rapidocr-onnxruntime
A cross platform OCR Library based on OnnxRuntime.
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has low install friction, carries no known vulnerabilities, and is widely adopted in production systems. Apache 2.0 licensing is permissive. Install it if you need offline OCR with reasonable speed and accuracy; verify model download behavior and performance on your target hardware before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- onnxruntime must be installed separately; models are downloaded on first use and require internet access or manual placement.
- Low friction: pure Python wheel with no compiled dependencies beyond onnxruntime.
- Active maintenance with recent commits and 7492 repository stars.
License · maintenance · safety
Apache-2.0 (permissive) — Apache 2.0 permissive license. The OCR model copyright is held by Baidu; engineering scripts are owned by the repository. You may use, modify, and distribute freely with attribution.
last release 2025-01-17 (574 days) · last repo commit 2026-08-14 · 7,492 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,517,725 downloads/mo, #3,027 on PyPI
Alternatives
Verify before relying
pip install rapidocr-onnxruntime onnxruntime
from rapidocr import RapidOCR
engine = RapidOCR()
result = engine("path/to/image.jpg")
print(result)- Whether model download/caching behavior and disk space requirements are documented
- Performance characteristics (inference speed, memory usage) on typical hardware
- Accuracy metrics for supported languages beyond Chinese and English
What it is and what it does
RapidOCR is an open-source OCR library that converts images to text using ONNX-format models derived from PaddleOCR. It wraps nine runtime dependencies—opencv-python, numpy, Pillow, onnxruntime, and others—to provide text detection and recognition in a single Python interface. The package is designed for offline deployment with minimal resource consumption and cross-platform compatibility.
You instantiate a RapidOCR engine and call it on image paths or URLs; it returns structured results containing detected text boxes and their content. The library supports Chinese and English by default, with other languages available via model substitution. It is actively maintained, widely used in downstream projects (langchain, Docling, and others), and carries no known security vulnerabilities.
Use it for
- Extract text from scanned documents or screenshots for archival or processing pipelines.
- Build document understanding workflows that combine OCR with language models for semantic analysis.
- Automate data entry by recognizing text in forms, receipts, or invoices without cloud API calls.
- Integrate OCR into desktop or embedded applications requiring offline text recognition.
- Detect and extract multilingual text from images in real-time applications.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has low install friction, carries no known vulnerabilities, and is widely adopted in production systems. Apache 2.0 licensing is permissive. Install it if you need offline OCR with reasonable speed and accuracy; verify model download behavior and performance on your target hardware before committing to production use.
Install
rapidocr-onnxruntime on PyPI
Before you install
Low friction: pure Python wheel with no compiled dependencies beyond onnxruntime. Active maintenance with recent commits and 7492 repository stars. Supports Python 3.6 through 3.12.
onnxruntime must be installed separately; models are downloaded on first use and require internet access or manual placement.
License in practice
Apache 2.0 permissive license. The OCR model copyright is held by Baidu; engineering scripts are owned by the repository. You may use, modify, and distribute freely with attribution.
Quickstart
pip install rapidocr-onnxruntime onnxruntime
from rapidocr import RapidOCR
engine = RapidOCR()
result = engine("path/to/image.jpg")
print(result)Verify before relying
- Whether model download/caching behavior and disk space requirements are documented
- Performance characteristics (inference speed, memory usage) on typical hardware
- Accuracy metrics for supported languages beyond Chinese and English
Package facts
| License | Apache-2.0 permissive |
| Python support | Capped below the current Python release <3.13,>=3.6 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagespyclipperopencv-pythonnumpysixShapelyPyYAMLPillowonnxruntimetqdm |
| Maintenance | Actively maintained 574 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 2,517,725 / month, #3,027 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.6Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9 |
Evidence: rapidocr_onnxruntime-1.4.4-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 › “chinese english ocr”
- rapidocr-onnxruntimePerforms optical character recognition (OCR) on images to extract…
- cnocrCnOCR recognizes text in images—Chinese (simplified and traditional),…
- cnstdDetects text and mathematical formulas in images using pre-trained…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also cnocr · rapidocr · easyocr · cnstd · paddleocr · onnxtr · ddddocr · paddlex · winrt-Windows.Media.Ocr · python-doctr