See it in action
Video coming soon
What are Relational Transformers?
A transformer normally attends over word tokens. A relational transformer attends over a small subgraph of your database. The relational analogue of prompting an LLM, in a 86M-parameter model that scales.Capability Relational TransformerRelativeDB GBDTsXGBoost & co. Graph neural netsper-schema GNNs LLMs on rowsserialized to text No hand-built features yes — raw cells. no — feature tables. partial — graph wiring. partial — prompt design. No per-task training yes — pretrained. no — every task. no — schema + task. yes — pretrained. Zero-shot on new tasks yes — in-context. no. no. partial — if it fits text. Schema-native structure yes — keys, rows, cols. no — flat table. yes — graph edges. no — flattened text. Typed cells & real time yes — native. partial — manual. partial — manual. no — lost as text. No train/serve skew yes. no — common. no — common. yes. Small & scalable yes — 86M params. yes — tiny. partial — grows. no — billions.
RelativeDB ships RT-J inference as a highly optimized, dependency-light C++ engine, with several quantized models for highly constrained environments. Read more →