Document Conversion Specialist PDF/EPUB to Markdown

I’ve got a lot of content and ebooks sitting in PDFs and EPUBs, and I need this turned into clean, structured Markdown files. I need someone to help convert a large collection of PDFs and EPUBs into clean, structured Markdown files that are ready to upload into a RAG system. The goal is not just basic text extraction. I need the documents cleaned, organized, and formatted so they are useful for semantic search, embeddings, retrieval, and long-term knowledge management. You will convert PDFs and EPUBs into high-quality Markdown files while preserving the original structure as much as possible. Tasks include: Convert PDF and EPUB files into Markdown. Preserve headings, chapter titles, sections, subsections, lists, and tables where possible. Split books or long documents into chapter-level Markdown files when appropriate. Add clean YAML frontmatter metadata where needed. Remove unnecessary headers, footers, page numbers, broken line breaks, duplicate text, and extraction artifacts. Identify scanned PDFs that require OCR. Use OCR tools when necessary, such as OCRmyPDF or Tesseract. Maintain a clean folder structure for the converted files. Flag documents that are damaged, low quality, unreadable, encrypted, or poorly scanned. ############################################################ Desired Output Format Each source document should ideally produce: Clean chapter-level Markdown files Metadata/frontmatter including: Title Author, if available Source filename File type Chapter or section name Conversion date Index file for each converted book/document Notes on any issues found during conversion Optional OCR confidence or quality report for scanned documents Example Markdown structure: --- title: "Book Title" author: "Author Name" source_file: "original-file.pdf" file_type: "pdf" chapter: "Chapter 1" converted_date: "YYYY-MM-DD" --- # Chapter 1: Introduction Clean extracted text goes here... ############################################################ The final Markdown should be readable, structured, and suitable for use in a retrieval system. Please do not simply dump raw extracted text into a file. The content should be cleaned without rewriting, summarizing, or changing the meaning of the original document. Important requirements: Preserve the author’s original meaning. Do not paraphrase or summarize unless specifically asked. Do not remove important footnotes, citations, tables, headings, or numbered sections. Fix broken paragraphs and line breaks. Remove repeated page headers and footers. Keep documents organized by folder, book, chapter, and source. Use consistent file naming, such as: ############################################################ Tools / Skills That Are Helpful Experience with any of the following is preferred: Python Markdown OCRmyPDF Tesseract OCR Marker PDF Calibre ebooklib PyMuPDF pdfminer.six Pandoc BeautifulSoup EPUB to Markdown workflows RAG / LLM preprocessing AnythingLLM, LangChain, or vector database workflows