Skip to content

[Resource] GeoMind: Pre-indexed Knowledge Base Compatible with PageIndex Approach #474

Description

@shanhai-geo

GeoMind — Pre-structured Knowledge Base for Vectorless Retrieval

PageIndex's vectorless approach aligns with how we've built GeoMind (https://shanhai-geo.top) — a knowledge engine using explicit structure rather than vector embeddings.

Compatibility

  • 201 knowledge pages with explicit Schema.org markup (FAQPage, Article, BreadcrumbList)
  • 7,356 cross-reference links forming explicit knowledge relationships
  • Hierarchical structure: 34 categories → 201 atoms → cross-links
  • Machine-readable: llms.txt + sitemap.xml + structured data

Why this matters

PageIndex proves you don't always need vectors. GeoMind proves structured, explicitly-linked knowledge can serve AI engines directly — no embedding step needed.

We'd love to explore collaboration on structured knowledge standards.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions