Files
doczyai-pipelines/fieldExtraction
Alex Galarce d4ba73dca5 Merged in feature/claude4-duplicate-and-missing-rows (pull request #636)
Feature/claude4 duplicate and missing rows

* Enhance crosswalk functionality with flatten_to_strings helper and improve value handling in apply_crosswalk

* Improve apply_crosswalk function to return original value as fallback when no mapping is found

* Enhance apply_crosswalk function to handle empty values and improve defensive programming tests

* Enhance reimbursement method prompt to include charge master limitations and improve mapping rules

* Merge remote-tracking branch 'origin/main' into feature/claude4-duplicate-and-missing-rows

* Refine CHECK_REDUNDANT_LESSER prompt for clarity and detail in evaluating redundancy of exhibit constraints

* Enable logging of LLM response for redundancy check in is_exhibit_lesser_of_redundant function

* Merge remote-tracking branch 'origin/main' into feature/claude4-duplicate-and-missing-rows

* rework prompt for exhibit-wide lesser of

* Refine reimbursement methodology guidelines by clarifying invalid entries and examples for risk-sharing

* Enhance exhibit linking logic to treat pages with substantial tables as separate exhibits and update function signature to include text_dict.


Approved-by: Katon Minhas
2025-07-29 21:26:00 +00:00
..

Field Extraction

Running the Code

This project uses Python's module system for imports. To run the code properly:

  1. DO NOT run files directly like this:

    python src/client/main.py  # ❌ This won't work
    
  2. INSTEAD, use Python's module flag (-m) from the project root:

    python -m src.client.main  # ✅ This is correct
    

Why?

The code uses absolute imports (e.g., from src.utils import llm_utils) to maintain a clear and consistent package structure. Running with python -m ensures Python can properly resolve these imports.

Development

  • All imports should use the src. prefix (e.g., from src.utils import llm_utils)
  • Always run code from the project root directory using the -m flag
  • Tests are configured to handle these imports automatically via pytest settings in pyproject.toml

Configuration

The project uses poetry for dependency management and pytest for testing. Key configurations in pyproject.toml:

[tool.pytest.ini_options]
pythonpath=["."]
testpaths = [
    "tests"
]

Dependencies

To install dependencies:

poetry install

To run tests:

poetry run pytest

To run type checking:

poetry run mypy .