Katon Minhas
afb6d5185d
Feature/lesser table caching refactor hybrid * chore: Remove unused duplicate main.py from shared pipeline * fix: Correct crosswalk paths in aarete_derived.py * chore: Remove unused documentation files from fieldExtraction * docs: Add documentation files to documentation folder * docs: Update README with uv setup, expanded project structure, and branching conventions * docs: Add uv installation steps with Ubuntu/WSL emphasis * Enable prompt caching for all remaining LLM calls - Add _INSTRUCTION() functions for: EXHIBIT_HEADER, EXHIBIT_LINKAGE, EXHIBIT_TITLE_MATCH, DATE_FIX, DERIVED_TERM_DATE, CHECK_PROVIDER_NAME_MATCH, SPECIAL_CASE_ASSIGNMENT - Update all invoke_claude() calls in saas and clover pipelines to use cache=True with corresponding _INSTRUCTION() functions - Add new instructions to get_cacheable_instructions() for cache warming - Update tests for new instruction functions Functions now using caching: - prompt_exhibit_level - prompt_exhibit_lesser (EXHIBIT_LEVEL_LESSER_OF) - prompt_fee_schedule_breakout - prompt_grouper_breakout - prompt_special_case_assignment - prompt_exhibit_linkage - prompt_exhibit_header - prompt_smart_chunked (ONE_TO_ONE templates) - prompt_date_fix - prompt_derived_term_date - prompt_exhibit_title_match - provider_name_match_check 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Reorder * feat: Add bcbs_promise client pipeline with OFFSET_TERM extraction - Add new bcbs_promise client with HSC-based OFFSET_TERM field extraction - Extract full paragraph text of offset/recoupment provisions from contracts - Derive OFFSET_INDICATOR (Y/N) from OFFSET_TERM presence - Fix reorder_columns to preserve extra columns not in COLUMN_ORDER - Update QC/QA output path to outputs/qc_qa/ * fix: Update dev deps and test assertions for QC/QA output path - Add pytest/pytest-mock to dev dependencies for mypy type checking - Update test assertions to expect outputs/qc_qa instead of qa_qc_output * style: Apply black formatting to prompt_templates.py * Merge main, move scripts * Archive some scripts * update py version * remove .py version file * Remove ASCII characters * Restore testbed code * restore tracking * Update testbed metrics * Enable prompt caching for CODE_LAST_CHECK, FILL_BILL_TYPE, DUAL_LOB_CHECK, and GROUPER_BREAKOUT - Add CODE_LAST_CHECK_INSTRUCTION() for service specificity classification - Add FILL_BILL_TYPE_INSTRUCTION() for bill type code determination - Add DUAL_LOB_CHECK_INSTRUCTION() for Medicare/Medicaid classification - Update code_funcs.py to use caching for CODE_LAST_CHECK, FILL_BILL_TYPE, GROUPER_BREAKOUT - Update postprocessing_funcs.py to use caching for DUAL_LOB_CHECK - Add new instructions to get_cacheable_instructions() for cache warming - Add unit tests for new instruction functions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * Fix postprocessing_funcs to remove invalid columns * Merge branch 'main' into feature/lesser-table-caching-refactor-hybrid * Revert prompt caching changes from aed1b73c * update formatting * Update imports Approved-by: Sha Brown Approved-by: Praneel Panchigar
60 lines
1.3 KiB
TOML
60 lines
1.3 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",
|
|
]
|
|
|
|
[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"]
|