- Add AI alignment score display to asset metadata
- Implement image description fallback for non-workflow image assets
- Improve AI captioning UI and UX
- Optimize AI tagging suggestions with bootstrap generation
- Refactor collections controller to support AI toggling
- Enhance error handling and retry logic for asset indexing
- Implemented library audit route to surface assets based on completeness and quality scores.
- Created hybrid search route combining FTS and semantic search with inline filter parsing.
- Developed vector search routes for semantic search, find-similar, and alignment score retrieval.
- Added auto-clustering utility for grouping assets by visual similarity using K-Means.
- Enhanced vector search capabilities with support for AI auto-tags and clustering suggestions.