This blog post details how to build a GraphRAG agent using Neo4j graph database and Milvus vector database. The agent combines the power of graph databases and vector search to provide accurate and relevant answers to user queries. In this example, we use LangGraph, Llama 3.1 8B with Ollama, and GPT-4o. The architecture of our GraphRAG agent follows three key concepts: routing, fallback mechanisms, and self-correction. These principles are implemented through a series of LangGraph components including retrieval, graph enhancement, and LLMs integration. The GraphRAG Architecture is visualized as a workflow with several interconnected nodes such as question routing, retrieval, generation, evaluation, and refinement if needed.