doc2mark

Getting started

  • Installation
  • Quickstart
  • A minimal RAG pipeline

User guide

  • Loading documents
  • Supported formats
  • The result: ProcessedDocument
  • PDF text structure
  • Tables
  • Images
  • OCR
  • When pages and pictures are OCR’d
  • Contextual OCR strategy
  • Caching
  • Chunking and token usage
  • Optional judge (TypeSafe / Jev)
  • Command line
  • Troubleshooting

Reference

  • API reference
  • Development
doc2mark
  • Overview: module code

All modules for which code is available

  • doc2mark
    • doc2mark.core.base
    • doc2mark.core.chunker
    • doc2mark.core.loader
    • doc2mark.core.table
    • doc2mark.judge
      • doc2mark.judge.typesafe
    • doc2mark.ocr
      • doc2mark.ocr.base
      • doc2mark.ocr.cache
      • doc2mark.ocr.openai
      • doc2mark.ocr.schema
      • doc2mark.ocr.tesseract
      • doc2mark.ocr.vertex_ai

© Copyright 2026, Hao Liang Wen.

Built with Sphinx using a theme provided by Read the Docs.