Files
microsoft--graphrag/tests/verbs/test_create_base_text_units.py
T
wehub-resource-sync 6b7e6b44f1
Python Build and Type Check / python-ci (ubuntu-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
gh-pages / build (push) Has been cancelled
Python Publish (pypi) / Upload release to PyPI (push) Has been cancelled
Spellcheck / spellcheck (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:31 +08:00

36 lines
870 B
Python

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License
from graphrag.index.workflows.create_base_text_units import run_workflow
from tests.unit.config.utils import get_default_graphrag_config
from .util import (
compare_outputs,
create_test_context,
load_test_table,
)
async def test_create_base_text_units():
expected = load_test_table("text_units")
context = await create_test_context()
config = get_default_graphrag_config()
config.chunking.prepend_metadata = ["title"]
await run_workflow(config, context)
actual = await context.output_table_provider.read_dataframe("text_units")
print("EXPECTED")
print(expected.columns)
print(expected)
print("ACTUAL")
print(actual.columns)
print(actual)
compare_outputs(actual, expected, columns=["text", "document_id", "n_tokens"])