pyproject.toml

[tool.poetry]
name = "intelligence-toolkit"
version = "0.0.2"
description = "Interactive workflows for generating AI intelligence reports from real-world data sources using GPT models"
authors = [
    "Dayenne Souza <ddesouza@microsoft.com>",
    "Ha Trinh <trinhha@microsoft.com>",
    "Darren Edge <daedge@microsoft.com>"
    ]
readme = "DEVELOPING.md"
license = "MIT"
keywords = ["AI", "data analysis", "reports", "workflows"]  

[project.urls]
source = "https://github.com/microsoft/intelligence-toolkit"
issues = "https://github.com/microsoft/intelligence-toolkit/issues"


[tool.poetry.dependencies]
python = ">=3.11,<3.13"
altair = "4.2.2"
networkx = "3.3"
numpy = "1.26.4"
openai = "^1.37.1"
pac-synth = "0.0.8"
pdfplumber = "0.11.2"
plotly = "5.22.0"
plotly-express = "0.4.1"
polars = "0.20.10"
pyarrow = "15.0.0"
pydantic = "2.8.2"
pydantic_core = "2.20.1"
scikit-learn = "1.5.1"
scipy = "1.12.0"
streamlit = "1.31.1"
streamlit-aggrid = "0.3.4.post3"
streamlit-javascript = "0.1.5"
streamlit-agraph = "0.0.45"
tiktoken =    {version = "0.7.0", extras = ["azure"]}
pdfkit = "1.0.0"
markdown2 = "2.5.0"
azure-identity = "1.17.1"
azure-core = "1.30.2"
semchunk = "2.2.0"
lancedb = "0.12.0"
duckdb = "1.0.0"
seaborn = "0.13.2"
textblob = "0.18.0.post0"
jsonschema = "^4.23.0"
nest-asyncio = "^1.6.0"
altair-viewer = "^0.4.0"
poetry = "^1.8.3"
poethepoet = "^0.27.0"
torch = [
    {version = "2.4.1", source = "pytorch_cpu", markers = "sys_platform != 'darwin'"},
    {version = "2.5.1", markers = "sys_platform == 'darwin'"}
]
sentence-transformers = "^3.1.1"
graspologic = "^3.4.1"
future = "^1.0.0"

[tool.poetry.group.dev.dependencies]
newspaper3k = "^0.2.8"
coverage = "^7.6.0"
ruff = "^0.4.7"
pyright = "^1.1.371"
ipykernel = "^6.29.5"
pytest-cov = "^5.0.0"
pytest = "^8.2.2"
pytest-asyncio = "^0.23.7"
pytest-mock = "^3.14.0"
faker = "^28.0.0"
nbformat = "^5.10.4"
setuptools = "^75.3.0"
wheel = "^0.44.0"
twine = "^5.1.1"


[[tool.poetry.source]]
name = "pytorch_cpu"
url = "https://download.pytorch.org/whl/cpu"
priority = "explicit"


[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.poe.tasks]
_sort_imports = "ruff check --select I --fix . --preview"
_format_code = "ruff format  . --preview"
_ruff_check = 'ruff check . --preview'
_pyright = "pyright"
check_format = 'ruff format . --check --preview'
fix = "ruff  --preview check --fix ."
fix_unsafe = "ruff check --preview --fix --unsafe-fixes ."
test_unit = "pytest ./intelligence_toolkit/tests/unit"
test_smoke = "pytest ./intelligence_toolkit/tests/smoke"

run_streamlit = "python -m streamlit run app/Home.py ${ARGS}"  

[[tool.poe.tasks.format]]
sequence = ['_sort_imports', '_format_code']
ignore_fail = 'return_non_zero'

[[tool.poe.tasks.check]]
sequence = ['check_format', '_ruff_check']
ignore_fail = 'return_non_zero'

[tool.ruff]
target-version = "py310"
extend-include = ["*.ipynb"]

[tool.ruff.format]
docstring-code-format = true
docstring-code-line-length = 20

[tool.ruff.lint]
select = [
    "E4",
    "E7",
    "E9",
    "W291",
    "YTT",
    "T10",
    "ICN",
    "INP",
    "Q",
    "RSE",
    "SLOT",
    "INT",
    "FLY",
    "LOG",
    "C90",
    "T20",
    "RET",
    "PD",
    "N",
    "PIE",
    "SIM",
    "S",
    "G",
    "ERA",
    "ASYNC",
    "TID",
    "UP",
    "SLF",
    "BLE",
    "C4",
    "I",
    "F",
    "A",
    "ARG",
    "RUF",
    "B",
    "TCH",
    "DTZ",
    "PYI",
    "PT",
    "EM",
    "TRY",
    "PERF",
    "CPY",
    # "PTH", # Initial run, disabled for too much noise
    # "D", # Initial run, disabled for too much noise
    # "FBT", # use named arguments for boolean flags
    # "TD", # todos
    # "FIX", # fixme
    # "FURB" # preview rules
    # ANN # Type annotations, re-enable when we get bandwidth
]
ignore = [
    # Deprecated Rules
    "ANN101",
    "ANN102",
    # Conflicts with interface argument checking
    "ARG002",
    "ANN204",
    # TODO: Inspect these pandas rules for validity
    "PD002", # prevents inplace=True
    # TODO RE-Enable when we get bandwidth
    "PERF203", # Needs restructuring of errors, we should bail-out on first error
    "C901",    # needs refactoring to remove cyclomatic complexity
    "S311",    # random alert for use with cryptography. NA
    # Initial run, disabled for too much noise
    "T201", 
    "S404",
    "S603",
    "N806",
]

[tool.ruff.lint.per-file-ignores]
"intelligence_toolkit/tests/*" = ["S", "D", "ANN", "T201", "ASYNC", "ARG", "PTH", "TRY"]
# "examples/*" = ["S", "D", "ANN", "T201", "PTH", "TRY", "PERF"]
"*.ipynb" = ["S", "T201", "I001"]

[tool.ruff.lint.flake8-builtins]
builtins-ignorelist = ["input", "id", "bytes"]

[tool.ruff.lint.flake8-pytest-style]
fixture-parentheses = true

[tool.ruff.lint.pydocstyle]
convention = "numpy"

# https://github.com/microsoft/pyright/blob/9f81564a4685ff5c55edd3959f9b39030f590b2f/docs/configuration.md#sample-pyprojecttoml-file
[tool.pyright]
include = ["app", "intelligence_toolkit", "example_notebooks"]
typeCheckingMode = "off"


[virtualenvs]
in-project = true