mirror of
https://github.com/microsoft/graphrag.git
synced 2025-06-26 23:19:58 +00:00
1df89727c3
* Move covariate run conditional * All pipeline registration * Fix method name construction * Rename context storage -> output_storage * Rename OutputConfig as generic StorageConfig * Reuse Storage model under InputConfig * Move input storage creation out of document loading * Move document loading into workflows * Semver * Fix smoke test config for new workflows * Fix unit tests --------- Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
49 lines
1.2 KiB
Python
49 lines
1.2 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.data_model.schemas import COMMUNITIES_FINAL_COLUMNS
|
|
from graphrag.index.workflows.create_communities import (
|
|
run_workflow,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
compare_outputs,
|
|
create_test_context,
|
|
load_test_table,
|
|
)
|
|
|
|
|
|
async def test_create_communities():
|
|
expected = load_test_table("communities")
|
|
|
|
context = await create_test_context(
|
|
storage=[
|
|
"entities",
|
|
"relationships",
|
|
],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
|
|
await run_workflow(
|
|
config,
|
|
context,
|
|
)
|
|
|
|
actual = await load_table_from_storage("communities", context.output_storage)
|
|
|
|
columns = list(expected.columns.values)
|
|
# don't compare period since it is created with the current date each time
|
|
columns.remove("period")
|
|
compare_outputs(
|
|
actual,
|
|
expected,
|
|
columns=columns,
|
|
)
|
|
|
|
for column in COMMUNITIES_FINAL_COLUMNS:
|
|
assert column in actual.columns
|