2024-09-25 15:50:46 -07:00
|
|
|
# Copyright (c) 2024 Microsoft Corporation.
|
|
|
|
# Licensed under the MIT License
|
|
|
|
|
2024-11-13 15:11:19 -08:00
|
|
|
from graphrag.index.run.utils import create_run_context
|
2024-09-25 15:50:46 -07:00
|
|
|
from graphrag.index.workflows.v1.create_final_documents import (
|
|
|
|
build_steps,
|
|
|
|
workflow_name,
|
|
|
|
)
|
|
|
|
|
|
|
|
from .util import (
|
|
|
|
compare_outputs,
|
|
|
|
get_config_for_workflow,
|
|
|
|
get_workflow_output,
|
|
|
|
load_input_tables,
|
2024-12-05 09:57:26 -08:00
|
|
|
load_test_table,
|
2024-09-25 15:50:46 -07:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
async def test_create_final_documents():
|
|
|
|
input_tables = load_input_tables([
|
2024-11-13 15:11:19 -08:00
|
|
|
"workflow:create_base_text_units",
|
2024-09-25 15:50:46 -07:00
|
|
|
])
|
2024-12-05 09:57:26 -08:00
|
|
|
expected = load_test_table(workflow_name)
|
2024-09-25 15:50:46 -07:00
|
|
|
|
2024-11-13 15:11:19 -08:00
|
|
|
context = create_run_context(None, None, None)
|
|
|
|
await context.runtime_storage.set(
|
|
|
|
"base_text_units", input_tables["workflow:create_base_text_units"]
|
|
|
|
)
|
|
|
|
|
2024-09-25 15:50:46 -07:00
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
|
2024-10-02 08:57:08 -07:00
|
|
|
steps = build_steps(config)
|
2024-09-25 15:50:46 -07:00
|
|
|
|
|
|
|
actual = await get_workflow_output(
|
|
|
|
input_tables,
|
|
|
|
{
|
|
|
|
"steps": steps,
|
|
|
|
},
|
2024-11-13 15:11:19 -08:00
|
|
|
context=context,
|
2024-09-25 15:50:46 -07:00
|
|
|
)
|
|
|
|
|
|
|
|
compare_outputs(actual, expected)
|
|
|
|
|
|
|
|
|
2024-10-15 12:58:58 -07:00
|
|
|
async def test_create_final_documents_with_attribute_columns():
|
2024-11-13 15:11:19 -08:00
|
|
|
input_tables = load_input_tables(["workflow:create_base_text_units"])
|
2024-12-05 09:57:26 -08:00
|
|
|
expected = load_test_table(workflow_name)
|
2024-10-15 12:58:58 -07:00
|
|
|
|
2024-11-13 15:11:19 -08:00
|
|
|
context = create_run_context(None, None, None)
|
|
|
|
await context.runtime_storage.set(
|
|
|
|
"base_text_units", input_tables["workflow:create_base_text_units"]
|
|
|
|
)
|
|
|
|
|
2024-10-15 12:58:58 -07:00
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
|
|
|
|
config["document_attribute_columns"] = ["title"]
|
|
|
|
|
|
|
|
steps = build_steps(config)
|
|
|
|
|
|
|
|
actual = await get_workflow_output(
|
|
|
|
input_tables,
|
|
|
|
{
|
|
|
|
"steps": steps,
|
|
|
|
},
|
2024-11-13 15:11:19 -08:00
|
|
|
context=context,
|
2024-10-15 12:58:58 -07:00
|
|
|
)
|
|
|
|
|
|
|
|
# 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
|
2024-11-13 15:11:19 -08:00
|
|
|
compare_outputs(
|
|
|
|
actual, expected, columns=["id", "human_readable_id", "text", "text_unit_ids"]
|
|
|
|
)
|
|
|
|
assert len(actual.columns) == 5
|
|
|
|
assert "title" not in actual.columns
|
2024-10-15 12:58:58 -07:00
|
|
|
assert "attributes" in actual.columns
|