feat: Add ruff pre-commit hook for linting and formatting

Added formatting and linting on pre-commit hook

Feature COG-650

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.8.3
+  hooks:
+    # Run the linter.
+    - id: ruff
+      types_or: [ python, pyi ]
+    # Run the formatter.
+    - id: ruff-format
+      types_or: [ python, pyi ]

poetry.lock

@@ -726,6 +726,17 @@ files = [
 [package.dependencies]
 pycparser = "*"
 
+[[package]]
+name = "cfgv"
+version = "3.4.0"
+description = "Validate configuration and produce human readable error messages."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9"},
+    {file = "cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560"},
+]
+
 [[package]]
 name = "chardet"
 version = "5.2.0"
@@ -1379,6 +1390,17 @@ files = [
     {file = "dirtyjson-1.0.8.tar.gz", hash = "sha256:90ca4a18f3ff30ce849d100dcf4a003953c79d3a2348ef056f1d9c22231a25fd"},
 ]
 
+[[package]]
+name = "distlib"
+version = "0.3.9"
+description = "Distribution utilities"
+optional = false
+python-versions = "*"
+files = [
+    {file = "distlib-0.3.9-py2.py3-none-any.whl", hash = "sha256:47f8c22fd27c27e25a65601af709b38e4f0a45ea4fc2e710f65755fa8caaaf87"},
+    {file = "distlib-0.3.9.tar.gz", hash = "sha256:a60f20dea646b8a33f3e7772f74dc0b2d0772d2837ee1342a00645c81edf9403"},
+]
+
 [[package]]
 name = "distro"
 version = "1.9.0"
@@ -2527,6 +2549,20 @@ files = [
     {file = "hyperframe-6.0.1.tar.gz", hash = "sha256:ae510046231dc8e9ecb1a6586f63d2347bf4c8905914aa84ba585ae85f28a914"},
 ]
 
+[[package]]
+name = "identify"
+version = "2.6.3"
+description = "File identification library for Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "identify-2.6.3-py2.py3-none-any.whl", hash = "sha256:9edba65473324c2ea9684b1f944fe3191db3345e50b6d04571d10ed164f8d7bd"},
+    {file = "identify-2.6.3.tar.gz", hash = "sha256:62f5dae9b5fef52c84cc188514e9ea4f3f636b1d8799ab5ebc475471f9e47a02"},
+]
+
+[package.extras]
+license = ["ukkonen"]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -4535,6 +4571,17 @@ plot = ["matplotlib"]
 tgrep = ["pyparsing"]
 twitter = ["twython"]
 
+[[package]]
+name = "nodeenv"
+version = "1.9.1"
+description = "Node.js virtual environment builder"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+    {file = "nodeenv-1.9.1-py2.py3-none-any.whl", hash = "sha256:ba11c9782d29c27c70ffbdda2d7415098754709be8a7056d79a737cd901155c9"},
+    {file = "nodeenv-1.9.1.tar.gz", hash = "sha256:6ec12890a2dab7946721edbfbcd91f3319c6ccc9aec47be7c7e6b7011ee6645f"},
+]
+
 [[package]]
 name = "notebook"
 version = "7.3.1"
@@ -5348,6 +5395,24 @@ dev = ["black", "flake8", "flake8-print", "isort", "pre-commit"]
 sentry = ["django", "sentry-sdk"]
 test = ["coverage", "django", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint", "pytest", "pytest-timeout"]
 
+[[package]]
+name = "pre-commit"
+version = "4.0.1"
+description = "A framework for managing and maintaining multi-language pre-commit hooks."
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "pre_commit-4.0.1-py2.py3-none-any.whl", hash = "sha256:efde913840816312445dc98787724647c65473daefe420785f885e8ed9a06878"},
+    {file = "pre_commit-4.0.1.tar.gz", hash = "sha256:80905ac375958c0444c65e9cebebd948b3cdb518f335a091a670a89d652139d2"},
+]
+
+[package.dependencies]
+cfgv = ">=2.0.0"
+identify = ">=1.0.0"
+nodeenv = ">=0.11.1"
+pyyaml = ">=5.1"
+virtualenv = ">=20.10.0"
+
 [[package]]
 name = "prometheus-client"
 version = "0.21.1"
@@ -8375,6 +8440,26 @@ files = [
 [package.extras]
 crypto-eth-addresses = ["eth-hash[pycryptodome] (>=0.7.0)"]
 
+[[package]]
+name = "virtualenv"
+version = "20.28.0"
+description = "Virtual Python Environment builder"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "virtualenv-20.28.0-py3-none-any.whl", hash = "sha256:23eae1b4516ecd610481eda647f3a7c09aea295055337331bb4e6892ecce47b0"},
+    {file = "virtualenv-20.28.0.tar.gz", hash = "sha256:2c9c3262bb8e7b87ea801d715fae4495e6032450c71d2309be9550e7364049aa"},
+]
+
+[package.dependencies]
+distlib = ">=0.3.7,<1"
+filelock = ">=3.12.2,<4"
+platformdirs = ">=3.9.1,<5"
+
+[package.extras]
+docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.2,!=7.3)", "sphinx-argparse (>=0.4)", "sphinxcontrib-towncrier (>=0.2.1a0)", "towncrier (>=23.6)"]
+test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8)", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10)"]
+
 [[package]]
 name = "watchdog"
 version = "6.0.0"
@@ -8877,4 +8962,4 @@ weaviate = ["weaviate-client"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9.0,<3.12"
-content-hash = "af91e3dcf6a8927ed938fe3f78172a5f1e0c0f9c8fbcbc76767b0e0d84645c9e"
+content-hash = "7b339ad192fdc1bf97bbc0797b9657f0245b00627f811009a545e4a3380368bb"

pyproject.toml

@@ -74,6 +74,7 @@ deepeval = {version = "^2.0.1", optional = true}
 transformers = "^4.46.3"
 pymilvus = {version = "^2.5.0", optional = true}
 unstructured = { extras = ["csv", "doc", "docx", "epub", "md", "odt", "org", "ppt", "pptx", "rst", "rtf", "tsv", "xlsx"], version = "^0.16.10", optional = true }
+pre-commit = "^4.0.1"