Git Stars Git Stars

#document-parsing Repositories

Discover 42 active open source GitHub repositories tagged with #document-parsing, accumulating 356,240 total stars (averaging 8,481 stars per project). Leading this topic is PaddlePaddle/PaddleOCR with 92,972 stars.

42
Total Repositories
356,240
Total Stars
8,481
Avg Stars/Repo
1
PaddlePaddle/PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

PaddlePaddle
โญ 92,972 Python ๐Ÿ‘ค PaddlePaddle Organization ๐Ÿ• Updated 2026-09-16 ๐Ÿ“… Created 2020-05-08
2
docling-project/docling

Get your documents ready for gen AI

docling-project
โญ 70,843 Python ๐Ÿ‘ค docling-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-07-09
3
datalab-to/marker

Convert PDF to markdown + JSON quickly with high accuracy

datalab-to
โญ 41,010 Python ๐Ÿ‘ค datalab-to Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2023-10-30
4
opendataloader-project/opendataloader-pdf

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

opendataloader-project
โญ 30,355 Java ๐Ÿ‘ค opendataloader-project Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-05-13
5
Unstructured-IO/unstructured

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Unstructured-IO
โญ 15,769 HTML ๐Ÿ‘ค Unstructured-IO Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2022-09-26
6
netease-youdao/QAnything

Question and Answer based on Anything.

netease-youdao
โญ 14,210 Python ๐Ÿ‘ค netease-youdao User ๐Ÿ• Updated 2026-09-23 ๐Ÿ“… Created 2024-01-03
7
datalab-to/chandra

OCR model that handles complex tables, forms, handwriting with full layout.

datalab-to
โญ 12,741 Python ๐Ÿ‘ค datalab-to Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2025-10-08
8
facebookresearch/nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

facebookresearch
โญ 9,997 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2025-02-21 ๐Ÿ“… Created 2023-06-07
9
studio-dots-ai/dots.ocr

Multilingual Document Layout Parsing in a Single Vision-Language Model

studio-dots-ai
โญ 9,236 Python ๐Ÿ‘ค studio-dots-ai Organization ๐Ÿ• Updated 2026-03-24 ๐Ÿ“… Created 2025-07-30
10
Yuliang-Liu/MonkeyOCR

A lightweight LMM-based Document Parsing Model

Yuliang-Liu
โญ 6,653 Python ๐Ÿ‘ค Yuliang-Liu User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2025-06-03
11
mindee/doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

mindee
โญ 6,433 Python ๐Ÿ‘ค mindee Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2021-01-08
12
run-llama/llama_cloud_services

Knowledge Agents and Management in the Cloud

run-llama
โญ 4,273 TypeScript ๐Ÿ‘ค run-llama Organization ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2024-01-31
13
NVIDIA/NeMo-Retriever

NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.

NVIDIA
โญ 3,014 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-08-22
14
chatdoc-com/OCRFlux

OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.

chatdoc-com
โญ 2,532 Python ๐Ÿ‘ค chatdoc-com Organization ๐Ÿ• Updated 2026-04-14 ๐Ÿ“… Created 2025-06-04
15
Nutlope/llama-ocr

Document to Markdown OCR library with Llama 3.2 vision

Nutlope
โญ 2,445 TypeScript ๐Ÿ‘ค Nutlope User ๐Ÿ• Updated 2026-07-12 ๐Ÿ“… Created 2024-11-12
16
landing-ai/ade-cli

The official CLI for Agentic Document Extraction (ADE) by LandingAI โ€” parse documents and extract schema-shaped data from your terminal

landing-ai
โญ 2,427 Python ๐Ÿ‘ค landing-ai Organization ๐Ÿ• Updated 2026-10-30 ๐Ÿ“… Created 2025-03-12
โญ 2,300 Python ๐Ÿ‘ค pymupdf Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-03-21
18
dnGrep/dnGrep

Graphical GREP tool for Windows

dnGrep
โญ 2,246 C# ๐Ÿ‘ค dnGrep Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2014-10-09
19
opendatalab/OmniDocBench

[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation

opendatalab
โญ 2,183 Python ๐Ÿ‘ค opendatalab Organization ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2024-10-14
20
Tencent-Hunyuan/HunyuanOCR

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Tencent-Hunyuan
โญ 2,091 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-09-24 ๐Ÿ“… Created 2025-11-18
21
datalab-to/indra

1M-parameter OCR model โ€” runs on CPU, 15ร— faster than Tesseract, with accuracy close to that of models with 1B+ parameters

datalab-to
โญ 1,910 Python ๐Ÿ‘ค datalab-to Organization ๐Ÿ• Updated 2026-11-04 ๐Ÿ“… Created 2026-10-13
22
enoch3712/ExtractThinker

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

enoch3712
โญ 1,606 Python ๐Ÿ‘ค enoch3712 User ๐Ÿ• Updated 2026-09-16 ๐Ÿ“… Created 2024-02-01
23
NanoNets/docstrange

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

NanoNets
โญ 1,578 Python ๐Ÿ‘ค NanoNets Organization ๐Ÿ• Updated 2025-10-31 ๐Ÿ“… Created 2025-07-31
24
Topdu/OpenOCR

OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.

