community[patch]: upgrade to recent version of mypy (#21616)

This PR upgrades community to a recent version of mypy. It inserts type:
ignore on all existing failures.

libs/community/langchain_community/document_loaders/base_o365.py

@@ -70,7 +70,7 @@ def fetch_mime_types(file_types: Sequence[_FileType]) -> Dict[str, str]:
 class O365BaseLoader(BaseLoader, BaseModel):
     """Base class for all loaders that uses O365 Package"""
 
-    settings: _O365Settings = Field(default_factory=_O365Settings)
+    settings: _O365Settings = Field(default_factory=_O365Settings)  # type: ignore[arg-type]
     """Settings for the Office365 API client."""
     auth_with_token: bool = False
     """Whether to authenticate with a token or not. Defaults to False."""

libs/community/langchain_community/document_loaders/kinetica_loader.py

@@ -86,7 +86,7 @@ class KineticaLoader(BaseLoader):
         query_result = self._execute_query()
         if isinstance(query_result, Exception):
             print(f"An error occurred during the query: {query_result}")  # noqa: T201
-            return []
+            return []  # type: ignore[return-value]
         page_content_columns, metadata_columns = self._get_columns(query_result)
         if "*" in page_content_columns:
             page_content_columns = list(query_result[0].keys())

libs/community/langchain_community/document_loaders/mhtml.py

@@ -58,8 +58,8 @@ class MHTMLLoader(BaseLoader):
                 parts = [message]
 
             for part in parts:
-                if part.get_content_type() == "text/html":
-                    html = part.get_payload(decode=True).decode()
+                if part.get_content_type() == "text/html":  # type: ignore[union-attr]
+                    html = part.get_payload(decode=True).decode()  # type: ignore[union-attr]
 
                     soup = BeautifulSoup(html, **self.bs_kwargs)
                     text = soup.get_text(self.get_text_separator)

libs/community/langchain_community/document_loaders/onenote.py

@@ -31,7 +31,7 @@ class _OneNoteGraphSettings(BaseSettings):
 class OneNoteLoader(BaseLoader, BaseModel):
     """Load pages from OneNote notebooks."""
 
-    settings: _OneNoteGraphSettings = Field(default_factory=_OneNoteGraphSettings)
+    settings: _OneNoteGraphSettings = Field(default_factory=_OneNoteGraphSettings)  # type: ignore[arg-type]
     """Settings for the Microsoft Graph API client."""
     auth_with_token: bool = False
     """Whether to authenticate with a token or not. Defaults to False."""

libs/community/langchain_community/document_loaders/pdf.py

@@ -691,7 +691,7 @@ class AmazonTextractPDFLoader(BasePDFLoader):
         # raises ValueError when multi-page and not on S3"""
 
         if self.web_path and self._is_s3_url(self.web_path):
-            blob = Blob(path=self.web_path)  # type: ignore[misc]
+            blob = Blob(path=self.web_path)  # type: ignore[call-arg] # type: ignore[misc]
         else:
             blob = Blob.from_path(self.file_path)  # type: ignore[attr-defined]
             if AmazonTextractPDFLoader._get_number_of_pages(blob) > 1:

libs/community/langchain_community/document_loaders/pubmed.py

@@ -28,8 +28,8 @@ class PubMedLoader(BaseLoader):
         """
         self.query = query
         self.load_max_docs = load_max_docs
-        self._client = PubMedAPIWrapper(
-            top_k_results=load_max_docs,
+        self._client = PubMedAPIWrapper(  # type: ignore[call-arg]
+            top_k_results=load_max_docs,  # type: ignore[arg-type]
         )
 
     def lazy_load(self) -> Iterator[Document]:

libs/community/langchain_community/document_loaders/snowflake_loader.py

@@ -111,7 +111,7 @@ class SnowflakeLoader(BaseLoader):
         query_result = self._execute_query()
         if isinstance(query_result, Exception):
             print(f"An error occurred during the query: {query_result}")  # noqa: T201
-            return []
+            return []  # type: ignore[return-value]
         page_content_columns, metadata_columns = self._get_columns(query_result)
         if "*" in page_content_columns:
             page_content_columns = list(query_result[0].keys())

libs/community/langchain_community/document_loaders/tensorflow_datasets.py

@@ -66,10 +66,10 @@ class TensorflowDatasetLoader(BaseLoader):
         ] = sample_to_document_function
         """Custom function that transform a dataset sample into a Document."""
 
-        self._tfds_client = TensorflowDatasets(
+        self._tfds_client = TensorflowDatasets(  # type: ignore[call-arg]
             dataset_name=self.dataset_name,
             split_name=self.split_name,
-            load_max_docs=self.load_max_docs,
+            load_max_docs=self.load_max_docs,  # type: ignore[arg-type]
             sample_to_document_function=self.sample_to_document_function,
         )
 

libs/community/langchain_community/document_loaders/weather.py

@@ -32,7 +32,7 @@ class WeatherDataLoader(BaseLoader):
     def from_params(
         cls, places: Sequence[str], *, openweathermap_api_key: Optional[str] = None
     ) -> WeatherDataLoader:
-        client = OpenWeatherMapAPIWrapper(openweathermap_api_key=openweathermap_api_key)
+        client = OpenWeatherMapAPIWrapper(openweathermap_api_key=openweathermap_api_key)  # type: ignore[call-arg]
         return cls(client, places)
 
     def lazy_load(

libs/community/langchain_community/document_loaders/wikipedia.py

@@ -50,10 +50,10 @@ class WikipediaLoader(BaseLoader):
             A list of Document objects representing the loaded
                 Wikipedia pages.
         """
-        client = WikipediaAPIWrapper(
+        client = WikipediaAPIWrapper(  # type: ignore[call-arg]
             lang=self.lang,
-            top_k_results=self.load_max_docs,
-            load_all_available_meta=self.load_all_available_meta,
-            doc_content_chars_max=self.doc_content_chars_max,
+            top_k_results=self.load_max_docs,  # type: ignore[arg-type]
+            load_all_available_meta=self.load_all_available_meta,  # type: ignore[arg-type]
+            doc_content_chars_max=self.doc_content_chars_max,  # type: ignore[arg-type]
         )
         yield from client.load(self.query)