update ruff, move ruff settings to ruff.toml

.semversioner/next-release/patch-20241030195954756064.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "update project settings"
+}

.vscode/settings.json

@@ -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"
 }

cspell.config.yaml

@@ -19,6 +19,7 @@ ignorePaths:
   - temp_azurite/
   - __pycache__
   - pyproject.toml
+  - ruff.toml
   - entity_extraction.txt
   - package.json
   - tests/fixtures/

graphrag/query/structured_search/global_search/search.py

@@ -332,10 +332,10 @@ async def _reduce_response(
             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 @@ async def _stream_reduce_response(
         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)

pyproject.toml

@@ -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"
@@ -171,98 +171,6 @@ 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"]

ruff.toml

@@ -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"

tests/integration/_pipeline/test_run.py

@@ -66,10 +66,10 @@ def _assert_text_units_and_entities_reference_each_other(
         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"
+            )