The GraphRAG Python package from Neo4j provides end-to-end workflows for creating knowledge graphs, retrieving data from them, and running retrieval-augmented generation (RAG) pipelines. It allows users to incorporate knowledge graphs into their applications, improving the relevance, accuracy, and explainability of RAG models. The package supports various retrievers, including vector retrievers that use Approximate Nearest Neighbor (ANN) search, Vector Cypher Retriever that combines vector search with graph traversal logic in Neo4j's Graph Query language, Hybrid Retriever that combines vector and full-text search, and Custom Retriever for tailored retrieval methods. The GraphRAG Python package is designed to be easy to use, even for those without extensive knowledge of Neo4j or RAG pipelines, providing comprehensive options for designing GenAI applications with knowledge graphs.