infra: rm unused # noqa violations (langchain-ai#22049)

Updating langchain-ai#21137

.github/scripts/check_diff.py

@@ -91,4 +91,4 @@
     }
     for key, value in outputs.items():
         json_output = json.dumps(value)
-        print(f"{key}={json_output}")  # noqa: T201
+        print(f"{key}={json_output}")

.github/scripts/get_min_versions.py

@@ -76,4 +76,4 @@ def get_min_version_from_toml(toml_path: str):
 
     print(
         " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-    )  # noqa: T201
+    )

.github/workflows/extract_ignored_words_list.py

@@ -7,4 +7,4 @@
     pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
 )
 
-print(f"::set-output name=ignore_words_list::{ignore_words_list}")  # noqa: T201
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")

cookbook/rag_with_quantized_embeddings.ipynb

@@ -39,12 +39,10 @@
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
-    "\n",
-    "# noqa\n",
     "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# For our example, we'll load docs from the web\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter  # noqa\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "DOCSTORE_DIR = \".\"\n",
     "DOCSTORE_ID_KEY = \"doc_id\""

docs/api_reference/create_api_rst.py

@@ -187,7 +187,7 @@ def _load_package_modules(
             modules_by_namespace[top_namespace] = _module_members
 
         except ImportError as e:
-            print(f"Error: Unable to import module '{namespace}' with error: {e}")  # noqa: T201
+            print(f"Error: Unable to import module '{namespace}' with error: {e}")
 
     return modules_by_namespace
 

docs/docs/how_to/graph_mapping.ipynb

@@ -300,7 +300,7 @@
     "Entities in the question map to the following database values:\n",
     "{entities_list}\n",
     "Question: {question}\n",
-    "Cypher query:\"\"\"  # noqa: E501\n",
+    "Cypher query:\"\"\"\n",
     "\n",
     "cypher_prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -377,7 +377,7 @@
     "response_template = \"\"\"Based on the the question, Cypher query, and Cypher response, write a natural language response:\n",
     "Question: {question}\n",
     "Cypher query: {query}\n",
-    "Cypher Response: {response}\"\"\"  # noqa: E501\n",
+    "Cypher Response: {response}\"\"\"\n",
     "\n",
     "response_prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",

docs/docs/how_to/sql_csv.ipynb

@@ -503,7 +503,7 @@
     }
    ],
    "source": [
-    "chain = prompt | llm_with_tools | parser | tool  # noqa\n",
+    "chain = prompt | llm_with_tools | parser | tool\n",
     "chain.invoke({\"question\": \"What's the correlation between age and fare\"})"
    ]
   },

docs/docs/how_to/sql_large_db.ipynb

@@ -262,7 +262,7 @@
     "    return tables\n",
     "\n",
     "\n",
-    "table_chain = category_chain | get_tables  # noqa\n",
+    "table_chain = category_chain | get_tables\n",
     "table_chain.invoke({\"input\": \"What are all the genres of Alanis Morisette songs\"})"
    ]
   },

docs/docs/integrations/chat/anthropic.ipynb

@@ -670,7 +670,7 @@
     "                \"type\": \"image_url\",\n",
     "                \"image_url\": {\n",
     "                    # langchain logo\n",
-    "                    \"url\": f\"data:image/png;base64,{img_base64}\",  # noqa: E501\n",
+    "                    \"url\": f\"data:image/png;base64,{img_base64}\",\n",
     "                },\n",
     "            },\n",
     "            {\"type\": \"text\", \"text\": \"What is this logo for?\"},\n",

