docstrings: document_loaders consitency (#9139)

Formatted docstrings from different formats to consistent format, lile:
>Loads processed docs from Docugami.
"Load from `Docugami`."

>Loader that uses Unstructured to load HTML files.
"Load `HTML` files using `Unstructured`."

>Load documents from a directory.
"Load from a directory."
 
- `Load` - no `Loads`
- DocumentLoader always loads Documents, so no more
"documents/docs/texts/ etc"
- integrated systems and APIs enclosed in backticks,

libs/langchain/langchain/document_loaders/acreom.py

@@ -1,4 +1,3 @@
-"""Loads acreom vault from a directory."""
 import re
 from pathlib import Path
 from typing import Iterator, List
@@ -8,7 +7,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class AcreomLoader(BaseLoader):
-    """Loader that loads acreom vault from a directory."""
+    """Load `acreom` vault from a directory."""
 
     FRONT_MATTER_REGEX = re.compile(r"^---\n(.*?)\n---\n", re.MULTILINE | re.DOTALL)
     """Regex to match front matter metadata in markdown files."""
@@ -16,6 +15,7 @@ class AcreomLoader(BaseLoader):
     def __init__(
         self, path: str, encoding: str = "UTF-8", collect_metadata: bool = True
     ):
+        """Initialize the loader."""
         self.file_path = path
         """Path to the directory containing the markdown files."""
         self.encoding = encoding

libs/langchain/langchain/document_loaders/airbyte.py

@@ -1,4 +1,3 @@
-"""Loads local airbyte json files."""
 from typing import Any, Callable, Iterator, List, Mapping, Optional
 
 from langchain.docstore.document import Document
@@ -9,7 +8,7 @@ RecordHandler = Callable[[Any, Optional[str]], Document]
 
 
 class AirbyteCDKLoader(BaseLoader):
-    """Loads records using an Airbyte source connector implemented using the CDK."""
+    """Load with an `Airbyte` source connector implemented using the `CDK`."""
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/airbyte_json.py

@@ -1,4 +1,3 @@
-"""Loads local airbyte json files."""
 import json
 from typing import List
 
@@ -8,7 +7,7 @@ from langchain.utils import stringify_dict
 
 
 class AirbyteJSONLoader(BaseLoader):
-    """Loads local airbyte json files."""
+    """Load local `Airbyte` json files."""
 
     def __init__(self, file_path: str):
         """Initialize with a file path. This should start with '/tmp/airbyte_local/'."""

libs/langchain/langchain/document_loaders/airtable.py

@@ -5,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class AirtableLoader(BaseLoader):
-    """Loader for Airtable tables."""
+    """Load the `Airtable` tables."""
 
     def __init__(self, api_token: str, table_id: str, base_id: str):
         """Initialize with API token and the IDs for table and base"""

libs/langchain/langchain/document_loaders/apify_dataset.py

@@ -7,7 +7,8 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class ApifyDatasetLoader(BaseLoader, BaseModel):
-    """Loads datasets from Apify-a web scraping, crawling, and data extraction platform.
+    """Load datasets from `Apify` web scraping, crawling, and data extraction platform.
+
     For details, see https://docs.apify.com/platform/integrations/langchain
 
     Example:

libs/langchain/langchain/document_loaders/arxiv.py

@@ -6,7 +6,7 @@ from langchain.utilities.arxiv import ArxivAPIWrapper
 
 
 class ArxivLoader(BaseLoader):
-    """Loads a query result from arxiv.org into a list of Documents.
+    """Load a query result from `Arxiv`.
 
     The loader converts the original PDF format into the text.
     """

libs/langchain/langchain/document_loaders/async_html.py

@@ -24,7 +24,7 @@ default_header_template = {
 
 
 class AsyncHtmlLoader(BaseLoader):
-    """Loads HTML asynchronously."""
+    """Load `HTML` asynchronously."""
 
     def __init__(
         self,
@@ -36,7 +36,7 @@ class AsyncHtmlLoader(BaseLoader):
         requests_kwargs: Dict[str, Any] = {},
         raise_for_status: bool = False,
     ):
-        """Initialize with webpage path."""
+        """Initialize with a webpage path."""
 
