knowledge_base/prepare_documents.py

import os
import pymupdf.layout
import pymupdf4llm
from pathlib import Path
import glob

os.environ["TOKENIZERS_PARALLELISM"] = "false"

def pdf_to_markdown(pdf_path, output_dir):
    doc = pymupdf.open(pdf_path)
    md = pymupdf4llm.to_markdown(doc, header=False, footer=False, page_separators=True, ignore_images=True, write_images=False, image_path=None)
    md_cleaned = md.encode('utf-8', errors='surrogatepass').decode('utf-8', errors='ignore')
    output_path = Path(output_dir) / Path(doc.name).stem
    Path(output_path).with_suffix(".md").write_bytes(md_cleaned.encode('utf-8'))

def pdfs_to_markdowns(path_pattern, overwrite: bool = False):
    output_dir = Path('./docs/markdowns')
    output_dir.mkdir(parents=True, exist_ok=True)

    for pdf_path in map(Path, glob.glob(path_pattern)):
        md_path = (output_dir / pdf_path.stem).with_suffix(".md")
        if overwrite or not md_path.exists():
            pdf_to_markdown(pdf_path, output_dir)

if __name__ == "__main__":
    pdf_folder = Path('./docs/pdf')
    for file in os.listdir(pdf_folder):
        file_path = pdf_folder / file
        if file_path.suffix.lower() == '.pdf':
            print(f"Processing file: {file_path}")  
            pdf_to_markdown(file_path, './docs/markdowns')