docs/docs/integrations/chat_loaders/discord.ipynb

@@ -95,7 +95,7 @@
     "        \"\"\"\n",
     "        self.path = path\n",
     "        self._message_line_regex = re.compile(\n",
-    "            r\"(.+?) — (\\w{3,9} \\d{1,2}(?:st|nd|rd|th)?(?:, \\d{4})? \\d{1,2}:\\d{2} (?:AM|PM)|Today at \\d{1,2}:\\d{2} (?:AM|PM)|Yesterday at \\d{1,2}:\\d{2} (?:AM|PM))\",  # noqa\n",
+    "            r\"(.+?) — (\\w{3,9} \\d{1,2}(?:st|nd|rd|th)?(?:, \\d{4})? \\d{1,2}:\\d{2} (?:AM|PM)|Today at \\d{1,2}:\\d{2} (?:AM|PM)|Yesterday at \\d{1,2}:\\d{2} (?:AM|PM))\",\n",
     "            flags=re.DOTALL,\n",
     "        )\n",
     "\n",
@@ -120,7 +120,7 @@
     "        current_content = []\n",
     "        for line in lines:\n",
     "            if re.match(\n",
-    "                r\".+? — (\\d{2}/\\d{2}/\\d{4} \\d{1,2}:\\d{2} (?:AM|PM)|Today at \\d{1,2}:\\d{2} (?:AM|PM)|Yesterday at \\d{1,2}:\\d{2} (?:AM|PM))\",  # noqa\n",
+    "                r\".+? — (\\d{2}/\\d{2}/\\d{4} \\d{1,2}:\\d{2} (?:AM|PM)|Today at \\d{1,2}:\\d{2} (?:AM|PM)|Yesterday at \\d{1,2}:\\d{2} (?:AM|PM))\",\n",
     "                line,\n",
     "            ):\n",
     "                if current_sender and current_content:\n",

docs/docs/integrations/chat_loaders/wechat.ipynb

@@ -94,7 +94,7 @@
     "        \"\"\"\n",
     "        self.path = path\n",
     "        self._message_line_regex = re.compile(\n",
-    "            r\"(?P<sender>.+?) (?P<timestamp>\\d{4}/\\d{2}/\\d{2} \\d{1,2}:\\d{2} (?:AM|PM))\",  # noqa\n",
+    "            r\"(?P<sender>.+?) (?P<timestamp>\\d{4}/\\d{2}/\\d{2} \\d{1,2}:\\d{2} (?:AM|PM))\",\n",
     "            # flags=re.DOTALL,\n",
     "        )\n",
     "\n",

docs/docs/integrations/document_loaders/example_data/source_code/example.py

@@ -3,7 +3,7 @@ def __init__(self, name):
         self.name = name
 
     def greet(self):
-        print(f"Hello, {self.name}!")  # noqa: T201
+        print(f"Hello, {self.name}!")
 
 
 def main():

docs/scripts/arxiv_references.py

@@ -389,7 +389,7 @@ def get_papers(
 
         Returns:
             List of ArxivPaper objects.
-        """  # noqa: E501
+        """
 
         def cut_authors(authors: list) -> list[str]:
             if len(authors) > 3:

docs/scripts/generate_api_reference_links.py

@@ -186,7 +186,7 @@ def replacer(match):
     data = code_block_re.sub(replacer, data)
 
     # if all_imports:
-    #     print(f"Adding {len(all_imports)} links for imports in {file}")  # noqa: T201
+    #     print(f"Adding {len(all_imports)} links for imports in {file}")
     with open(file, "w") as f:
         f.write(data)
     return all_imports

docs/scripts/model_feat_table.py

@@ -116,7 +116,7 @@
 
 {table}
 
-"""  # noqa: E501
+"""
 
