VenkataKrishna Reddy Avula
0d6bdf9539
DRAFT: Bugfix/effective date fix * Merged in bugfix/extra-fields (pull request #500) Do not run Exhibit level prompt if there are no exhibit level fields * Do not run Exhibit level prompt if there are no exhibit level fields * Update dynamic test * Remove test from one-to-n test module * Update test * Fix unit test Approved-by: Alex Galarce * Merged in bugfix/tin-npi-prompt-fixes (pull request #499) Bugfix/tin npi prompt fixes * Change delimiter for other provider information from comma to pipe * filter out invalid providers * Update extraction and formatting instructions for provider entities in TIN_NPI_TEMPLATE * Merged main into bugfix/tin-npi-small-bugfixes * Refactor deduplication logic to use string_utils for checking empty provider fields * Merge branch 'bugfix/tin-npi-small-bugfixes' of https://bitbucket.org/aarete/doczy.ai into bugfix/tin-npi-small-bugfixes * Update deduplication logic to exclude providers with 'UNKNOWN' TIN, NPI, or NAME * Merge remote-tracking branch 'origin/main' into bugfix/tin-npi-small-bugfixes * Fix deduplication logic to not drop subsequent names * Fix formatting of provider names in deduplication logic * add payer name filtering * reorder execution order to allow to find payer_name first * Add handling for previously unfound group providers in identify_group_provider function * Merge remote-trackin… * Merged in feature/update-testbed-script (pull request #501) Feature/update testbed script * Update preprocessing * Update preprocessing * remove quit * Update date for filename * Merged main into feature/update-testbed-script Approved-by: Alex Galarce * Merged in bugfix/smart-chunks (pull request #503) missing of text in chunks fixed * missing of text in chunks fixed Approved-by: Katon Minhas * Merged in feature/rework-reimb-tin-npi (pull request #502) Feature/rework reimb tin npi * use LLM for reimb_[tin/npi/name] * Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi * Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi * deduplicate tin/name/npi before adding to prompt * Pull out prompt and llm_response in methodology_breakout_single_row for easier debugging * Refactor reimbursement_tin_npi to handle multiple providers and update valid TIN, NPI, and NAME fields accordingly * Reorder REIMB_PROV_NAME field in investment_prompts.json * Update REIMB_PROV_NAME prompt to specify valid values for provider names * Remove valid_values constraint from prov_name to raise accuracy * Remove debugging print statements from reimbursement_tin_npi and related functions * Remove debugging print statements from run_provider_info_fields function * Merge remote-tracking branch 'origin/main' into feature/rework-reimb-tin-npi * Remove debugging print statem… * Merged in feature/preformat-single-quotes-input (pull request #506) Replace double quotes with single quotes in context strings for parsability * Replace double quotes with single quotes in context strings for parsability * Merged main into feature/preformat-single-quotes-input Approved-by: Katon Minhas * updated sig pages fnxn * Merge branch 'main' into bugfix/effective_date_fix * poetry add pymupdf * created vision funcs * Merged main into bugfix/effective_date_fix * fixed pipeline issue * updated string_utils_test * updated test values * updated extract signature page fxn * updated test values * updated test values * Merged main into bugfix/effective_date_fix * Prompt template in all-caps * remove debugging prints * Merged main into bugfix/effective_date_fix * Change vision to False by default * Change vision to False by default * fix tests * fix tests Approved-by: Katon Minhas
63 lines
1.3 KiB
TOML
63 lines
1.3 KiB
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"
|
|
pytest-mock = "^3.14.0"
|
|
langchain = "^0.3.14"
|
|
langchainhub = "^0.1.21"
|
|
langchain-chroma = "^0.2.0"
|
|
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"
|
|
|
|
[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"
|
|
]
|