工程副总裁 Josh Clemm 谈我们如何在 Dash 中使用知识图谱、MCP 和 DSPy
I was recently a guest speaker in Jason Liu’s online course on RAG offered by the education platform Maven. I did some mini deep-dives into what we’ve been doing at Dropbox with knowledge graphs; how we’re thinking about indexes, MCP, and tool calling in general; some of the work we do with LLM as a judge; and how we use prompt optimizers like DSPy. This is an edited and condensed version of my talk. Visit Maven to watch the full video and hear my Q&A with Jason and his students. — Josh Clemm, vice president of engineering for Dropbox Dash
我最近是 Jason Liu 在教育平台 Maven 提供的 RAG 在线课程的客座演讲者。我对我们在 Dropbox 与知识图谱所做的一些事情做了小型深入探讨；我们如何思考索引、MCP 和工具调用一般；我们用 LLM 作为评判的一些工作；以及我们如何使用像 DSPy 这样的提示优化器。这是我的演讲的编辑和浓缩版本。访问 Maven 以 观看完整视频并听我和 Jason 及他的学生的 Q&A。 — Josh Clemm, Dropbox Dash 工程副总裁
~ ~ ~
~ ~ ~
I don't know about you, but I probably have about 50 tabs open right now—and at least another 50 accounts for other SaaS apps. It’s completely overwhelming. It means your content is all over the place, and that makes it very, very hard to find what you're looking for. The good news is we have all these amazing LLMs coming out every day that can tell you about quantum physics. But the bad news is they don’t have access to your content. All of your work content is proprietary. It's within your walled garden. It means most LLMs can’t help when it comes to your work.
我不知道您怎么样，但我现在可能有大约 50 个标签页打开——而且还有至少另外 50 个其他 SaaS 应用的账户。这完全令人不知所措。这意味着您的内容散落在各处，这使得查找您需要的东西非常、非常困难。好消息是我们每天都有这些惊人的 LLM 出现，它们可以告诉您关于 量子物理 的知识。但坏消息是它们无法访问您的内容。您的所有工作内容都是专有的。它处于您的封闭花园中。这意味着大多数 LLM 在您的工作方面无法提供帮助。
That’s why we’ve been building Dropbox Dash. It doesn't just look at your Dropbox content. It connects to all your third-party apps and brings it into one place, so you can search, get answers, and do the agentic queries that you want to do at work.
这就是为什么我们一直在构建 Dropbox Dash。它不仅仅查看你的 Dropbox 内容。它连接到你所有的第三方应用，并将其带到一个地方，这样你就可以搜索、获取答案，并进行你想在工作中进行的 agentic queries。
Here’s a brief primer on our tech stack and how Dash works.
这里是我们技术栈的简要入门以及 Dash 的工作原理。