使用 Neo4j 和 Milvus 构建 GraphRAG 代理

This blog was originally posted on Neo4j and reposted here with permission

本文最初发布于Neo4j，并经许可在此转载

This blog post details how to build a GraphRAG agent using the Neo4j graph database and Milvus vector database. This agent combines the power of graph databases and vector search to provide accurate and relevant answers to user queries. In this example, we will use LangGraph, Llama 3.1 8B with Ollama and GPT-4o.

这篇博客文章详细介绍了如何使用Neo4j图数据库和Milvus向量数据库构建一个GraphRAG代理。这个代理结合了图数据库和向量搜索的力量，为用户查询提供准确和相关的答案。在这个例子中，我们将使用LangGraph、Llama 3.1 8B与Ollama和GPT-4o。

Traditional Retrieval Augmented Generation (RAG) systems rely solely on vector databases to retrieve relevant documents. Our approach goes further by incorporating Neo4j to capture relationships between entities and concepts, offering a more nuanced understanding of the information. We want to create a more robust and informative RAG system by combining these two techniques.

传统的检索增强生成（RAG）系统仅依赖于向量数据库来检索相关文档。我们的方法更进一步，通过结合Neo4j来捕捉实体和概念之间的关系，从而提供对信息的更细致理解。我们希望通过结合这两种技术创建一个更强大和信息丰富的RAG系统。

Our agent follows three key concepts: routing, fallback mechanisms, and self-correction. These principles are implemented through a series of LangGraph components:

我们的代理遵循三个关键概念：路由、回退机制和自我纠正。这些原则通过一系列LangGraph组件实现：

• Routing – A dedicated routing mechanism decides whether to use the vector database, the knowledge graph, or a combination of both based on the query.

  路由 – 专门的路由机制根据查询决定是使用向量数据库、知识图谱，还是两者结合。

• Fallback – In situations where the initial retrieval is insufficient, the agent falls back to a web search using Tavily.

  回退 – 在初始检索不足的情况下，代理会使用Tavily进行网络搜索作为回退。

• Self-correction – The agent evaluates its own answers and attempts to correct hallucinations or inaccuracies.

  自我纠正 – 代理评估自己的答案，并尝试纠正幻觉或不准确之处。

We then have other components, such as:

然后我们还有其他组件，例如：

• Retrieval – We use Milvus, an open-source and high-performance vector database, to store and retrieve document chunks based on semantic similarity to the user's query.

  检索 – 我们使用Milvus，一个开源且高性能的向量数据库，根据与用户查询的语义相似性来存储和检索文档片段。

• Graph enhanceme...