Katon Minhas
86db2ea0b7
Bugfix/table error fix * handle multipage table data correctly * same metadata for all tables on the page * Multiple tables on page, non-continuous, split * Add back align_and_format_tables * update unit tests * Merged main into bugfix/table-error-fix * improved align and format table prompt * Successful E2E test on San Joaquin - without running align and format table prompt * San Joaquin e2e test passed * Merged main into bugfix/table-error-fix * Merge branch 'main' into bugfix/table-error-fix * Add same number of columns condition * Merged main into bugfix/table-error-fix * Clean investment_values * Remove import * docstrings * Remove test doc * Add back original ALIGN_AND_FORMAT_TABLES prompt for client work * Remove import * Add config reference * Merged main into bugfix/table-error-fix * Move table_utils to investment.table_funcs * restore table_utils.py * Update tests * update preprocess Approved-by: Alex Galarce
Field Extraction
Running the Code
This project uses Python's module system for imports. To run the code properly:
-
DO NOT run files directly like this:
python src/client/main.py # ❌ This won't work -
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
-mflag - 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 .