The Graph Maker: Turn Text into Knowledge Graphs via Ontology
tom_doerr · x · 2026-07-20
The Graph Maker is a Python library that converts arbitrary text into knowledge graphs. Core idea: use a predefined ontology to constrain extraction, then extract entities and relations to build structured graphs for graph databases or analysis. Use cases include graph algorithms, node centrality, community detection, and GRAG (Graph Retrieval Augmented Generation), which the author describes as better than traditional vector RAG for 'chatting with documents'.
More from Research
- EdgeRock open-sourced: 72 MiB KV cache at 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Latent-Foresight: world models that learn to predict their own future — abursuc · 2026-10-27
- UK AISI papers: no good safeguards yet against misuse of biological AI tools — davidmanheim · 2026-10-27
- CMU's XYBench: LLMs answer queries literally and reinforce user misconceptions — valentina__py · 2026-10-27