kanshan/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-02-22 10:44:59 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

update ruff, move ruff settings to ruff.toml

Browse Source
This commit is contained in:
Chris Trevino 2024-10-30 12:55:37 -07:00
parent 7235c6faf5
commit 2f763f51c0
11 changed files with 543 additions and 523 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
.gitattributes vendored Normal file
View File

@ -0,0 +1,11 @@
*.txt text eol=lf
*.md text eol=lf
*.yml text eol=lf
*.html text eol=lf
*.py text eol=lf
*.toml text eol=lf
.gitattributes text eol=lf
.gitignore text eol=lf
*.lock
CODEOWNERS text eol=lf
LICENSE text eol=lf

27
.vscode/settings.json vendored
View File

@ -12,19 +12,11 @@
"typescript.preferences.importModuleSpecifierEnding": "js",
"explorer.fileNesting.enabled": true,
"explorer.fileNesting.patterns": {
"*.ts": "${capture}.ts, ${capture}.hooks.ts, ${capture}.hooks.tsx, ${capture}.contexts.ts, ${capture}.stories.tsx, ${capture}.story.tsx, ${capture}.spec.tsx, ${capture}.base.ts, ${capture}.base.tsx, ${capture}.types.ts, ${capture}.styles.ts, ${capture}.styles.tsx, ${capture}.utils.ts, ${capture}.utils.tsx, ${capture}.constants.ts, ${capture}.module.scss, ${capture}.module.css, ${capture}.md",
"*.js": "${capture}.js.map, ${capture}.min.js, ${capture}.d.ts",
"*.jsx": "${capture}.js",
"*.tsx": "${capture}.ts, ${capture}.hooks.ts, ${capture}.hooks.tsx, ${capture}.contexts.ts, ${capture}.stories.tsx, ${capture}.story.tsx, ${capture}.spec.tsx, ${capture}.base.ts, ${capture}.base.tsx, ${capture}.types.ts, ${capture}.styles.ts, ${capture}.styles.tsx, ${capture}.utils.ts, ${capture}.utils.tsx, ${capture}.constants.ts, ${capture}.module.scss, ${capture}.module.css, ${capture}.md, ${capture}.css",
"tsconfig.json": "tsconfig.*.json",
"package.json": "package-lock.json, turbo.json, tsconfig.json, rome.json, biome.json, .npmignore, dictionary.txt, cspell.config.yaml",
"README.md": "*.md, LICENSE, CODEOWNERS",
".eslintrc": ".eslintignore",
".prettierrc": ".prettierignore",
".gitattributes": ".gitignore",
".yarnrc.yml": "yarn.lock, .pnp.*",
"jest.config.js": "jest.setup.mjs",
"pyproject.toml": "poetry.lock, poetry.toml, mkdocs.yaml",
"pyproject.toml": "*.lock, *.toml, mkdocs.yaml",
"cspell.config.yaml": "dictionary.txt"
},
"azureFunctions.postDeployTask": "npm install (functions)",
@ -36,6 +28,19 @@
"node_modules{,/**}",
".vscode{,/**}"
],
"[python]": {
"editor.formatOnSave": true,
"editor.codeActionsOnSave": {
"source.organizeImports": "explicit",
"source.fixAll": "explicit"
},
"editor.defaultFormatter": "charliermarsh.ruff"
},
"notebook.formatOnSave.enabled": true,
"notebook.codeActionsOnSave": {
"notebook.source.fixAll": "explicit",
"notebook.source.organizeImports": "explicit"
},
"python.defaultInterpreterPath": "python/services/.venv/bin/python",
"python.languageServer": "Pylance",
"cSpell.customDictionaries": {
@ -47,5 +52,7 @@
},
"custom": true, // Enable the `custom` dictionary
"internal-terms": true // Disable the `internal-terms` dictionary
}
},
"ruff.configuration": "./ruff.toml",
"ruff.nativeServer": "on"
}

