paddleocr
Awesome multilingual OCR and document parsing toolkits based on PaddlePaddle
Decision gist · record as of 2026-08-14
Yes. PaddleOCR is actively maintained, permissively licensed, has low install friction, and zero known vulnerabilities. It addresses a well-defined problem (document parsing and multilingual OCR) with broad ecosystem integration. Install it if you need OCR or document-to-structured-data conversion; the main gotcha is that models download on first use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Models are downloaded on first use; initial run may require network access and disk space for model files.
- Low friction installation with a pure Python wheel.
- Active maintenance with recent releases and strong community signal.
License · maintenance · safety
Apache License 2.0 (permissive) — Apache License 2.0 is permissive, allowing commercial and private use with minimal restrictions—suitable for most production deployments.
last release 2026-06-11 (64 days) · last repo commit 2026-07-22 · 87,658 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 3,152,944 downloads/mo, #2,722 on PyPI
Alternatives
Verify before relying
pip install paddleocr
from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True, lang='en')
result = ocr.ocr('image.jpg', cls=True)- Exact model download size and disk space requirements for different model tiers (tiny, small, medium).
- Performance benchmarks on specific hardware (GPU models, CPU types) beyond the general speedup claims.
- Whether all 100+ languages are equally accurate or if accuracy varies significantly by language.
- Real-world latency and throughput on production-scale document batches.
What it is and what it does
PaddleOCR is a multilingual optical character recognition and document parsing toolkit that converts images and PDFs into structured, machine-readable formats (JSON or Markdown). It combines traditional scene text recognition with specialized vision-language models for document understanding, supporting over 100 languages through unified models that eliminate the need for language switching. The package includes multiple model tiers (tiny, small, medium) optimized for different deployment scenarios—from edge devices to cloud servers—and handles complex document elements like tables, formulas, and charts alongside plain text.
The toolkit is designed for building RAG and agentic AI applications, with integration points for popular frameworks. Runtime dependencies are minimal: PyYAML, requests, aiohttp, typing-extensions, and paddlex, keeping the installation footprint light despite the capability breadth.
Use it for
- Extract text and tables from scanned documents or PDFs for data entry automation or archival systems.
- Convert business documents (invoices, receipts, forms) into structured JSON for downstream processing or database ingestion.
- Build document-aware RAG pipelines by parsing PDFs into Markdown and feeding them to LLM retrieval systems.
- Recognize text in natural scene images (street signs, license plates, industrial labels) for computer vision applications.
- Parse multilingual documents without model switching, handling mixed-language content in a single pass.
- Deploy lightweight OCR on edge devices or mobile environments using the tiny model tier.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
PaddleOCR is actively maintained, permissively licensed, has low install friction, and zero known vulnerabilities. It addresses a well-defined problem (document parsing and multilingual OCR) with broad ecosystem integration. Install it if you need OCR or document-to-structured-data conversion; the main gotcha is that models download on first use.
Install
paddleocr on PyPI
Before you install
Low friction installation with a pure Python wheel. Active maintenance with recent releases and strong community signal. Supports Python 3.8–3.13.
Models are downloaded on first use; initial run may require network access and disk space for model files.
License in practice
Apache License 2.0 is permissive, allowing commercial and private use with minimal restrictions—suitable for most production deployments.
Quickstart
pip install paddleocr
from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True, lang='en')
result = ocr.ocr('image.jpg', cls=True)Verify before relying
- Exact model download size and disk space requirements for different model tiers (tiny, small, medium).
- Performance benchmarks on specific hardware (GPU models, CPU types) beyond the general speedup claims.
- Whether all 100+ languages are equally accurate or if accuracy varies significantly by language.
- Real-world latency and throughput on production-scale document batches.
Package facts
| License | Apache License 2.0 permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagespaddlexPyYAMLrequestsaiohttptyping-extensions |
| Maintenance | Actively maintained 64 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 3,152,944 / month, #2,722 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersNatural Language :: Chinese (Simplified)Operating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Utilities |
Evidence: paddleocr-3.7.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “multilingual document parsing”
- paddleocrPaddleOCR extracts text, tables, and structured data from images and…
- sumySumy extracts summaries from HTML pages or plain text using multiple…
- BabelDOCBabelDOC translates PDF documents between languages, primarily…
Give your agent the search over MCP, or paste the wish link into any chat.
More Utilities packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Pygments is a syntax highlighter that colorizes source code and text in over 500 languages and formats, outputting to HTML, LaTeX, RTF, SVG, images, or ANSI terminal sequences.
Install it if you need to display or transform source code.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
See also mineru · paddlex · surya-ocr · rapidocr · marker-pdf · cnocr · rapidocr-onnxruntime · unstructured-inference · img2table · kreuzberg