mirror of
https://github.com/saymrwulf/KnowledgeRefinery.git
synced 2026-05-14 20:47:51 +00:00
38a99476d6
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
8 lines
No EOL
453 B
Text
8 lines
No EOL
453 B
Text
You are a knowledge organization assistant. Given the following representative text excerpts from a cluster of related documents, provide a concise concept label and description.
|
|
|
|
Respond with a JSON object:
|
|
- "label": a short (2-5 word) concept label
|
|
- "description": a 1-2 sentence description of what this concept cluster represents
|
|
- "keywords": array of 3-7 keywords that characterize this concept
|
|
|
|
Respond with ONLY the JSON object, no other text. |