add pre-commit-config.yml apply linter and formater over the code + add github linter on push to main

Author: GishB

.github/workflows/ruff.yml

@@ -0,0 +1,34 @@
+name: Ruff Linting
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    name: Ruff Check
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.10"
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install ruff
+        pip install .
+
+    - name: Run Ruff Check
+      run: ruff check --output-format=github .
+
+    - name: Run Ruff Format Check
+      run: ruff format --check .

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.3
+    hooks:
+      - id: ruff
+        args: [ --fix ]
+      - id: ruff-format

setup.cfg

@@ -0,0 +1,47 @@
+[tool:ruff]
+line-length = 88
+target-version = py310
+exclude =
+    .bzr,
+    .direnv,
+    .eggs,
+    .git,
+    .git-rewrite,
+    .hg,
+    .mypy_cache,
+    .nox,
+    .pants.d,
+    .pyenv,
+    .pytest_cache,
+    .pytype,
+    .ruff_cache,
+    .svn,
+    .tox,
+    .venv,
+    .vscode,
+    __pypackages__,
+    _build,
+    buck-out,
+    build,
+    dist,
+    node_modules,
+    site-packages,
+    venv
+
+[tool:ruff.lint]
+select = E4,E7,E9,F,I,B,C4,W
+ignore = E501,B008,B904
+fixable = ALL
+unfixable =
+dummy-variable-rgx = ^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$
+
+[tool:ruff.format]
+quote-style = double
+indent-style = space
+skip-magic-trailing-comma = false
+line-ending = auto
+docstring-code-format = false
+docstring-code-line-length = dynamic
+
+[tool:ruff.lint.isort]
+known-first-party = UnionChatBot

setup.py

@@ -3,53 +3,53 @@
 __version__ = "0.1.0"
 
 # Read requirements from requirements.txt
-with open('requirements.txt') as f:
-    requirements = [line.strip() for line in f if line.strip() and not line.startswith('#')]
+with open("requirements.txt") as f:
+    requirements = [
+        line.strip() for line in f if line.strip() and not line.startswith("#")
+    ]
 
 # Read long description from README.md
-with open('README.md', 'r', encoding='utf-8') as f:
+with open("README.md", "r", encoding="utf-8") as f:
     long_description = f.read()
 
 setup(
-    name='UnionChatBot',
+    name="UnionChatBot",
     version=__version__,
-    python_requires='>=3.10.0',
-    url='https://github.com/GishB/GeneralPurposeTelegramBOT',
-    license='MIT License',
-    author='Aleksandr Samofalov',
-    author_email='SamofalovWORK@yandex.ru',
-    description='TelegramBot for general questions related to documents via Yandex API',
+    python_requires=">=3.10.0",
+    url="https://github.com/GishB/GeneralPurposeTelegramBOT",
+    license="MIT License",
+    author="Aleksandr Samofalov",
+    author_email="SamofalovWORK@yandex.ru",
+    description="TelegramBot for general questions related to documents via Yandex API",
     long_description=long_description,
-    long_description_content_type='text/markdown',
-    package_dir={'': 'src'},
-    packages=find_packages(where="src", exclude=[
-            'tests*',
-            'experiments*',
-            'docs*',
-            '.*',
-            '*.egg-info',
-            'build*',
-            'dist*'
-        ]),
+    long_description_content_type="text/markdown",
+    package_dir={"": "src"},
+    packages=find_packages(
+        where="src",
+        exclude=[
+            "tests*",
+            "experiments*",
+            "docs*",
+            ".*",
+            "*.egg-info",
+            "build*",
+            "dist*",
+        ],
+    ),
     install_requires=requirements,
     include_package_data=True,
     zip_safe=False,
     classifiers=[
-        'Development Status :: Alpha',
-        'Intended Audience :: Develop',
-        'License :: OSI Approved :: MIT License',
-        'Programming Language :: Python :: 3.10',
-        'Topic :: Develop/Engineering :: Text Information Analysis',
-        'Operating System :: OS Ubuntu 2022 TLS',
+        "Development Status :: Alpha",
+        "Intended Audience :: Develop",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3.10",
+        "Topic :: Develop/Engineering :: Text Information Analysis",
+        "Operating System :: OS Ubuntu 2022 TLS",
     ],
     project_urls={
-        'Bug Reports': 'https://github.com/GishB/GeneralPurposeTelegramBOT/issues',
-        'Source': 'https://github.com/GishB/GeneralPurposeTelegramBOT',
+        "Bug Reports": "https://github.com/GishB/GeneralPurposeTelegramBOT/issues",
+        "Source": "https://github.com/GishB/GeneralPurposeTelegramBOT",
     },
-    keywords=[
-        'YandexGPT API',
-        'LLM',
-        'RAG',
-        'TelegramBot'
-    ],
-)
+    keywords=["YandexGPT API", "LLM", "RAG", "TelegramBot"],
+)

