forked from chonkie-ai/chonkie
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpyproject.toml
92 lines (84 loc) · 2.54 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
[build-system]
requires = ["setuptools>=45", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "chonkie"
version = "0.5.1"
description = "🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library"
readme = "README.md"
requires-python = ">=3.9"
license = {file = "LICENSE"}
keywords = ["chunking", "rag", "nlp", "text-processing"]
authors = [
{name = "Bhavnick Minhas", email = "[email protected]"},
{name = "Shreyash Nigam", email = "[email protected]"}
]
classifiers = [
"License :: OSI Approved :: MIT License",
"Programming Language :: Python",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"Intended Audience :: Information Technology",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Scientific/Engineering :: Information Analysis",
"Topic :: Text Processing :: Linguistic"
]
dependencies = [
"tokenizers>=0.16.0",
"tqdm>=4.64.0"
]
[project.urls]
Homepage = "https://github.com/bhavnicksm/chonkie"
Documentation = "https://docs.chonkie.ai"
[project.optional-dependencies]
model2vec = ["model2vec>=0.3.0", "numpy>=1.23.0, <2.2"]
st = ["sentence-transformers>=3.0.0", "numpy>=1.23.0, <2.2"]
openai = ["tiktoken>=0.5.0", "openai>=1.0.0", "numpy>=1.23.0, <2.2"]
semantic = ["model2vec>=0.3.0", "numpy>=1.23.0, <2.2"]
cohere = ["cohere>=5.13.0", "numpy>=1.23.0, <2.2"]
all = [
"sentence-transformers>=3.0.0",
"numpy>=1.23.0, <2.2",
"openai>=1.0.0",
"tiktoken>=0.5.0",
"model2vec>=0.3.0",
"cohere>=5.13.0"
]
dev = [
"tiktoken>=0.5.0",
"datasets>=1.14.0",
"transformers>=4.0.0",
"pytest>=6.2.0",
"pytest-cov>=4.0.0",
"ruff>=0.0.265",
"mypy>=1.11.0"
]
[tool.pytest.ini_options]
pythonpath = "src"
[tool.setuptools]
package-dir = {"" = "src"}
packages = ["chonkie",
"chonkie.chunker",
"chonkie.embeddings",
"chonkie.refinery",
"chonkie.chef"]
[tool.ruff]
exclude = ["*.ipynb"]
lint.select = ["F", "I", "D", "DOC"]
lint.ignore = ["D211", "D213"]
[tool.ruff.format]
preview = true
indent-style = "space"
[tool.mypy]
disallow_untyped_defs = true
no_implicit_optional = true
check_untyped_defs = true
warn_return_any = true
show_error_codes = true