Files
semantica/pyproject.toml
T

391 lines
8.3 KiB
TOML

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "semanticore"
version = "0.1.0"
description = "Open Source Semantic Layer Toolkit - Transform any unstructured data into intelligent knowledge graphs"
readme = "README.md"
license = {text = "MIT"}
authors = [
{name = "SemantiCore Team", email = "team@semanticore.io"}
]
maintainers = [
{name = "SemantiCore Team", email = "team@semanticore.io"}
]
keywords = [
"semantic", "nlp", "knowledge-graph", "ai", "machine-learning",
"data-processing", "embeddings", "ontology", "rdf", "sparql"
]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Libraries :: Python Modules",
"Topic :: Text Processing :: Linguistic",
"Topic :: Database",
"Topic :: Internet :: WWW/HTTP :: Dynamic Content",
"Topic :: Scientific/Engineering :: Information Analysis",
]
requires-python = ">=3.8"
dependencies = [
# Core dependencies
"requests>=2.28.0",
"beautifulsoup4>=4.11.0",
"lxml>=4.9.0",
"pandas>=1.5.0",
"numpy>=1.21.0",
"scikit-learn>=1.1.0",
"pydantic>=1.10.0",
"typing-extensions>=4.0.0",
# NLP and ML
"transformers>=4.20.0",
"torch>=1.12.0",
"sentence-transformers>=2.2.0",
"spacy>=3.4.0",
"nltk>=3.8",
# Semantic Web
"rdflib>=6.2.0",
"owlready2>=0.44",
"pyshacl>=0.20.0",
# Data processing
"openpyxl>=3.0.10",
"python-docx>=0.8.11",
"python-pptx>=0.6.21",
"PyPDF2>=3.0.0",
"pdfplumber>=0.7.0",
"feedparser>=6.0.0",
"selenium>=4.0.0",
"requests-html>=0.10.0",
# Vector databases
"faiss-cpu>=1.7.0",
"chromadb>=0.4.0",
"pinecone-client>=2.2.0",
# Graph databases
"neo4j>=5.0.0",
"pymongo>=4.0.0",
"redis>=4.0.0",
# Streaming and async
"aiohttp>=3.8.0",
"asyncio-mqtt>=0.11.0",
"kafka-python>=2.0.0",
# Utilities
"python-multipart>=0.0.5",
"python-dateutil>=2.8.0",
"pytz>=2022.1",
"tqdm>=4.64.0",
"click>=8.0.0",
"rich>=12.0.0",
]
[project.optional-dependencies]
# Document processing
pdf = [
"PyPDF2>=3.0.0",
"pdfplumber>=0.7.0",
"pdf2image>=1.16.0",
"pymupdf>=1.22.0",
]
office = [
"python-docx>=0.8.11",
"openpyxl>=3.0.10",
"python-pptx>=0.6.21",
"xlrd>=2.0.1",
]
text = [
"markdown>=3.4.0",
"rst2html5>=1.0.0",
"asciidoc>=10.0.0",
]
# Web processing
web = [
"selenium>=4.0.0",
"feedparser>=6.0.0",
"requests-html>=0.10.0",
"scrapy>=2.5.0",
"newspaper3k>=0.2.8",
]
feeds = [
"feedparser>=6.0.0",
"requests-html>=0.10.0",
"aiohttp>=3.8.0",
]
# Structured data
structured = [
"openpyxl>=3.0.10",
"xlrd>=2.0.1",
"pyyaml>=6.0",
"xmltodict>=0.13.0",
"jsonschema>=4.0.0",
]
# Email and archives
email = [
"email-validator>=1.3.0",
"extract-msg>=0.41.0",
"pypff>=20220101",
]
archives = [
"patool>=1.12.0",
"py7zr>=0.20.0",
"rarfile>=4.0",
]
# Academic and scientific
academic = [
"bibtexparser>=1.4.0",
"scholarly>=1.7.0",
"arxiv>=1.4.0",
"crossref-commons>=0.0.7",
]
# Database integrations
database = [
"neo4j>=5.0.0",
"pymongo>=4.0.0",
"redis>=4.0.0",
"sqlalchemy>=1.4.0",
"psycopg2-binary>=2.9.0",
"pymysql>=1.0.0",
]
graphdb = [
"neo4j>=5.0.0",
"py2neo>=2021.0.0",
"gremlinpython>=3.6.0",
"amazon-neptune-python-utils>=1.0.0",
]
# Vector stores
vector = [
"faiss-cpu>=1.7.0",
"chromadb>=0.4.0",
"pinecone-client>=2.2.0",
"weaviate-client>=3.15.0",
"qdrant-client>=1.1.0",
"milvus>=2.2.0",
]
# Machine learning
ml = [
"sentence-transformers>=2.2.0",
"transformers>=4.20.0",
"torch>=1.12.0",
"tensorflow>=2.10.0",
"scikit-learn>=1.1.0",
"spacy>=3.4.0",
"nltk>=3.8",
"gensim>=4.2.0",