src/UnionChatBot/utils/ChatHistoryManager.py

@@ -4,13 +4,16 @@
 from datetime import datetime, timedelta
 from typing import Optional
 
+
 class ChatHistoryManager:
-    def __init__(self,
-                 redis_host: str = 'localhost',
-                 redis_port: int = 6379,
-                 redis_db: int = 1,
-                 history_ttl_days: Optional[int] = None,
-                 max_history_length: Optional[int] = None):
+    def __init__(
+        self,
+        redis_host: str = "localhost",
+        redis_port: int = 6379,
+        redis_db: int = 1,
+        history_ttl_days: Optional[int] = None,
+        max_history_length: Optional[int] = None,
+    ):
         """
         Инициализация менеджера истории чата.
 
@@ -19,13 +22,21 @@ def __init__(self,
             redis_port: порт Redis
             redis_db: номер базы данных Redis
         """
-        self.max_history_length = max_history_length if max_history_length else os.environ["MAX_HISTORY_USER_LENGTH"]
-        self.history_ttl_days = history_ttl_days if history_ttl_days else os.environ["HISTORY_USER_TTL_DAYS"]
+        self.max_history_length = (
+            max_history_length
+            if max_history_length
+            else os.environ["MAX_HISTORY_USER_LENGTH"]
+        )
+        self.history_ttl_days = (
+            history_ttl_days
+            if history_ttl_days
+            else os.environ["HISTORY_USER_TTL_DAYS"]
+        )
         self.redis_client = redis.StrictRedis(
             host=redis_host,
             port=redis_port,
             db=redis_db,
-            decode_responses=True  # Автоматически декодируем из bytes в str
+            decode_responses=True,  # Автоматически декодируем из bytes в str
         )
         self.history_ttl_days = history_ttl_days
 
@@ -61,7 +72,7 @@ def add_message_to_history(self, user_id: str, message: str) -> None:
         history_key = self._get_history_key(user_id)
 
         # Добавляем сообщение с временной меткой
-        timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+        timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
         formatted_message = f"[{timestamp}] {message}"
 
         # Добавляем в начало списка и ограничиваем длину
@@ -100,4 +111,4 @@ def clear_user_history(self, user_id: str) -> None:
             user_id: идентификатор пользователя
         """
         history_key = self._get_history_key(user_id)
-        self.redis_client.delete(history_key)
+        self.redis_client.delete(history_key)

src/UnionChatBot/utils/ChromaAdapter.py

@@ -6,20 +6,21 @@
 from UnionChatBot.utils.EmbeddingAPI import MyEmbeddingFunction
 from UnionChatBot.utils.RerankerAPI import BM25Reranker
 
