mirror of
https://github.com/microsoft/graphrag.git
synced 2025-07-25 18:01:14 +00:00
61b3d6d56a
* Remove genid * Move snapshot_rows * Move snapshot * Delete spread_json * Delete unzip * Delete zip * Move unpack_graph * Move compute_edge_combined_degree * Delete create_graph * Delete concat * Delete text replace * Delete text_translate * Move text_split * Inline aggregate override * Move cluster_graph * Move merge_graphs * Semver * Move text_chunk * Move layout_graph and fix some __init__s * Move extract_covariates * Rename text_split -> split_text * Move extract_entities * Move summarize_descriptions * Rename text_chunk -> chunk_text * Move community report creation * Remove verb-level packing operators * Streamline some naming * Streamline param name/order * Move mock LLM data to tests * Fixed missed rename * Update some strategy refs * Rename run_gi * Inject mock responses into integ test config
134 lines
3.9 KiB
Python
134 lines
3.9 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
import json
|
|
|
|
import pytest
|
|
from datashaper.errors import VerbParallelizationError
|
|
|
|
from graphrag.config.enums import LLMType
|
|
from graphrag.index.workflows.v1.create_final_community_reports import (
|
|
build_steps,
|
|
workflow_name,
|
|
)
|
|
|
|
from .util import (
|
|
compare_outputs,
|
|
get_config_for_workflow,
|
|
get_workflow_output,
|
|
load_expected,
|
|
load_input_tables,
|
|
)
|
|
|
|
MOCK_RESPONSES = [
|
|
json.dumps({
|
|
"title": "<report_title>",
|
|
"summary": "<executive_summary>",
|
|
"rating": 2,
|
|
"rating_explanation": "<rating_explanation>",
|
|
"findings": [
|
|
{
|
|
"summary": "<insight_1_summary>",
|
|
"explanation": "<insight_1_explanation",
|
|
},
|
|
{
|
|
"summary": "<insight_2_summary>",
|
|
"explanation": "<insight_2_explanation",
|
|
},
|
|
],
|
|
})
|
|
]
|
|
|
|
MOCK_LLM_CONFIG = {"type": LLMType.StaticResponse, "responses": MOCK_RESPONSES}
|
|
|
|
|
|
async def test_create_final_community_reports():
|
|
input_tables = load_input_tables([
|
|
"workflow:create_final_nodes",
|
|
"workflow:create_final_covariates",
|
|
"workflow:create_final_relationships",
|
|
])
|
|
expected = load_expected(workflow_name)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
config["create_community_reports"]["strategy"]["llm"] = MOCK_LLM_CONFIG
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|
|
|
|
assert len(actual.columns) == len(expected.columns)
|
|
|
|
# only assert a couple of columns that are not mock - most of this table is LLM-generated
|
|
compare_outputs(actual, expected, columns=["community", "level"])
|
|
|
|
# assert a handful of mock data items to confirm they get put in the right spot
|
|
assert actual["rank"][:1][0] == 2
|
|
assert actual["rank_explanation"][:1][0] == "<rating_explanation>"
|
|
|
|
|
|
async def test_create_final_community_reports_with_embeddings():
|
|
input_tables = load_input_tables([
|
|
"workflow:create_final_nodes",
|
|
"workflow:create_final_covariates",
|
|
"workflow:create_final_relationships",
|
|
])
|
|
expected = load_expected(workflow_name)
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
config["create_community_reports"]["strategy"]["llm"] = MOCK_LLM_CONFIG
|
|
|
|
config["skip_full_content_embedding"] = False
|
|
config["community_report_full_content_embed"]["strategy"]["type"] = "mock"
|
|
config["skip_summary_embedding"] = False
|
|
config["community_report_summary_embed"]["strategy"]["type"] = "mock"
|
|
config["skip_title_embedding"] = False
|
|
config["community_report_title_embed"]["strategy"]["type"] = "mock"
|
|
|
|
steps = build_steps(config)
|
|
|
|
actual = await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|
|
|
|
assert len(actual.columns) == len(expected.columns) + 3
|
|
assert "full_content_embedding" in actual.columns
|
|
assert len(actual["full_content_embedding"][:1][0]) == 3
|
|
assert "summary_embedding" in actual.columns
|
|
assert len(actual["summary_embedding"][:1][0]) == 3
|
|
assert "title_embedding" in actual.columns
|
|
assert len(actual["title_embedding"][:1][0]) == 3
|
|
|
|
|
|
async def test_create_final_community_reports_missing_llm_throws():
|
|
input_tables = load_input_tables([
|
|
"workflow:create_final_nodes",
|
|
"workflow:create_final_covariates",
|
|
"workflow:create_final_relationships",
|
|
])
|
|
|
|
config = get_config_for_workflow(workflow_name)
|
|
|
|
# deleting the llm config results in a default mock injection in run_graph_intelligence
|
|
del config["create_community_reports"]["strategy"]["llm"]
|
|
|
|
steps = build_steps(config)
|
|
|
|
with pytest.raises(VerbParallelizationError):
|
|
await get_workflow_output(
|
|
input_tables,
|
|
{
|
|
"steps": steps,
|
|
},
|
|
)
|