), it calls show(io, "text/plain", x), or equivalently loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

way it thinks best. (This might even be a graphical display in something like a Jupyter or Pluto notebook.) By default (e.g. in scripts or in the text REPL), it calls show(io, "text/plain", x), or equivalently loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()

loading external modules or by using graphical Julia environments (such as the IPython-based IJulia notebook). Base.Multimedia.AbstractDisplay – Type. AbstractDisplay Abstract supertype for rich display prompt It is possible to get an interface which is similar to the IPython REPL and the Mathematica notebook with numbered input prompts and output prefixes. This is done by calling REPL.numbered_prompt!()