mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-03 07:04:19 +00:00
7ec9ef0261
* Unify Workflow and Verb callbacks interfaces * Semver * Fix storage class instantiation (#1582) --------- Co-authored-by: Josh Bradley <joshbradley@microsoft.com>
66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.callbacks.noop_workflow_callbacks import NoopWorkflowCallbacks
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.config.enums import TextEmbeddingTarget
|
|
from graphrag.index.config.embeddings import (
|
|
all_embeddings,
|
|
)
|
|
from graphrag.index.workflows.generate_text_embeddings import (
|
|
run_workflow,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
create_test_context,
|
|
)
|
|
|
|
|
|
async def test_generate_text_embeddings():
|
|
context = await create_test_context(
|
|
storage=[
|
|
"create_final_documents",
|
|
"create_final_relationships",
|
|
"create_final_text_units",
|
|
"create_final_entities",
|
|
"create_final_community_reports",
|
|
]
|
|
)
|
|
|
|
config = create_graphrag_config()
|
|
config.embeddings.strategy = {
|
|
"type": "mock",
|
|
}
|
|
config.embeddings.target = TextEmbeddingTarget.all
|
|
config.snapshots.embeddings = True
|
|
|
|
await run_workflow(
|
|
config,
|
|
context,
|
|
NoopWorkflowCallbacks(),
|
|
)
|
|
|
|
parquet_files = context.storage.keys()
|
|
|
|
for field in all_embeddings:
|
|
assert f"embeddings.{field}.parquet" in parquet_files
|
|
|
|
# entity description should always be here, let's assert its format
|
|
entity_description_embeddings = await load_table_from_storage(
|
|
"embeddings.entity.description", context.storage
|
|
)
|
|
|
|
assert len(entity_description_embeddings.columns) == 2
|
|
assert "id" in entity_description_embeddings.columns
|
|
assert "embedding" in entity_description_embeddings.columns
|
|
|
|
# every other embedding is optional but we've turned them all on, so check a random one
|
|
document_text_embeddings = await load_table_from_storage(
|
|
"embeddings.document.text", context.storage
|
|
)
|
|
|
|
assert len(document_text_embeddings.columns) == 2
|
|
assert "id" in document_text_embeddings.columns
|
|
assert "embedding" in document_text_embeddings.columns
|