--- schema: 1 type: video title: >- RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j description: >- An agent answering questions about a course needs more than the five chunks closest to a query. It also needs the connections between lessons, concepts, and the sources behind its answer. Nyah Macklin builds that retrieval path with Neo4j, combining vector search with a knowledge graph that people can inspect and query. The workshop starts with the difference between semantic similarity and relationships, then walks through GraphAcademy, an Aura database, and a Python environment. An LLM extracts entities and relationships from course material, embeddings support similarity search, and Cypher exposes the resulting structure. Vectors remain part of the system; the graph adds connected context and a way to answer questions that require traversal or aggregation. The hands on build moves from a knowledge graph pipeline to an agent in Aura. Macklin creates a vector index, configures a lesson search tool, adds a retrieval query that returns related graph data, and enables natural language questions through text to Cypher. The agent answers a question about temperature using course content and displays its sources. A lesson count prompts a closer check of the underlying database query, showing why visible evidence matters even after the pipeline works. The final code walkthrough covers chunking, entity types, relationship types, and a schema that guides extraction rather than leaving the model to invent the graph's structure. Speaker info: - https://x.com/nyahmacklindev - https://www.linkedin.com/in/nyahmacklin - https://graphacademy.neo4j.com/courses/workshop-genai - https://github.com/neo4j/neo4j-graphrag-python Timestamps: 0:00 - Workshop introduction 3:07 - GraphAcademy and workshop setup 5:18 - Create an Aura database 7:07 - Vectors and graph context 9:13 - Relationships and explainability 11:38 - From RAG to GraphRAG 13:00 - When connected retrieval helps 16:11 - Retriever types and architecture 18:42 - Knowledge graph fundamentals 20:18 - Extract entities and relationships 23:08 - Python package and Codespace setup 27:32 - Test the environment 28:40 - Run the knowledge graph builder 30:53 - Inspect nodes and relationships 32:16 - Enable and create an Aura agent 36:51 - Create the vector index 40:14 - Configure lesson similarity search 42:22 - Return connected graph data 44:12 - Test the agent and inspect sources 45:48 - Check a lesson count against the graph 47:55 - Walk through the pipeline code 51:07 - Further learning and wrap up --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/LJ2a9nX3vlo-youtube-cf62a92c82ed1de99233 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: 'https://liquidgold.cc/watch/LJ2a9nX3vlo' markdown: 'https://liquidgold.cc/watch/LJ2a9nX3vlo.md' llms: 'https://liquidgold.cc/watch/LJ2a9nX3vlo/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:19:20.632Z' language: null children: [] videoId: LJ2a9nX3vlo durationSeconds: 3179 publishedAt: '2026-10-11T10:30:20.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 713 endSeconds: 780 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=713' heldReason: rights - ordinal: 1 text: null startSeconds: 438 endSeconds: 553 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=438' heldReason: rights - ordinal: 2 text: null startSeconds: 790 endSeconds: 979 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=790' heldReason: rights - ordinal: 3 text: null startSeconds: 790 endSeconds: 979 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=790' heldReason: rights - ordinal: 4 text: null startSeconds: 564 endSeconds: 703 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=564' heldReason: rights - ordinal: 5 text: null startSeconds: 564 endSeconds: 703 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=564' heldReason: rights - ordinal: 6 text: null startSeconds: 979 endSeconds: 990 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=979' heldReason: rights - ordinal: 7 text: null startSeconds: 990 endSeconds: 1124 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=990' heldReason: rights - ordinal: 8 text: null startSeconds: 1221 endSeconds: 1233 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1221' heldReason: rights - ordinal: 9 text: null startSeconds: 1233 endSeconds: 1388 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1233' heldReason: rights - ordinal: 10 text: null startSeconds: 1400 endSeconds: 1652 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1400' heldReason: rights - ordinal: 11 text: null startSeconds: 1663 endSeconds: 1720 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1663' heldReason: rights - ordinal: 12 text: null startSeconds: 1730 endSeconds: 1853 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1730' heldReason: rights - ordinal: 13 text: null startSeconds: 1864 endSeconds: 1942 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=1864' heldReason: rights - ordinal: 14 text: null startSeconds: 2223 endSeconds: 2414 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2223' heldReason: rights - ordinal: 15 text: null startSeconds: 2427 endSeconds: 2549 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2427' heldReason: rights - ordinal: 16 text: null startSeconds: 2567 endSeconds: 2659 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2567' heldReason: rights - ordinal: 17 text: null startSeconds: 2760 endSeconds: 2885 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2760' heldReason: rights - ordinal: 18 text: null startSeconds: 2896 endSeconds: 3074 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2896' heldReason: rights - ordinal: 19 text: null startSeconds: 2896 endSeconds: 3074 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2896' heldReason: rights - ordinal: 20 text: null startSeconds: 2671 endSeconds: 2750 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=2671' heldReason: rights - ordinal: 21 text: null startSeconds: 209 endSeconds: 318 watch: 'https://liquidgold.cc/watch/LJ2a9nX3vlo?t=209' heldReason: rights --- # RAG Needs a Map: Using GraphRAG to Retrieve Connected Context — Nyah Macklin, Neo4j An agent answering questions about a course needs more than the five chunks closest to a query. It also needs the connections between lessons, concepts, and the sources behind its answer. Nyah Macklin builds that retrieval path with Neo4j, combining vector search with a knowledge graph that people can inspect and query. The workshop starts with the difference between semantic similarity and relationships, then walks through GraphAcademy, an Aura database, and a Python environment. An LLM extracts entities and relationships from course material, embeddings support similarity search, and Cypher exposes the resulting structure. Vectors remain part of the system; the graph adds connected context and a way to answer questions that require traversal or aggregation. The hands on build moves from a knowledge graph pipeline to an agent in Aura. Macklin creates a vector index, configures a lesson search tool, adds a retrieval query that returns related graph data, and enables natural language questions through text to Cypher. The agent answers a question about temperature using course content and displays its sources. A lesson count prompts a closer check of the underlying database query, showing why visible evidence matters even after the pipeline works. The final code walkthrough covers chunking, entity types, relationship types, and a schema that guides extraction rather than leaving the model to invent the graph's structure. Speaker info: - https://x.com/nyahmacklindev - https://www.linkedin.com/in/nyahmacklin - https://graphacademy.neo4j.com/courses/workshop-genai - https://github.com/neo4j/neo4j-graphrag-python Timestamps: 0:00 - Workshop introduction 3:07 - GraphAcademy and workshop setup 5:18 - Create an Aura database 7:07 - Vectors and graph context 9:13 - Relationships and explainability 11:38 - From RAG to GraphRAG 13:00 - When connected retrieval helps 16:11 - Retriever types and architecture 18:42 - Knowledge graph fundamentals 20:18 - Extract entities and relationships 23:08 - Python package and Codespace setup 27:32 - Test the environment 28:40 - Run the knowledge graph builder 30:53 - Inspect nodes and relationships 32:16 - Enable and create an Aura agent 36:51 - Create the vector index 40:14 - Configure lesson similarity search 42:22 - Return connected graph data 44:12 - Test the agent and inspect sources 45:48 - Check a lesson count against the graph 47:55 - Walk through the pipeline code 51:07 - Further learning and wrap up --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/LJ2a9nX3vlo-youtube-cf62a92c82ed1de99233 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/watch/LJ2a9nX3vlo · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.