代理RAG：公司知识Slack代理
[
[
Agent has access to different RAG tools or APIs | Image by author
代理可以访问不同的 RAG 工具或 API | 作者图片
If you’re not a member and you would like to read this story click here.
如果您不是会员并且想阅读此故事，请点击 这里。
I would have figured that most companies would have built or implemented their own RAG agents by now.
我本以为大多数公司现在应该已经构建或实施了自己的 RAG 代理。
An AI knowledge agent can dig through internal documentation — websites, PDFs, random docs — and answer employees in Slack (or Teams/Discord) within a few seconds. So, these bots should significantly reduce time sifting through information for employees.
一个 AI 知识代理可以在几秒钟内浏览内部文档——网站、PDF、随机文档——并在 Slack（或 Teams/Discord）中回答员工。因此，这些机器人应该显著减少员工筛选信息的时间。
I’ve seen a few of these in bigger tech companies, like AskHR from IBM, but they aren’t all that mainstream yet.
我在一些大型科技公司见过几个这样的例子，比如 IBM 的 AskHR，但它们还没有那么主流。
If you’re keen to understand how they are built and how much resources it takes to build a simple one, this is an article for you.
如果您想了解它们是如何构建的，以及构建一个简单的代理需要多少资源，这篇文章适合您。
I’ll go through the tools, techniques, and architecture involved, while also looking at the economics of building something like this. I’ll also include a section on what you’ll end up focusing the most on.
我将介绍涉及的工具、技术和架构，同时也会关注构建类似东西的经济学。我还会包括一个关于您最终将最关注的内容的部分。