KnowledgeRefinery/shared/models/data_model.md
oho 38a99476d6 Knowledge Refinery: local-first semantic search & 3D concept visualization
macOS app for corpus ingestion, semantic search, and concept universe
visualization powered by local LLMs via LM Studio.

Architecture:
- Go daemon (17MB single binary, zero dependencies)
  - chi router, pure-Go SQLite, tiktoken tokenizer
  - 6-stage pipeline: scan → extract → chunk → embed → annotate → conceptualize
  - Brute-force cosine vector search in memory
  - 89 tests across 8 packages
- SwiftUI app (macOS 15+)
  - Multi-workspace management with auto-start daemons
  - Live pipeline progress, search, concept browser
  - WebGPU 3D universe renderer with Canvas2D fallback
  - Custom crystal app icon
2026-02-13 18:09:46 +01:00

560 B

Canonical Data Model

See ../../docs/data-model.md for the full data model documentation.

Pipeline Version Tracking

Every derived artifact stores:

  • pipeline_version - Overall pipeline version (e.g., "v1.0")
  • model_id - LM Studio model used (for annotations/concepts)
  • prompt_id + prompt_version - Prompt template version (for annotations)

This enables:

  • Re-running with updated models/prompts without losing previous results
  • A/B comparison of different model outputs
  • Audit trail of how insights were derived