Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

3.0 KB
Raw Blame
[project]
name = "hyperextract"
version = "0.11.0"
description = "An intelligent, LLM-powered knowledge extraction and evolution framework with semantic search capabilities"
readme = "README.md"
requires-python = ">=3.11"
keywords = [
    "llm",
    "knowledge-extraction",
    "langchain",
    "faiss",
    "semantic-search",
    "pydantic",
    "nlp",
    "rag",
]
authors = [{ name = "Yifan Feng", email = "[email protected]" }]
license = { text = "Apache-2.0" }
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules",
]
dependencies = [
    "faiss-cpu>=1.13.2",
    "langchain>=1.2.6",
    "langchain-community>=0.4.1",
    "langchain-openai>=1.1.7",
    "structlog>=25.5.0",
    "ontomem>=0.6.1",
    "ontosight>=0.1.8",
    "python-dotenv>=1.2.1",
    "semhash>=0.4.1",
    # cli dependencies
    "typer>=0.13.0",
    "rich>=13.7.0",
    "tomli-w>=1.0.0",
]

[dependency-groups]
dev = [
    "mkdocs>=1.6.1",
    "mkdocs-material>=9.7.1",
    "mkdocs-static-i18n>=1.0.0",
    "mkdocstrings[python]>=1.0.0",
    "pymdown-extensions>=10.0",
    "mike>=2.0",
    "pytest>=9.0.2",
    # document conversion backend for readers.py (kept in dev so CI tests it)
    "markitdown[pdf,docx,pptx,xlsx]>=0.1.4",
]


[project.optional-dependencies]
anthropic = ["langchain-anthropic>=0.3.0"]
google = ["langchain-google-genai>=2.1.0"]
mcp = ["mcp>=1.2.0,<3"]
ingest = ["markitdown[pdf,docx,pptx,xlsx]>=0.1.4"]
all = [
    "hyperextract[anthropic,google,mcp,ingest]",
]

[project.urls]
Homepage = "https://github.com/yifanfeng97/hyper-extract"
Repository = "https://github.com/yifanfeng97/hyper-extract"
Issues = "https://github.com/yifanfeng97/hyper-extract/issues"

[project.scripts]
he = "hyperextract.cli:app"
he-mcp = "hyperextract.mcp_server:main"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build]
exclude = [
    "docs/",
    "tests/",
    ".github/",
    "*.md",
    "mkdocs.yml",
    "docs_hooks.py",
    ".env",
    ".env.example",
    ".python-version",
    "uv.lock",
]

[tool.hatch.build.targets.wheel]
packages = ["hyperextract"]

[tool.ruff.lint]
ignore = [
    "E731",   # Lambda assignment is fine
    "BLE001", # Blind except Exception — common pattern in this codebase
    "DTZ005", # datetime.now() without tz — not needed for this project
    "SIM102", # Nested if/else style preference
    "TRY002", # Custom exception class design preference
    "TRY004", # TypeError vs ValueError preference
    "S110",   # try/except/pass — intentional in some places
    "TC010",  # String forward-ref in X | Y union — needed for recursive types
]

[tool.ruff.lint.flake8-bugbear]
extend-immutable-calls = ["typer.Option", "typer.Argument"]