mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-19 15:01:54 +00:00
c8c354e357
* Add source documents for verb tests * Remove entity_type erroneous column * Add new test data * Remove source/target degree columns * Remove top_level_node_id * Remove chunk column configs * Rename "chunk" to "text" * Rename "chunk" to "text" in base * Re-map document input to use base text units * Revert base text units as final documents dep * Update test data * Split/rename node source_id * Drop node size (dup of degree) * Drop document_ids from covariates * Remove unused document_ids from models * Remove n_tokens from covariate table * Fix missed document_ids delete * Wire base text units to final documents * Rename relationship rank as combined_degree * Add rank as first-class property to Relationship * Remove split_text operation * Fix relationships test parquet * Update test parquets * Add entity ids to community table * Remove stored graph embedding columns * Format * Semver * Fix JSON typo * Spelling * Rename lancedb * Sort lancedb * Fix unit test * Fix test to account for changing period * Update tests for separate embeddings * Format * Better assertion printing * Fix unit test for windows * Rename document.raw_content -> document.text * Remove read_documents function * Remove unused document summary from model * Remove unused imports * Format * Add new snapshots to default init * Use util to construct embeddings collection name * Align inc index model with branch changes * Update data and tests for int ids * Clean up embedding locs * Switch entity "name" to "title" for consistency * Fix short_id -> human_readable_id defaults * Format * Rework community IDs * Fix community size compute * Fix unit tests * Fix report read * Pare down nodes table output * Fix unit test * Fix merge * Fix community loading * Format * Fix community id report extraction * Update tests * Consistent short IDs and ordering * Update ordering and tests * Update incremental for new nodes model * Guard document columns loc * Match column ordering * Fix document guard * Update smoke tests * Fill NA on community extract * Logging for smoke test debug * Add parquet schema details doc * Fix community hierarchy guard * Use better empty hierarchy guard * Back-compat shims * Semver * Fix warning * Format * Remove default fallback * Reuse key
77 lines
2.0 KiB
Python
77 lines
2.0 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
from graphrag.index.run.utils import create_run_context
|
|
from graphrag.index.workflows.v1.create_final_documents import (
|
|
build_steps,
|
|
workflow_name,
|
|
)
|
|
|
|
from .util import (
|
|
compare_outputs,
|
|
get_config_for_workflow,
|
|
get_workflow_output,
|
|
load_expected,
|
|
load_input_tables,
|
|
)
|
|
|
|
|
|
async def test_create_final_documents():
|
|
input_tables = load_input_tables([
|
|
"workflow:create_base_text_units",
|
|
])
|
|
expected = load_expected(workflow_name)
|
|
|
|
context = create_run_context(None, None, None)
|
|
await context.runtime_storage.set(
|
|
"base_text_units", input_tables["workflow:create_base_text_units"]
|
|
)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
context=context,
|
|
)
|
|
|
|
compare_outputs(actual, expected)
|
|
|
|
|
|
async def test_create_final_documents_with_attribute_columns():
|
|
input_tables = load_input_tables(["workflow:create_base_text_units"])
|
|
expected = load_expected(workflow_name)
|
|
|
|
context = create_run_context(None, None, None)
|
|
await context.runtime_storage.set(
|
|
"base_text_units", input_tables["workflow:create_base_text_units"]
|
|
)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
config["document_attribute_columns"] = ["title"]
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
context=context,
|
|
)
|
|
|
|
# we should have dropped "title" and added "attributes"
|
|
# our test dataframe does not have attributes, so we'll assert without it
|
|
# and separately confirm it is in the output
|
|
compare_outputs(
|
|
actual, expected, columns=["id", "human_readable_id", "text", "text_unit_ids"]
|
|
)
|
|
assert len(actual.columns) == 5
|
|
assert "title" not in actual.columns
|
|
assert "attributes" in actual.columns
|