mirror of
https://github.com/microsoft/graphrag.git
synced 2025-06-26 23:19:58 +00:00
bd06d8b4f0
* Add pipeline state property bag to run context * Move state creation out of context util * Move callbacks into PipelineRunContext * Semver * Rename state.json to context.json to avoid confusion with stats.json * Expand smoke test row count * Add util to create storage and cache
34 lines
1.0 KiB
Python
34 lines
1.0 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.index.workflows.extract_graph_nlp import (
|
|
run_workflow,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
create_test_context,
|
|
)
|
|
|
|
|
|
async def test_extract_graph_nlp():
|
|
context = await create_test_context(
|
|
storage=["text_units"],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
|
|
await run_workflow(config, context)
|
|
|
|
nodes_actual = await load_table_from_storage("entities", context.storage)
|
|
edges_actual = await load_table_from_storage("relationships", context.storage)
|
|
|
|
# this will be the raw count of entities and edges with no pruning
|
|
# with NLP it is deterministic, so we can assert exact row counts
|
|
assert len(nodes_actual) == 1148
|
|
assert len(nodes_actual.columns) == 5
|
|
assert len(edges_actual) == 29445
|
|
assert len(edges_actual.columns) == 5
|