BaseLoader
Class Introduction
Loader base class for document loading. For .xlsx, .docx, and .pptx files, perform ZIP bomb file verification. Note that the size of the decompressed file cannot exceed 500 MB, the number of decompressed files cannot exceed 5,120, and the drive space after decompression must be greater than 200 MB.
Documents to be parsed must be in UTF-8 format; otherwise, the parsing may fail.
Prototype
from mx_rag.document.loader import BaseLoader BaseLoader(file_path)
Parameters
Parameter |
Data Type |
Required/Optional |
Description |
|---|---|---|---|
file_path |
String |
Required |
Document path. The path length range is [1, 1024]. The path cannot be a soft link or contain two consecutive dots (..). The document size cannot exceed 100 MB. |
Parent topic: Document Parsing