Files
microsoft--graphrag/tests/verbs/test_update_text_embeddings.py
wehub-resource-sync 6b7e6b44f1
gh-pages / build (push) Waiting to run
Python Publish (pypi) / Upload release to PyPI (push) Waiting to run
Spellcheck / spellcheck (push) Waiting to run
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
chore: import upstream snapshot with attribution
2026-07-13 12:37:31 +08:00

66 lines
1.9 KiB
Python

# Copyright (C) 2026 Microsoft
# Licensed under the MIT License
"""Verb test for the update_text_embeddings workflow."""
from unittest.mock import patch
from graphrag.config.embeddings import all_embeddings
from graphrag.index.workflows.update_text_embeddings import (
run_workflow,
)
from tests.unit.config.utils import get_default_graphrag_config
from .util import create_test_context
async def test_update_text_embeddings():
"""Verify update_text_embeddings produces embedding tables.
Mocks get_update_table_providers to return the test context's
output_table_provider, simulating the merged tables written by
upstream update workflows.
"""
context = await create_test_context(
storage=[
"documents",
"relationships",
"text_units",
"entities",
"community_reports",
]
)
context.state["update_timestamp"] = "20260220-000000"
config = get_default_graphrag_config()
llm_settings = config.get_embedding_model_config(
config.embed_text.embedding_model_id
)
llm_settings.type = "mock"
llm_settings.mock_responses = [1.0] * 3072
config.embed_text.names = list(all_embeddings)
config.snapshots.embeddings = True
with patch(
"graphrag.index.workflows.update_text_embeddings.get_update_table_providers",
) as mock_providers:
mock_providers.return_value = (
context.output_table_provider,
None,
None,
)
await run_workflow(config, context)
parquet_files = context.output_storage.keys()
for field in all_embeddings:
assert f"embeddings.{field}.parquet" in parquet_files
entity_embeddings = await context.output_table_provider.read_dataframe(
"embeddings.entity_description"
)
assert len(entity_embeddings.columns) == 2
assert "id" in entity_embeddings.columns
assert "embedding" in entity_embeddings.columns