Changes: - Add Z-Image prompt style with 6-part formula support - Add vocabulary enhancement system (984 terms) - Add classification improvements (age, clothing, subject count) - Add Full and Z-Image prompt styles preserving Florence prose - Add pipeline design document (docs/COMPOSE_PIPELINE_DESIGN.md) - Remove RAG system (not working well) - Remove use_rag input from compose node Key insight: Pipeline should PRESERVE information, not destroy it. - Florence descriptions kept intact (not tokenized) - Tags organized into Z-Image categories - NLP mode = structured output - LLM mode = natural prose generation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Simple CLI script to rebuild RAG index from scraped data: python scripts/reindex_rag.py [input_path] [--device cuda|cpu] 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
