version unknown

paddleocr-text-recognition

paddlepaddle@paddlepaddle⭐ 92.6k stars· last commit 2mo ago· 167 open issues

>-

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

7.7/10
Verified
Oct 8, 2026

// RATINGS

⭐GitHub Stars
⭐⭐⭐⭐⭐ 92.6k on GitHubGitHub ↗

Very popular

🟢ProSkills ScoreAI Verified
7.7/10
📍

Not yet listed on ClawHub or SkillsMP

// README

English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Français | Русский | Español | العربية

PyPI Downloads Used by python os hardware

AI Studio Ask DeepWiki License

PaddleOCR converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) with industry-leading accuracy. With 70k+ Stars and trusted by top-tier projects like Dify, RAGFlow, and Cherry Studio, PaddleOCR is the bedrock for building intelligent RAG and Agentic applications.

🚀 Key Features

📄 Intelligent Document Parsing (LLM-Ready)

Transforming messy visuals into structured data for the LLM era.

  • SOTA Document VLM: Featuring PaddleOCR-VL-1.6 (0.9B), the industry's leading lightweight vision-language model for document parsing. It achieves 96.3% accuracy on OmniDocBench v1.6, leads in text, formula, and table recognition, and shows significantly enhanced capabilities in ancient documents, rare characters, seals, and charts, with structured outputs in Markdown and JSON formats.
  • Structure-Aware Conversion: Powered by PP-StructureV3, seamlessly convert complex PDFs and images into Markdown or JSON. Unlike the PaddleOCR-VL series models, it provides more fine-grained coordinate information, including table cell coordinates, text coordinates, and more.
  • Production-Ready Efficiency: Achieve commercial-grade accuracy with an ultra-small footprint. Outperforms numerous closed-source solutions in public benchmarks while remaining resource-efficient for edge/cloud deployment.

🔍 Universal Text Recognition (Scene OCR)

The global gold standard for high-speed, multilingual text spotting.

  • 100+ Languages Supported: Native recognition for a vast global library. PP-OCRv6 supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages) — no model switching needed for multilingual documents.
  • Complex Element Mastery: Beyond standard text recognition, we support natural scene text spotting across a wide range of environments, including IDs, street views, books, and industrial components
  • Performance Leap: PP-OCRv6 achieves +4.6% detection and +5.1% recognition accuracy over PP-OCRv5, surpassing mainstream Vision-Language Models. 5.2× CPU inference speedup end-to-end.

🛠️ Developer-Centric Ecosystem

  • Seamless Integration: The premier choice for the AI Agent ecosystem—deeply integrated with Dify, RAGFlow, Pathway, and Cherry Studio.
  • LLM Data Flywheel: A complete pipeline to build high-quality datasets, providing a sustainable "Data Engine" for fine-tuning Large Language Models.
  • One-Click Deployment: Supports various hardware backends (NVIDIA GPU, Intel CPU, Kunlunxin XPU, and diverse AI Accelerators).

📣 Recent updates

🔥 2026.07.22: HPD-Parsing is now available

  • HPD-Parsing is a lightweight vision-language model designed for high-throughput document parsing. It adopts a hierarchical parallel decoding paradigm and Progressive Multi-Token Prediction (P-MTP), achieving a peak throughput of 4,752 tokens/s on public benchmarks while maintaining competitive parsing accuracy.
  • HPD-Parsing supports both OpenAI-compatible serving and local inference through a customized vLLM runtime, making it suitable for document parsing scenarios with high demands on inference efficiency and deployment throughput.
  • See the HPD-Parsing usage tutorial for environment setup, serving, and local inference instructions.
  • PP-OCRv6 highlights:

    • Accuracy boost: Medium tier achieves +4.6% detection and +5.1% recognition over PP-OCRv5_server, surpassing mainstream VLMs (Qwen3-VL-235B, GPT-5.5) with only 34.5M parameters.
    • 50 languages unified: Single model covers Chinese, English, Japanese, and 46 Latin-script languages — no model switching needed.
    • Specialized scenarios: Major improvemen