8
graphrag/query/structured_search/global_search/search.py
View File

@ -332,10 +332,10 @@ class GlobalSearch(BaseSearch[GlobalContextBuilder]):
for point in filtered_key_points:
formatted_response_data = []
formatted_response_data.append(
f'----Analyst {point["analyst"] + 1}----'
f"----Analyst {point['analyst'] + 1}----"
)
formatted_response_data.append(
f'Importance Score: {point["score"]}' # type: ignore
f"Importance Score: {point['score']}" # type: ignore
)
formatted_response_data.append(point["answer"]) # type: ignore
formatted_response_text = "\n".join(formatted_response_data)
@ -431,8 +431,8 @@ class GlobalSearch(BaseSearch[GlobalContextBuilder]):
total_tokens = 0
for point in filtered_key_points:
formatted_response_data = [
f'----Analyst {point["analyst"] + 1}----',
f'Importance Score: {point["score"]}',
f"----Analyst {point['analyst'] + 1}----",
f"Importance Score: {point['score']}",
point["answer"],
]
formatted_response_text = "\n".join(formatted_response_data)

748
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

96
pyproject.toml
View File

@ -99,11 +99,11 @@ ipykernel = "^6.29.4"
jupyter = "^1.1.1"
nbconvert = "^7.16.3"
poethepoet = "^0.28.0"
pyright = "^1.1.384"
pyright = "^1.1.387"
pytest = "^8.3.2"
pytest-asyncio = "^0.24.0"
pytest-timeout = "^2.3.1"
ruff = "^0.6.9"
ruff = "^0.7.1"
semversioner = "^2.0.3"
update-toml = "^0.2.1"
deptry = "^0.20.0"
@ -170,98 +170,6 @@ ignore_fail = 'return_non_zero'
sequence = ['_test_all', 'coverage_report']
ignore_fail = 'return_non_zero'
[tool.ruff]
target-version = "py310"
extend-include = ["*.ipynb"]
[tool.ruff.format]
preview = true
docstring-code-format = true
docstring-code-line-length = 20
[tool.ruff.lint]
preview = true
select = [
"E4",
"E7",
"E9",
"W291",
"YTT",
"T10",
"ICN",
"INP",
"Q",
"RSE",
"SLOT",
"INT",
"FLY",
"LOG",
"C90",
"T20",
"D",
"RET",
"PD",
"N",
"PIE",
"SIM",
"S",
"G",
"ERA",
"ASYNC",
"TID",
"UP",
"SLF",
"BLE",
"C4",
"I",
"F",
"A",
"ARG",
"PTH",
"RUF",
"B",
"TCH",
"DTZ",
"PYI",
"PT",
"EM",
"TRY",
"PERF",
"CPY",
# "FBT", # use named arguments for boolean flags
# "TD", # todos
# "FIX", # fixme
# "FURB" # preview rules
# ANN # Type annotations, re-enable when we get bandwidth
]
ignore = [
# Ignore module names shadowing Python builtins
"A005",
# Deprecated Rules
"ANN101",
"ANN102",
# Conflicts with interface argument checking
"ARG002",
"ANN204",
# TODO: Inspect these pandas rules for validity
"PD002", # prevents inplace=True
# TODO RE-Enable when we get bandwidth
"PERF203", # Needs restructuring of errors, we should bail-out on first error
"C901", # needs refactoring to remove cyclomatic complexity
]
[tool.ruff.lint.per-file-ignores]
"tests/*" = ["S", "D", "ANN", "T201", "ASYNC", "ARG", "PTH", "TRY"]
"examples/*" = ["S", "D", "ANN", "T201", "PTH", "TRY", "PERF"]
"graphrag/index/config/*" = ["TCH"]
"*.ipynb" = ["T201"]
[tool.ruff.lint.flake8-builtins]
builtins-ignorelist = ["input", "id", "bytes"]
[tool.ruff.lint.pydocstyle]
convention = "numpy"
# https://github.com/microsoft/pyright/blob/9f81564a4685ff5c55edd3959f9b39030f590b2f/docs/configuration.md#sample-pyprojecttoml-file
[tool.pyright]
include = ["graphrag", "tests", "examples", "examples_notebooks"]

