mirror of
https://github.com/microsoft/graphrag.git
synced 2025-06-26 23:19:58 +00:00

* 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
32 lines
895 B
Python
32 lines
895 B
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.config.create_graphrag_config import create_graphrag_config
|
|
from graphrag.config.models.prune_graph_config import PruneGraphConfig
|
|
from graphrag.index.workflows.prune_graph import (
|
|
run_workflow,
|
|
)
|
|
from graphrag.utils.storage import load_table_from_storage
|
|
|
|
from .util import (
|
|
DEFAULT_MODEL_CONFIG,
|
|
create_test_context,
|
|
)
|
|
|
|
|
|
async def test_prune_graph():
|
|
context = await create_test_context(
|
|
storage=["entities", "relationships"],
|
|
)
|
|
|
|
config = create_graphrag_config({"models": DEFAULT_MODEL_CONFIG})
|
|
config.prune_graph = PruneGraphConfig(
|
|
min_node_freq=4, min_node_degree=0, min_edge_weight_pct=0
|
|
)
|
|
|
|
await run_workflow(config, context)
|
|
|
|
nodes_actual = await load_table_from_storage("entities", context.storage)
|
|
|
|
assert len(nodes_actual) == 21
|