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/paddleocr-text-recognition/SKILL.md3.6 KBupstream ↗
    ---
    name: paddleocr-text-recognition
    description: >-
      Use this skill whenever the user wants text extracted from images, photos, scans, screenshots,
      or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox
      coordinates. Strong accuracy for CJK, small print, and handwritten text.
      Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字,
      plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan,
      recognize text.
    license: Apache-2.0
    metadata:
      openclaw:
        requires:
          env:
            - PADDLEOCR_ACCESS_TOKEN
          bins:
            - paddleocr
        primaryEnv: PADDLEOCR_ACCESS_TOKEN
        emoji: "🔤"
        install:
          - kind: uv
            package: paddleocr
            bins: [paddleocr]
    ---
    
    # PaddleOCR Text Recognition
    
    ## When to Use This Skill
    
    **Use this skill for**:
    
    - Extract text from images (screenshots, photos, scans)
    - Extract text from PDFs or document images when the goal is **line/box-level text**
    - Extract text from URLs or local files that point to images/PDFs
    
    **Do not use for**:
    
    - Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead
    
    ## Usage
    
    ### Basic OCR
    
    From URL:
    
    ```bash
    paddleocr api \
      --model_type ocr \
      --file_url "https://example.com/image.png"
    ```
    
    From local file:
    
    ```bash
    paddleocr api \
      --model_type ocr \
      --file_path "./document.pdf"
    ```
    
    ### Common Options
    
    ```bash
    # With specific model
    paddleocr api \
      --model_type ocr \
      --model PP-OCRv5 \
      --file_path "./report.pdf"
    
    # Disable preprocessing (faster, for flat/well-oriented images)
    paddleocr api \
      --model_type ocr \
      --file_path "./document.pdf" \
      --use_doc_unwarping False \
      --use_doc_orientation_classify False
    
    # Save result to file
    paddleocr api \
      --model_type ocr \
      --file_url "https://..." \
      --output result.json
    
    # Page ranges
    paddleocr api \
      --model_type ocr \
      --file_path "./large.pdf" \
      --page_ranges "1-5,10,15-20"
    ```
    
    ### Output Format
    
    ```json
    {
      "jobId": "job-xxx",
      "pages": [
        {
          "prunedResult": {
            "rec_texts": ["Line 1", "Line 2"],
            "rec_scores": [0.98, 0.95]
          },
          "ocrImageUrl": "https://..."
        }
      ]
    }
    ```
    
    ## Important Notes
    
    **Preprocessing options**: By default, the API enables document preprocessing (unwarping and orientation classification). For flat, well-oriented images (screenshots, properly scanned documents), you can disable preprocessing for faster results:
    
    ```bash
    paddleocr api --model_type ocr --file_path "./document.pdf" --use_doc_unwarping False --use_doc_orientation_classify False
    ```
    
    Keep preprocessing enabled when:
    - The input is a photo of a curved or folded document
    - The document has significant perspective distortion
    - Orientation is uncertain (rotated 90/180/270 degrees)
    
    **Display complete results**: Always show the full extracted content to users. Do not truncate with "..." unless content exceeds 10,000 characters. When multiple pages are processed, summarize if needed but provide complete results when explicitly requested.
    
    **Handle errors gracefully**: When the CLI returns an error, inform the user of the specific issue rather than silently failing or falling back to your own vision capabilities. Common errors:
    - Authentication: `PADDLEOCR_ACCESS_TOKEN` invalid or missing
    - Quota: API rate limit exceeded
    - No content detected: Image may be blank or contain no text
    
    ## CLI Reference
    
    Run `paddleocr api --help` for all options.
    
    For full documentation, see: [PaddleOCR Official Documentation](https://www.paddleocr.ai/latest/en/version3.x/inference_deployment/serving/paddleocr_official_api/cli.html)
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/paddlepaddle-paddleocr-skills-paddleocr-text-recognition.md

// REPO STATS

92.6k stars
167 open issues
Last commit: 2mo ago