Alex Galarce
d345dd0ed3
Feature/integrate standard and complex * last edits to merge_tables_draft_v2 before moving to table_funcs * migrate to table_utils.py * fix typehint that caused mypy error * fix mypy errors * black and isort * fix error with multi-table pages * update poetry.lock * add tests, fix bug when table start marker or table end marker is missing * added more tests * tests for get_str_dictionaries_from_text() * fix edge case in get_str_dictionaries_from_text * fix mypy error * more tests * add tests, add handling for invalid dictionaries * add tests * add tests for insert_column_headers() * update requirements * add new simple/complex logic to preprocess.py * remove files used solely for testing * split pages into sub-pages by tables * add table split on end marker. Also add tests * add docstrings, change control flow * remove unused tests, add TODO for new tests * get in prompt changes and intermediate decisions * TODO for future enhancement for get_exhibit_pages Approved-by: Katon Minhas
48 lines
964 B
TOML
48 lines
964 B
TOML
[tool.poetry]
|
|
name = "doczy-smart-chunking"
|
|
version = "0.1.0"
|
|
description = ""
|
|
authors = ["Alex Galarce <agalarce@aarete.com>"]
|
|
readme = "README.md"
|
|
package-mode = false
|
|
|
|
[tool.poetry.dependencies]
|
|
python = "^3.12"
|
|
pandas = "^2.2.3"
|
|
boto3 = "^1.35.40"
|
|
anthropic = "^0.36.0"
|
|
python-dotenv = "^1.0.1"
|
|
psutil = "^6.1.0"
|
|
rapidfuzz = "^3.10.1"
|
|
pyxlsb = "^1.0.10"
|
|
openpyxl = "^3.1.5"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = "^24.10.0"
|
|
mypy = "^1.12.0"
|
|
jupyter = "^1.1.1"
|
|
isort = "^5.13.2"
|
|
|
|
[tool.poetry.group.test.dependencies]
|
|
pytest = "^8.3.3"
|
|
pytest-mock = "^3.14.0"
|
|
pytest-cov = "^6.0.0"
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.black]
|
|
line-length = 88
|
|
target-version = ['py312']
|
|
|
|
[tool.mypy]
|
|
disable_error_code = ["import-untyped","assignment","name-defined","call-arg","var-annotated","attr-defined","arg-type"]
|
|
exclude = ["scripts/"]
|
|
|
|
[tool.pytest.ini_options]
|
|
pythonpath=["."]
|
|
testpaths = [
|
|
"tests"
|
|
]
|