Knowledge Graph

The knowledge graph connects entities with directional edges so you can traverse related context instead of only reading raw text.

What this page covers

This page covers edge types, how links are created, and how graph traversal is used in retrieval and entity inspection.

Core workflow

1. Create manual links with relation labels:

pgm link <source-id> <target-id> --relation involves

2. Expand a node’s neighborhood to see neighbors and relationship direction:

pgm expand <entity-id> --depth 2

3. Delete outdated or incorrect edges when needed:

pgm unlink <edge-id>

4. Use the same pattern through API endpoints:

• POST /api/edges
• DELETE /api/edges/:id
• GET /api/entities/:id/graph

Notes

• Default relation examples include involves, assigned_to, part_of, blocked_by, mentioned_in, and related_to.
• Manual edges are typically high-confidence (confidence = 1.0); extracted edges carry model-derived confidence.
• Duplicate edges are prevented by source/target/relation constraints.