langchain/libs/community/langchain_community/document_loaders/base_o365.py
MacanPN bce69ae43d
community[patch]: Changes to base_o365 and sharepoint document loaders (#20373)
## Description:
The PR introduces 3 changes:
1. added `recursive` property to `O365BaseLoader`. (To keep the behavior
unchanged, by default is set to `False`). When `recursive=True`,
`_load_from_folder()` also recursively loads all nested folders.
2. added `folder_id` to SharePointLoader.(similar to (this
PR)[https://github.com/langchain-ai/langchain/pull/10780] ) This
provides an alternative to `folder_path` that doesn't seem to reliably
work.
3. when none of `document_ids`, `folder_id`, `folder_path` is provided,
the loader fetches documets from root folder. Combined with
`recursive=True` this provides an easy way of loading all compatible
documents from SharePoint.

The PR contains the same logic as [this stale
PR](https://github.com/langchain-ai/langchain/pull/10780) by
@WaleedAlfaris. I'd like to ask his blessing for moving forward with
this one.

## Issue:
- As described in https://github.com/langchain-ai/langchain/issues/19938
and https://github.com/langchain-ai/langchain/pull/10780 the sharepoint
loader often does not seem to work with folder_path.
- Recursive loading of subfolders is a missing functionality

## Dependecies: None

Twitter handle:
@martintriska1 @WRhetoric

This is my first PR here, please be gentle :-)
Please review @baskaryan

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-17 00:36:15 +00:00

200 lines
7.1 KiB
Python

"""Base class for all loaders that uses O365 Package"""
from __future__ import annotations
import logging
import os
import tempfile
from abc import abstractmethod
from enum import Enum
from pathlib import Path
from typing import TYPE_CHECKING, Dict, Iterable, List, Sequence, Union
from langchain_core.pydantic_v1 import (
BaseModel,
BaseSettings,
Field,
FilePath,
SecretStr,
)
from langchain_community.document_loaders.base import BaseLoader
from langchain_community.document_loaders.blob_loaders.file_system import (
FileSystemBlobLoader,
)
from langchain_community.document_loaders.blob_loaders.schema import Blob
if TYPE_CHECKING:
from O365 import Account
from O365.drive import Drive, Folder
logger = logging.getLogger(__name__)
CHUNK_SIZE = 1024 * 1024 * 5
class _O365Settings(BaseSettings):
client_id: str = Field(..., env="O365_CLIENT_ID")
client_secret: SecretStr = Field(..., env="O365_CLIENT_SECRET")
class Config:
env_prefix = ""
case_sentive = False
env_file = ".env"
class _O365TokenStorage(BaseSettings):
token_path: FilePath = Path.home() / ".credentials" / "o365_token.txt"
class _FileType(str, Enum):
DOC = "doc"
DOCX = "docx"
PDF = "pdf"
def fetch_mime_types(file_types: Sequence[_FileType]) -> Dict[str, str]:
"""Fetch the mime types for the specified file types."""
mime_types_mapping = {}
for file_type in file_types:
if file_type.value == "doc":
mime_types_mapping[file_type.value] = "application/msword"
elif file_type.value == "docx":
mime_types_mapping[
file_type.value
] = "application/vnd.openxmlformats-officedocument.wordprocessingml.document" # noqa: E501
elif file_type.value == "pdf":
mime_types_mapping[file_type.value] = "application/pdf"
return mime_types_mapping
class O365BaseLoader(BaseLoader, BaseModel):
"""Base class for all loaders that uses O365 Package"""
settings: _O365Settings = Field(default_factory=_O365Settings)
"""Settings for the Office365 API client."""
auth_with_token: bool = False
"""Whether to authenticate with a token or not. Defaults to False."""
chunk_size: Union[int, str] = CHUNK_SIZE
"""Number of bytes to retrieve from each api call to the server. int or 'auto'."""
recursive: bool = False
"""Should the loader recursively load subfolders?"""
@property
@abstractmethod
def _file_types(self) -> Sequence[_FileType]:
"""Return supported file types."""
@property
def _fetch_mime_types(self) -> Dict[str, str]:
"""Return a dict of supported file types to corresponding mime types."""
return fetch_mime_types(self._file_types)
@property
@abstractmethod
def _scopes(self) -> List[str]:
"""Return required scopes."""
def _load_from_folder(self, folder: Folder) -> Iterable[Blob]:
"""Lazily load all files from a specified folder of the configured MIME type.
Args:
folder: The Folder instance from which the files are to be loaded. This
Folder instance should represent a directory in a file system where the
files are stored.
Yields:
An iterator that yields Blob instances, which are binary representations of
the files loaded from the folder.
"""
file_mime_types = self._fetch_mime_types
items = folder.get_items()
with tempfile.TemporaryDirectory() as temp_dir:
os.makedirs(os.path.dirname(temp_dir), exist_ok=True)
for file in items:
if file.is_file:
if file.mime_type in list(file_mime_types.values()):
file.download(to_path=temp_dir, chunk_size=self.chunk_size)
loader = FileSystemBlobLoader(path=temp_dir)
yield from loader.yield_blobs()
if self.recursive:
for subfolder in folder.get_child_folders():
yield from self._load_from_folder(subfolder)
def _load_from_object_ids(
self, drive: Drive, object_ids: List[str]
) -> Iterable[Blob]:
"""Lazily load files specified by their object_ids from a drive.
Load files into the system as binary large objects (Blobs) and return Iterable.
Args:
drive: The Drive instance from which the files are to be loaded. This Drive
instance should represent a cloud storage service or similar storage
system where the files are stored.
object_ids: A list of object_id strings. Each object_id represents a unique
identifier for a file in the drive.
Yields:
An iterator that yields Blob instances, which are binary representations of
the files loaded from the drive using the specified object_ids.
"""
file_mime_types = self._fetch_mime_types
with tempfile.TemporaryDirectory() as temp_dir:
for object_id in object_ids:
file = drive.get_item(object_id)
if not file:
logging.warning(
"There isn't a file with"
f"object_id {object_id} in drive {drive}."
)
continue
if file.is_file:
if file.mime_type in list(file_mime_types.values()):
file.download(to_path=temp_dir, chunk_size=self.chunk_size)
loader = FileSystemBlobLoader(path=temp_dir)
yield from loader.yield_blobs()
def _auth(self) -> Account:
"""Authenticates the OneDrive API client
Returns:
The authenticated Account object.
"""
try:
from O365 import Account, FileSystemTokenBackend
except ImportError:
raise ImportError(
"O365 package not found, please install it with `pip install o365`"
)
if self.auth_with_token:
token_storage = _O365TokenStorage()
token_path = token_storage.token_path
token_backend = FileSystemTokenBackend(
token_path=token_path.parent, token_filename=token_path.name
)
account = Account(
credentials=(
self.settings.client_id,
self.settings.client_secret.get_secret_value(),
),
scopes=self._scopes,
token_backend=token_backend,
**{"raise_http_errors": False},
)
else:
token_backend = FileSystemTokenBackend(
token_path=Path.home() / ".credentials"
)
account = Account(
credentials=(
self.settings.client_id,
self.settings.client_secret.get_secret_value(),
),
scopes=self._scopes,
token_backend=token_backend,
**{"raise_http_errors": False},
)
# make the auth
account.authenticate()
return account