SharePointLoader#
- class langchain_community.document_loaders.sharepoint.SharePointLoader[source]#
Bases:
O365BaseLoader
,BaseLoader
Load from SharePoint.
- param auth_with_token: bool = False#
Whether to authenticate with a token or not. Defaults to False.
- param chunk_size: int | str = 5242880#
Number of bytes to retrieve from each api call to the server. int or ‘auto’.
- param document_library_id: str [Required]#
The ID of the SharePoint document library to load data from.
- param folder_id: str | None = None#
The ID of the folder to load data from.
- param folder_path: str | None = None#
The path to the folder to load data from.
- param handlers: Dict[str, Any] | None = {}#
Provide custom handlers for MimeTypeBasedParser.
Pass a dictionary mapping either file extensions (like “doc”, “pdf”, etc.) or MIME types (like “application/pdf”, “text/plain”, etc.) to parsers. Note that you must use either file extensions or MIME types exclusively and cannot mix them.
Do not include the leading dot for file extensions.
Example using file extensions: ```python
- handlers = {
“doc”: MsWordParser(), “pdf”: PDFMinerParser(), “txt”: TextParser()
}
Example using MIME types: ```python
- handlers = {
“application/msword”: MsWordParser(), “application/pdf”: PDFMinerParser(), “text/plain”: TextParser()
}
- param load_auth: bool | None = False#
Whether to load authorization identities.
- param load_extended_metadata: bool | None = False#
Whether to load extended metadata. Size, Owner and full_path.
- param modified_since: datetime | None = None#
Only fetch documents modified since given datetime. The datetime object must be timezone aware.
- param object_ids: List[str] | None = None#
The IDs of the objects to load data from.
- param recursive: bool = False#
Should the loader recursively load subfolders?
- param settings: _O365Settings [Optional]#
Settings for the Office365 API client.
- param token_path: Path = PosixPath('/home/runner/.credentials/o365_token.txt')#
The path to the token to make api calls
- async alazy_load() → AsyncIterator[Document]#
A lazy loader for Documents.
- Return type:
AsyncIterator[Document]
- authorized_identities(file_id: str) → List[source]#
Retrieve the access identities (user/group emails) for a given file. :param file_id: The ID of the file. :type file_id: str
- Returns:
- A list of group names (email addresses) that have
access to the file.
- Return type:
List
- Parameters:
file_id (str)
- get_extended_metadata(file_id: str) → Dict[source]#
Retrieve extended metadata for a file in SharePoint. As of today, following fields are supported in the extended metadata: - size: size of the source file. - owner: display name of the owner of the source file. - full_path: pretty human readable path of the source file. :param file_id: The ID of the file. :type file_id: str
- Returns:
- A dictionary containing the extended metadata of the file,
including size, owner, and full path.
- Return type:
dict
- Parameters:
file_id (str)
- lazy_load() → Iterator[Document][source]#
Load documents lazily. Use this when working at a large scale. :Yields: Document – A document object representing the parsed blob.
- Return type:
Iterator[Document]
- load_and_split(text_splitter: TextSplitter | None = None) → list[Document]#
Load Documents and split into chunks. Chunks are returned as Documents.
Do not override this method. It should be considered to be deprecated!
- Parameters:
text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.
- Returns:
List of Documents.
- Return type:
list[Document]
Examples using SharePointLoader