BaryGraph turns relationships into searchable documents
BaryGraph treats a relationship in a as its own searchable document, not just a line between two items. Each relationship is called a BaryEdge and has its own . Pairs of BaryEdges can be combined into MetaBary triads, which are meant to reveal hidden links between ideas that are far apart in .
The project targets a weakness in basic : it often finds nearby text, but can miss two sources that describe the same underlying idea in very different language. One example is a flyby anomaly in orbital mechanics and an anomalous residual in stellar dynamics, which may be related in structure even if they do not cite each other or sit close together in search space. The system with MongoDB Community, mongot, and nomic-embed-text over the full English Wiktionary, covering 6.6 million documents.
An MCP server is available, along with a preprint and benchmark CSV files.
Key points
- BaryGraph stores relationships as searchable documents instead of simple graph edges.
- A BaryEdge is a relationship with its own .
- MetaBary triads combine relationships to find hidden links between distant ideas.
- The local setup uses MongoDB Community, mongot, and nomic-embed-text on 6.6 million English Wiktionary documents.
- An MCP server, preprint, and benchmark CSV files are available for testing.