mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-28 11:23:44 +00:00
f5c5876dde
* Extract base docs and entity graph * Move extracted entities and text units * Move communities and community reports * Move covariates and final documents * Move entities, nodes, relationships * Move text_units and summarized entities * Assert all snapshot null cases * Remove disabled steps util * Remove incorrect use of input "others" * Convert text_embed_df to just return the embeddings, not update the df * Convert snapshot functions to noops * Semver * Remove lingering covariates_enabled param * Name consistency * Syntax cleanup
79 lines
2.0 KiB
Python
79 lines
2.0 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
import networkx as nx
|
|
|
|
from graphrag.index.storage.memory_pipeline_storage import MemoryPipelineStorage
|
|
from graphrag.index.workflows.v1.create_base_extracted_entities import (
|
|
build_steps,
|
|
workflow_name,
|
|
)
|
|
|
|
from .util import (
|
|
get_config_for_workflow,
|
|
get_workflow_output,
|
|
load_expected,
|
|
load_input_tables,
|
|
)
|
|
|
|
|
|
async def test_create_base_extracted_entities():
|
|
input_tables = load_input_tables(["workflow:create_base_text_units"])
|
|
expected = load_expected(workflow_name)
|
|
|
|
storage = MemoryPipelineStorage()
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
del config["entity_extract"]["strategy"]["llm"]
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
storage=storage,
|
|
)
|
|
|
|
# let's parse a sample of the raw graphml
|
|
actual_graphml_0 = actual["entity_graph"][:1][0]
|
|
actual_graph_0 = nx.parse_graphml(actual_graphml_0)
|
|
|
|
assert actual_graph_0.number_of_nodes() == 3
|
|
assert actual_graph_0.number_of_edges() == 2
|
|
|
|
assert actual.columns == expected.columns
|
|
|
|
assert len(storage.keys()) == 0, "Storage should be empty"
|
|
|
|
|
|
async def test_create_base_extracted_entities_with_snapshots():
|
|
input_tables = load_input_tables(["workflow:create_base_text_units"])
|
|
expected = load_expected(workflow_name)
|
|
|
|
storage = MemoryPipelineStorage()
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
del config["entity_extract"]["strategy"]["llm"]
|
|
config["raw_entity_snapshot"] = True
|
|
config["graphml_snapshot"] = True
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
storage=storage,
|
|
)
|
|
|
|
print(storage.keys())
|
|
|
|
assert actual.columns == expected.columns
|
|
|
|
assert storage.keys() == ["raw_extracted_entities.json", "merged_graph.graphml"]
|