从失败到成功：GrabGPT的诞生，Grab内部的ChatGPT

In March 2023, I embarked on a mission to explore the potential of Large Language Models (LLMs) within Grab. What started off as an attempt to solve a specific problem—reducing the burden on our ML Platform team’s support channels, ended up becoming something much bigger. The creation of GrabGPT, an internal ChatGPT-like tool that has transformed how folks in Grab interact with AI. This is the story of how a failed experiment led to one of Grab’s most impactful internal tools.

在2023年3月，我开始了一项探索大型语言模型（LLMs）在Grab中潜力的任务。最初是为了尝试解决一个特定问题——减轻我们机器学习平台团队的支持渠道的负担，最终变成了更大的事情。创建了GrabGPT，一个内部的类似ChatGPT的工具，改变了Grab员工与AI互动的方式。这是一个失败的实验如何导致Grab最具影响力的内部工具之一的故事。

The problem: Overwhelmed support channels

问题：支持渠道不堪重负

As part of Grab’s machine learning platform team, we were drowning in user inquiries. Slack channels were flooded with questions and our on-call engineers were spending more time answering repetitive queries than building innovative solutions. This led me to ponder on this question, “could we use LLMs to build a chatbot that understands our platform’s documentation and answers these questions automatically?”

作为Grab机器学习平台团队的一部分，我们在用户咨询中感到不堪重负。Slack频道被问题淹没，我们的值班工程师花费更多时间回答重复的查询，而不是构建创新的解决方案。这让我思考这个问题，“我们能否使用LLMs构建一个理解我们平台文档并自动回答这些问题的聊天机器人？”

The first attempt: A chatbot for platform support

第一次尝试：一个平台支持的聊天机器人

I started by exploring open-source frameworks to build a chatbot. I stumbled upon chatbot-ui, a simple yet powerful tool that could be wired up with LLMs. My idea was to feed the chatbot our platform’s Q\&A documentation (over 20,000 words) and let it handle user queries.

我开始探索开源框架来构建一个聊天机器人。我偶然发现了chatbot-ui，这是一个简单而强大的工具，可以与LLM连接。我的想法是将我们平台的问答文档（超过20,000字）输入聊天机器人，让它处理用户查询。

But there was a catch: GPT-3.5-turbo could only handle 8,000 tokens (~2,000 words). I spent days summarising the documentation, reducing it to less than 800 words. While the chatbot worked for a handful of frequently asked questions, it was clear that this approach wasn’t scalable. I tried with embedding search and it didn’t work that well too, so I d...