HomeProjectsArticlesPK BoardAbout
Explore Projects

PaddleOCR

Active
GitHub Python Apache-2.0

Description

PaddleOCR is Baidu's open-source multilingual OCR and document-AI toolkit supporting 80+ languages and PP-Structure layout analysis.

Key Features

  • Multilingual recognition — 80+ languages out of the box including Chinese (Simplified/Traditional), English, Arabic
  • PP-Structure layout analysis — text blocks, tables, figures, formulas auto-classified and located
  • PP-OCRv4 high accuracy — state-of-the-art detection + recognition end-to-end accuracy
  • PP-StructureV2 — unified table recognition (TableMaster) and key information extraction (KIE)
  • PaddleInference / ONNX — supports PaddlePaddle native and ONNX cross-platform deployment
  • Rich model zoo — detection, recognition, direction classification, layout, formula recognition

Use Cases

💡 Powering OCR and layout parsing for document-AI agent scenarios
💡 Building PDF/image preprocessing pipelines for RAG systems
💡 Table and key-information extraction for contracts, invoices, ID documents
💡 Multilingual document digitization and cross-language retrieval

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (87.7k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

ocr paddlepaddle document-ai multilingual deep-learning

Categories

⚡ Agent Tools

Quick Start

pip install paddleocr

paddleocr --image_dir ./doc.jpg --use_angle_cls true --lang ch
Visit GitHub Visit Website

Related Projects

ComfyUI LLM Party

2.3k · Python
Active A

LLM Agent framework within ComfyUI integrating MCP server, TTS, OCR, GraphRAG, and other AI tool nodes for visual workflow building

comfyuimcpgraphrag +4
  • · Complete set of LLM workflow nodes for ComfyUI including API, local, GGUF, and VLM loaders
  • · MCP server integration for connecting external tools via modelcontextprotocol.json configuration
  • · Multi-agent pipeline support with agent-agent radial and ring interaction patterns
View on GitHub

Kreuzberg

9.1k · Rust
Active A+

Polyglot document intelligence framework with a Rust core, extracting text, metadata, and structured data from PDFs, Office documents, images and 91+ formats via MCP server, CLI, and REST API.

document-extractionmcpocr +2
  • · Polyglot document intelligence extraction: Rust core engine natively supports PDFs, Office documents, images, and 91+ file formats
  • · Code intelligence analysis: extracts functions, classes, imports, symbols, and docstrings from 300+ programming languages via tree-sitter
  • · Multi-language bindings: supports 15+ languages including Python, TypeScript/Node.js, Ruby, Go, Java, Kotlin, C#, PHP, Swift, and Zig
View full details → View on GitHub