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>
60 lines
1.7 KiB
Python
60 lines
1.7 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 DOCUMENTS_FINAL_COLUMNS
|
|
from graphrag.index.workflows.create_final_documents 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,
|
|
update_document_metadata,
|
|
)
|
|
|
|
|
|
async def test_create_final_documents():
|
|
expected = load_test_table("documents")
|
|
|
|
context = await create_test_context(
|
|
storage=["text_units"],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
|
|
await run_workflow(config, context)
|
|
|
|
actual = await load_table_from_storage("documents", context.output_storage)
|
|
|
|
compare_outputs(actual, expected)
|
|
|
|
for column in DOCUMENTS_FINAL_COLUMNS:
|
|
assert column in actual.columns
|
|
|
|
|
|
async def test_create_final_documents_with_metadata_column():
|
|
context = await create_test_context(
|
|
storage=["text_units"],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
config.input.metadata = ["title"]
|
|
|
|
# simulate the metadata construction during initial input loading
|
|
await update_document_metadata(config.input.metadata, context)
|
|
|
|
expected = await load_table_from_storage("documents", context.output_storage)
|
|
|
|
await run_workflow(config, context)
|
|
|
|
actual = await load_table_from_storage("documents", context.output_storage)
|
|
|
|
compare_outputs(actual, expected)
|
|
|
|
for column in DOCUMENTS_FINAL_COLUMNS:
|
|
assert column in actual.columns
|