When running AI organize on a folder that already contains subfolders,
the AI will now consider reusing existing folder names if the theme
matches, instead of always generating new titles. This prevents
duplicate folders from being created when re-organizing the same
directory multiple times.
- Add existing_folder_names parameter to ClusterIibOutputReq
- Pass existing folder names from dest directory to AI title generation
- Update AI prompt to prioritize reusing matching folder names
Co-Authored-By: Claude <noreply@anthropic.com>
- Pass recursive parameter from request to _build_embeddings_one_folder
- Include recursive in cache_params to avoid cache collision between
recursive and non-recursive clustering results
- Add debug logging for recursive parameter tracking
Co-Authored-By: Claude <noreply@anthropic.com>
- Add smart organize feature that groups similar images based on prompt semantics
- AI generates meaningful folder names in user's preferred language
- Preview before action: review proposed organization, skip or adjust as needed
- Background processing for large folders
- Support move or copy, configurable min cluster size, include subfolders option
Backend changes:
- Add organize_files.py with job management and file operations
- Add recursive parameter to embedding and clustering APIs
- Default recursive=true for Topic Search (backward compatible)
- Default recursive=false for Smart Organize (first-level only)
- Update database on file move to preserve tags
Frontend changes:
- Add SmartOrganizeConfigModal for configuration
- Add OrganizeJobsPanel for progress tracking
- Add OrganizePreview for reviewing and confirming
- Add smart organize button to address bar
- Add i18n translations for zh-hans, zh-hant, en, de
Documentation:
- Update README.md and README-zh.md with feature description
- Update change.log.md with screenshots and video demo
Co-Authored-By: Claude <noreply@anthropic.com>
- Add keyword count limit (default 600) for Tag layer to improve performance
- Implement irregular node layout with random perturbations
- Add layer spacing based on adjacent layer widths for consistent gaps
- Add cache result banner with collapse/expand functionality
- Add streaming response utility for LLM API calls
- Update i18n translations for new cache banner texts
- Optimize tag graph: increase max tags to 500, add level-2 tiered requirements
- Fix keyword deduplication and null handling in tag graph
- Add get_all_keywords_frequency method to TopicTitleCache
- Initialize keyword frequency from historical cached cluster keywords
- Prioritize top 100 high-frequency keywords when generating new keywords
- Update LLM prompt to prefer existing keywords from frequency list
- Reduce duplicate/similar keyword generation across clusters
- Add streaming support for tag_graph LLM requests
- Increase LLM timeout and retry limits for better reliability
zanllp
wuqinchuan