graphrag/tests/verbs/test_create_final_documents.py
Nathan Evans a35cb12741
Remove datashaper strip code (#1581)
Remove datashaper
2025-01-03 13:59:26 -08:00

66 lines
1.7 KiB
Python

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License
from graphrag.callbacks.noop_verb_callbacks import NoopVerbCallbacks
from graphrag.config.create_graphrag_config import create_graphrag_config
from graphrag.index.workflows.create_final_documents import (
run_workflow,
workflow_name,
)
from graphrag.utils.storage import load_table_from_storage
from .util import (
compare_outputs,
create_test_context,
load_test_table,
)
async def test_create_final_documents():
expected = load_test_table(workflow_name)
context = await create_test_context(
storage=["create_base_text_units"],
)
config = create_graphrag_config()
await run_workflow(
config,
context,
NoopVerbCallbacks(),
)
actual = await load_table_from_storage(workflow_name, context.storage)
compare_outputs(actual, expected)
async def test_create_final_documents_with_attribute_columns():
expected = load_test_table(workflow_name)
context = await create_test_context(
storage=["create_base_text_units"],
)
config = create_graphrag_config()
config.input.document_attribute_columns = ["title"]
await run_workflow(
config,
context,
NoopVerbCallbacks(),
)
actual = await load_table_from_storage(workflow_name, context.storage)
# we should have dropped "title" and added "attributes"
# our test dataframe does not have attributes, so we'll assert without it
# and separately confirm it is in the output
compare_outputs(
actual, expected, columns=["id", "human_readable_id", "text", "text_unit_ids"]
)
assert len(actual.columns) == 5
assert "title" not in actual.columns
assert "attributes" in actual.columns