 CHAT_MODEL_TEMPLATE = """\
 ---
@@ -133,7 +133,7 @@
 
 {table}
 
-"""  # noqa: E501
+"""
 
 
 def get_llm_table():

libs/cli/tests/unit_tests/migrate/test_replace_imports.py

@@ -17,7 +17,7 @@
         "langchain_to_core",
         "community_to_core",
     ]
-)  # type: ignore[attr-defined] # noqa: E501
+)  # type: ignore[attr-defined]
 
 
 class TestReplaceImportsCommand(CodemodTest):

libs/community/langchain_community/callbacks/manager.py

@@ -28,7 +28,7 @@
 wandb_tracing_callback_var: ContextVar[Optional[WandbTracer]] = ContextVar(
     "tracing_wandb_callback", default=None
 )
-comet_tracing_callback_var: ContextVar[Optional[CometTracer]] = ContextVar(  # noqa: E501
+comet_tracing_callback_var: ContextVar[Optional[CometTracer]] = ContextVar(
     "tracing_comet_callback", default=None
 )
 

libs/community/langchain_community/chat_loaders/langsmith.py

@@ -143,7 +143,7 @@ def lazy_load(self) -> Iterator[ChatSession]:
 
         :return: Iterator of chat sessions containing messages.
         """
-        from langchain_community.adapters import openai as oai_adapter  # noqa: E402
+        from langchain_community.adapters import openai as oai_adapter
 
         data = self.client.read_dataset_openai_finetuning(
             dataset_name=self.dataset_name

libs/community/langchain_community/chat_message_histories/cosmos_db.py

@@ -62,7 +62,7 @@ def __init__(
 
         self.messages: List[BaseMessage] = []
         try:
-            from azure.cosmos import (  # pylint: disable=import-outside-toplevel # noqa: E501
+            from azure.cosmos import (  # pylint: disable=import-outside-toplevel
                 CosmosClient,
             )
         except ImportError as exc:
@@ -91,7 +91,7 @@ def prepare_cosmos(self) -> None:
         Use this function or the context manager to make sure your database is ready.
         """
         try:
-            from azure.cosmos import (  # pylint: disable=import-outside-toplevel # noqa: E501
+            from azure.cosmos import (  # pylint: disable=import-outside-toplevel
                 PartitionKey,
             )
         except ImportError as exc:
@@ -128,7 +128,7 @@ def load_messages(self) -> None:
         if not self._container:
             raise ValueError("Container not initialized")
         try:
-            from azure.cosmos.exceptions import (  # pylint: disable=import-outside-toplevel # noqa: E501
+            from azure.cosmos.exceptions import (  # pylint: disable=import-outside-toplevel
                 CosmosHttpResponseError,
             )
         except ImportError as exc:

libs/community/langchain_community/chat_models/azure_openai.py

@@ -85,7 +85,7 @@ class AzureChatOpenAI(ChatOpenAI):
         
         For more: 
         https://www.microsoft.com/en-us/security/business/identity-access/microsoft-entra-id.
-    """  # noqa: E501
+    """
     azure_ad_token_provider: Union[Callable[[], str], None] = None
     """A function that returns an Azure Active Directory token.
         

libs/community/langchain_community/chat_models/azureml_endpoint.py

@@ -233,7 +233,7 @@ class AzureMLChatOnlineEndpoint(BaseChatModel, AzureMLBaseEndpoint):
                 endpoint_api_key="my-api-key",
                 content_formatter=chat_content_formatter,
             )
-    """  # noqa: E501
+    """
 
     @property
     def _identifying_params(self) -> Dict[str, Any]:

libs/community/langchain_community/document_loaders/__init__.py

@@ -214,7 +214,7 @@
         GitHubIssuesLoader,
     )
     from langchain_community.document_loaders.glue_catalog import (
-        GlueCatalogLoader,  # noqa: F401
+        GlueCatalogLoader,
     )
     from langchain_community.document_loaders.google_speech_to_text import (
         GoogleSpeechToTextLoader,
@@ -332,8 +332,8 @@
         OracleAutonomousDatabaseLoader,
     )
     from langchain_community.document_loaders.oracleai import (
-        OracleDocLoader,  # noqa: F401
-        OracleTextSplitter,  # noqa: F401
+        OracleDocLoader,
+        OracleTextSplitter,
     )
     from langchain_community.document_loaders.org_mode import (
         UnstructuredOrgModeLoader,

libs/community/langchain_community/document_loaders/blackboard.py

@@ -31,7 +31,7 @@ class BlackboardLoader(WebBaseLoader):
             )
             documents = loader.load()
 
