如何使用 Agentic RAG 和 LangGraph 构建智能 FAQ 聊天机器人

AI agents are now a part of enterprises big and small. From filling forms at hospitals and checking legal documents to analyzing video footage and handling customer support – we have AI agents for all kinds of tasks. Companies often spend hundreds of thousands of dollars on hiring customer support staff who can understand the needs of a customer and resolve them based on the company’s guidelines. Today, having an intelligent chatbot to answer FAQs can efficiently improve customer service. In this article, we will learn how to build an FAQ chatbot that can resolve customer queries in seconds, using agentic RAG (Retrieval Augmented Generation), LangGraph and ChromaDB.

AI agents 现在已成为各类规模企业的一部分。从在医院填写表格、检查法律文件，到分析视频素材、处理 customer support —— 我们拥有适用于各种任务的 AI agents。公司往往花费数十万美元聘请能够理解客户需求并根据公司指南解决问题的客户支持人员。如今，拥有一个能够回答常见问题的智能聊天机器人可以高效提升客户服务。在本文中，我们将学习如何使用 agentic RAG（Retrieval Augmented Generation）、LangGraph 和 ChromaDB 构建一个能在几秒钟内解决客户查询的 FAQ 聊天机器人。

RAG is a hot topic nowadays. Everyone is talking about RAG and building applications on top of it. RAG helps LLMs to get access to the real-time data, which makes LLMs more accurate than ever before.  However, traditional RAG systems tend to fail when it comes to choosing the best retrieval method, changing the retrieval workflow, or providing multi-step reasoning. This is where agentic RAG comes in.

RAG 如今是一个热门话题。每个人都在谈论 RAG 并在此基础上构建应用。RAG 帮助 LLM 获取实时数据，使 LLM 比以往任何时候都更准确。然而，传统的 RAG 系统在选择最佳检索方法、更改检索工作流或提供多步推理时往往会失败。这就是 agentic RAG 的用武之地。

Agentic RAG enhances traditional RAG by incorporating the capabilities of AI agents into it. With this superpower, RAGs can dynamically change the workflow based on the nature of the query, do multi-step reasoning, and multi-step retrieval as well. We can even integrate tools into the agentic RAG system, and it can dynamically decide which tool to use when. Overall, it results in improved accuracy and makes the system more efficient and scalable.

Agentic RAG 通过将 AI agent 的能力融入传统 RAG 来增强其功能。凭借这一超能力，RAG 可以根据查询的性质动态改变工作流，进行多步推理和多步检索。我们甚至可以将工具集成到 a...