]
# Streaming and real-time
streaming = [
"kafka-python>=2.0.0",
"pika>=1.3.0",
"aiohttp>=3.8.0",
"websockets>=10.0",
"asyncio-mqtt>=0.11.0",
]
# Deployment and scaling
deployment = [
"kubernetes>=26.0.0",
"docker>=6.0.0",
"prometheus-client>=0.14.0",
"grafana-api>=1.0.3",
]
# Development dependencies
dev = [
"pytest>=7.0.0",
"pytest-cov>=4.0.0",
"pytest-asyncio>=0.21.0",
"pytest-mock>=3.8.0",
"black>=22.0.0",
"isort>=5.10.0",
"flake8>=5.0.0",
"mypy>=0.991",
"pre-commit>=2.20.0",
"tox>=3.25.0",
"coverage>=6.0.0",
"bandit>=1.7.0",
"safety>=2.0.0",
]
# Documentation
docs = [
"sphinx>=5.0.0",
"sphinx-rtd-theme>=1.0.0",
"sphinx-autodoc-typehints>=1.19.0",
"myst-parser>=0.18.0",
"sphinx-copybutton>=0.5.0",
]
# Testing
test = [
"pytest>=7.0.0",
"pytest-cov>=4.0.0",
"pytest-asyncio>=0.21.0",
"pytest-mock>=3.8.0",
"pytest-benchmark>=4.0.0",
"factory-boy>=3.2.0",
"faker>=18.0.0",
]
# All optional dependencies
all = [
"semanticore[pdf,office,text,web,feeds,structured,email,archives,academic,database,graphdb,vector,ml,streaming,deployment]"
]
[project.urls]
Homepage = "https://semanticore.io"
Documentation = "https://semanticore.readthedocs.io"
Repository = "https://github.com/semanticore/semanticore"
"Bug Tracker" = "https://github.com/semanticore/semanticore/issues"
Discussions = "https://github.com/semanticore/semanticore/discussions"
Discord = "https://discord.gg/semanticore"
Twitter = "https://twitter.com/semanticore"
Blog = "https://blog.semanticore.io"
[project.scripts]
semanticore = "semanticore.cli:main"
[project.gui-scripts]
semanticore-gui = "semanticore.gui:main"
[tool.setuptools]
packages = ["semanticore"]
[tool.setuptools.package-data]
semanticore = ["py.typed", "*.pyi"]
[tool.black]
line-length = 88
target-version = ['py38']
include = '\.pyi?$'
extend-exclude = '''
/(
# directories
\.eggs
| \.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| build
| dist
)/
'''
[tool.isort]
profile = "black"
multi_line_output = 3
line_length = 88
known_first_party = ["semanticore"]
known_third_party = ["pytest", "numpy", "pandas", "torch", "transformers"]
[tool.mypy]
python_version = "3.8"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
[[tool.mypy.overrides]]
module = [
"torch.*",
"transformers.*",
"spacy.*",
"nltk.*",
"selenium.*",
"scrapy.*",
"kafka.*",
"pika.*",
"redis.*",
"pymongo.*",
"neo4j.*",
"faiss.*",
"chromadb.*",
"pinecone.*",
"weaviate.*",
"qdrant.*",
"milvus.*",
"prometheus_client.*",
"grafana_api.*",
"kubernetes.*",
"docker.*",
]
ignore_missing_imports = true
[tool.pytest.ini_options]
minversion = "6.0"
addopts = "-ra -q --strict-markers --strict-config"
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
markers = [
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
"integration: marks tests as integration tests",
"unit: marks tests as unit tests",
"performance: marks tests as performance tests",
]
[tool.coverage.run]
source = ["semanticore"]
omit = [
"*/tests/*",
"*/test_*",
"*/__pycache__/*",
"*/venv/*",
"*/env/*",
"*/\.venv/*",
]
[tool.coverage.report]
exclude_lines = [
"pragma: no cover",
"def __repr__",
"if self.debug:",
"if settings.DEBUG",
"raise AssertionError",
"raise NotImplementedError",
"if 0:",
"if __name__ == .__main__.:",
"class .*\\bProtocol\\):",
"@(abc\\.)?abstractmethod",
]
[tool.bandit]
exclude_dirs = ["tests", "docs"]
skips = ["B101", "B601"]
[tool.safety]
output = "json"