forked from microsoft/graphrag
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pyproject.toml
277 lines (245 loc) · 7.02 KB
/
pyproject.toml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
[tool.poetry]
name = "graphrag"
# Maintainers: do not change the version here manually, use ./scripts/release.sh
version = "0.5.0"
description = "GraphRAG: A graph-based retrieval-augmented generation (RAG) system."
authors = [
"Alonso Guevara Fernández <[email protected]>",
"Andrés Morales Esquivel <[email protected]>",
"Chris Trevino <[email protected]>",
"David Tittsworth <[email protected]>",
"Dayenne de Souza <[email protected]>",
"Derek Worthen <[email protected]>",
"Gaudy Blanco Meneses <[email protected]>",
"Ha Trinh <[email protected]>",
"Jonathan Larson <[email protected]>",
"Josh Bradley <[email protected]>",
"Kate Lytvynets <[email protected]>",
"Kenny Zhang <[email protected]>",
"Mónica Carvajal",
"Nathan Evans <[email protected]>",
"Rodrigo Racanicci <[email protected]>",
"Sarah Smith <[email protected]>",
]
license = "MIT"
readme = "README.md"
packages = [{ include = "graphrag" }]
[tool.poetry.urls]
"Source" = "https://github.com/microsoft/graphrag"
[tool.poetry.scripts]
graphrag = "graphrag.cli.main:app"
[tool.poetry-dynamic-versioning]
enable = true
style = "pep440"
vcs = "git"
bump = true
format-jinja = """
{%- if distance == 0 -%}
{{ serialize_pep440(base, stage, revision) }}
{%- else -%}
{{ serialize_pep440(base, stage, revision, dev=distance) }}
{%- endif -%}
"""
[tool.poetry.dependencies]
python = ">=3.10,<3.13"
environs = "^11.0.0"
datashaper = "^0.0.49"
# Vector Stores
azure-search-documents = "^11.4.0"
lancedb = "^0.13.0"
# Async IO
aiolimiter = "^1.1.0"
aiofiles = "^24.1.0"
# LLM
openai = "^1.51.2"
nltk = "3.9.1"
tiktoken = "^0.7.0"
# Data-Sci
numpy = "^1.25.2"
graspologic = "^3.4.1"
networkx = "^3"
pandas = "^2.2.3"
matplotlib = "^3.9.0"
pyarrow = "^15.0.0"
umap-learn = "^0.5.6"
# Configuration
pyyaml = "^6.0.2"
pyaml-env = "^1.2.1"
python-dotenv = "^1.0.0"
# Network
tenacity = "^9.0.0"
pydantic = "^2.9.2"
rich = "^13.6.0"
devtools = "^0.12.2"
typing-extensions = "^4.12.2"
#Azure
azure-storage-blob = "^12.22.0"
azure-identity = "^1.17.1"
json-repair = "^0.30.0"
future = "^1.0.0" # Needed until graspologic fixes their dependency
typer = "^0.12.5"
[tool.poetry.group.dev.dependencies]
coverage = "^7.6.0"
ipykernel = "^6.29.4"
jupyter = "^1.1.1"
nbconvert = "^7.16.3"
poethepoet = "^0.28.0"
pyright = "^1.1.384"
pytest = "^8.3.2"
pytest-asyncio = "^0.24.0"
pytest-timeout = "^2.3.1"
ruff = "^0.6.9"
semversioner = "^2.0.3"
update-toml = "^0.2.1"
deptry = "^0.20.0"
mkdocs-material = "^9.5.39"
mkdocs-jupyter = "^0.25.0"
mkdocs-exclude-search = "^0.6.6"
mkdocs-typer = "^0.0.3"
[build-system]
requires = ["poetry-core>=1.0.0", "poetry-dynamic-versioning>=1.0.0,<2.0.0"]
build-backend = "poetry_dynamic_versioning.backend"
[tool.poe.tasks]
_sort_imports = "ruff check --select I --fix ."
_format_code = "ruff format ."
_ruff_check = 'ruff check .'
_pyright = "pyright"
_convert_local_search_nb = 'jupyter nbconvert --output-dir=docsite/posts/query/notebooks/ --output="{notebook_name}_nb" --template=docsite/nbdocsite_template --to markdown examples_notebooks/local_search.ipynb'
_convert_global_search_nb = 'jupyter nbconvert --output-dir=docsite/posts/query/notebooks/ --output="{notebook_name}_nb" --template=docsite/nbdocsite_template --to markdown examples_notebooks/global_search.ipynb'
_semversioner_release = "semversioner release"
_semversioner_changelog = "semversioner changelog > CHANGELOG.md"
_semversioner_update_toml_version = "update-toml update --path tool.poetry.version --value $(poetry run semversioner current-version)"
semversioner_add = "semversioner add-change"
coverage_report = 'coverage report --omit "**/tests/**" --show-missing'
check_format = 'ruff format . --check'
fix = "ruff check --fix ."
fix_unsafe = "ruff check --fix --unsafe-fixes ."
_test_all = "coverage run -m pytest ./tests"
test_unit = "pytest ./tests/unit"
test_integration = "pytest ./tests/integration"
test_smoke = "pytest ./tests/smoke"
test_notebook = "pytest ./tests/notebook"
test_verbs = "pytest ./tests/verbs"
index = "python -m graphrag index"
update = "python -m graphrag update"
init = "python -m graphrag init"
query = "python -m graphrag query"
prompt_tune = "python -m graphrag prompt-tune"
# Pass in a test pattern
test_only = "pytest -s -k"
serve_docs = "mkdocs serve"
build_docs = "mkdocs build"
[[tool.poe.tasks.release]]
sequence = [
'_semversioner_release',
'_semversioner_changelog',
'_semversioner_update_toml_version',
]
ignore_fail = 'return_non_zero'
[[tool.poe.tasks.convert_docsite_notebooks]]
sequence = ['_convert_local_search_nb', '_convert_global_search_nb']
ignore_fail = 'return_non_zero'
[[tool.poe.tasks.format]]
sequence = ['_sort_imports', '_format_code']
ignore_fail = 'return_non_zero'
[[tool.poe.tasks.check]]
sequence = ['check_format', '_ruff_check', '_pyright']
ignore_fail = 'return_non_zero'
[[tool.poe.tasks.test]]
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"]
exclude = ["**/node_modules", "**/__pycache__"]
[tool.pytest.ini_options]
asyncio_mode = "auto"
timeout = 1000
# log_cli = true
# log_cli_level = "INFO"