         # TODO: Deprecate web_path in favor of web_paths, and remove this
         # left like this because there are a number of loaders that expect single

libs/langchain/langchain/document_loaders/azlyrics.py

@@ -1,4 +1,3 @@
-"""Loads AZLyrics."""
 from typing import List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,7 @@ from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class AZLyricsLoader(WebBaseLoader):
-    """Loads AZLyrics webpages."""
+    """Load `AZLyrics` webpages."""
 
     def load(self) -> List[Document]:
         """Load webpages into Documents."""

libs/langchain/langchain/document_loaders/azure_blob_storage_container.py

@@ -1,4 +1,3 @@
-"""Loading logic for loading documents from an Azure Blob Storage container."""
 from typing import List
 
 from langchain.docstore.document import Document
@@ -9,7 +8,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class AzureBlobStorageContainerLoader(BaseLoader):
-    """Loading Documents from Azure Blob Storage."""
+    """Load from `Azure Blob Storage` container."""
 
     def __init__(self, conn_str: str, container: str, prefix: str = ""):
         """Initialize with connection string, container and blob prefix."""

libs/langchain/langchain/document_loaders/azure_blob_storage_file.py

@@ -8,7 +8,7 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class AzureBlobStorageFileLoader(BaseLoader):
-    """Loading Documents from Azure Blob Storage."""
+    """Load from `Azure Blob Storage` files."""
 
     def __init__(self, conn_str: str, container: str, blob_name: str):
         """Initialize with connection string, container and blob name."""

libs/langchain/langchain/document_loaders/base.py

@@ -8,7 +8,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter, TextSplitter
 
 
 class BaseLoader(ABC):
-    """Interface for loading Documents.
+    """Interface for Document Loader.
 
     Implementations should implement the lazy-loading method using generators
     to avoid loading all Documents into memory at once.

libs/langchain/langchain/document_loaders/bibtex.py

@@ -11,7 +11,7 @@ logger = logging.getLogger(__name__)
 
 
 class BibtexLoader(BaseLoader):
-    """Loads a bibtex file into a list of Documents.
+    """Load a `bibtex` file.
 
     Each document represents one entry from the bibtex file.
 

libs/langchain/langchain/document_loaders/bigquery.py

@@ -10,7 +10,7 @@ if TYPE_CHECKING:
 
 
 class BigQueryLoader(BaseLoader):
-    """Loads a query result from BigQuery into a list of documents.
+    """Load from the Google Cloud Platform `BigQuery`.
 
     Each document represents one row of the result. The `page_content_columns`
     are written into the `page_content` of the document. The `metadata_columns`

libs/langchain/langchain/document_loaders/bilibili.py

@@ -10,7 +10,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class BiliBiliLoader(BaseLoader):
-    """Loads bilibili transcripts."""
+    """Load `BiliBili` video transcripts."""
 
     def __init__(self, video_urls: List[str]):
         """Initialize with bilibili url.

libs/langchain/langchain/document_loaders/blackboard.py

@@ -1,4 +1,3 @@
-"""Loads all documents from a blackboard course."""
 import contextlib
 import re
 from pathlib import Path
@@ -12,7 +11,7 @@ from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class BlackboardLoader(WebBaseLoader):
-    """Loads all documents from a Blackboard course.
+    """Load a `Blackboard` course.
 
     This loader is not compatible with all Blackboard courses. It is only
     compatible with courses that use the new Blackboard interface.

libs/langchain/langchain/document_loaders/blockchain.py

@@ -20,7 +20,7 @@ class BlockchainType(Enum):
 
 
 class BlockchainDocumentLoader(BaseLoader):
-    """Loads elements from a blockchain smart contract into Langchain documents.
+    """Load elements from a blockchain smart contract.
 
     The supported blockchains are: Ethereum mainnet, Ethereum Goerli testnet,
     Polygon mainnet, and Polygon Mumbai testnet.

libs/langchain/langchain/document_loaders/brave_search.py

@@ -6,7 +6,7 @@ from langchain.utilities.brave_search import BraveSearchWrapper
 
 
 class BraveSearchLoader(BaseLoader):
-    """Loads a query result from Brave Search engine into a list of Documents."""
+    """Load with `Brave Search` engine."""
 
     def __init__(self, query: str, api_key: str, search_kwargs: Optional[dict] = None):
         """Initializes the BraveLoader.

