Extract triples with Ollama or vLLM, store them in a graph database, and explore them in a GPU-accelerated web UI
Transform unstructured text into a structured knowledge graph you can explore and query. This playbook extracts subject–predicate–object triples with a local LLM, stores them in a graph database, and renders the graph in an interactive GPU-accelerated web UI.
The workflow covers:
A running, containerized system that:
Required:
Optional:
Use the matrix below to confirm your hardware platform, OS, memory, and whether multi-node applies. The same base workflow applies across supported hardware platforms; ./start.sh always starts the default ArangoDB + Ollama stack.
| Hardware platform | OS | Memory | Multi-node capable hardware |
|---|---|---|---|
| DGX Spark | DGX OS (Linux) | 128 GB Unified Memory | — |
| DGX Station | DGX OS (Linux) | Large HBM + Grace DRAM | — |
| Hardware platform | Default start command | Other stack options |
|---|---|---|
| DGX Spark | ./start.sh → ArangoDB + Ollama | ./start.sh --neo4j → Neo4j + Ollama; ./start.sh --vllm → Neo4j + vLLM |
| DGX Station | ./start.sh → ArangoDB + Ollama | ./start.sh --neo4j → Neo4j + Ollama; ./start.sh --vllm → Neo4j + vLLM |
IMPORTANT
The 64 KB page-size issue is specific to DGX Station; DGX Spark is not affected. On affected DGX Station systems, prefer ./start.sh --neo4j. Some upstream ArangoDB and Qdrant container images can abort at startup with <jemalloc>: Unsupported system page size; the Neo4j + Ollama stack preserves the fast local Ollama flow while avoiding ArangoDB.
NOTE
Larger models generally produce higher-quality triples. Choose a model that fits the memory available on your hardware platform. See Instructions → Step 3 for defaults and links to explore more models.
Hardware requirements
Software requirements
Ancillary files (in nvidia/playbook-txt2kg/assets after Step 1):
start.sh / stop.sh — launch and shut down servicesdeploy/compose/ — Docker Compose configurations