Copyright | (C) 2025 Tushar Adhatrao |
---|---|
License | MIT |
Maintainer | Tushar Adhatrao <tusharadhatrao@gmail.com> |
Stability | experimental |
Safe Haskell | Safe-Inferred |
Language | Haskell2010 |
Langchain.DocumentLoader.PdfLoader
Description
This module provides a loader for PDF files by implementing the
BaseLoader
interface from Langchain.DocumentLoader.Core. It uses
the Document
library to open a PDF and extract its content, turning
each page into a Document
. Additionally, it provides a method to load the
raw content of the file and split it using a recursive character splitter.
Documentation
A loader for PDF files.
The PdfLoader
data type encapsulates a FilePath
pointing to a PDF document.
It implements the BaseLoader
interface to provide methods for loading and
splitting PDF content.