91
ruff.toml Normal file
View File

@ -0,0 +1,91 @@
target-version = "py310"
extend-include = ["*.ipynb"]
[format]
preview = true
docstring-code-format = true
docstring-code-line-length = 20
[lint]
preview = true
select = [
"E4",
"E7",
"E9",
"W291",
"YTT",
"T10",
"ICN",
"INP",
"Q",
"RSE",
"SLOT",
"INT",
"FLY",
"LOG",
"C90",
"T20",
"D",
"RET",
"PD",
"N",
"PIE",
"SIM",
"S",
"G",
"ERA",
"ASYNC",
"TID",
"UP",
"SLF",
"BLE",
"C4",
"I",
"F",
"A",
"ARG",
"PTH",
"RUF",
"B",
"TCH",
"DTZ",
"PYI",
"PT",
"EM",
"TRY",
"PERF",
"CPY",
# "FBT", # use named arguments for boolean flags
# "TD", # todos
# "FIX", # fixme
# "FURB" # preview rules
# ANN # Type annotations, re-enable when we get bandwidth
]
ignore = [
# Ignore module names shadowing Python builtins
"A005",
# Deprecated Rules
"ANN101",
"ANN102",
# Conflicts with interface argument checking
"ARG002",
"ANN204",
# TODO: Inspect these pandas rules for validity
"PD002", # prevents inplace=True
# TODO RE-Enable when we get bandwidth
"PERF203", # Needs restructuring of errors, we should bail-out on first error
"C901", # needs refactoring to remove cyclomatic complexity
]
[lint.per-file-ignores]
"tests/*" = ["S", "D", "ANN", "T201", "ASYNC", "ARG", "PTH", "TRY"]
"examples/*" = ["S", "D", "ANN", "T201", "PTH", "TRY", "PERF"]
"graphrag/index/config/*" = ["TCH"]
"*.ipynb" = ["T201"]
[lint.flake8-builtins]
builtins-ignorelist = ["input", "id", "bytes"]
[lint.pydocstyle]
convention = "numpy"

12
tests/integration/_pipeline/test_run.py
View File

@ -66,10 +66,10 @@ class TestRun(unittest.IsolatedAsyncioTestCase):
entity_ids = set(entity_text_unit_map.keys())
for text_unit_id, text_unit_entities in text_unit_entity_map.items():
assert text_unit_entities.issubset(
entity_ids
), f"Text unit {text_unit_id} has entities {text_unit_entities} that are not in the entity set"
assert text_unit_entities.issubset(entity_ids), (
f"Text unit {text_unit_id} has entities {text_unit_entities} that are not in the entity set"
)
for entity_id, entity_text_units in entity_text_unit_map.items():
assert entity_text_units.issubset(
text_unit_ids
), f"Entity {entity_id} has text units {entity_text_units} that are not in the text unit set"
assert entity_text_units.issubset(text_unit_ids), (
f"Entity {entity_id} has text units {entity_text_units} that are not in the text unit set"
)

