A fixed RAG pipeline follows a predefined retrieval path. Agentic GraphRAG lets an agent select tools and adapt its investigation. Neo4j provides the connected data those tools query.
The agent first identifies what the question requires. A similarity search can locate relevant text, while Cypher can retrieve precise relationships. Combining retrieval methods helps when a question needs both narrative evidence and structured facts.
Suppose we ask which customers face disruption from a supplier delay. The agent can find the event, follow product and order dependencies and retrieve delivery commitments. It can then check whether the collected evidence covers the question.
Neo4j’s GraphRAG Python package provides vector, hybrid and Cypher-based retrievers. Its ToolsRetriever supports LLM-guided tool selection. A surrounding orchestration loop can add follow-up retrieval, evaluation and stopping conditions.
Use bounded, authorized queries and retain the sources behind each claim. If evidence is missing or contradictory, retrieve again within a budget or state the uncertainty. The goal is a grounded answer, not an endlessly busy agent.
Which customers are affected?
Choose the evidence needed.
Vector, hybrid, Cypher and traversal.
Coverage, sources and contradictions.
Include sources and uncertainty.
Further reading: Neo4j GraphRAG retrieval guide · ToolsRetriever API