booksmith/requirements.txt at master · Firindil/booksmith · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
# EPUB LLM Cleaner - Python Dependencies
# Install with: pip install -r requirements.txt

# =============================================================================
# CORE DEPENDENCIES
# Required for basic functionality
# =============================================================================

# Claude API client for LLM-powered content analysis and cleaning
# Used by: epub_cleaner.py, style_profiler.py, style_validator.py,
#          book_analyzer.py, change_planner.py, annotator.py, consistency_checker.py
anthropic>=0.18.0

# HTML parsing library for processing EPUB chapter content
# Used by: epub_cleaner.py, style_profiler.py, book_analyzer.py,
#          footnote_inserter.py, annotator.py, consistency_checker.py
beautifulsoup4>=4.12.0

# YAML parser for configuration and prompt file loading
# Used by: epub_cleaner.py, annotator.py, cli.py
pyyaml>=6.0

# Fast, feature-rich HTML/XML parser (BeautifulSoup backend)
# Provides better performance and handling of malformed HTML
lxml>=4.9.0

# =============================================================================
# EPUB HANDLING
# =============================================================================

# Alternative EPUB library for reading/writing EPUB files
# Provides higher-level API than raw zipfile manipulation
ebooklib>=0.18

# =============================================================================
# STYLE PROFILING & ANALYSIS
# =============================================================================

# NLP library for linguistic analysis: POS tagging, sentence parsing,
# named entity recognition, and other linguistic features
# Used by style_profiler.py for extracting author style metrics
spacy>=3.7.0

# Sentence embeddings for semantic similarity and style comparison
# Used by style_profiler.py and style_validator.py for drift scoring
sentence-transformers>=2.2.0

# =============================================================================
# VALIDATION & SCHEMAS
# =============================================================================

# JSON Schema validation for author_profile.json, book_model.json,
# and change_plan.json validation
# Used for: epub_validator.py (planned), configuration validation
jsonschema>=4.20.0

# =============================================================================
# INTERACTIVE MODE & CLI ENHANCEMENTS
# =============================================================================

# Advanced terminal input with autocomplete, syntax highlighting,
# history, and multi-line editing support
# Used by: interactive.py (planned) for guided editing workflows
prompt_toolkit>=3.0.0

# Rich terminal output with colors, tables, and progress bars
# Enhances CLI output formatting and progress display
rich>=13.0.0

# =============================================================================
# OPTIONAL DEPENDENCIES (install as needed)
# =============================================================================

# For downloading spaCy language models after install:
#   python -m spacy download en_core_web_sm   (small, fast)
#   python -m spacy download en_core_web_md   (medium, with word vectors)
#   python -m spacy download en_core_web_lg   (large, best accuracy)

# For OpenAI API support (future):
# openai>=1.0.0

# For local LLM support via Ollama (future):
# ollama>=0.1.0

# For voice composition features (voice_composer.py - planned):
# numpy>=1.24.0
# scikit-learn>=1.3.0