49
tests/smoke/test_fixtures.py
View File

@ -145,9 +145,9 @@ class TestIndexer:
completion = subprocess.run(
command, env={**os.environ, "GRAPHRAG_INPUT_FILE_TYPE": input_file_type}
)
assert (
completion.returncode == 0
), f"Indexer failed with return code: {completion.returncode}"
assert completion.returncode == 0, (
f"Indexer failed with return code: {completion.returncode}"
)
def __assert_indexer_outputs(
self, root: Path, workflow_config: dict[str, dict[str, Any]]
@ -158,9 +158,9 @@ class TestIndexer:
output_entries.sort(key=lambda entry: entry.stat().st_ctime, reverse=True)
if not debug:
assert (
len(output_entries) == 1
), f"Expected one output folder, found {len(output_entries)}"
assert len(output_entries) == 1, (
f"Expected one output folder, found {len(output_entries)}"
)
output_path = output_entries[0]
assert output_path.exists(), "output folder does not exist"
@ -174,18 +174,18 @@ class TestIndexer:
# Check all workflows run
expected_workflows = set(workflow_config.keys())
workflows = set(stats["workflows"].keys())
assert (
workflows == expected_workflows
), f"Workflows missing from stats.json: {expected_workflows - workflows}. Unexpected workflows in stats.json: {workflows - expected_workflows}"
assert workflows == expected_workflows, (
f"Workflows missing from stats.json: {expected_workflows - workflows}. Unexpected workflows in stats.json: {workflows - expected_workflows}"
)
# [OPTIONAL] Check runtime
for workflow in expected_workflows:
# Check max runtime
max_runtime = workflow_config[workflow].get("max_runtime", None)
if max_runtime:
assert (
stats["workflows"][workflow]["overall"] <= max_runtime
), f"Expected max runtime of {max_runtime}, found: {stats['workflows'][workflow]['overall']} for workflow: {workflow}"
assert stats["workflows"][workflow]["overall"] <= max_runtime, (
f"Expected max runtime of {max_runtime}, found: {stats['workflows'][workflow]['overall']} for workflow: {workflow}"
)
# Check artifacts
artifact_files = os.listdir(artifacts)
@ -195,10 +195,11 @@ class TestIndexer:
transient_workflows = [
"workflow:create_base_text_units",
]
assert (
len(artifact_files)
== (len(expected_workflows) - len(transient_workflows) + 1)
), f"Expected {len(expected_workflows) + 1} artifacts, found: {len(artifact_files)}"
assert len(artifact_files) == (
len(expected_workflows) - len(transient_workflows) + 1
), (
f"Expected {len(expected_workflows) + 1} artifacts, found: {len(artifact_files)}"
)
for artifact in artifact_files:
if artifact.endswith(".parquet"):
@ -211,16 +212,18 @@ class TestIndexer:
workflow["row_range"][0]
<= len(output_df)
<= workflow["row_range"][1]
), f"Expected between {workflow['row_range'][0]} and {workflow['row_range'][1]}, found: {len(output_df)} for file: {artifact}"
), (
f"Expected between {workflow['row_range'][0]} and {workflow['row_range'][1]}, found: {len(output_df)} for file: {artifact}"
)
# Get non-nan rows
nan_df = output_df.loc[
:, ~output_df.columns.isin(workflow.get("nan_allowed_columns", []))
]
nan_df = nan_df[nan_df.isna().any(axis=1)]
assert (
len(nan_df) == 0
), f"Found {len(nan_df)} rows with NaN values for file: {artifact} on columns: {nan_df.columns[nan_df.isna().any()].tolist()}"
assert len(nan_df) == 0, (
f"Found {len(nan_df)} rows with NaN values for file: {artifact} on columns: {nan_df.columns[nan_df.isna().any()].tolist()}"
)
def __run_query(self, root: Path, query_config: dict[str, str]):
command = [
@ -296,8 +299,8 @@ class TestIndexer:
result.stderr if "No existing dataset at" not in result.stderr else ""
)
assert (
stderror == "" or stderror.replace("\n", "") in KNOWN_WARNINGS
), f"Query failed with error: {stderror}"
assert stderror == "" or stderror.replace("\n", "") in KNOWN_WARNINGS, (
f"Query failed with error: {stderror}"
)
assert result.stdout is not None, "Query returned no output"
assert len(result.stdout) > 0, "Query returned empty output"

6
tests/unit/indexing/workflows/test_emit.py
View File

@ -81,9 +81,9 @@ async def test_normal_result_emits_parquet():
]
assert len(pipeline_result) == 1
assert (
storage.keys() == ["stats.json", "mock_write", "mock_workflow.parquet"]
), "Mock workflow output should be written to storage by the emitter when there is a non-empty data frame"
assert storage.keys() == ["stats.json", "mock_write", "mock_workflow.parquet"], (
"Mock workflow output should be written to storage by the emitter when there is a non-empty data frame"
)
async def test_empty_result_does_not_emit_parquet():

12
tests/verbs/test_create_base_entity_graph.py
View File

@ -74,9 +74,9 @@ async def test_create_base_entity_graph():
context=context,
)
assert len(actual.columns) == len(
expected.columns
), "Graph dataframe columns differ"
assert len(actual.columns) == len(expected.columns), (
"Graph dataframe columns differ"
)
# let's parse a sample of the raw graphml
actual_graphml_0 = actual["clustered_graph"][:1][0]
actual_graph_0 = nx.parse_graphml(actual_graphml_0)
@ -121,9 +121,9 @@ async def test_create_base_entity_graph_with_embeddings():
context=context,
)
assert (
len(actual.columns) == len(expected.columns) + 1
), "Graph dataframe missing embedding column"
assert len(actual.columns) == len(expected.columns) + 1, (
"Graph dataframe missing embedding column"
)
assert "embeddings" in actual.columns, "Graph dataframe missing embedding column"

6
tests/verbs/util.py
View File

@ -86,9 +86,9 @@ def compare_outputs(
"""
cols = expected.columns if columns is None else columns
assert len(actual) == len(
expected
), f"Expected: {len(expected)} rows, Actual: {len(actual)} rows"
assert len(actual) == len(expected), (
f"Expected: {len(expected)} rows, Actual: {len(actual)} rows"
)
for column in cols:
assert column in actual.columns