a5c743f37f
Feature/chc client * Add CHC client pipeline with Claims Coding/Editing Determinations extraction - Add CHC client to pipelines with regex-based extraction - Create extraction/claims_coding_funcs.py for section extraction - Add chc_prompts.json with non_prompt field type - Add CHC_PROMPTS_PATH to config - Add tests for extraction function (11 test cases) * Add black[jupyter] for code formatting * Format testing notebook with black * Remove unused prompt field from chc_prompts.json * Merged main into feature/chc-client Approved-by: Katon Minhas
61 lines
1.4 KiB
TOML
61 lines
1.4 KiB
TOML
[project]
|
|
name = "doczy-field-extraction"
|
|
version = "0.1.0"
|
|
description = "Contract field extraction using LLMs"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"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",
|
|
"langchain>=0.3.14",
|
|
"langchainhub>=0.1.21",
|
|
"langchain-aws>=0.2.11",
|
|
"langchain-text-splitters>=0.3.5",
|
|
"langchain-community>=0.3.15",
|
|
"nltk>=3.9.1",
|
|
"rank-bm25>=0.2.2",
|
|
"sentence-transformers>=3.4.1",
|
|
"faiss-cpu>=1.10.0",
|
|
"word2number>=1.1",
|
|
"orjson>=3.10.16",
|
|
"pymupdf>=1.25.5",
|
|
"pillow>=11.2.1",
|
|
"xlsxwriter>=3.2.9",
|
|
"langchain-classic>=1.0.1",
|
|
"black[jupyter]>=25.12.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"black>=24.10.0",
|
|
"mypy>=1.12.0",
|
|
"jupyter>=1.1.1",
|
|
"isort>=5.13.2",
|
|
"pytest>=8.3.3",
|
|
"pytest-mock>=3.14.0",
|
|
]
|
|
test = [
|
|
"pytest>=8.3.3",
|
|
"pytest-mock>=3.14.0",
|
|
"pytest-cov>=6.0.0",
|
|
]
|
|
|
|
[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","return-value"]
|
|
exclude = ["scripts/"]
|
|
explicit_package_bases = true
|
|
|
|
[tool.pytest.ini_options]
|
|
pythonpath = ["."]
|
|
testpaths = ["src/tests"]
|