Documents and OCR

Best of each kind

1. Ready to useRAGFlow

   RAG engine with deep document parsing, template chunking and agentic retrieval

   74 score92.6k stars
   #1 of 8 · RAG and search
2. Parts to build with · AI apps and modelsmineru

   Document parser that converts PDFs, images and Office files to Markdown and JSON

   81 score82.2k stars
   #1 of 13 · Data and scraping
3. Parts to build with · Vibe codingkami

   Agent skill that renders styled PDF, PNG and PPTX documents from templates

   90 score12.1k stars
   #1 of 2 · Skills and plugins

1. 1
   RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval5th in RAG and search · Apache-2.0
   92.6k ★
   74
2. 2
   pageindexVectorless RAG that builds a tree index of a PDF and lets an LLM search it10th in RAG and search · MIT
   39.4k ★
   68
3. 3
   rag-anythingPython library for RAG over PDFs, Office files, images, tables and equations14th in RAG and search · MIT
   24k ★
   65
4. 4
   paperless-gptLLM-based OCR, titles, tags and document linking for paperless-ngx20th in RAG and search · MIT
   2.8k ★
   59
5. 5
   pixelragVisual RAG that renders pages and PDFs to screenshots and searches the images24th in RAG and search · Apache-2.0
   10.3k ★
   56
6. 6
   Docling ServeDocling document conversion as an HTTP API with playground UI29th in RAG and search · MIT
   1.9k ★
   54
7. 7
   MorphikMultimodal retrieval engine for visually rich PDFs, images and video32nd in RAG and search · custom license
   3.7k ★
   46
8. 8
   Paperless-AIAuto-tags Paperless-ngx documents and adds RAG chat over the archive37th in RAG and search · MIT
   6k ★
   32

1. 1
   mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON1st in Data and scraping · custom license
   82.2k ★
   81
2. 2
   doclingPython library and CLI that converts PDFs, Office files and more into structured text3rd in Data and scraping · MIT
   69.3k ★
   79
3. 3
   markitdownPython tool that converts PDF, Office, HTML and audio files to Markdown for LLMs5th in Data and scraping · MIT
   191.5k ★
   71
4. 4
   pdfmathtranslateTranslates scientific PDFs while keeping formulas, figures and layout intact10th in Data and scraping · AGPL-3.0
   37.7k ★
   64
5. 5
   unstructuredPython library that parses PDFs, Office files and HTML into typed elements11th in Data and scraping · Apache-2.0
   15.6k ★
   63
6. 6
   opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF13th in Data and scraping · Apache-2.0
   29.8k ★
   59
7. 7
   markerConverts PDFs, Office files and images to markdown, JSON, HTML or chunks14th in Data and scraping · Apache-2.0
   40.6k ★
   58
8. 8
   unlimited-ocrOCR model that parses long documents and multi-page PDFs in one pass11th in Open models · MIT
   28.1k ★
   58
9. 9
   paddleocrOCR and document parsing toolkit that outputs Markdown and JSON from PDFs and images15th in Data and scraping · Apache-2.0
   91.5k ★
   56
10. 10
    olmocrPDF and image to Markdown converter built on a 7B vision-language model16th in Data and scraping · Apache-2.0
    19.8k ★
    49
11. 11
    unstractExtracts structured JSON from PDFs and scans using LLM prompts19th in Data and scraping · AGPL-3.0
    7.3k ★
    46
12. 12
    chandraOCR model that converts PDFs and images to Markdown, HTML or JSON with layout21st in Data and scraping · Apache-2.0
    12.5k ★
    36
13. 13
    easyocrPython OCR library for text detection and recognition in 80+ languages23rd in Data and scraping · Apache-2.0
    30.1k ★
    26

1. 1
   kamiAgent skill that renders styled PDF, PNG and PPTX documents from templates19th in Skills and plugins · MIT
   12.1k ★
   90
2. 2
   markdownify-mcpMCP server that converts PDFs, Office files, audio and web pages to Markdown64th in Dev MCP servers · MIT
   3k ★
   36