Preprocessing

Preprocessing functions for converting input documents to markdown.

Functions:

Name	Description
read_pdf_as_markdown_via_pymupdf4llm	Read a PDF file and convert it to markdown using pymupdf4llm.

read_pdf_as_markdown_via_pymupdf4llm(file_name, base_path)

Read a PDF file and convert it to markdown using pymupdf4llm.

Parameters:

Name	Type	Description	Default
file_name	str	The name of the PDF file to read.	required
base_path	Path	The base path where the PDF file is located.	required

Returns:

Type	Description
str	The Markdown text.

Source code in src/kibad_llm/preprocessing.py

def read_pdf_as_markdown_via_pymupdf4llm(file_name: str, base_path: Path) -> str:
    """Read a PDF file and convert it to markdown using pymupdf4llm.

    Args:
        file_name: The name of the PDF file to read.
        base_path: The base path where the PDF file is located.

    Returns:
        The Markdown text.
    """
    return pymupdf4llm.to_markdown(str(base_path / file_name))