Topdu
โญ 1,498 Python ๐Ÿ‘ค Topdu User ๐Ÿ• Updated 2026-09-21 ๐Ÿ“… Created 2024-05-31
25
zstar1003/ragflow-plus

Ragflow-Plus is a secondary development version of Ragflow, making it more concise and practical

zstar1003
โญ 1,471 Python ๐Ÿ‘ค zstar1003 User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2025-03-24
27
nlmatics/nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

nlmatics
โญ 1,282 Python ๐Ÿ‘ค nlmatics Organization ๐Ÿ• Updated 2025-03-28 ๐Ÿ“… Created 2024-01-17
28
laramies/metagoofil

Metadata harvester

laramies
โญ 1,201 Python ๐Ÿ‘ค laramies User ๐Ÿ• Updated 2024-03-21 ๐Ÿ“… Created 2015-08-13
29
aiptimizer/TurboOCR

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

aiptimizer
โญ 1,162 C++ ๐Ÿ‘ค aiptimizer Organization ๐Ÿ• Updated 2026-09-27 ๐Ÿ“… Created 2026-03-20
30
allenai/s2orc

S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/

allenai
โญ 996 Python ๐Ÿ‘ค allenai Organization ๐Ÿ• Updated 2024-04-26 ๐Ÿ“… Created 2019-11-04
31
flyhunterl/flymd

High-performance Markdown note tool! Free AI, smart notes, TODO reminders, local knowledge base, AI novel engine. PDF parsing, auto voice notes, audio-to-text. Millisecond startup.

flyhunterl
โญ 900 JavaScript ๐Ÿ‘ค flyhunterl User ๐Ÿ• Updated 2026-07-22 ๐Ÿ“… Created 2025-10-24
32
freelawproject/x-ray

A tool to detect whether a PDF has a bad redaction

freelawproject
โญ 837 Python ๐Ÿ‘ค freelawproject Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2020-12-17
33
deep-diver/paper-reviewer

Generate a comprehensive review from an arXiv paper, then turn it into a blog post. This project powers the website below for the HuggingFace's Daily Papers (https://huggingface.co/papers).

deep-diver
โญ 834 Python ๐Ÿ‘ค deep-diver User ๐Ÿ• Updated 2025-02-20 ๐Ÿ“… Created 2024-10-21
34
FengZhenfei/carrel

Ontology-Augmented Generation for AI Agents.

FengZhenfei
โญ 808 Python ๐Ÿ‘ค FengZhenfei User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-09-28
36
Steven-Luo/MasteringRAG

Enterprise RAG Systems: From Novice to Expert

Steven-Luo
โญ 699 Jupyter Notebook ๐Ÿ‘ค Steven-Luo User ๐Ÿ• Updated 2025-06-25 ๐Ÿ“… Created 2024-07-16
37
ggozad/haiku.rag

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking, and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

ggozad
โญ 665 Python ๐Ÿ‘ค ggozad User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-10-13
38
run-llama/ParseBench

ParseBench - A Document Parsing Benchmark for AI Agents

run-llama
โญ 650 Python ๐Ÿ‘ค run-llama Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-04-10
39
skygazer42/MimirQ

Chinese-first enterprise RAG knowledge base: controllable parsing, governance, chunking, hybrid retrieval, reranking, citations, knowledge graphs, evaluation, and Dify integration.

skygazer42
โญ 613 Python ๐Ÿ‘ค skygazer42 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-11-28
40
ankushshah89/python-docx2txt

A pure python based utility to extract text and images from docx files.

ankushshah89
โญ 584 Python ๐Ÿ‘ค ankushshah89 User ๐Ÿ• Updated 2025-03-24 ๐Ÿ“… Created 2015-10-28
41
fufankeji/DeepSeek-OCR-Web

Out-of-the-box DeepSeek OCR document parsing Web Studio

fufankeji
โญ 568 TypeScript ๐Ÿ‘ค fufankeji User ๐Ÿ• Updated 2025-10-27 ๐Ÿ“… Created 2025-10-23
42
LeDat98/NexusRAG

Hybrid RAG system combining vector search, a knowledge graph (LightRAG), and cross-encoder reranking โ€” with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.

LeDat98
โญ 533 Python ๐Ÿ‘ค LeDat98 User ๐Ÿ• Updated 2026-04-20 ๐Ÿ“… Created 2026-03-15

Frequently Asked Questions

1

What is the most popular #document-parsing repository on GitHub?

The top ranked open source #document-parsing project on GitHub is PaddlePaddle/PaddleOCR with 92,972 stars. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

2

Which programming languages are most used in #document-parsing repositories?

Among the top ranked #document-parsing projects on GitHub, the most common programming languages are Python, TypeScript, Java, HTML.

3

How is the #document-parsing repository ranking calculated?

We track 42 active open source repositories tagged with #document-parsing (500+ stars), totaling 356,240 stars with an average of 8,481 stars per repository. Rankings update daily from the GitHub API.