libs/langchain/langchain/document_loaders/browserless.py

@@ -7,7 +7,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class BrowserlessLoader(BaseLoader):
-    """Loads the content of webpages using Browserless' /content endpoint"""
+    """Load webpages with `Browserless` /content endpoint."""
 
     def __init__(
         self, api_token: str, urls: Union[str, List[str]], text_content: bool = True

libs/langchain/langchain/document_loaders/chatgpt.py

@@ -1,4 +1,3 @@
-"""Load conversations from ChatGPT data export"""
 import datetime
 import json
 from typing import List
@@ -29,7 +28,7 @@ def concatenate_rows(message: dict, title: str) -> str:
 
 
 class ChatGPTLoader(BaseLoader):
-    """Load conversations from exported ChatGPT data."""
+    """Load conversations from exported `ChatGPT` data."""
 
     def __init__(self, log_file: str, num_logs: int = -1):
         """Initialize a class object.

libs/langchain/langchain/document_loaders/college_confidential.py

@@ -1,4 +1,3 @@
-"""Loads College Confidential."""
 from typing import List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,7 @@ from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class CollegeConfidentialLoader(WebBaseLoader):
-    """Loads College Confidential webpages."""
+    """Load `College Confidential` webpages."""
 
     def load(self) -> List[Document]:
         """Load webpages as Documents."""

libs/langchain/langchain/document_loaders/concurrent.py

@@ -16,9 +16,7 @@ DEFAULT = Literal["default"]
 
 
 class ConcurrentLoader(GenericLoader):
-    """
-    A generic document loader that loads and parses documents concurrently.
-    """
+    """Load and pars Documents concurrently."""
 
     def __init__(
         self, blob_loader: BlobLoader, blob_parser: BaseBlobParser, num_workers: int = 4

libs/langchain/langchain/document_loaders/confluence.py

@@ -1,4 +1,3 @@
-"""Load Data from a Confluence Space"""
 import logging
 from enum import Enum
 from io import BytesIO
@@ -33,7 +32,7 @@ class ContentFormat(str, Enum):
 
 
 class ConfluenceLoader(BaseLoader):
-    """Load Confluence pages.
+    """Load `Confluence` pages.
 
     Port of https://llamahub.ai/l/confluence
     This currently supports username/api_key, Oauth2 login or personal access token

libs/langchain/langchain/document_loaders/conllu.py

@@ -1,4 +1,3 @@
-"""Load CoNLL-U files."""
 import csv
 from typing import List
 
@@ -7,7 +6,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class CoNLLULoader(BaseLoader):
-    """Load CoNLL-U files."""
+    """Load `CoNLL-U` files."""
 
     def __init__(self, file_path: str):
         """Initialize with a file path."""

libs/langchain/langchain/document_loaders/csv_loader.py

@@ -10,7 +10,7 @@ from langchain.document_loaders.unstructured import (
 
 
 class CSVLoader(BaseLoader):
-    """Loads a CSV file into a list of documents.
+    """Load a `CSV` file into a list of Documents.
 
     Each document represents one row of the CSV file. Every row is converted into a
     key/value pair and outputted to a new line in the document's page_content.

libs/langchain/langchain/document_loaders/cube_semantic.py

@@ -12,7 +12,7 @@ logger = logging.getLogger(__name__)
 
 
 class CubeSemanticLoader(BaseLoader):
-    """Load Cube semantic layer metadata.
+    """Load `Cube semantic layer` metadata.
 
     Args:
         cube_api_url: REST API endpoint.

libs/langchain/langchain/document_loaders/datadog_logs.py

@@ -1,4 +1,3 @@
-"""Load Datadog logs."""
 from datetime import datetime, timedelta
 from typing import List, Optional
 
@@ -7,7 +6,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class DatadogLogsLoader(BaseLoader):
-    """Loads a query result from Datadog into a list of documents.
+    """Load `Datadog` logs.
 