+
 class ChromaAdapter:
     def __init__(
-            self,
-            host: str = "localhost",
-            port: int = 32000,
-            max_rag_documents: int = 20,
-            topk_documents: int = 3,
-            similarity_filter: float = 1.5,
-            embedding_model: str = "all-MiniLM-L6-v2",
-            reranker_type: str = "bm25",
-            api_key: Optional[str] = None,
-            folder_id: Optional[str] = None,
-            text_type: str = "doc",
-            api_url: Optional[str] = None
+        self,
+        host: str = "localhost",
+        port: int = 32000,
+        max_rag_documents: int = 20,
+        topk_documents: int = 3,
+        similarity_filter: float = 1.5,
+        embedding_model: str = "all-MiniLM-L6-v2",
+        reranker_type: str = "bm25",
+        api_key: Optional[str] = None,
+        folder_id: Optional[str] = None,
+        text_type: str = "doc",
+        api_url: Optional[str] = None,
     ):
         self.reranker_type = reranker_type
         if reranker_type == "bm25":
@@ -48,29 +49,26 @@ def embedding_function(self):
                 api_url=self.api_url,
                 folder_id=self.folder_id,
                 iam_token=self.api_key,
-                text_type=self.text_type
+                text_type=self.text_type,
             )
         return self._embedding_function
 
     def get_info_from_db(
-            self,
-            query: str,
-            collection_name: str,
-            n_results: int = 30,
-            **kwargs
+        self, query: str, collection_name: str, n_results: int = 30, **kwargs
     ) -> Dict[str, Any]:
         collection = self.client.get_collection(
-            name=collection_name,
-            embedding_function=self.embedding_function
+            name=collection_name, embedding_function=self.embedding_function
         )
         return collection.query(
             query_texts=[query],
             n_results=n_results,
-            include=["documents", "metadatas", "distances"]
+            include=["documents", "metadatas", "distances"],
         )
 
     def get_filtered_documents(self, data_raw: Dict[str, Any]) -> dict:
-        distances = data_raw["distances"][0]  # Берем первый элемент, так как query_texts=[query]
+        distances = data_raw["distances"][
+            0
+        ]  # Берем первый элемент, так как query_texts=[query]
         documents = data_raw["documents"][0]
         metadatas = data_raw["metadatas"][0]
 
@@ -84,7 +82,8 @@ def get_filtered_documents(self, data_raw: Dict[str, Any]) -> dict:
                 metadatas[idx]
                 for idx, dist in enumerate(distances)
                 if dist < self.similarity_filter
-            ]}
+            ],
+        }
 
     def get_pairs(self, query: str, documents: List[str]) -> List[List[str]]:
         return [[query, doc] for doc in documents]
@@ -100,7 +99,7 @@ def get_info(self, query: str, collection_name: str) -> dict[str, list[Any] | st
         data_raw = self.get_info_from_db(
             query=query,
             collection_name=collection_name,
-            n_results=self.max_rag_documents
+            n_results=self.max_rag_documents,
         )
         filtered_documents = self.get_filtered_documents(data_raw)
 
@@ -109,13 +108,19 @@ def get_info(self, query: str, collection_name: str) -> dict[str, list[Any] | st
                 "documents": [],
                 "metadatas": [],
                 "query": query,
-                "collection_name": collection_name
+                "collection_name": collection_name,
             }
 
-        idx_relevant_documents = self.apply_reranker(query=query, documents=filtered_documents["documents"])
+        idx_relevant_documents = self.apply_reranker(
+            query=query, documents=filtered_documents["documents"]
+        )
         return {
-            "documents": [filtered_documents["documents"][idx] for idx in idx_relevant_documents],
-            "metadatas": [filtered_documents["metadatas"][idx] for idx in idx_relevant_documents],
+            "documents": [
+                filtered_documents["documents"][idx] for idx in idx_relevant_documents
+            ],
+            "metadatas": [
+                filtered_documents["metadatas"][idx] for idx in idx_relevant_documents
+            ],
             "query": query,
-            "collection_name": collection_name
-        }
+            "collection_name": collection_name,
+        }