This is the beginner capstone: you'll combine everything from the track — graph modeling, Cypher, and graph algorithms — with an LLM to build a working GraphRAG pipeline. You'll link the entities in a user's question to nodes in your graph, traverse out to a relevant subgraph, assemble that structured context into a prompt, and let the model generate a grounded, citable answer that naive vector RAG simply can't reach.
GraphRAG is Retrieval-Augmented Generation where the retrieval step walks a knowledge graph instead of (or alongside) a flat vector index. The LLM still generates the final answer, but the context it receives is a set of explicit, connected facts pulled from your graph rather than a bag of loosely related text chunks.
Classic RAG embeds your documents into chunks, stores the vectors, embeds the user's question, retrieves the top-K most similar chunks by cosine similarity, and stuffs them into the prompt.
That works well when the answer lives inside a single chunk. It breaks down on multi-hop questions.
Consider: "Which products are made by companies that my manager has invested in?"
To answer this you must connect:
manages ← my managerinvested_in → companiesproduces → productsNo single document chunk contains that whole chain. Vector search retrieves chunks that mention "products" or "investments" but has no mechanism to follow the relationships between them. It returns plausible-looking but disconnected text, and the LLM is left to guess at the links — which is exactly when it hallucinates.
A knowledge graph stores those relationships as first-class, traversable edges (everything you built in Days 1–2). The retrieval step becomes a traversal (Day 3's Cypher) optionally ranked by graph algorithms (Day 4's centrality/community detection). The result is a connected subgraph — the exact chain of facts needed — handed to the LLM as grounded context.
| Naive Vector RAG | GraphRAG | |
|---|---|---|
| Retrieval unit | Text chunk | Connected subgraph |
| Multi-hop questions | Weak (no link-following) | Strong (traversal is native) |
| Provenance | "These chunks were similar" | "These specific facts/paths" |
| Best for | "Find docs about X" | "How is X connected to Y?" |