langchain_community.document_loaders.rspace.RSpaceLoader¶

class langchain_community.document_loaders.rspace.RSpaceLoader(global_id: str, api_key: Optional[str] = None, url: Optional[str] = None)[source]¶

Loads content from RSpace notebooks, folders, documents or PDF Gallery files into Langchain documents.

Maps RSpace document <-> Langchain Document in 1-1. PDFs are imported using PyPDF.

Requirements are rspace_client (pip install rspace_client) and PyPDF if importing

PDF docs (pip install pypdf).

api_key: RSpace API key - can also be supplied as environment variable ‘RSPACE_API_KEY’ url: str The URL of your RSpace instance - can also be supplied as environment variable ‘RSPACE_URL’ global_id: str

The global ID of the resource to load,

e.g. ‘SD12344’ (a single document); ‘GL12345’(A PDF file in the gallery); ‘NB4567’ (a notebook); ‘FL12244’ (a folder)

Methods

__init__(global_id[, api_key, url])

api_key: RSpace API key - can also be supplied as environment variable 'RSPACE_API_KEY' url: str The URL of your RSpace instance - can also be supplied as environment variable 'RSPACE_URL' global_id: str The global ID of the resource to load, e.g. 'SD12344' (a single document); 'GL12345'(A PDF file in the gallery); 'NB4567' (a notebook); 'FL12244' (a folder).

lazy_load()

A lazy loader for Documents.

load()

Load data into Document objects.

load_and_split([text_splitter])

Load Documents and split into chunks.

validate_environment(values)

Validate that API key and URL exists in environment.

__init__(global_id: str, api_key: Optional[str] = None, url: Optional[str] = None)[source]¶

api_key: RSpace API key - can also be supplied as environment variable ‘RSPACE_API_KEY’ url: str The URL of your RSpace instance - can also be supplied as environment variable ‘RSPACE_URL’ global_id: str

The global ID of the resource to load,

e.g. ‘SD12344’ (a single document); ‘GL12345’(A PDF file in the gallery); ‘NB4567’ (a notebook); ‘FL12244’ (a folder)

lazy_load() Iterator[Document][source]¶

A lazy loader for Documents.

load() List[Document][source]¶

Load data into Document objects.

load_and_split(text_splitter: Optional[TextSplitter] = None) List[Document]¶

Load Documents and split into chunks. Chunks are returned as Documents.

Parameters

text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.

classmethod validate_environment(values: Dict) Dict[source]¶

Validate that API key and URL exists in environment.