lakehouse

T

rootandClaude Opus 4.6 bf033b2d9d Metacognitive knowledge extraction: 496 topics, 300 decisions, 100 insights

- extract_knowledge.py: LLM processes sampled pages from all conversations
- Extracts structured JSON: topics, decisions, insights, open questions
- Stores as queryable Parquet tables (knowledge_topics, knowledge_decisions,
  knowledge_insights, knowledge_questions)
- Each finding traces to source conversation + page number
- Fixed Unicode chunker crash (byte boundary on multi-byte chars)
- Tested on 8 real ChatGPT PDFs, 477 pages:
  496 topics, 300 decisions, 100 insights, 200 open questions extracted

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-27 23:06:36 -05:00

apps/observer-kb

Observer KB: full knowledge base interface

2026-03-27 22:57:19 -05:00

crates

Observer KB: 477 pages from 8 ChatGPT PDFs indexed and searchable

2026-03-27 22:53:27 -05:00

data

Metacognitive knowledge extraction: 496 topics, 300 decisions, 100 insights

2026-03-27 23:06:36 -05:00

docs

Sync memory + phases: all 15 phases marked complete