     Logs are written into the `page_content` and into the `metadata`.
     """

libs/langchain/langchain/document_loaders/dataframe.py

@@ -1,4 +1,3 @@
-"""Load from a Dataframe object"""
 from typing import Any, Iterator, List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class DataFrameLoader(BaseLoader):
-    """Load Pandas DataFrame."""
+    """Load `Pandas` DataFrame."""
 
     def __init__(self, data_frame: Any, page_content_column: str = "text"):
         """Initialize with dataframe object.

libs/langchain/langchain/document_loaders/diffbot.py

@@ -1,4 +1,3 @@
-"""Loader that uses Diffbot to load webpages in text format."""
 import logging
 from typing import Any, List
 
@@ -11,7 +10,7 @@ logger = logging.getLogger(__name__)
 
 
 class DiffbotLoader(BaseLoader):
-    """Loads Diffbot file json."""
+    """Load `Diffbot` json file."""
 
     def __init__(
         self, api_token: str, urls: List[str], continue_on_failure: bool = True

libs/langchain/langchain/document_loaders/directory.py

@@ -1,4 +1,3 @@
-"""Load documents from a directory."""
 import concurrent
 import logging
 import random
@@ -26,7 +25,7 @@ def _is_visible(p: Path) -> bool:
 
 
 class DirectoryLoader(BaseLoader):
-    """Load documents from a directory."""
+    """Load from a directory."""
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/discord.py

@@ -1,4 +1,3 @@
-"""Load from Discord chat dump"""
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, List
@@ -11,7 +10,7 @@ if TYPE_CHECKING:
 
 
 class DiscordChatLoader(BaseLoader):
-    """Load Discord chat logs."""
+    """Load `Discord` chat logs."""
 
     def __init__(self, chat_log: pd.DataFrame, user_id_col: str = "ID"):
         """Initialize with a Pandas DataFrame containing chat logs.

libs/langchain/langchain/document_loaders/docugami.py

@@ -1,5 +1,3 @@
-"""Loads processed documents from Docugami."""
-
 import io
 import logging
 import os
@@ -29,7 +27,7 @@ logger = logging.getLogger(__name__)
 
 
 class DocugamiLoader(BaseLoader, BaseModel):
-    """Loads processed docs from Docugami.
+    """Load from `Docugami`.
 
     To use, you should have the ``lxml`` python package installed.
     """

libs/langchain/langchain/document_loaders/dropbox.py

@@ -1,5 +1,3 @@
-"""Loads data from Dropbox."""
-
 # Prerequisites:
 # 1. Create a Dropbox app.
 # 2. Give the app these scope permissions: `files.metadata.read`
@@ -20,7 +18,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class DropboxLoader(BaseLoader, BaseModel):
-    """Loads files from Dropbox.
+    """Load files from `Dropbox`.
 
     In addition to common files such as text and PDF files, it also supports
     *Dropbox Paper* files.

libs/langchain/langchain/document_loaders/duckdb_loader.py

@@ -5,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class DuckDBLoader(BaseLoader):
-    """Loads a query result from DuckDB into a list of documents.
+    """Load from `DuckDB`.
 
     Each document represents one row of the result. The `page_content_columns`
     are written into the `page_content` of the document. The `metadata_columns`

libs/langchain/langchain/document_loaders/email.py

@@ -1,4 +1,3 @@
-"""Loads email files."""
 import os
 from typing import Any, List
 
@@ -11,7 +10,9 @@ from langchain.document_loaders.unstructured import (
 
 
 class UnstructuredEmailLoader(UnstructuredFileLoader):
-    """Loader that uses unstructured to load email files. Works with both
+    """Load email files with `unstructured`.
+
+    Works with both
     .eml and .msg files. You can process attachments in addition to the
     e-mail message itself by passing process_attachments=True into the
     constructor for the loader. By default, attachments will be processed

libs/langchain/langchain/document_loaders/embaas.py

@@ -52,7 +52,7 @@ class EmbaasDocumentExtractionPayload(EmbaasDocumentExtractionParameters):
 
 
 class BaseEmbaasLoader(BaseModel):
-    """Base class for embedding a model into an Embaas document extraction API."""
+    """Base loader for embedding a model into an `Embaas` document extraction API."""
 
     embaas_api_key: Optional[str] = None
     """The API key for the embaas document extraction API."""
@@ -72,7 +72,7 @@ class BaseEmbaasLoader(BaseModel):
 
 
 class EmbaasBlobLoader(BaseEmbaasLoader, BaseBlobParser):
-    """Embaas's document byte loader.
+    """Load `Embaas` blob.
 
     To use, you should have the
     environment variable ``EMBAAS_API_KEY`` set with your API key, or pass
@@ -178,7 +178,7 @@ class EmbaasBlobLoader(BaseEmbaasLoader, BaseBlobParser):
 
 
 class EmbaasLoader(BaseEmbaasLoader, BaseLoader):
-    """Embaas's document loader.
+    """Load from `Embaas`.
 
