MoE Document Classification CLI v3.0
Command-line interface for classifying documents using the Mixture of Experts classification system with 13 Type Experts.
Version History:
- v2.1: 13 Type Experts, autonomous mode, expert mode
- v3.0: Enhanced frontmatter, threshold, type override, respect-directory
Usage: # Classify a single file python classify.py path/to/file.md
# Classify a directory
python classify.py path/to/docs/ --recursive
# Batch classify with output
python classify.py docs/ -r --output results.json --format json
# Update frontmatter with classifications
python classify.py docs/ -r --update-frontmatter
# Dry run (show what would happen)
python classify.py docs/ -r --dry-run
# V3: ENHANCE FRONTMATTER MODE
# Add explicit type fields to boost low-confidence files
python classify.py docs/ -r --enhance-frontmatter
# V3: With custom threshold (default 95%)
python classify.py docs/ -r --enhance-frontmatter --threshold 90
# V3: Dry run to preview enhancements
python classify.py docs/ -r --enhance-frontmatter --dry-run
# V3: TYPE OVERRIDE MODE
# Force specific type on all files in a directory
python classify.py docs/workflows/ -r --enhance-frontmatter --type-override workflow
# V3: Correct misclassified WF-* files
python classify.py docs/workflows/WF-*.md --enhance-frontmatter --type-override workflow
# V3: RESPECT DIRECTORY MODE
# Use directory path as classification hint
python classify.py docs/ -r --enhance-frontmatter --respect-directory
# V3: Dry run to see where directory hints would be applied
python classify.py docs/ -r --enhance-frontmatter --respect-directory --dry-run --verbose
# V3: SUGGEST ENHANCEMENTS MODE
# Analyze files and suggest specific content additions
python classify.py docs/ -r --suggest-enhancements
# V3: Verbose to see content previews
python classify.py docs/ -r --suggest-enhancements --verbose
# V3: JSON OUTPUT MODE (CI/CD integration)
# Get structured JSON output for any mode
python classify.py docs/ -r --enhance-frontmatter --dry-run --json
python classify.py docs/ -r --suggest-enhancements --json
python classify.py docs/ -r --json # Standard classification
File: classify.py
Classes
BatchResult
Result of batch classification.
ClassificationCLI
Command-line interface for MoE classification.
Functions
check_embeddings_available()
Check if sentence-transformers is available for embeddings.
create_orchestrator(use_embeddings)
Create the appropriate orchestrator based on configuration.
create_parser()
Create argument parser.
get_directory_hint(file_path)
Get type hint from directory path.
enhance_frontmatter_mode(args)
V3 Enhance Frontmatter Mode.
suggest_enhancements_mode(args)
V3 Suggest Enhancements Mode.
main()
Main entry point.
run()
Execute the classification based on CLI arguments.
Usage
python classify.py