graphragzen.load_documents.load_documents.load_text_documents

graphragzen.load_documents.load_documents.load_text_documents(raw_documents_folder, raw_content_column='content')[source]

loads files from folder path and subfolders as raw text.

Parameters:

raw_documents_folder (str) – Folder to search for text documents
raw_content_column (str, optional) – Name of the dataframe column to store each document’s content. Defaults to ‘content’.

Returns:

Includes the columns ‘document_path’ and ‘document_id’

Return type:

pd.DataFrame