Module · Knowledge Graph

Entity relationships across your data. RAG that actually works.

Move beyond keyword search. Surface entity relationships across your data so agents reason about what's connected.

Capabilities

What Knowledge Graph ships with.

  • Entity extraction

    Auto-extracted entities and relationships from your knowledge sources.

    Extracted entities 6 found
    HDFC Bank approved a ₹12L home loan for Aarav Sharma in Mumbai.
    • ORG · HDFC Bank 0.97
    • MONEY · ₹12L 0.99
    • PERSON · Aarav Sharma 0.93
    3 types · auto-linked Open graph
  • Graph traversal

    Multi-hop reasoning across entities for richer agent context.

    Query 3 hops
    12ms
    Aarav → HDFC → Mumbai → RBI rule Explore
  • Schema flexibility

    Start with auto-extracted, evolve to a curated ontology.

    Ontology v3 · 4 types
    • Customer auto
      8,442
    • Account auto
      12,808
    • Transaction curated
      1.2M
    • RegulatoryRule curated
      184
    2 curated · 2 auto Edit schema
  • Privacy-aware

    Entity-level access control respected across traversals.

    Access matrix HIPAA
    Field Doctor Nurse Admin Auditor
    Patient.SSN , , ,
    Patient.diagnosis ,
    Patient.contact ,
    12 fields policed Policy
Integrates with

Plays nicely with the rest of the platform.

  • Knowledge Base

    Build the graph from the same sources you're already indexing.

  • Agent Studio

    Drop graph traversal into agents as a single canvas node.

  • Observability

    Trace which entities a query traversed, debug graph reasoning.

30-minute demo. Your environment. No screenshare theatre.

Live walkthrough with an architect. Watch the module do exactly what we say it does. Your data, your stack, your guardrails.

Book a demo