Skip to content

Concepts

The ideas behind Odin: what it does, how the retrieval pipeline is assembled, and how each scoring signal contributes to the final ranking.

Odin's job is narrow and deliberate: given seed entities, return the most relevant scored paths through a knowledge graph. It does not answer natural-language questions or generate prose; that is the agent's job. Odin is the compass; the agent is the explorer.

  • Architecture

    How PPR, beam search, NPLL, and aggregation compose into one pipeline.

    Read more →

  • Data Model

    Entities, relationships, and communities: how Odin sees your graph.

    Read more →

  • Personalized PageRank

    Finding the structurally important nodes relative to your seeds.

    Read more →

  • Beam Search

    Bounded, best-first multi-hop path exploration.

    Read more →

  • NPLL Edge Scoring

    Learned edge plausibility that filters invalid paths.

    Read more →

  • Motifs & Aggregation

    Turning paths into recurring patterns and summaries.

    Read more →

  • Triage & Insight Scoring

    Collapsing many signals into one 0-100 prioritization number.

    Read more →

  • Caching

    Why graph access is LRU-cached and what it costs.

    Read more →

  • Adapters

    Connect Odin to ArangoDB, JanusGraph, or your own backend.

    Read more →


The three signals

Every path Odin returns is scored by combining three complementary signals:

Signal Question it answers Component
Structural Is this node important in the graph? Personalized PageRank
Reachable Can we get there efficiently? Beam Search
Semantic Is this edge plausible? NPLL

No single signal is sufficient. PPR alone finds important nodes but follows nonsensical edges. Beam search alone explodes without a scoring signal to prune. NPLL alone validates edges but has no notion of importance. Together they let an agent focus on paths that are important, reachable, and plausible.