     To use, you should have the
     environment variable ``EMBAAS_API_KEY`` set with your API key, or pass

libs/langchain/langchain/document_loaders/epub.py

@@ -1,4 +1,3 @@
-"""Loads EPub files."""
 from typing import List
 
 from langchain.document_loaders.unstructured import (
@@ -8,7 +7,7 @@ from langchain.document_loaders.unstructured import (
 
 
 class UnstructuredEPubLoader(UnstructuredFileLoader):
-    """Loader that uses Unstructured to load EPUB files.
+    """Load `EPub` files using `Unstructured`.
 
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single

libs/langchain/langchain/document_loaders/etherscan.py

@@ -9,8 +9,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class EtherscanLoader(BaseLoader):
-    """
-    Load transactions from an account on Ethereum mainnet.
+    """Load transactions from `Ethereum` mainnet.
 
     The Loader use Etherscan API to interact with Ethereum mainnet.
 

libs/langchain/langchain/document_loaders/evernote.py

@@ -15,7 +15,7 @@ logger = logging.getLogger(__name__)
 
 
 class EverNoteLoader(BaseLoader):
-    """EverNote Loader.
+    """Load from `EverNote`.
 
     Loads an EverNote notebook export file e.g. my_notebook.enex into Documents.
     Instructions on producing this file can be found at

libs/langchain/langchain/document_loaders/excel.py

@@ -8,7 +8,9 @@ from langchain.document_loaders.unstructured import (
 
 
 class UnstructuredExcelLoader(UnstructuredFileLoader):
-    """Loader that uses unstructured to load Excel files. Like other
+    """Load Microsoft Excel files using `Unstructured`.
+
+    Like other
     Unstructured loaders, UnstructuredExcelLoader can be used in both
     "single" and "elements" mode. If you use the loader in "elements"
     mode, each sheet in the Excel file will be a an Unstructured Table

libs/langchain/langchain/document_loaders/facebook_chat.py

@@ -1,4 +1,3 @@
-"""Loads Facebook chat json dump."""
 import datetime
 import json
 from pathlib import Path
@@ -23,7 +22,7 @@ def concatenate_rows(row: dict) -> str:
 
 
 class FacebookChatLoader(BaseLoader):
-    """Loads Facebook messages json directory dump."""
+    """Load `Facebook Chat` messages directory dump."""
 
     def __init__(self, path: str):
         """Initialize with a path."""

libs/langchain/langchain/document_loaders/fauna.py

@@ -5,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class FaunaLoader(BaseLoader):
-    """FaunaDB Loader.
+    """Load from `FaunaDB`.
 
     Attributes:
         query (str): The FQL query string to execute.

libs/langchain/langchain/document_loaders/figma.py

@@ -1,4 +1,3 @@
-"""Loads Figma files json dump."""
 import json
 import urllib.request
 from typing import Any, List
@@ -9,7 +8,7 @@ from langchain.utils import stringify_dict
 
 
 class FigmaFileLoader(BaseLoader):
-    """Loads Figma file json."""
+    """Load `Figma` file."""
 
     def __init__(self, access_token: str, ids: str, key: str):
         """Initialize with access token, ids, and key.

libs/langchain/langchain/document_loaders/gcs_directory.py

@@ -1,4 +1,3 @@
-"""Loading logic for loading documents from an GCS directory."""
 from typing import Callable, List, Optional
 
 from langchain.docstore.document import Document
@@ -7,7 +6,7 @@ from langchain.document_loaders.gcs_file import GCSFileLoader
 
 
 class GCSDirectoryLoader(BaseLoader):
-    """Loads Documents from GCS."""
+    """Load from GCS directory."""
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/gcs_file.py

@@ -1,4 +1,3 @@
-"""Load documents from a GCS file."""
 import os
 import tempfile
 from typing import Callable, List, Optional
@@ -9,7 +8,7 @@ from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class GCSFileLoader(BaseLoader):
-    """Load Documents from a GCS file."""
+    """Load from GCS file."""
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/generic.py

@@ -15,7 +15,7 @@ DEFAULT = Literal["default"]
 
 
 class GenericLoader(BaseLoader):
-    """A generic document loader.
+    """Generic Document Loader.
 