-    """  # noqa: E501
+    """
 
     def __init__(
         self,

libs/community/langchain_community/document_loaders/evernote.py

@@ -34,7 +34,7 @@ class EverNoteLoader(BaseLoader):
             notes into a single long Document.
         If this is set to True (default) then the only metadata on the document will be
             the 'source' which contains the file name of the export.
-    """  # noqa: E501
+    """
 
     def __init__(self, file_path: Union[str, Path], load_single_document: bool = True):
         """Initialize with file path."""

libs/community/langchain_community/document_loaders/pebblo.py

@@ -208,9 +208,9 @@ def _classify_doc(self, loaded_docs: list, loading_end: bool = False) -> list:
         if loading_end is True:
             payload["loading_end"] = "true"
             if "loader_details" in payload:
-                payload["loader_details"]["source_aggregate_size"] = (  # noqa
-                    self.source_aggregate_size
-                )
+                payload["loader_details"][
+                    "source_aggregate_size"
+                ] = self.source_aggregate_size
         payload = Doc(**payload).dict(exclude_unset=True)
         load_doc_url = f"{self.classifier_url}{LOADER_DOC_URL}"
         classified_docs = []

libs/community/langchain_community/document_transformers/__init__.py

@@ -81,7 +81,7 @@
     "GoogleTranslateTransformer": "langchain_community.document_transformers.google_translate",  # noqa: E501
     "Html2TextTransformer": "langchain_community.document_transformers.html2text",
     "LongContextReorder": "langchain_community.document_transformers.long_context_reorder",  # noqa: E501
-    "MarkdownifyTransformer": "langchain_community.document_transformers.markdownify",  # noqa: E501
+    "MarkdownifyTransformer": "langchain_community.document_transformers.markdownify",
     "NucliaTextTransformer": "langchain_community.document_transformers.nuclia_text_transform",  # noqa: E501
     "OpenAIMetadataTagger": "langchain_community.document_transformers.openai_functions",  # noqa: E501
     "get_stateful_documents": "langchain_community.document_transformers.embeddings_redundant_filter",  # noqa: E501

libs/community/langchain_community/document_transformers/openai_functions.py

@@ -57,7 +57,7 @@ def transform_documents(
         new_documents = []
 
         for document in documents:
-            extracted_metadata: Dict = self.tagging_chain.run(document.page_content)  # type: ignore[assignment]  # noqa: E501
+            extracted_metadata: Dict = self.tagging_chain.run(document.page_content)  # type: ignore[assignment]
             new_document = Document(
                 page_content=document.page_content,
                 metadata={**extracted_metadata, **document.metadata},

libs/community/langchain_community/embeddings/__init__.py

@@ -173,7 +173,7 @@
         QuantizedBiEncoderEmbeddings,
     )
     from langchain_community.embeddings.oracleai import (
-        OracleEmbeddings,  # noqa: F401
+        OracleEmbeddings,
     )
     from langchain_community.embeddings.premai import (
         PremAIEmbeddings,

libs/community/langchain_community/embeddings/azure_openai.py

@@ -44,7 +44,7 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings):
 
         For more: 
         https://www.microsoft.com/en-us/security/business/identity-access/microsoft-entra-id.
-    """  # noqa: E501
+    """
     azure_ad_token_provider: Union[Callable[[], str], None] = None
     """A function that returns an Azure Active Directory token.
 

libs/community/langchain_community/embeddings/elasticsearch.py

@@ -25,7 +25,7 @@ class ElasticsearchEmbeddings(Embeddings):
     In Elasticsearch you need to have an embedding model loaded and deployed.
     - https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-trained-model.html
     - https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-deploy-models.html
-    """  # noqa: E501
+    """
 
     def __init__(
         self,

libs/community/langchain_community/embeddings/infinity.py

@@ -182,7 +182,7 @@ def _permute(
         length_sorted_idx = np.argsort([-sorter(sen) for sen in texts])
         texts_sorted = [texts[idx] for idx in length_sorted_idx]
 
