Document Ai Python Packages

deepdoctection

A Repo For Document AI

exstruct

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.

dd-core

A Repo For Document AI

dd-datasets

A Repo For Document AI

mdify-cli

MDify is a document-to-Markdown conversion library for extracting structured content from complex PDFs and document images, including tables, charts, and scanned documents.

ethos-pdf

Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.

ocrcontext

Intelligent document OCR and structured extraction. Turn PDFs and images into typed JSON with zero vendor lock-in.

docnest-ai

The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.

pdfhell

PDF Hell — adversarial PDFs that break AI document readers. Procedural ground truth, not LLM-as-judge.

nanoindex

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

donut-python

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

anyparse-python

Parse any file to Markdown and JSON, anyparse, document-parsing, document-understanding, ocr, vlm, multimodal, image, pdf, markdown, docx, pptx, xlsx, tsv, csv, txt, md, rst, htm, html, xhtml, shtml, png, jpeg, jpg, webp, epub, ipynb, eml

tinydoc

Python SDK for TinyDoc-VLM document understanding — the world's smallest document-specialist VLM

optical-context-mcp

MCP server that compresses OCR-heavy PDFs into dense packed images so AI agents can handle long visual documents

ocrqueen

Official Python SDK for the OCRQueen document extraction API

docvision

Python library for intelligent document parsing using Vision Language Models. Extract structured text and markdown from PDFs and images with self-correcting AI workflows. Supports OpenAI-compatible APIs.

flash-mineru

Ray-powered accelerator for MinerU, turning PDF → Markdown into a scalable, cluster-ready data infrastructure. 基于 Ray 的 MinerU 加速层，将 PDF → Markdown 构建为可扩展、面向集群的数据基础设施。

grepctl

One-command orchestration for multimodal semantic search in BigQuery

german-ocr

German-OCR is specifically trained to extract text from German documents including invoices, receipts, forms, and other business documents.

tokenpack-rag

Query-aware semantic chunk selection under LLM context-window budgets.

iflow-mcp-harumiweb-exstruct

Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines

gdoczai

Python SDK for GdoczAI — OCR, extract, and segment documents

doc-vision-parser

Production-ready document parsing with Vision Language Models