pyproject.toml

[project]
name = "unstract-sdk"
dynamic = ["version"]
description = "A framework for writing Unstract Tools/Apps"
readme = "README.md"
urls = { Homepage = "https://unstract.com", "Release notes" = "https://github.com/Zipstack/unstract-sdk/releases", Source = "https://github.com/Zipstack/unstract-sdk" }
license = { text = "AGPL v3" }
authors = [{ name = "Zipstack Inc", email = "devsupport@zipstack.com" }]
keywords = ["unstract tools-development-kit apps development-kit sdk"]
requires-python = ">=3.9, <3.13"
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: GNU Affero General Public License v3",
    "Operating System :: POSIX :: Linux",
    "Operating System :: MacOS :: MacOS X",
    "Programming Language :: Python",
    "Programming Language :: Python :: 3.9",
    "Topic :: Scientific/Engineering",
    "Topic :: Software Development :: Libraries :: Python Modules",
]

dependencies = [
    # Specs and validation
    "jsonschema~=4.18.2",
    "python-magic~=0.4.27",
    "python-dotenv==1.0.0",
    # Adapter changes
    "llama-index==0.12.8",
    "tiktoken~=0.9.0",
    "transformers==4.37.0",
    "llama-index-embeddings-google==0.3.0",
    "llama-index-embeddings-azure-openai==0.3.0",
    # Disabling Hugging Face & FastEmbed to
    # keep the image size under check
    #        "llama-index-embeddings-huggingface==0.2.0",
    # Disabling fast embed due to high processing power
    #        "llama-index-embeddings-fastembed==0.1.4",
    "llama-index-embeddings-openai==0.3.1",
    "llama-index-embeddings-ollama==0.5.0",
    "llama-index-embeddings-bedrock==0.5.0",
    "llama-index-embeddings-vertex==0.3.1",
    "llama-index-vector-stores-postgres==0.4.1",
    # Including Supabase conflicts with postgres on pg-vector.
    # Hence, commenting it out at the moment
    #        "llama-index-vector-stores-supabase==0.1.3",
    "llama-index-vector-stores-milvus==0.4.0",
    "llama-index-vector-stores-weaviate==1.3.1",
    "llama-index-vector-stores-pinecone==0.4.2",
    "llama-index-vector-stores-qdrant==0.4.2",
    "llama-index-llms-openai==0.3.25",
    "llama-index-llms-palm==0.3.0",
    "llama-index-llms-mistralai==0.3.1",
    "mistralai==1.2.5",
    "llama-index-llms-anyscale==0.3.0",
    "llama-index-llms-anthropic==0.6.10",
    "llama-index-llms-azure-openai==0.3.1",
    "llama-index-llms-vertex==0.4.2",
    "llama-index-llms-replicate==0.4.0",
    "llama-index-llms-ollama==0.5.0",
    "llama-index-llms-bedrock==0.3.3",
    # For Llama Parse X2Text
    "llama-parse==0.5.19",
    # OCR
    "filetype~=1.2.0",
    # Others
    # For singleton classes
    "singleton-decorator~=1.0.0",
    "httpx>=0.25.2",
    "pdfplumber>=0.11.2",
    "redis>=5.2.1",
    "llmwhisperer-client>=2.2.1",
]

[project.optional-dependencies]
aws = ["s3fs[boto3]~=2024.10.0", "boto3~=1.34.131"]
gcs = ["gcsfs~=2024.10.0"]
azure = ["adlfs~=2024.7.0"]

[dependency-groups]
dev = [
    "docutils~=0.20.1",
    "mypy~=1.2.0",
    "pre-commit~=3.3.1",
    "yamllint>=1.35.1",
    "ruff<1.0.0,>=0.2.2",
    "pytest>=8.0.1",
    "pycln>=2.5.0",
]
docs = ["lazydocs~=0.4.8"]
test = [
    "parameterized==0.9.0",
    "pytest==8.3.3",
    "pytest-mock==3.14.0",
    "gcsfs==2024.10.0",
    "s3fs==2024.10.0",
    "adlfs~=2024.7.0",
]

[project.scripts]
unstract-tool-gen = "unstract.sdk.scripts.tool_gen:main"

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

[tool.hatch.version]
path = "src/unstract/sdk/__init__.py"

[tool.hatch.build.targets.wheel]
packages = ["src/unstract"]

# === Development tool configurations ===

[tool.ruff]
line-length = 90
target-version = "py312"
exclude = [
    ".bzr",
    ".direnv",
    ".eggs",
    ".git",
    ".git-rewrite",
    ".hg",
    ".mypy_cache",
    ".nox",
    ".pants.d",
    ".pytype",
    ".ruff_cache",
    ".svn",
    ".tox",
    ".venv",
    "__pypackages__",
    "_build",
    "buck-out",
    "build",
    "dist",
    "node_modules",
    "venv",
]

[tool.ruff.lint]
select = [
    "E",   # pycodestyle (formatting)
    "F",   # Pyflakes (static analysis)
    "I",   # isort (import sorting)
    "B",   # bugbear (security/performance)
    "W",   # warnings
    "C90", # mccabe complexity
    "N",   # pep8-naming
    "D",   # pydocstyle
    "UP",  # pyupgrade
    "ANN", # flake8-annotations
    "TCH", # flake8-type-checking
    "PYI", # flake8-pyi
]
fixable = ["ALL"]
ignore = [
    "D100",   # Missing docstring in public module
    "D101",   # Missing docstring in public class
    "D102",   # Missing docstring in public method
    "D104",   # Missing docstring in public package
    "D103",   # Missing docstring in public function
    "D106",   # Missing docstring in public nested class
    "ANN101", # Missing type annotation for self
    "ANN102", # Missing type annotation for cls
]

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
line-ending = "auto"
docstring-code-format = true

[tool.ruff.mccabe]
max-complexity = 10

[tool.ruff.pydocstyle]
convention = "google"

[tool.pycln]
all = true
expand-stars = true
no-gitignore = false
verbose = true

[tool.pyupgrade]
keep-runtime-typing = true
py39-plus = true
keep-dict-typing = true


[tool.pytest.ini_options]
python_files = ["tests.py", "test_*.py", "*_tests.py"]
testpaths = ["tests"]
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration (deselect with '-m \"not integration\"')",
]

[tool.mypy]
python_version = "3.12"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = false
no_implicit_optional = true
strict_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
allow_untyped_globals = false
allow_redefinition = false
local_partial_types = true
implicit_reexport = true
follow_imports = "silent"
ignore_missing_imports = true
pretty = true
show_column_numbers = true
show_error_codes = true
exclude = ["venv", ".venv"]

[tool.yamllint]
relaxed = true