     A generic document loader that allows combining an arbitrary blob loader with
     a blob parser.

libs/langchain/langchain/document_loaders/geodataframe.py

@@ -1,4 +1,3 @@
-"""Load from Dataframe object"""
 from typing import Any, Iterator, List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class GeoDataFrameLoader(BaseLoader):
-    """Load geopandas Dataframe."""
+    """Load `geopandas` Dataframe."""
 
     def __init__(self, data_frame: Any, page_content_column: str = "geometry"):
         """Initialize with geopandas Dataframe.

libs/langchain/langchain/document_loaders/git.py

@@ -6,7 +6,8 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class GitLoader(BaseLoader):
-    """Loads files from a Git repository into a list of documents.
+    """Load `Git` repository files.
+
     The Repository can be local on disk available at `repo_path`,
     or remote at `clone_url` that will be cloned to `repo_path`.
     Currently, supports only text files.

libs/langchain/langchain/document_loaders/gitbook.py

@@ -1,4 +1,3 @@
-"""Loads GitBook."""
 from typing import Any, List, Optional
 from urllib.parse import urljoin, urlparse
 
@@ -7,7 +6,7 @@ from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class GitbookLoader(WebBaseLoader):
-    """Load GitBook data.
+    """Load `GitBook` data.
 
     1. load from either a single page, or
     2. load all (relative) paths in the navbar.

libs/langchain/langchain/document_loaders/github.py

@@ -11,7 +11,7 @@ from langchain.utils import get_from_dict_or_env
 
 
 class BaseGitHubLoader(BaseLoader, BaseModel, ABC):
-    """Load issues of a GitHub repository."""
+    """Load `GitHub` repository Issues."""
 
     repo: str
     """Name of repository"""

libs/langchain/langchain/document_loaders/googledrive.py

@@ -1,5 +1,3 @@
-"""Loads data from Google Drive."""
-
 # Prerequisites:
 # 1. Create a Google Cloud project
 # 2. Enable the Google Drive API:
@@ -22,7 +20,7 @@ SCOPES = ["https://www.googleapis.com/auth/drive.readonly"]
 
 
 class GoogleDriveLoader(BaseLoader, BaseModel):
-    """Loads Google Docs from Google Drive."""
+    """Load Google Docs from `Google Drive`."""
 
     service_account_key: Path = Path.home() / ".credentials" / "keys.json"
     """Path to the service account key file."""

libs/langchain/langchain/document_loaders/gutenberg.py

@@ -1,4 +1,3 @@
-"""Loads .txt web files."""
 from typing import List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,7 @@ from langchain.document_loaders.base import BaseLoader
 
 
 class GutenbergLoader(BaseLoader):
-    """Loader that uses urllib to load .txt web files."""
+    """Load from `Gutenberg.org`."""
 
     def __init__(self, file_path: str):
         """Initialize with a file path."""

libs/langchain/langchain/document_loaders/hn.py

@@ -1,4 +1,3 @@
-"""Loads HN."""
 from typing import Any, List
 
 from langchain.docstore.document import Document
@@ -6,7 +5,9 @@ from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class HNLoader(WebBaseLoader):
-    """Load Hacker News data from either main page results or the comments page."""
+    """Load `Hacker News` data.
+
+    It loads data from either main page results or the comments page."""
 
     def load(self) -> List[Document]:
         """Get important HN webpage information.

libs/langchain/langchain/document_loaders/html.py

@@ -1,11 +1,10 @@
-"""Loader that uses unstructured to load HTML files."""
 from typing import List
 
 from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredHTMLLoader(UnstructuredFileLoader):
-    """Loader that uses Unstructured to load HTML files.
+    """Load `HTML` files using `Unstructured`.
 
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single

libs/langchain/langchain/document_loaders/html_bs.py

@@ -1,5 +1,3 @@
-"""Loader that uses bs4 to load HTML files, enriching metadata with page title."""
-
 import logging
 from typing import Dict, List, Union
 
@@ -10,7 +8,7 @@ logger = logging.getLogger(__name__)
 
 
 class BSHTMLLoader(BaseLoader):
-    """Loader that uses beautiful soup to parse HTML files."""
+    """Load `HTML` files and parse them with `beautiful soup`."""
 
     def __init__(
         self,