-        return texts_sorted, lambda unsorted_embeddings: [  # noqa E731
+        return texts_sorted, lambda unsorted_embeddings: [  # E731
             unsorted_embeddings[idx] for idx in np.argsort(length_sorted_idx)
         ]
 

libs/community/langchain_community/embeddings/localai.py

@@ -254,7 +254,7 @@ def _invocation_params(self) -> Dict:
             openai.proxy = {
                 "http": self.openai_proxy,
                 "https": self.openai_proxy,
-            }  # type: ignore[assignment]  # noqa: E501
+            }  # type: ignore[assignment]
         return openai_args
 
     def _embedding_func(self, text: str, *, engine: str) -> List[float]:

libs/community/langchain_community/embeddings/openai.py

@@ -390,7 +390,7 @@ def _invocation_params(self) -> Dict[str, Any]:
                 openai.proxy = {
                     "http": self.openai_proxy,
                     "https": self.openai_proxy,
-                }  # type: ignore[assignment]  # noqa: E501
+                }  # type: ignore[assignment]
         return openai_args
 
     # please refer to

libs/community/langchain_community/embeddings/yandex.py

@@ -107,13 +107,13 @@ def validate_environment(cls, values: Dict) -> Dict:
                 raise ValueError("'doc_model_uri' or 'folder_id' must be provided.")
             values[
                 "doc_model_uri"
-            ] = f"emb://{values['folder_id']}/{values['doc_model_name']}/{values['model_version']}"  # noqa: E501
+            ] = f"emb://{values['folder_id']}/{values['doc_model_name']}/{values['model_version']}"
         if not values.get("model_uri"):
             if values["folder_id"] == "":
                 raise ValueError("'model_uri' or 'folder_id' must be provided.")
             values[
                 "model_uri"
-            ] = f"emb://{values['folder_id']}/{values['model_name']}/{values['model_version']}"  # noqa: E501
+            ] = f"emb://{values['folder_id']}/{values['model_name']}/{values['model_version']}"
         if values["disable_request_logging"]:
             values["_grpc_metadata"].append(
                 (

libs/community/langchain_community/graphs/arangodb_graph.py

@@ -174,9 +174,9 @@ def get_arangodb_client(
             "Unable to import arango, please install with `pip install python-arango`."
         ) from e
 
-    _url: str = url or os.environ.get("ARANGODB_URL", "http://localhost:8529")  # type: ignore[assignment]  # noqa: E501
-    _dbname: str = dbname or os.environ.get("ARANGODB_DBNAME", "_system")  # type: ignore[assignment]  # noqa: E501
-    _username: str = username or os.environ.get("ARANGODB_USERNAME", "root")  # type: ignore[assignment]  # noqa: E501
-    _password: str = password or os.environ.get("ARANGODB_PASSWORD", "")  # type: ignore[assignment]  # noqa: E501
+    _url: str = url or os.environ.get("ARANGODB_URL", "http://localhost:8529")  # type: ignore[assignment]
+    _dbname: str = dbname or os.environ.get("ARANGODB_DBNAME", "_system")  # type: ignore[assignment]
+    _username: str = username or os.environ.get("ARANGODB_USERNAME", "root")  # type: ignore[assignment]
+    _password: str = password or os.environ.get("ARANGODB_PASSWORD", "")  # type: ignore[assignment]
 
     return ArangoClient(_url).db(_dbname, _username, _password, verify=True)

libs/community/langchain_community/llms/azureml_endpoint.py

@@ -496,7 +496,7 @@ class AzureMLOnlineEndpoint(BaseLLM, AzureMLBaseEndpoint):
                 timeout=120,
                 content_formatter=content_formatter,
             )
-    """  # noqa: E501
+    """
 
     @property
     def _identifying_params(self) -> Mapping[str, Any]: